diff options
Diffstat (limited to 'venv/lib/python3.11/site-packages/pkg_resources/_vendor')
82 files changed, 21610 insertions, 0 deletions
diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/__init__.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/__init__.py new file mode 100644 index 0000000..e69de29 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/__init__.py diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/__pycache__/__init__.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/__pycache__/__init__.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..3115d28 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/__pycache__/__init__.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/__pycache__/appdirs.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/__pycache__/appdirs.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..32f6a28 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/__pycache__/appdirs.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/__pycache__/zipp.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/__pycache__/zipp.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..87a74fc --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/__pycache__/zipp.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/appdirs.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/appdirs.py new file mode 100644 index 0000000..ae67001 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/appdirs.py @@ -0,0 +1,608 @@ +#!/usr/bin/env python +# -*- coding: utf-8 -*- +# Copyright (c) 2005-2010 ActiveState Software Inc. +# Copyright (c) 2013 Eddy Petrișor + +"""Utilities for determining application-specific dirs. + +See <http://github.com/ActiveState/appdirs> for details and usage. +""" +# Dev Notes: +# - MSDN on where to store app data files: +# http://support.microsoft.com/default.aspx?scid=kb;en-us;310294#XSLTH3194121123120121120120 +# - Mac OS X: http://developer.apple.com/documentation/MacOSX/Conceptual/BPFileSystem/index.html +# - XDG spec for Un*x: http://standards.freedesktop.org/basedir-spec/basedir-spec-latest.html + +__version_info__ = (1, 4, 3) +__version__ = '.'.join(map(str, __version_info__)) + + +import sys +import os + +PY3 = sys.version_info[0] == 3 + +if PY3: + unicode = str + +if sys.platform.startswith('java'): + import platform + os_name = platform.java_ver()[3][0] + if os_name.startswith('Windows'): # "Windows XP", "Windows 7", etc. + system = 'win32' + elif os_name.startswith('Mac'): # "Mac OS X", etc. + system = 'darwin' + else: # "Linux", "SunOS", "FreeBSD", etc. + # Setting this to "linux2" is not ideal, but only Windows or Mac + # are actually checked for and the rest of the module expects + # *sys.platform* style strings. + system = 'linux2' +else: + system = sys.platform + + + +def user_data_dir(appname=None, appauthor=None, version=None, roaming=False): + r"""Return full path to the user-specific data dir for this application. + + "appname" is the name of application. + If None, just the system directory is returned. + "appauthor" (only used on Windows) is the name of the + appauthor or distributing body for this application. Typically + it is the owning company name. This falls back to appname. You may + pass False to disable it. + "version" is an optional version path element to append to the + path. You might want to use this if you want multiple versions + of your app to be able to run independently. If used, this + would typically be "<major>.<minor>". + Only applied when appname is present. + "roaming" (boolean, default False) can be set True to use the Windows + roaming appdata directory. That means that for users on a Windows + network setup for roaming profiles, this user data will be + sync'd on login. See + <http://technet.microsoft.com/en-us/library/cc766489(WS.10).aspx> + for a discussion of issues. + + Typical user data directories are: + Mac OS X: ~/Library/Application Support/<AppName> + Unix: ~/.local/share/<AppName> # or in $XDG_DATA_HOME, if defined + Win XP (not roaming): C:\Documents and Settings\<username>\Application Data\<AppAuthor>\<AppName> + Win XP (roaming): C:\Documents and Settings\<username>\Local Settings\Application Data\<AppAuthor>\<AppName> + Win 7 (not roaming): C:\Users\<username>\AppData\Local\<AppAuthor>\<AppName> + Win 7 (roaming): C:\Users\<username>\AppData\Roaming\<AppAuthor>\<AppName> + + For Unix, we follow the XDG spec and support $XDG_DATA_HOME. + That means, by default "~/.local/share/<AppName>". + """ + if system == "win32": + if appauthor is None: + appauthor = appname + const = roaming and "CSIDL_APPDATA" or "CSIDL_LOCAL_APPDATA" + path = os.path.normpath(_get_win_folder(const)) + if appname: + if appauthor is not False: + path = os.path.join(path, appauthor, appname) + else: + path = os.path.join(path, appname) + elif system == 'darwin': + path = os.path.expanduser('~/Library/Application Support/') + if appname: + path = os.path.join(path, appname) + else: + path = os.getenv('XDG_DATA_HOME', os.path.expanduser("~/.local/share")) + if appname: + path = os.path.join(path, appname) + if appname and version: + path = os.path.join(path, version) + return path + + +def site_data_dir(appname=None, appauthor=None, version=None, multipath=False): + r"""Return full path to the user-shared data dir for this application. + + "appname" is the name of application. + If None, just the system directory is returned. + "appauthor" (only used on Windows) is the name of the + appauthor or distributing body for this application. Typically + it is the owning company name. This falls back to appname. You may + pass False to disable it. + "version" is an optional version path element to append to the + path. You might want to use this if you want multiple versions + of your app to be able to run independently. If used, this + would typically be "<major>.<minor>". + Only applied when appname is present. + "multipath" is an optional parameter only applicable to *nix + which indicates that the entire list of data dirs should be + returned. By default, the first item from XDG_DATA_DIRS is + returned, or '/usr/local/share/<AppName>', + if XDG_DATA_DIRS is not set + + Typical site data directories are: + Mac OS X: /Library/Application Support/<AppName> + Unix: /usr/local/share/<AppName> or /usr/share/<AppName> + Win XP: C:\Documents and Settings\All Users\Application Data\<AppAuthor>\<AppName> + Vista: (Fail! "C:\ProgramData" is a hidden *system* directory on Vista.) + Win 7: C:\ProgramData\<AppAuthor>\<AppName> # Hidden, but writeable on Win 7. + + For Unix, this is using the $XDG_DATA_DIRS[0] default. + + WARNING: Do not use this on Windows. See the Vista-Fail note above for why. + """ + if system == "win32": + if appauthor is None: + appauthor = appname + path = os.path.normpath(_get_win_folder("CSIDL_COMMON_APPDATA")) + if appname: + if appauthor is not False: + path = os.path.join(path, appauthor, appname) + else: + path = os.path.join(path, appname) + elif system == 'darwin': + path = os.path.expanduser('/Library/Application Support') + if appname: + path = os.path.join(path, appname) + else: + # XDG default for $XDG_DATA_DIRS + # only first, if multipath is False + path = os.getenv('XDG_DATA_DIRS', + os.pathsep.join(['/usr/local/share', '/usr/share'])) + pathlist = [os.path.expanduser(x.rstrip(os.sep)) for x in path.split(os.pathsep)] + if appname: + if version: + appname = os.path.join(appname, version) + pathlist = [os.sep.join([x, appname]) for x in pathlist] + + if multipath: + path = os.pathsep.join(pathlist) + else: + path = pathlist[0] + return path + + if appname and version: + path = os.path.join(path, version) + return path + + +def user_config_dir(appname=None, appauthor=None, version=None, roaming=False): + r"""Return full path to the user-specific config dir for this application. + + "appname" is the name of application. + If None, just the system directory is returned. + "appauthor" (only used on Windows) is the name of the + appauthor or distributing body for this application. Typically + it is the owning company name. This falls back to appname. You may + pass False to disable it. + "version" is an optional version path element to append to the + path. You might want to use this if you want multiple versions + of your app to be able to run independently. If used, this + would typically be "<major>.<minor>". + Only applied when appname is present. + "roaming" (boolean, default False) can be set True to use the Windows + roaming appdata directory. That means that for users on a Windows + network setup for roaming profiles, this user data will be + sync'd on login. See + <http://technet.microsoft.com/en-us/library/cc766489(WS.10).aspx> + for a discussion of issues. + + Typical user config directories are: + Mac OS X: same as user_data_dir + Unix: ~/.config/<AppName> # or in $XDG_CONFIG_HOME, if defined + Win *: same as user_data_dir + + For Unix, we follow the XDG spec and support $XDG_CONFIG_HOME. + That means, by default "~/.config/<AppName>". + """ + if system in ["win32", "darwin"]: + path = user_data_dir(appname, appauthor, None, roaming) + else: + path = os.getenv('XDG_CONFIG_HOME', os.path.expanduser("~/.config")) + if appname: + path = os.path.join(path, appname) + if appname and version: + path = os.path.join(path, version) + return path + + +def site_config_dir(appname=None, appauthor=None, version=None, multipath=False): + r"""Return full path to the user-shared data dir for this application. + + "appname" is the name of application. + If None, just the system directory is returned. + "appauthor" (only used on Windows) is the name of the + appauthor or distributing body for this application. Typically + it is the owning company name. This falls back to appname. You may + pass False to disable it. + "version" is an optional version path element to append to the + path. You might want to use this if you want multiple versions + of your app to be able to run independently. If used, this + would typically be "<major>.<minor>". + Only applied when appname is present. + "multipath" is an optional parameter only applicable to *nix + which indicates that the entire list of config dirs should be + returned. By default, the first item from XDG_CONFIG_DIRS is + returned, or '/etc/xdg/<AppName>', if XDG_CONFIG_DIRS is not set + + Typical site config directories are: + Mac OS X: same as site_data_dir + Unix: /etc/xdg/<AppName> or $XDG_CONFIG_DIRS[i]/<AppName> for each value in + $XDG_CONFIG_DIRS + Win *: same as site_data_dir + Vista: (Fail! "C:\ProgramData" is a hidden *system* directory on Vista.) + + For Unix, this is using the $XDG_CONFIG_DIRS[0] default, if multipath=False + + WARNING: Do not use this on Windows. See the Vista-Fail note above for why. + """ + if system in ["win32", "darwin"]: + path = site_data_dir(appname, appauthor) + if appname and version: + path = os.path.join(path, version) + else: + # XDG default for $XDG_CONFIG_DIRS + # only first, if multipath is False + path = os.getenv('XDG_CONFIG_DIRS', '/etc/xdg') + pathlist = [os.path.expanduser(x.rstrip(os.sep)) for x in path.split(os.pathsep)] + if appname: + if version: + appname = os.path.join(appname, version) + pathlist = [os.sep.join([x, appname]) for x in pathlist] + + if multipath: + path = os.pathsep.join(pathlist) + else: + path = pathlist[0] + return path + + +def user_cache_dir(appname=None, appauthor=None, version=None, opinion=True): + r"""Return full path to the user-specific cache dir for this application. + + "appname" is the name of application. + If None, just the system directory is returned. + "appauthor" (only used on Windows) is the name of the + appauthor or distributing body for this application. Typically + it is the owning company name. This falls back to appname. You may + pass False to disable it. + "version" is an optional version path element to append to the + path. You might want to use this if you want multiple versions + of your app to be able to run independently. If used, this + would typically be "<major>.<minor>". + Only applied when appname is present. + "opinion" (boolean) can be False to disable the appending of + "Cache" to the base app data dir for Windows. See + discussion below. + + Typical user cache directories are: + Mac OS X: ~/Library/Caches/<AppName> + Unix: ~/.cache/<AppName> (XDG default) + Win XP: C:\Documents and Settings\<username>\Local Settings\Application Data\<AppAuthor>\<AppName>\Cache + Vista: C:\Users\<username>\AppData\Local\<AppAuthor>\<AppName>\Cache + + On Windows the only suggestion in the MSDN docs is that local settings go in + the `CSIDL_LOCAL_APPDATA` directory. This is identical to the non-roaming + app data dir (the default returned by `user_data_dir` above). Apps typically + put cache data somewhere *under* the given dir here. Some examples: + ...\Mozilla\Firefox\Profiles\<ProfileName>\Cache + ...\Acme\SuperApp\Cache\1.0 + OPINION: This function appends "Cache" to the `CSIDL_LOCAL_APPDATA` value. + This can be disabled with the `opinion=False` option. + """ + if system == "win32": + if appauthor is None: + appauthor = appname + path = os.path.normpath(_get_win_folder("CSIDL_LOCAL_APPDATA")) + if appname: + if appauthor is not False: + path = os.path.join(path, appauthor, appname) + else: + path = os.path.join(path, appname) + if opinion: + path = os.path.join(path, "Cache") + elif system == 'darwin': + path = os.path.expanduser('~/Library/Caches') + if appname: + path = os.path.join(path, appname) + else: + path = os.getenv('XDG_CACHE_HOME', os.path.expanduser('~/.cache')) + if appname: + path = os.path.join(path, appname) + if appname and version: + path = os.path.join(path, version) + return path + + +def user_state_dir(appname=None, appauthor=None, version=None, roaming=False): + r"""Return full path to the user-specific state dir for this application. + + "appname" is the name of application. + If None, just the system directory is returned. + "appauthor" (only used on Windows) is the name of the + appauthor or distributing body for this application. Typically + it is the owning company name. This falls back to appname. You may + pass False to disable it. + "version" is an optional version path element to append to the + path. You might want to use this if you want multiple versions + of your app to be able to run independently. If used, this + would typically be "<major>.<minor>". + Only applied when appname is present. + "roaming" (boolean, default False) can be set True to use the Windows + roaming appdata directory. That means that for users on a Windows + network setup for roaming profiles, this user data will be + sync'd on login. See + <http://technet.microsoft.com/en-us/library/cc766489(WS.10).aspx> + for a discussion of issues. + + Typical user state directories are: + Mac OS X: same as user_data_dir + Unix: ~/.local/state/<AppName> # or in $XDG_STATE_HOME, if defined + Win *: same as user_data_dir + + For Unix, we follow this Debian proposal <https://wiki.debian.org/XDGBaseDirectorySpecification#state> + to extend the XDG spec and support $XDG_STATE_HOME. + + That means, by default "~/.local/state/<AppName>". + """ + if system in ["win32", "darwin"]: + path = user_data_dir(appname, appauthor, None, roaming) + else: + path = os.getenv('XDG_STATE_HOME', os.path.expanduser("~/.local/state")) + if appname: + path = os.path.join(path, appname) + if appname and version: + path = os.path.join(path, version) + return path + + +def user_log_dir(appname=None, appauthor=None, version=None, opinion=True): + r"""Return full path to the user-specific log dir for this application. + + "appname" is the name of application. + If None, just the system directory is returned. + "appauthor" (only used on Windows) is the name of the + appauthor or distributing body for this application. Typically + it is the owning company name. This falls back to appname. You may + pass False to disable it. + "version" is an optional version path element to append to the + path. You might want to use this if you want multiple versions + of your app to be able to run independently. If used, this + would typically be "<major>.<minor>". + Only applied when appname is present. + "opinion" (boolean) can be False to disable the appending of + "Logs" to the base app data dir for Windows, and "log" to the + base cache dir for Unix. See discussion below. + + Typical user log directories are: + Mac OS X: ~/Library/Logs/<AppName> + Unix: ~/.cache/<AppName>/log # or under $XDG_CACHE_HOME if defined + Win XP: C:\Documents and Settings\<username>\Local Settings\Application Data\<AppAuthor>\<AppName>\Logs + Vista: C:\Users\<username>\AppData\Local\<AppAuthor>\<AppName>\Logs + + On Windows the only suggestion in the MSDN docs is that local settings + go in the `CSIDL_LOCAL_APPDATA` directory. (Note: I'm interested in + examples of what some windows apps use for a logs dir.) + + OPINION: This function appends "Logs" to the `CSIDL_LOCAL_APPDATA` + value for Windows and appends "log" to the user cache dir for Unix. + This can be disabled with the `opinion=False` option. + """ + if system == "darwin": + path = os.path.join( + os.path.expanduser('~/Library/Logs'), + appname) + elif system == "win32": + path = user_data_dir(appname, appauthor, version) + version = False + if opinion: + path = os.path.join(path, "Logs") + else: + path = user_cache_dir(appname, appauthor, version) + version = False + if opinion: + path = os.path.join(path, "log") + if appname and version: + path = os.path.join(path, version) + return path + + +class AppDirs(object): + """Convenience wrapper for getting application dirs.""" + def __init__(self, appname=None, appauthor=None, version=None, + roaming=False, multipath=False): + self.appname = appname + self.appauthor = appauthor + self.version = version + self.roaming = roaming + self.multipath = multipath + + @property + def user_data_dir(self): + return user_data_dir(self.appname, self.appauthor, + version=self.version, roaming=self.roaming) + + @property + def site_data_dir(self): + return site_data_dir(self.appname, self.appauthor, + version=self.version, multipath=self.multipath) + + @property + def user_config_dir(self): + return user_config_dir(self.appname, self.appauthor, + version=self.version, roaming=self.roaming) + + @property + def site_config_dir(self): + return site_config_dir(self.appname, self.appauthor, + version=self.version, multipath=self.multipath) + + @property + def user_cache_dir(self): + return user_cache_dir(self.appname, self.appauthor, + version=self.version) + + @property + def user_state_dir(self): + return user_state_dir(self.appname, self.appauthor, + version=self.version) + + @property + def user_log_dir(self): + return user_log_dir(self.appname, self.appauthor, + version=self.version) + + +#---- internal support stuff + +def _get_win_folder_from_registry(csidl_name): + """This is a fallback technique at best. I'm not sure if using the + registry for this guarantees us the correct answer for all CSIDL_* + names. + """ + if PY3: + import winreg as _winreg + else: + import _winreg + + shell_folder_name = { + "CSIDL_APPDATA": "AppData", + "CSIDL_COMMON_APPDATA": "Common AppData", + "CSIDL_LOCAL_APPDATA": "Local AppData", + }[csidl_name] + + key = _winreg.OpenKey( + _winreg.HKEY_CURRENT_USER, + r"Software\Microsoft\Windows\CurrentVersion\Explorer\Shell Folders" + ) + dir, type = _winreg.QueryValueEx(key, shell_folder_name) + return dir + + +def _get_win_folder_with_pywin32(csidl_name): + from win32com.shell import shellcon, shell + dir = shell.SHGetFolderPath(0, getattr(shellcon, csidl_name), 0, 0) + # Try to make this a unicode path because SHGetFolderPath does + # not return unicode strings when there is unicode data in the + # path. + try: + dir = unicode(dir) + + # Downgrade to short path name if have highbit chars. See + # <http://bugs.activestate.com/show_bug.cgi?id=85099>. + has_high_char = False + for c in dir: + if ord(c) > 255: + has_high_char = True + break + if has_high_char: + try: + import win32api + dir = win32api.GetShortPathName(dir) + except ImportError: + pass + except UnicodeError: + pass + return dir + + +def _get_win_folder_with_ctypes(csidl_name): + import ctypes + + csidl_const = { + "CSIDL_APPDATA": 26, + "CSIDL_COMMON_APPDATA": 35, + "CSIDL_LOCAL_APPDATA": 28, + }[csidl_name] + + buf = ctypes.create_unicode_buffer(1024) + ctypes.windll.shell32.SHGetFolderPathW(None, csidl_const, None, 0, buf) + + # Downgrade to short path name if have highbit chars. See + # <http://bugs.activestate.com/show_bug.cgi?id=85099>. + has_high_char = False + for c in buf: + if ord(c) > 255: + has_high_char = True + break + if has_high_char: + buf2 = ctypes.create_unicode_buffer(1024) + if ctypes.windll.kernel32.GetShortPathNameW(buf.value, buf2, 1024): + buf = buf2 + + return buf.value + +def _get_win_folder_with_jna(csidl_name): + import array + from com.sun import jna + from com.sun.jna.platform import win32 + + buf_size = win32.WinDef.MAX_PATH * 2 + buf = array.zeros('c', buf_size) + shell = win32.Shell32.INSTANCE + shell.SHGetFolderPath(None, getattr(win32.ShlObj, csidl_name), None, win32.ShlObj.SHGFP_TYPE_CURRENT, buf) + dir = jna.Native.toString(buf.tostring()).rstrip("\0") + + # Downgrade to short path name if have highbit chars. See + # <http://bugs.activestate.com/show_bug.cgi?id=85099>. + has_high_char = False + for c in dir: + if ord(c) > 255: + has_high_char = True + break + if has_high_char: + buf = array.zeros('c', buf_size) + kernel = win32.Kernel32.INSTANCE + if kernel.GetShortPathName(dir, buf, buf_size): + dir = jna.Native.toString(buf.tostring()).rstrip("\0") + + return dir + +if system == "win32": + try: + import win32com.shell + _get_win_folder = _get_win_folder_with_pywin32 + except ImportError: + try: + from ctypes import windll + _get_win_folder = _get_win_folder_with_ctypes + except ImportError: + try: + import com.sun.jna + _get_win_folder = _get_win_folder_with_jna + except ImportError: + _get_win_folder = _get_win_folder_from_registry + + +#---- self test code + +if __name__ == "__main__": + appname = "MyApp" + appauthor = "MyCompany" + + props = ("user_data_dir", + "user_config_dir", + "user_cache_dir", + "user_state_dir", + "user_log_dir", + "site_data_dir", + "site_config_dir") + + print("-- app dirs %s --" % __version__) + + print("-- app dirs (with optional 'version')") + dirs = AppDirs(appname, appauthor, version="1.0") + for prop in props: + print("%s: %s" % (prop, getattr(dirs, prop))) + + print("\n-- app dirs (without optional 'version')") + dirs = AppDirs(appname, appauthor) + for prop in props: + print("%s: %s" % (prop, getattr(dirs, prop))) + + print("\n-- app dirs (without optional 'appauthor')") + dirs = AppDirs(appname) + for prop in props: + print("%s: %s" % (prop, getattr(dirs, prop))) + + print("\n-- app dirs (with disabled 'appauthor')") + dirs = AppDirs(appname, appauthor=False) + for prop in props: + print("%s: %s" % (prop, getattr(dirs, prop))) diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__init__.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__init__.py new file mode 100644 index 0000000..34e3a99 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__init__.py @@ -0,0 +1,36 @@ +"""Read resources contained within a package.""" + +from ._common import ( + as_file, + files, + Package, +) + +from ._legacy import ( + contents, + open_binary, + read_binary, + open_text, + read_text, + is_resource, + path, + Resource, +) + +from .abc import ResourceReader + + +__all__ = [ + 'Package', + 'Resource', + 'ResourceReader', + 'as_file', + 'contents', + 'files', + 'is_resource', + 'open_binary', + 'open_text', + 'path', + 'read_binary', + 'read_text', +] diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/__init__.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/__init__.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..285513d --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/__init__.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/_adapters.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/_adapters.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..52e7288 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/_adapters.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/_common.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/_common.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..0bcf878 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/_common.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/_compat.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/_compat.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..07b5211 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/_compat.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/_itertools.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/_itertools.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..71100ae --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/_itertools.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/_legacy.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/_legacy.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..35f04d9 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/_legacy.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/abc.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/abc.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..ac37d24 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/abc.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/readers.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/readers.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..987c790 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/readers.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/simple.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/simple.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..38b35f7 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/__pycache__/simple.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/_adapters.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/_adapters.py new file mode 100644 index 0000000..ea363d8 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/_adapters.py @@ -0,0 +1,170 @@ +from contextlib import suppress +from io import TextIOWrapper + +from . import abc + + +class SpecLoaderAdapter: + """ + Adapt a package spec to adapt the underlying loader. + """ + + def __init__(self, spec, adapter=lambda spec: spec.loader): + self.spec = spec + self.loader = adapter(spec) + + def __getattr__(self, name): + return getattr(self.spec, name) + + +class TraversableResourcesLoader: + """ + Adapt a loader to provide TraversableResources. + """ + + def __init__(self, spec): + self.spec = spec + + def get_resource_reader(self, name): + return CompatibilityFiles(self.spec)._native() + + +def _io_wrapper(file, mode='r', *args, **kwargs): + if mode == 'r': + return TextIOWrapper(file, *args, **kwargs) + elif mode == 'rb': + return file + raise ValueError( + "Invalid mode value '{}', only 'r' and 'rb' are supported".format(mode) + ) + + +class CompatibilityFiles: + """ + Adapter for an existing or non-existent resource reader + to provide a compatibility .files(). + """ + + class SpecPath(abc.Traversable): + """ + Path tied to a module spec. + Can be read and exposes the resource reader children. + """ + + def __init__(self, spec, reader): + self._spec = spec + self._reader = reader + + def iterdir(self): + if not self._reader: + return iter(()) + return iter( + CompatibilityFiles.ChildPath(self._reader, path) + for path in self._reader.contents() + ) + + def is_file(self): + return False + + is_dir = is_file + + def joinpath(self, other): + if not self._reader: + return CompatibilityFiles.OrphanPath(other) + return CompatibilityFiles.ChildPath(self._reader, other) + + @property + def name(self): + return self._spec.name + + def open(self, mode='r', *args, **kwargs): + return _io_wrapper(self._reader.open_resource(None), mode, *args, **kwargs) + + class ChildPath(abc.Traversable): + """ + Path tied to a resource reader child. + Can be read but doesn't expose any meaningful children. + """ + + def __init__(self, reader, name): + self._reader = reader + self._name = name + + def iterdir(self): + return iter(()) + + def is_file(self): + return self._reader.is_resource(self.name) + + def is_dir(self): + return not self.is_file() + + def joinpath(self, other): + return CompatibilityFiles.OrphanPath(self.name, other) + + @property + def name(self): + return self._name + + def open(self, mode='r', *args, **kwargs): + return _io_wrapper( + self._reader.open_resource(self.name), mode, *args, **kwargs + ) + + class OrphanPath(abc.Traversable): + """ + Orphan path, not tied to a module spec or resource reader. + Can't be read and doesn't expose any meaningful children. + """ + + def __init__(self, *path_parts): + if len(path_parts) < 1: + raise ValueError('Need at least one path part to construct a path') + self._path = path_parts + + def iterdir(self): + return iter(()) + + def is_file(self): + return False + + is_dir = is_file + + def joinpath(self, other): + return CompatibilityFiles.OrphanPath(*self._path, other) + + @property + def name(self): + return self._path[-1] + + def open(self, mode='r', *args, **kwargs): + raise FileNotFoundError("Can't open orphan path") + + def __init__(self, spec): + self.spec = spec + + @property + def _reader(self): + with suppress(AttributeError): + return self.spec.loader.get_resource_reader(self.spec.name) + + def _native(self): + """ + Return the native reader if it supports files(). + """ + reader = self._reader + return reader if hasattr(reader, 'files') else self + + def __getattr__(self, attr): + return getattr(self._reader, attr) + + def files(self): + return CompatibilityFiles.SpecPath(self.spec, self._reader) + + +def wrap_spec(package): + """ + Construct a package spec with traversable compatibility + on the spec/loader/reader. + """ + return SpecLoaderAdapter(package.__spec__, TraversableResourcesLoader) diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/_common.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/_common.py new file mode 100644 index 0000000..a12e2c7 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/_common.py @@ -0,0 +1,104 @@ +import os +import pathlib +import tempfile +import functools +import contextlib +import types +import importlib + +from typing import Union, Optional +from .abc import ResourceReader, Traversable + +from ._compat import wrap_spec + +Package = Union[types.ModuleType, str] + + +def files(package): + # type: (Package) -> Traversable + """ + Get a Traversable resource from a package + """ + return from_package(get_package(package)) + + +def get_resource_reader(package): + # type: (types.ModuleType) -> Optional[ResourceReader] + """ + Return the package's loader if it's a ResourceReader. + """ + # We can't use + # a issubclass() check here because apparently abc.'s __subclasscheck__() + # hook wants to create a weak reference to the object, but + # zipimport.zipimporter does not support weak references, resulting in a + # TypeError. That seems terrible. + spec = package.__spec__ + reader = getattr(spec.loader, 'get_resource_reader', None) # type: ignore + if reader is None: + return None + return reader(spec.name) # type: ignore + + +def resolve(cand): + # type: (Package) -> types.ModuleType + return cand if isinstance(cand, types.ModuleType) else importlib.import_module(cand) + + +def get_package(package): + # type: (Package) -> types.ModuleType + """Take a package name or module object and return the module. + + Raise an exception if the resolved module is not a package. + """ + resolved = resolve(package) + if wrap_spec(resolved).submodule_search_locations is None: + raise TypeError(f'{package!r} is not a package') + return resolved + + +def from_package(package): + """ + Return a Traversable object for the given package. + + """ + spec = wrap_spec(package) + reader = spec.loader.get_resource_reader(spec.name) + return reader.files() + + +@contextlib.contextmanager +def _tempfile(reader, suffix=''): + # Not using tempfile.NamedTemporaryFile as it leads to deeper 'try' + # blocks due to the need to close the temporary file to work on Windows + # properly. + fd, raw_path = tempfile.mkstemp(suffix=suffix) + try: + try: + os.write(fd, reader()) + finally: + os.close(fd) + del reader + yield pathlib.Path(raw_path) + finally: + try: + os.remove(raw_path) + except FileNotFoundError: + pass + + +@functools.singledispatch +def as_file(path): + """ + Given a Traversable object, return that object as a + path on the local file system in a context manager. + """ + return _tempfile(path.read_bytes, suffix=path.name) + + +@as_file.register(pathlib.Path) +@contextlib.contextmanager +def _(path): + """ + Degenerate behavior for pathlib.Path objects. + """ + yield path diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/_compat.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/_compat.py new file mode 100644 index 0000000..cb9fc82 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/_compat.py @@ -0,0 +1,98 @@ +# flake8: noqa + +import abc +import sys +import pathlib +from contextlib import suppress + +if sys.version_info >= (3, 10): + from zipfile import Path as ZipPath # type: ignore +else: + from ..zipp import Path as ZipPath # type: ignore + + +try: + from typing import runtime_checkable # type: ignore +except ImportError: + + def runtime_checkable(cls): # type: ignore + return cls + + +try: + from typing import Protocol # type: ignore +except ImportError: + Protocol = abc.ABC # type: ignore + + +class TraversableResourcesLoader: + """ + Adapt loaders to provide TraversableResources and other + compatibility. + + Used primarily for Python 3.9 and earlier where the native + loaders do not yet implement TraversableResources. + """ + + def __init__(self, spec): + self.spec = spec + + @property + def path(self): + return self.spec.origin + + def get_resource_reader(self, name): + from . import readers, _adapters + + def _zip_reader(spec): + with suppress(AttributeError): + return readers.ZipReader(spec.loader, spec.name) + + def _namespace_reader(spec): + with suppress(AttributeError, ValueError): + return readers.NamespaceReader(spec.submodule_search_locations) + + def _available_reader(spec): + with suppress(AttributeError): + return spec.loader.get_resource_reader(spec.name) + + def _native_reader(spec): + reader = _available_reader(spec) + return reader if hasattr(reader, 'files') else None + + def _file_reader(spec): + try: + path = pathlib.Path(self.path) + except TypeError: + return None + if path.exists(): + return readers.FileReader(self) + + return ( + # native reader if it supplies 'files' + _native_reader(self.spec) + or + # local ZipReader if a zip module + _zip_reader(self.spec) + or + # local NamespaceReader if a namespace module + _namespace_reader(self.spec) + or + # local FileReader + _file_reader(self.spec) + # fallback - adapt the spec ResourceReader to TraversableReader + or _adapters.CompatibilityFiles(self.spec) + ) + + +def wrap_spec(package): + """ + Construct a package spec with traversable compatibility + on the spec/loader/reader. + + Supersedes _adapters.wrap_spec to use TraversableResourcesLoader + from above for older Python compatibility (<3.10). + """ + from . import _adapters + + return _adapters.SpecLoaderAdapter(package.__spec__, TraversableResourcesLoader) diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/_itertools.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/_itertools.py new file mode 100644 index 0000000..cce0558 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/_itertools.py @@ -0,0 +1,35 @@ +from itertools import filterfalse + +from typing import ( + Callable, + Iterable, + Iterator, + Optional, + Set, + TypeVar, + Union, +) + +# Type and type variable definitions +_T = TypeVar('_T') +_U = TypeVar('_U') + + +def unique_everseen( + iterable: Iterable[_T], key: Optional[Callable[[_T], _U]] = None +) -> Iterator[_T]: + "List unique elements, preserving order. Remember all elements ever seen." + # unique_everseen('AAAABBBCCDAABBB') --> A B C D + # unique_everseen('ABBCcAD', str.lower) --> A B C D + seen: Set[Union[_T, _U]] = set() + seen_add = seen.add + if key is None: + for element in filterfalse(seen.__contains__, iterable): + seen_add(element) + yield element + else: + for element in iterable: + k = key(element) + if k not in seen: + seen_add(k) + yield element diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/_legacy.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/_legacy.py new file mode 100644 index 0000000..1d5d3f1 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/_legacy.py @@ -0,0 +1,121 @@ +import functools +import os +import pathlib +import types +import warnings + +from typing import Union, Iterable, ContextManager, BinaryIO, TextIO, Any + +from . import _common + +Package = Union[types.ModuleType, str] +Resource = str + + +def deprecated(func): + @functools.wraps(func) + def wrapper(*args, **kwargs): + warnings.warn( + f"{func.__name__} is deprecated. Use files() instead. " + "Refer to https://importlib-resources.readthedocs.io" + "/en/latest/using.html#migrating-from-legacy for migration advice.", + DeprecationWarning, + stacklevel=2, + ) + return func(*args, **kwargs) + + return wrapper + + +def normalize_path(path): + # type: (Any) -> str + """Normalize a path by ensuring it is a string. + + If the resulting string contains path separators, an exception is raised. + """ + str_path = str(path) + parent, file_name = os.path.split(str_path) + if parent: + raise ValueError(f'{path!r} must be only a file name') + return file_name + + +@deprecated +def open_binary(package: Package, resource: Resource) -> BinaryIO: + """Return a file-like object opened for binary reading of the resource.""" + return (_common.files(package) / normalize_path(resource)).open('rb') + + +@deprecated +def read_binary(package: Package, resource: Resource) -> bytes: + """Return the binary contents of the resource.""" + return (_common.files(package) / normalize_path(resource)).read_bytes() + + +@deprecated +def open_text( + package: Package, + resource: Resource, + encoding: str = 'utf-8', + errors: str = 'strict', +) -> TextIO: + """Return a file-like object opened for text reading of the resource.""" + return (_common.files(package) / normalize_path(resource)).open( + 'r', encoding=encoding, errors=errors + ) + + +@deprecated +def read_text( + package: Package, + resource: Resource, + encoding: str = 'utf-8', + errors: str = 'strict', +) -> str: + """Return the decoded string of the resource. + + The decoding-related arguments have the same semantics as those of + bytes.decode(). + """ + with open_text(package, resource, encoding, errors) as fp: + return fp.read() + + +@deprecated +def contents(package: Package) -> Iterable[str]: + """Return an iterable of entries in `package`. + + Note that not all entries are resources. Specifically, directories are + not considered resources. Use `is_resource()` on each entry returned here + to check if it is a resource or not. + """ + return [path.name for path in _common.files(package).iterdir()] + + +@deprecated +def is_resource(package: Package, name: str) -> bool: + """True if `name` is a resource inside `package`. + + Directories are *not* resources. + """ + resource = normalize_path(name) + return any( + traversable.name == resource and traversable.is_file() + for traversable in _common.files(package).iterdir() + ) + + +@deprecated +def path( + package: Package, + resource: Resource, +) -> ContextManager[pathlib.Path]: + """A context manager providing a file path object to the resource. + + If the resource does not already exist on its own on the file system, + a temporary file will be created. If the file was created, the file + will be deleted upon exiting the context manager (no exception is + raised if the file was deleted prior to the context manager + exiting). + """ + return _common.as_file(_common.files(package) / normalize_path(resource)) diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/abc.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/abc.py new file mode 100644 index 0000000..d39dc1a --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/abc.py @@ -0,0 +1,137 @@ +import abc +from typing import BinaryIO, Iterable, Text + +from ._compat import runtime_checkable, Protocol + + +class ResourceReader(metaclass=abc.ABCMeta): + """Abstract base class for loaders to provide resource reading support.""" + + @abc.abstractmethod + def open_resource(self, resource: Text) -> BinaryIO: + """Return an opened, file-like object for binary reading. + + The 'resource' argument is expected to represent only a file name. + If the resource cannot be found, FileNotFoundError is raised. + """ + # This deliberately raises FileNotFoundError instead of + # NotImplementedError so that if this method is accidentally called, + # it'll still do the right thing. + raise FileNotFoundError + + @abc.abstractmethod + def resource_path(self, resource: Text) -> Text: + """Return the file system path to the specified resource. + + The 'resource' argument is expected to represent only a file name. + If the resource does not exist on the file system, raise + FileNotFoundError. + """ + # This deliberately raises FileNotFoundError instead of + # NotImplementedError so that if this method is accidentally called, + # it'll still do the right thing. + raise FileNotFoundError + + @abc.abstractmethod + def is_resource(self, path: Text) -> bool: + """Return True if the named 'path' is a resource. + + Files are resources, directories are not. + """ + raise FileNotFoundError + + @abc.abstractmethod + def contents(self) -> Iterable[str]: + """Return an iterable of entries in `package`.""" + raise FileNotFoundError + + +@runtime_checkable +class Traversable(Protocol): + """ + An object with a subset of pathlib.Path methods suitable for + traversing directories and opening files. + """ + + @abc.abstractmethod + def iterdir(self): + """ + Yield Traversable objects in self + """ + + def read_bytes(self): + """ + Read contents of self as bytes + """ + with self.open('rb') as strm: + return strm.read() + + def read_text(self, encoding=None): + """ + Read contents of self as text + """ + with self.open(encoding=encoding) as strm: + return strm.read() + + @abc.abstractmethod + def is_dir(self) -> bool: + """ + Return True if self is a directory + """ + + @abc.abstractmethod + def is_file(self) -> bool: + """ + Return True if self is a file + """ + + @abc.abstractmethod + def joinpath(self, child): + """ + Return Traversable child in self + """ + + def __truediv__(self, child): + """ + Return Traversable child in self + """ + return self.joinpath(child) + + @abc.abstractmethod + def open(self, mode='r', *args, **kwargs): + """ + mode may be 'r' or 'rb' to open as text or binary. Return a handle + suitable for reading (same as pathlib.Path.open). + + When opening as text, accepts encoding parameters such as those + accepted by io.TextIOWrapper. + """ + + @abc.abstractproperty + def name(self) -> str: + """ + The base name of this object without any parent references. + """ + + +class TraversableResources(ResourceReader): + """ + The required interface for providing traversable + resources. + """ + + @abc.abstractmethod + def files(self): + """Return a Traversable object for the loaded package.""" + + def open_resource(self, resource): + return self.files().joinpath(resource).open('rb') + + def resource_path(self, resource): + raise FileNotFoundError(resource) + + def is_resource(self, path): + return self.files().joinpath(path).is_file() + + def contents(self): + return (item.name for item in self.files().iterdir()) diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/readers.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/readers.py new file mode 100644 index 0000000..f1190ca --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/readers.py @@ -0,0 +1,122 @@ +import collections +import pathlib +import operator + +from . import abc + +from ._itertools import unique_everseen +from ._compat import ZipPath + + +def remove_duplicates(items): + return iter(collections.OrderedDict.fromkeys(items)) + + +class FileReader(abc.TraversableResources): + def __init__(self, loader): + self.path = pathlib.Path(loader.path).parent + + def resource_path(self, resource): + """ + Return the file system path to prevent + `resources.path()` from creating a temporary + copy. + """ + return str(self.path.joinpath(resource)) + + def files(self): + return self.path + + +class ZipReader(abc.TraversableResources): + def __init__(self, loader, module): + _, _, name = module.rpartition('.') + self.prefix = loader.prefix.replace('\\', '/') + name + '/' + self.archive = loader.archive + + def open_resource(self, resource): + try: + return super().open_resource(resource) + except KeyError as exc: + raise FileNotFoundError(exc.args[0]) + + def is_resource(self, path): + # workaround for `zipfile.Path.is_file` returning true + # for non-existent paths. + target = self.files().joinpath(path) + return target.is_file() and target.exists() + + def files(self): + return ZipPath(self.archive, self.prefix) + + +class MultiplexedPath(abc.Traversable): + """ + Given a series of Traversable objects, implement a merged + version of the interface across all objects. Useful for + namespace packages which may be multihomed at a single + name. + """ + + def __init__(self, *paths): + self._paths = list(map(pathlib.Path, remove_duplicates(paths))) + if not self._paths: + message = 'MultiplexedPath must contain at least one path' + raise FileNotFoundError(message) + if not all(path.is_dir() for path in self._paths): + raise NotADirectoryError('MultiplexedPath only supports directories') + + def iterdir(self): + files = (file for path in self._paths for file in path.iterdir()) + return unique_everseen(files, key=operator.attrgetter('name')) + + def read_bytes(self): + raise FileNotFoundError(f'{self} is not a file') + + def read_text(self, *args, **kwargs): + raise FileNotFoundError(f'{self} is not a file') + + def is_dir(self): + return True + + def is_file(self): + return False + + def joinpath(self, child): + # first try to find child in current paths + for file in self.iterdir(): + if file.name == child: + return file + # if it does not exist, construct it with the first path + return self._paths[0] / child + + __truediv__ = joinpath + + def open(self, *args, **kwargs): + raise FileNotFoundError(f'{self} is not a file') + + @property + def name(self): + return self._paths[0].name + + def __repr__(self): + paths = ', '.join(f"'{path}'" for path in self._paths) + return f'MultiplexedPath({paths})' + + +class NamespaceReader(abc.TraversableResources): + def __init__(self, namespace_path): + if 'NamespacePath' not in str(namespace_path): + raise ValueError('Invalid path') + self.path = MultiplexedPath(*list(namespace_path)) + + def resource_path(self, resource): + """ + Return the file system path to prevent + `resources.path()` from creating a temporary + copy. + """ + return str(self.path.joinpath(resource)) + + def files(self): + return self.path diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/simple.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/simple.py new file mode 100644 index 0000000..da073cb --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/importlib_resources/simple.py @@ -0,0 +1,116 @@ +""" +Interface adapters for low-level readers. +""" + +import abc +import io +import itertools +from typing import BinaryIO, List + +from .abc import Traversable, TraversableResources + + +class SimpleReader(abc.ABC): + """ + The minimum, low-level interface required from a resource + provider. + """ + + @abc.abstractproperty + def package(self): + # type: () -> str + """ + The name of the package for which this reader loads resources. + """ + + @abc.abstractmethod + def children(self): + # type: () -> List['SimpleReader'] + """ + Obtain an iterable of SimpleReader for available + child containers (e.g. directories). + """ + + @abc.abstractmethod + def resources(self): + # type: () -> List[str] + """ + Obtain available named resources for this virtual package. + """ + + @abc.abstractmethod + def open_binary(self, resource): + # type: (str) -> BinaryIO + """ + Obtain a File-like for a named resource. + """ + + @property + def name(self): + return self.package.split('.')[-1] + + +class ResourceHandle(Traversable): + """ + Handle to a named resource in a ResourceReader. + """ + + def __init__(self, parent, name): + # type: (ResourceContainer, str) -> None + self.parent = parent + self.name = name # type: ignore + + def is_file(self): + return True + + def is_dir(self): + return False + + def open(self, mode='r', *args, **kwargs): + stream = self.parent.reader.open_binary(self.name) + if 'b' not in mode: + stream = io.TextIOWrapper(*args, **kwargs) + return stream + + def joinpath(self, name): + raise RuntimeError("Cannot traverse into a resource") + + +class ResourceContainer(Traversable): + """ + Traversable container for a package's resources via its reader. + """ + + def __init__(self, reader): + # type: (SimpleReader) -> None + self.reader = reader + + def is_dir(self): + return True + + def is_file(self): + return False + + def iterdir(self): + files = (ResourceHandle(self, name) for name in self.reader.resources) + dirs = map(ResourceContainer, self.reader.children()) + return itertools.chain(files, dirs) + + def open(self, *args, **kwargs): + raise IsADirectoryError() + + def joinpath(self, name): + return next( + traversable for traversable in self.iterdir() if traversable.name == name + ) + + +class TraversableReader(TraversableResources, SimpleReader): + """ + A TraversableResources based on SimpleReader. Resource providers + may derive from this class to provide the TraversableResources + interface by supplying the SimpleReader interface. + """ + + def files(self): + return ResourceContainer(self) diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/__init__.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/__init__.py new file mode 100644 index 0000000..e69de29 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/__init__.py diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/__pycache__/__init__.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/__pycache__/__init__.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..127ad01 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/__pycache__/__init__.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/__pycache__/context.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/__pycache__/context.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..ac400b4 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/__pycache__/context.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/__pycache__/functools.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/__pycache__/functools.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..538d939 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/__pycache__/functools.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/context.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/context.py new file mode 100644 index 0000000..87a4e3d --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/context.py @@ -0,0 +1,213 @@ +import os +import subprocess +import contextlib +import functools +import tempfile +import shutil +import operator + + +@contextlib.contextmanager +def pushd(dir): + orig = os.getcwd() + os.chdir(dir) + try: + yield dir + finally: + os.chdir(orig) + + +@contextlib.contextmanager +def tarball_context(url, target_dir=None, runner=None, pushd=pushd): + """ + Get a tarball, extract it, change to that directory, yield, then + clean up. + `runner` is the function to invoke commands. + `pushd` is a context manager for changing the directory. + """ + if target_dir is None: + target_dir = os.path.basename(url).replace('.tar.gz', '').replace('.tgz', '') + if runner is None: + runner = functools.partial(subprocess.check_call, shell=True) + # In the tar command, use --strip-components=1 to strip the first path and + # then + # use -C to cause the files to be extracted to {target_dir}. This ensures + # that we always know where the files were extracted. + runner('mkdir {target_dir}'.format(**vars())) + try: + getter = 'wget {url} -O -' + extract = 'tar x{compression} --strip-components=1 -C {target_dir}' + cmd = ' | '.join((getter, extract)) + runner(cmd.format(compression=infer_compression(url), **vars())) + with pushd(target_dir): + yield target_dir + finally: + runner('rm -Rf {target_dir}'.format(**vars())) + + +def infer_compression(url): + """ + Given a URL or filename, infer the compression code for tar. + """ + # cheat and just assume it's the last two characters + compression_indicator = url[-2:] + mapping = dict(gz='z', bz='j', xz='J') + # Assume 'z' (gzip) if no match + return mapping.get(compression_indicator, 'z') + + +@contextlib.contextmanager +def temp_dir(remover=shutil.rmtree): + """ + Create a temporary directory context. Pass a custom remover + to override the removal behavior. + """ + temp_dir = tempfile.mkdtemp() + try: + yield temp_dir + finally: + remover(temp_dir) + + +@contextlib.contextmanager +def repo_context(url, branch=None, quiet=True, dest_ctx=temp_dir): + """ + Check out the repo indicated by url. + + If dest_ctx is supplied, it should be a context manager + to yield the target directory for the check out. + """ + exe = 'git' if 'git' in url else 'hg' + with dest_ctx() as repo_dir: + cmd = [exe, 'clone', url, repo_dir] + if branch: + cmd.extend(['--branch', branch]) + devnull = open(os.path.devnull, 'w') + stdout = devnull if quiet else None + subprocess.check_call(cmd, stdout=stdout) + yield repo_dir + + +@contextlib.contextmanager +def null(): + yield + + +class ExceptionTrap: + """ + A context manager that will catch certain exceptions and provide an + indication they occurred. + + >>> with ExceptionTrap() as trap: + ... raise Exception() + >>> bool(trap) + True + + >>> with ExceptionTrap() as trap: + ... pass + >>> bool(trap) + False + + >>> with ExceptionTrap(ValueError) as trap: + ... raise ValueError("1 + 1 is not 3") + >>> bool(trap) + True + + >>> with ExceptionTrap(ValueError) as trap: + ... raise Exception() + Traceback (most recent call last): + ... + Exception + + >>> bool(trap) + False + """ + + exc_info = None, None, None + + def __init__(self, exceptions=(Exception,)): + self.exceptions = exceptions + + def __enter__(self): + return self + + @property + def type(self): + return self.exc_info[0] + + @property + def value(self): + return self.exc_info[1] + + @property + def tb(self): + return self.exc_info[2] + + def __exit__(self, *exc_info): + type = exc_info[0] + matches = type and issubclass(type, self.exceptions) + if matches: + self.exc_info = exc_info + return matches + + def __bool__(self): + return bool(self.type) + + def raises(self, func, *, _test=bool): + """ + Wrap func and replace the result with the truth + value of the trap (True if an exception occurred). + + First, give the decorator an alias to support Python 3.8 + Syntax. + + >>> raises = ExceptionTrap(ValueError).raises + + Now decorate a function that always fails. + + >>> @raises + ... def fail(): + ... raise ValueError('failed') + >>> fail() + True + """ + + @functools.wraps(func) + def wrapper(*args, **kwargs): + with ExceptionTrap(self.exceptions) as trap: + func(*args, **kwargs) + return _test(trap) + + return wrapper + + def passes(self, func): + """ + Wrap func and replace the result with the truth + value of the trap (True if no exception). + + First, give the decorator an alias to support Python 3.8 + Syntax. + + >>> passes = ExceptionTrap(ValueError).passes + + Now decorate a function that always fails. + + >>> @passes + ... def fail(): + ... raise ValueError('failed') + + >>> fail() + False + """ + return self.raises(func, _test=operator.not_) + + +class suppress(contextlib.suppress, contextlib.ContextDecorator): + """ + A version of contextlib.suppress with decorator support. + + >>> @suppress(KeyError) + ... def key_error(): + ... {}[''] + >>> key_error() + """ diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/functools.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/functools.py new file mode 100644 index 0000000..a3fea3a --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/functools.py @@ -0,0 +1,525 @@ +import functools +import time +import inspect +import collections +import types +import itertools + +import pkg_resources.extern.more_itertools + +from typing import Callable, TypeVar + + +CallableT = TypeVar("CallableT", bound=Callable[..., object]) + + +def compose(*funcs): + """ + Compose any number of unary functions into a single unary function. + + >>> import textwrap + >>> expected = str.strip(textwrap.dedent(compose.__doc__)) + >>> strip_and_dedent = compose(str.strip, textwrap.dedent) + >>> strip_and_dedent(compose.__doc__) == expected + True + + Compose also allows the innermost function to take arbitrary arguments. + + >>> round_three = lambda x: round(x, ndigits=3) + >>> f = compose(round_three, int.__truediv__) + >>> [f(3*x, x+1) for x in range(1,10)] + [1.5, 2.0, 2.25, 2.4, 2.5, 2.571, 2.625, 2.667, 2.7] + """ + + def compose_two(f1, f2): + return lambda *args, **kwargs: f1(f2(*args, **kwargs)) + + return functools.reduce(compose_two, funcs) + + +def method_caller(method_name, *args, **kwargs): + """ + Return a function that will call a named method on the + target object with optional positional and keyword + arguments. + + >>> lower = method_caller('lower') + >>> lower('MyString') + 'mystring' + """ + + def call_method(target): + func = getattr(target, method_name) + return func(*args, **kwargs) + + return call_method + + +def once(func): + """ + Decorate func so it's only ever called the first time. + + This decorator can ensure that an expensive or non-idempotent function + will not be expensive on subsequent calls and is idempotent. + + >>> add_three = once(lambda a: a+3) + >>> add_three(3) + 6 + >>> add_three(9) + 6 + >>> add_three('12') + 6 + + To reset the stored value, simply clear the property ``saved_result``. + + >>> del add_three.saved_result + >>> add_three(9) + 12 + >>> add_three(8) + 12 + + Or invoke 'reset()' on it. + + >>> add_three.reset() + >>> add_three(-3) + 0 + >>> add_three(0) + 0 + """ + + @functools.wraps(func) + def wrapper(*args, **kwargs): + if not hasattr(wrapper, 'saved_result'): + wrapper.saved_result = func(*args, **kwargs) + return wrapper.saved_result + + wrapper.reset = lambda: vars(wrapper).__delitem__('saved_result') + return wrapper + + +def method_cache( + method: CallableT, + cache_wrapper: Callable[ + [CallableT], CallableT + ] = functools.lru_cache(), # type: ignore[assignment] +) -> CallableT: + """ + Wrap lru_cache to support storing the cache data in the object instances. + + Abstracts the common paradigm where the method explicitly saves an + underscore-prefixed protected property on first call and returns that + subsequently. + + >>> class MyClass: + ... calls = 0 + ... + ... @method_cache + ... def method(self, value): + ... self.calls += 1 + ... return value + + >>> a = MyClass() + >>> a.method(3) + 3 + >>> for x in range(75): + ... res = a.method(x) + >>> a.calls + 75 + + Note that the apparent behavior will be exactly like that of lru_cache + except that the cache is stored on each instance, so values in one + instance will not flush values from another, and when an instance is + deleted, so are the cached values for that instance. + + >>> b = MyClass() + >>> for x in range(35): + ... res = b.method(x) + >>> b.calls + 35 + >>> a.method(0) + 0 + >>> a.calls + 75 + + Note that if method had been decorated with ``functools.lru_cache()``, + a.calls would have been 76 (due to the cached value of 0 having been + flushed by the 'b' instance). + + Clear the cache with ``.cache_clear()`` + + >>> a.method.cache_clear() + + Same for a method that hasn't yet been called. + + >>> c = MyClass() + >>> c.method.cache_clear() + + Another cache wrapper may be supplied: + + >>> cache = functools.lru_cache(maxsize=2) + >>> MyClass.method2 = method_cache(lambda self: 3, cache_wrapper=cache) + >>> a = MyClass() + >>> a.method2() + 3 + + Caution - do not subsequently wrap the method with another decorator, such + as ``@property``, which changes the semantics of the function. + + See also + http://code.activestate.com/recipes/577452-a-memoize-decorator-for-instance-methods/ + for another implementation and additional justification. + """ + + def wrapper(self: object, *args: object, **kwargs: object) -> object: + # it's the first call, replace the method with a cached, bound method + bound_method: CallableT = types.MethodType( # type: ignore[assignment] + method, self + ) + cached_method = cache_wrapper(bound_method) + setattr(self, method.__name__, cached_method) + return cached_method(*args, **kwargs) + + # Support cache clear even before cache has been created. + wrapper.cache_clear = lambda: None # type: ignore[attr-defined] + + return ( # type: ignore[return-value] + _special_method_cache(method, cache_wrapper) or wrapper + ) + + +def _special_method_cache(method, cache_wrapper): + """ + Because Python treats special methods differently, it's not + possible to use instance attributes to implement the cached + methods. + + Instead, install the wrapper method under a different name + and return a simple proxy to that wrapper. + + https://github.com/jaraco/jaraco.functools/issues/5 + """ + name = method.__name__ + special_names = '__getattr__', '__getitem__' + if name not in special_names: + return + + wrapper_name = '__cached' + name + + def proxy(self, *args, **kwargs): + if wrapper_name not in vars(self): + bound = types.MethodType(method, self) + cache = cache_wrapper(bound) + setattr(self, wrapper_name, cache) + else: + cache = getattr(self, wrapper_name) + return cache(*args, **kwargs) + + return proxy + + +def apply(transform): + """ + Decorate a function with a transform function that is + invoked on results returned from the decorated function. + + >>> @apply(reversed) + ... def get_numbers(start): + ... "doc for get_numbers" + ... return range(start, start+3) + >>> list(get_numbers(4)) + [6, 5, 4] + >>> get_numbers.__doc__ + 'doc for get_numbers' + """ + + def wrap(func): + return functools.wraps(func)(compose(transform, func)) + + return wrap + + +def result_invoke(action): + r""" + Decorate a function with an action function that is + invoked on the results returned from the decorated + function (for its side-effect), then return the original + result. + + >>> @result_invoke(print) + ... def add_two(a, b): + ... return a + b + >>> x = add_two(2, 3) + 5 + >>> x + 5 + """ + + def wrap(func): + @functools.wraps(func) + def wrapper(*args, **kwargs): + result = func(*args, **kwargs) + action(result) + return result + + return wrapper + + return wrap + + +def call_aside(f, *args, **kwargs): + """ + Call a function for its side effect after initialization. + + >>> @call_aside + ... def func(): print("called") + called + >>> func() + called + + Use functools.partial to pass parameters to the initial call + + >>> @functools.partial(call_aside, name='bingo') + ... def func(name): print("called with", name) + called with bingo + """ + f(*args, **kwargs) + return f + + +class Throttler: + """ + Rate-limit a function (or other callable) + """ + + def __init__(self, func, max_rate=float('Inf')): + if isinstance(func, Throttler): + func = func.func + self.func = func + self.max_rate = max_rate + self.reset() + + def reset(self): + self.last_called = 0 + + def __call__(self, *args, **kwargs): + self._wait() + return self.func(*args, **kwargs) + + def _wait(self): + "ensure at least 1/max_rate seconds from last call" + elapsed = time.time() - self.last_called + must_wait = 1 / self.max_rate - elapsed + time.sleep(max(0, must_wait)) + self.last_called = time.time() + + def __get__(self, obj, type=None): + return first_invoke(self._wait, functools.partial(self.func, obj)) + + +def first_invoke(func1, func2): + """ + Return a function that when invoked will invoke func1 without + any parameters (for its side-effect) and then invoke func2 + with whatever parameters were passed, returning its result. + """ + + def wrapper(*args, **kwargs): + func1() + return func2(*args, **kwargs) + + return wrapper + + +def retry_call(func, cleanup=lambda: None, retries=0, trap=()): + """ + Given a callable func, trap the indicated exceptions + for up to 'retries' times, invoking cleanup on the + exception. On the final attempt, allow any exceptions + to propagate. + """ + attempts = itertools.count() if retries == float('inf') else range(retries) + for attempt in attempts: + try: + return func() + except trap: + cleanup() + + return func() + + +def retry(*r_args, **r_kwargs): + """ + Decorator wrapper for retry_call. Accepts arguments to retry_call + except func and then returns a decorator for the decorated function. + + Ex: + + >>> @retry(retries=3) + ... def my_func(a, b): + ... "this is my funk" + ... print(a, b) + >>> my_func.__doc__ + 'this is my funk' + """ + + def decorate(func): + @functools.wraps(func) + def wrapper(*f_args, **f_kwargs): + bound = functools.partial(func, *f_args, **f_kwargs) + return retry_call(bound, *r_args, **r_kwargs) + + return wrapper + + return decorate + + +def print_yielded(func): + """ + Convert a generator into a function that prints all yielded elements + + >>> @print_yielded + ... def x(): + ... yield 3; yield None + >>> x() + 3 + None + """ + print_all = functools.partial(map, print) + print_results = compose(more_itertools.consume, print_all, func) + return functools.wraps(func)(print_results) + + +def pass_none(func): + """ + Wrap func so it's not called if its first param is None + + >>> print_text = pass_none(print) + >>> print_text('text') + text + >>> print_text(None) + """ + + @functools.wraps(func) + def wrapper(param, *args, **kwargs): + if param is not None: + return func(param, *args, **kwargs) + + return wrapper + + +def assign_params(func, namespace): + """ + Assign parameters from namespace where func solicits. + + >>> def func(x, y=3): + ... print(x, y) + >>> assigned = assign_params(func, dict(x=2, z=4)) + >>> assigned() + 2 3 + + The usual errors are raised if a function doesn't receive + its required parameters: + + >>> assigned = assign_params(func, dict(y=3, z=4)) + >>> assigned() + Traceback (most recent call last): + TypeError: func() ...argument... + + It even works on methods: + + >>> class Handler: + ... def meth(self, arg): + ... print(arg) + >>> assign_params(Handler().meth, dict(arg='crystal', foo='clear'))() + crystal + """ + sig = inspect.signature(func) + params = sig.parameters.keys() + call_ns = {k: namespace[k] for k in params if k in namespace} + return functools.partial(func, **call_ns) + + +def save_method_args(method): + """ + Wrap a method such that when it is called, the args and kwargs are + saved on the method. + + >>> class MyClass: + ... @save_method_args + ... def method(self, a, b): + ... print(a, b) + >>> my_ob = MyClass() + >>> my_ob.method(1, 2) + 1 2 + >>> my_ob._saved_method.args + (1, 2) + >>> my_ob._saved_method.kwargs + {} + >>> my_ob.method(a=3, b='foo') + 3 foo + >>> my_ob._saved_method.args + () + >>> my_ob._saved_method.kwargs == dict(a=3, b='foo') + True + + The arguments are stored on the instance, allowing for + different instance to save different args. + + >>> your_ob = MyClass() + >>> your_ob.method({str('x'): 3}, b=[4]) + {'x': 3} [4] + >>> your_ob._saved_method.args + ({'x': 3},) + >>> my_ob._saved_method.args + () + """ + args_and_kwargs = collections.namedtuple('args_and_kwargs', 'args kwargs') + + @functools.wraps(method) + def wrapper(self, *args, **kwargs): + attr_name = '_saved_' + method.__name__ + attr = args_and_kwargs(args, kwargs) + setattr(self, attr_name, attr) + return method(self, *args, **kwargs) + + return wrapper + + +def except_(*exceptions, replace=None, use=None): + """ + Replace the indicated exceptions, if raised, with the indicated + literal replacement or evaluated expression (if present). + + >>> safe_int = except_(ValueError)(int) + >>> safe_int('five') + >>> safe_int('5') + 5 + + Specify a literal replacement with ``replace``. + + >>> safe_int_r = except_(ValueError, replace=0)(int) + >>> safe_int_r('five') + 0 + + Provide an expression to ``use`` to pass through particular parameters. + + >>> safe_int_pt = except_(ValueError, use='args[0]')(int) + >>> safe_int_pt('five') + 'five' + + """ + + def decorate(func): + @functools.wraps(func) + def wrapper(*args, **kwargs): + try: + return func(*args, **kwargs) + except exceptions: + try: + return eval(use) + except TypeError: + return replace + + return wrapper + + return decorate diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/text/__init__.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/text/__init__.py new file mode 100644 index 0000000..c466378 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/text/__init__.py @@ -0,0 +1,599 @@ +import re +import itertools +import textwrap +import functools + +try: + from importlib.resources import files # type: ignore +except ImportError: # pragma: nocover + from pkg_resources.extern.importlib_resources import files # type: ignore + +from pkg_resources.extern.jaraco.functools import compose, method_cache +from pkg_resources.extern.jaraco.context import ExceptionTrap + + +def substitution(old, new): + """ + Return a function that will perform a substitution on a string + """ + return lambda s: s.replace(old, new) + + +def multi_substitution(*substitutions): + """ + Take a sequence of pairs specifying substitutions, and create + a function that performs those substitutions. + + >>> multi_substitution(('foo', 'bar'), ('bar', 'baz'))('foo') + 'baz' + """ + substitutions = itertools.starmap(substitution, substitutions) + # compose function applies last function first, so reverse the + # substitutions to get the expected order. + substitutions = reversed(tuple(substitutions)) + return compose(*substitutions) + + +class FoldedCase(str): + """ + A case insensitive string class; behaves just like str + except compares equal when the only variation is case. + + >>> s = FoldedCase('hello world') + + >>> s == 'Hello World' + True + + >>> 'Hello World' == s + True + + >>> s != 'Hello World' + False + + >>> s.index('O') + 4 + + >>> s.split('O') + ['hell', ' w', 'rld'] + + >>> sorted(map(FoldedCase, ['GAMMA', 'alpha', 'Beta'])) + ['alpha', 'Beta', 'GAMMA'] + + Sequence membership is straightforward. + + >>> "Hello World" in [s] + True + >>> s in ["Hello World"] + True + + You may test for set inclusion, but candidate and elements + must both be folded. + + >>> FoldedCase("Hello World") in {s} + True + >>> s in {FoldedCase("Hello World")} + True + + String inclusion works as long as the FoldedCase object + is on the right. + + >>> "hello" in FoldedCase("Hello World") + True + + But not if the FoldedCase object is on the left: + + >>> FoldedCase('hello') in 'Hello World' + False + + In that case, use ``in_``: + + >>> FoldedCase('hello').in_('Hello World') + True + + >>> FoldedCase('hello') > FoldedCase('Hello') + False + """ + + def __lt__(self, other): + return self.lower() < other.lower() + + def __gt__(self, other): + return self.lower() > other.lower() + + def __eq__(self, other): + return self.lower() == other.lower() + + def __ne__(self, other): + return self.lower() != other.lower() + + def __hash__(self): + return hash(self.lower()) + + def __contains__(self, other): + return super().lower().__contains__(other.lower()) + + def in_(self, other): + "Does self appear in other?" + return self in FoldedCase(other) + + # cache lower since it's likely to be called frequently. + @method_cache + def lower(self): + return super().lower() + + def index(self, sub): + return self.lower().index(sub.lower()) + + def split(self, splitter=' ', maxsplit=0): + pattern = re.compile(re.escape(splitter), re.I) + return pattern.split(self, maxsplit) + + +# Python 3.8 compatibility +_unicode_trap = ExceptionTrap(UnicodeDecodeError) + + +@_unicode_trap.passes +def is_decodable(value): + r""" + Return True if the supplied value is decodable (using the default + encoding). + + >>> is_decodable(b'\xff') + False + >>> is_decodable(b'\x32') + True + """ + value.decode() + + +def is_binary(value): + r""" + Return True if the value appears to be binary (that is, it's a byte + string and isn't decodable). + + >>> is_binary(b'\xff') + True + >>> is_binary('\xff') + False + """ + return isinstance(value, bytes) and not is_decodable(value) + + +def trim(s): + r""" + Trim something like a docstring to remove the whitespace that + is common due to indentation and formatting. + + >>> trim("\n\tfoo = bar\n\t\tbar = baz\n") + 'foo = bar\n\tbar = baz' + """ + return textwrap.dedent(s).strip() + + +def wrap(s): + """ + Wrap lines of text, retaining existing newlines as + paragraph markers. + + >>> print(wrap(lorem_ipsum)) + Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do + eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad + minim veniam, quis nostrud exercitation ullamco laboris nisi ut + aliquip ex ea commodo consequat. Duis aute irure dolor in + reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla + pariatur. Excepteur sint occaecat cupidatat non proident, sunt in + culpa qui officia deserunt mollit anim id est laborum. + <BLANKLINE> + Curabitur pretium tincidunt lacus. Nulla gravida orci a odio. Nullam + varius, turpis et commodo pharetra, est eros bibendum elit, nec luctus + magna felis sollicitudin mauris. Integer in mauris eu nibh euismod + gravida. Duis ac tellus et risus vulputate vehicula. Donec lobortis + risus a elit. Etiam tempor. Ut ullamcorper, ligula eu tempor congue, + eros est euismod turpis, id tincidunt sapien risus a quam. Maecenas + fermentum consequat mi. Donec fermentum. Pellentesque malesuada nulla + a mi. Duis sapien sem, aliquet nec, commodo eget, consequat quis, + neque. Aliquam faucibus, elit ut dictum aliquet, felis nisl adipiscing + sapien, sed malesuada diam lacus eget erat. Cras mollis scelerisque + nunc. Nullam arcu. Aliquam consequat. Curabitur augue lorem, dapibus + quis, laoreet et, pretium ac, nisi. Aenean magna nisl, mollis quis, + molestie eu, feugiat in, orci. In hac habitasse platea dictumst. + """ + paragraphs = s.splitlines() + wrapped = ('\n'.join(textwrap.wrap(para)) for para in paragraphs) + return '\n\n'.join(wrapped) + + +def unwrap(s): + r""" + Given a multi-line string, return an unwrapped version. + + >>> wrapped = wrap(lorem_ipsum) + >>> wrapped.count('\n') + 20 + >>> unwrapped = unwrap(wrapped) + >>> unwrapped.count('\n') + 1 + >>> print(unwrapped) + Lorem ipsum dolor sit amet, consectetur adipiscing ... + Curabitur pretium tincidunt lacus. Nulla gravida orci ... + + """ + paragraphs = re.split(r'\n\n+', s) + cleaned = (para.replace('\n', ' ') for para in paragraphs) + return '\n'.join(cleaned) + + + + +class Splitter(object): + """object that will split a string with the given arguments for each call + + >>> s = Splitter(',') + >>> s('hello, world, this is your, master calling') + ['hello', ' world', ' this is your', ' master calling'] + """ + + def __init__(self, *args): + self.args = args + + def __call__(self, s): + return s.split(*self.args) + + +def indent(string, prefix=' ' * 4): + """ + >>> indent('foo') + ' foo' + """ + return prefix + string + + +class WordSet(tuple): + """ + Given an identifier, return the words that identifier represents, + whether in camel case, underscore-separated, etc. + + >>> WordSet.parse("camelCase") + ('camel', 'Case') + + >>> WordSet.parse("under_sep") + ('under', 'sep') + + Acronyms should be retained + + >>> WordSet.parse("firstSNL") + ('first', 'SNL') + + >>> WordSet.parse("you_and_I") + ('you', 'and', 'I') + + >>> WordSet.parse("A simple test") + ('A', 'simple', 'test') + + Multiple caps should not interfere with the first cap of another word. + + >>> WordSet.parse("myABCClass") + ('my', 'ABC', 'Class') + + The result is a WordSet, so you can get the form you need. + + >>> WordSet.parse("myABCClass").underscore_separated() + 'my_ABC_Class' + + >>> WordSet.parse('a-command').camel_case() + 'ACommand' + + >>> WordSet.parse('someIdentifier').lowered().space_separated() + 'some identifier' + + Slices of the result should return another WordSet. + + >>> WordSet.parse('taken-out-of-context')[1:].underscore_separated() + 'out_of_context' + + >>> WordSet.from_class_name(WordSet()).lowered().space_separated() + 'word set' + + >>> example = WordSet.parse('figured it out') + >>> example.headless_camel_case() + 'figuredItOut' + >>> example.dash_separated() + 'figured-it-out' + + """ + + _pattern = re.compile('([A-Z]?[a-z]+)|([A-Z]+(?![a-z]))') + + def capitalized(self): + return WordSet(word.capitalize() for word in self) + + def lowered(self): + return WordSet(word.lower() for word in self) + + def camel_case(self): + return ''.join(self.capitalized()) + + def headless_camel_case(self): + words = iter(self) + first = next(words).lower() + new_words = itertools.chain((first,), WordSet(words).camel_case()) + return ''.join(new_words) + + def underscore_separated(self): + return '_'.join(self) + + def dash_separated(self): + return '-'.join(self) + + def space_separated(self): + return ' '.join(self) + + def trim_right(self, item): + """ + Remove the item from the end of the set. + + >>> WordSet.parse('foo bar').trim_right('foo') + ('foo', 'bar') + >>> WordSet.parse('foo bar').trim_right('bar') + ('foo',) + >>> WordSet.parse('').trim_right('bar') + () + """ + return self[:-1] if self and self[-1] == item else self + + def trim_left(self, item): + """ + Remove the item from the beginning of the set. + + >>> WordSet.parse('foo bar').trim_left('foo') + ('bar',) + >>> WordSet.parse('foo bar').trim_left('bar') + ('foo', 'bar') + >>> WordSet.parse('').trim_left('bar') + () + """ + return self[1:] if self and self[0] == item else self + + def trim(self, item): + """ + >>> WordSet.parse('foo bar').trim('foo') + ('bar',) + """ + return self.trim_left(item).trim_right(item) + + def __getitem__(self, item): + result = super(WordSet, self).__getitem__(item) + if isinstance(item, slice): + result = WordSet(result) + return result + + @classmethod + def parse(cls, identifier): + matches = cls._pattern.finditer(identifier) + return WordSet(match.group(0) for match in matches) + + @classmethod + def from_class_name(cls, subject): + return cls.parse(subject.__class__.__name__) + + +# for backward compatibility +words = WordSet.parse + + +def simple_html_strip(s): + r""" + Remove HTML from the string `s`. + + >>> str(simple_html_strip('')) + '' + + >>> print(simple_html_strip('A <bold>stormy</bold> day in paradise')) + A stormy day in paradise + + >>> print(simple_html_strip('Somebody <!-- do not --> tell the truth.')) + Somebody tell the truth. + + >>> print(simple_html_strip('What about<br/>\nmultiple lines?')) + What about + multiple lines? + """ + html_stripper = re.compile('(<!--.*?-->)|(<[^>]*>)|([^<]+)', re.DOTALL) + texts = (match.group(3) or '' for match in html_stripper.finditer(s)) + return ''.join(texts) + + +class SeparatedValues(str): + """ + A string separated by a separator. Overrides __iter__ for getting + the values. + + >>> list(SeparatedValues('a,b,c')) + ['a', 'b', 'c'] + + Whitespace is stripped and empty values are discarded. + + >>> list(SeparatedValues(' a, b , c, ')) + ['a', 'b', 'c'] + """ + + separator = ',' + + def __iter__(self): + parts = self.split(self.separator) + return filter(None, (part.strip() for part in parts)) + + +class Stripper: + r""" + Given a series of lines, find the common prefix and strip it from them. + + >>> lines = [ + ... 'abcdefg\n', + ... 'abc\n', + ... 'abcde\n', + ... ] + >>> res = Stripper.strip_prefix(lines) + >>> res.prefix + 'abc' + >>> list(res.lines) + ['defg\n', '\n', 'de\n'] + + If no prefix is common, nothing should be stripped. + + >>> lines = [ + ... 'abcd\n', + ... '1234\n', + ... ] + >>> res = Stripper.strip_prefix(lines) + >>> res.prefix = '' + >>> list(res.lines) + ['abcd\n', '1234\n'] + """ + + def __init__(self, prefix, lines): + self.prefix = prefix + self.lines = map(self, lines) + + @classmethod + def strip_prefix(cls, lines): + prefix_lines, lines = itertools.tee(lines) + prefix = functools.reduce(cls.common_prefix, prefix_lines) + return cls(prefix, lines) + + def __call__(self, line): + if not self.prefix: + return line + null, prefix, rest = line.partition(self.prefix) + return rest + + @staticmethod + def common_prefix(s1, s2): + """ + Return the common prefix of two lines. + """ + index = min(len(s1), len(s2)) + while s1[:index] != s2[:index]: + index -= 1 + return s1[:index] + + +def remove_prefix(text, prefix): + """ + Remove the prefix from the text if it exists. + + >>> remove_prefix('underwhelming performance', 'underwhelming ') + 'performance' + + >>> remove_prefix('something special', 'sample') + 'something special' + """ + null, prefix, rest = text.rpartition(prefix) + return rest + + +def remove_suffix(text, suffix): + """ + Remove the suffix from the text if it exists. + + >>> remove_suffix('name.git', '.git') + 'name' + + >>> remove_suffix('something special', 'sample') + 'something special' + """ + rest, suffix, null = text.partition(suffix) + return rest + + +def normalize_newlines(text): + r""" + Replace alternate newlines with the canonical newline. + + >>> normalize_newlines('Lorem Ipsum\u2029') + 'Lorem Ipsum\n' + >>> normalize_newlines('Lorem Ipsum\r\n') + 'Lorem Ipsum\n' + >>> normalize_newlines('Lorem Ipsum\x85') + 'Lorem Ipsum\n' + """ + newlines = ['\r\n', '\r', '\n', '\u0085', '\u2028', '\u2029'] + pattern = '|'.join(newlines) + return re.sub(pattern, '\n', text) + + +def _nonblank(str): + return str and not str.startswith('#') + + +@functools.singledispatch +def yield_lines(iterable): + r""" + Yield valid lines of a string or iterable. + + >>> list(yield_lines('')) + [] + >>> list(yield_lines(['foo', 'bar'])) + ['foo', 'bar'] + >>> list(yield_lines('foo\nbar')) + ['foo', 'bar'] + >>> list(yield_lines('\nfoo\n#bar\nbaz #comment')) + ['foo', 'baz #comment'] + >>> list(yield_lines(['foo\nbar', 'baz', 'bing\n\n\n'])) + ['foo', 'bar', 'baz', 'bing'] + """ + return itertools.chain.from_iterable(map(yield_lines, iterable)) + + +@yield_lines.register(str) +def _(text): + return filter(_nonblank, map(str.strip, text.splitlines())) + + +def drop_comment(line): + """ + Drop comments. + + >>> drop_comment('foo # bar') + 'foo' + + A hash without a space may be in a URL. + + >>> drop_comment('http://example.com/foo#bar') + 'http://example.com/foo#bar' + """ + return line.partition(' #')[0] + + +def join_continuation(lines): + r""" + Join lines continued by a trailing backslash. + + >>> list(join_continuation(['foo \\', 'bar', 'baz'])) + ['foobar', 'baz'] + >>> list(join_continuation(['foo \\', 'bar', 'baz'])) + ['foobar', 'baz'] + >>> list(join_continuation(['foo \\', 'bar \\', 'baz'])) + ['foobarbaz'] + + Not sure why, but... + The character preceeding the backslash is also elided. + + >>> list(join_continuation(['goo\\', 'dly'])) + ['godly'] + + A terrible idea, but... + If no line is available to continue, suppress the lines. + + >>> list(join_continuation(['foo', 'bar\\', 'baz\\'])) + ['foo'] + """ + lines = iter(lines) + for item in lines: + while item.endswith('\\'): + try: + item = item[:-2].strip() + next(lines) + except StopIteration: + return + yield item diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/text/__pycache__/__init__.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/text/__pycache__/__init__.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..e98d295 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/jaraco/text/__pycache__/__init__.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/__init__.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/__init__.py new file mode 100644 index 0000000..ea38bef --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/__init__.py @@ -0,0 +1,4 @@ +from .more import * # noqa +from .recipes import * # noqa + +__version__ = '8.12.0' diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/__pycache__/__init__.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/__pycache__/__init__.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..0dc00b2 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/__pycache__/__init__.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/__pycache__/more.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/__pycache__/more.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..180ddc7 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/__pycache__/more.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/__pycache__/recipes.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/__pycache__/recipes.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..38f7493 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/__pycache__/recipes.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/more.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/more.py new file mode 100644 index 0000000..6b6a5ca --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/more.py @@ -0,0 +1,4316 @@ +import warnings + +from collections import Counter, defaultdict, deque, abc +from collections.abc import Sequence +from functools import partial, reduce, wraps +from heapq import merge, heapify, heapreplace, heappop +from itertools import ( + chain, + compress, + count, + cycle, + dropwhile, + groupby, + islice, + repeat, + starmap, + takewhile, + tee, + zip_longest, +) +from math import exp, factorial, floor, log +from queue import Empty, Queue +from random import random, randrange, uniform +from operator import itemgetter, mul, sub, gt, lt, ge, le +from sys import hexversion, maxsize +from time import monotonic + +from .recipes import ( + consume, + flatten, + pairwise, + powerset, + take, + unique_everseen, +) + +__all__ = [ + 'AbortThread', + 'SequenceView', + 'UnequalIterablesError', + 'adjacent', + 'all_unique', + 'always_iterable', + 'always_reversible', + 'bucket', + 'callback_iter', + 'chunked', + 'chunked_even', + 'circular_shifts', + 'collapse', + 'collate', + 'combination_index', + 'consecutive_groups', + 'consumer', + 'count_cycle', + 'countable', + 'difference', + 'distinct_combinations', + 'distinct_permutations', + 'distribute', + 'divide', + 'duplicates_everseen', + 'duplicates_justseen', + 'exactly_n', + 'filter_except', + 'first', + 'groupby_transform', + 'ichunked', + 'ilen', + 'interleave', + 'interleave_evenly', + 'interleave_longest', + 'intersperse', + 'is_sorted', + 'islice_extended', + 'iterate', + 'last', + 'locate', + 'lstrip', + 'make_decorator', + 'map_except', + 'map_if', + 'map_reduce', + 'mark_ends', + 'minmax', + 'nth_or_last', + 'nth_permutation', + 'nth_product', + 'numeric_range', + 'one', + 'only', + 'padded', + 'partitions', + 'peekable', + 'permutation_index', + 'product_index', + 'raise_', + 'repeat_each', + 'repeat_last', + 'replace', + 'rlocate', + 'rstrip', + 'run_length', + 'sample', + 'seekable', + 'set_partitions', + 'side_effect', + 'sliced', + 'sort_together', + 'split_after', + 'split_at', + 'split_before', + 'split_into', + 'split_when', + 'spy', + 'stagger', + 'strip', + 'strictly_n', + 'substrings', + 'substrings_indexes', + 'time_limited', + 'unique_in_window', + 'unique_to_each', + 'unzip', + 'value_chain', + 'windowed', + 'windowed_complete', + 'with_iter', + 'zip_broadcast', + 'zip_equal', + 'zip_offset', +] + + +_marker = object() + + +def chunked(iterable, n, strict=False): + """Break *iterable* into lists of length *n*: + + >>> list(chunked([1, 2, 3, 4, 5, 6], 3)) + [[1, 2, 3], [4, 5, 6]] + + By the default, the last yielded list will have fewer than *n* elements + if the length of *iterable* is not divisible by *n*: + + >>> list(chunked([1, 2, 3, 4, 5, 6, 7, 8], 3)) + [[1, 2, 3], [4, 5, 6], [7, 8]] + + To use a fill-in value instead, see the :func:`grouper` recipe. + + If the length of *iterable* is not divisible by *n* and *strict* is + ``True``, then ``ValueError`` will be raised before the last + list is yielded. + + """ + iterator = iter(partial(take, n, iter(iterable)), []) + if strict: + if n is None: + raise ValueError('n must not be None when using strict mode.') + + def ret(): + for chunk in iterator: + if len(chunk) != n: + raise ValueError('iterable is not divisible by n.') + yield chunk + + return iter(ret()) + else: + return iterator + + +def first(iterable, default=_marker): + """Return the first item of *iterable*, or *default* if *iterable* is + empty. + + >>> first([0, 1, 2, 3]) + 0 + >>> first([], 'some default') + 'some default' + + If *default* is not provided and there are no items in the iterable, + raise ``ValueError``. + + :func:`first` is useful when you have a generator of expensive-to-retrieve + values and want any arbitrary one. It is marginally shorter than + ``next(iter(iterable), default)``. + + """ + try: + return next(iter(iterable)) + except StopIteration as e: + if default is _marker: + raise ValueError( + 'first() was called on an empty iterable, and no ' + 'default value was provided.' + ) from e + return default + + +def last(iterable, default=_marker): + """Return the last item of *iterable*, or *default* if *iterable* is + empty. + + >>> last([0, 1, 2, 3]) + 3 + >>> last([], 'some default') + 'some default' + + If *default* is not provided and there are no items in the iterable, + raise ``ValueError``. + """ + try: + if isinstance(iterable, Sequence): + return iterable[-1] + # Work around https://bugs.python.org/issue38525 + elif hasattr(iterable, '__reversed__') and (hexversion != 0x030800F0): + return next(reversed(iterable)) + else: + return deque(iterable, maxlen=1)[-1] + except (IndexError, TypeError, StopIteration): + if default is _marker: + raise ValueError( + 'last() was called on an empty iterable, and no default was ' + 'provided.' + ) + return default + + +def nth_or_last(iterable, n, default=_marker): + """Return the nth or the last item of *iterable*, + or *default* if *iterable* is empty. + + >>> nth_or_last([0, 1, 2, 3], 2) + 2 + >>> nth_or_last([0, 1], 2) + 1 + >>> nth_or_last([], 0, 'some default') + 'some default' + + If *default* is not provided and there are no items in the iterable, + raise ``ValueError``. + """ + return last(islice(iterable, n + 1), default=default) + + +class peekable: + """Wrap an iterator to allow lookahead and prepending elements. + + Call :meth:`peek` on the result to get the value that will be returned + by :func:`next`. This won't advance the iterator: + + >>> p = peekable(['a', 'b']) + >>> p.peek() + 'a' + >>> next(p) + 'a' + + Pass :meth:`peek` a default value to return that instead of raising + ``StopIteration`` when the iterator is exhausted. + + >>> p = peekable([]) + >>> p.peek('hi') + 'hi' + + peekables also offer a :meth:`prepend` method, which "inserts" items + at the head of the iterable: + + >>> p = peekable([1, 2, 3]) + >>> p.prepend(10, 11, 12) + >>> next(p) + 10 + >>> p.peek() + 11 + >>> list(p) + [11, 12, 1, 2, 3] + + peekables can be indexed. Index 0 is the item that will be returned by + :func:`next`, index 1 is the item after that, and so on: + The values up to the given index will be cached. + + >>> p = peekable(['a', 'b', 'c', 'd']) + >>> p[0] + 'a' + >>> p[1] + 'b' + >>> next(p) + 'a' + + Negative indexes are supported, but be aware that they will cache the + remaining items in the source iterator, which may require significant + storage. + + To check whether a peekable is exhausted, check its truth value: + + >>> p = peekable(['a', 'b']) + >>> if p: # peekable has items + ... list(p) + ['a', 'b'] + >>> if not p: # peekable is exhausted + ... list(p) + [] + + """ + + def __init__(self, iterable): + self._it = iter(iterable) + self._cache = deque() + + def __iter__(self): + return self + + def __bool__(self): + try: + self.peek() + except StopIteration: + return False + return True + + def peek(self, default=_marker): + """Return the item that will be next returned from ``next()``. + + Return ``default`` if there are no items left. If ``default`` is not + provided, raise ``StopIteration``. + + """ + if not self._cache: + try: + self._cache.append(next(self._it)) + except StopIteration: + if default is _marker: + raise + return default + return self._cache[0] + + def prepend(self, *items): + """Stack up items to be the next ones returned from ``next()`` or + ``self.peek()``. The items will be returned in + first in, first out order:: + + >>> p = peekable([1, 2, 3]) + >>> p.prepend(10, 11, 12) + >>> next(p) + 10 + >>> list(p) + [11, 12, 1, 2, 3] + + It is possible, by prepending items, to "resurrect" a peekable that + previously raised ``StopIteration``. + + >>> p = peekable([]) + >>> next(p) + Traceback (most recent call last): + ... + StopIteration + >>> p.prepend(1) + >>> next(p) + 1 + >>> next(p) + Traceback (most recent call last): + ... + StopIteration + + """ + self._cache.extendleft(reversed(items)) + + def __next__(self): + if self._cache: + return self._cache.popleft() + + return next(self._it) + + def _get_slice(self, index): + # Normalize the slice's arguments + step = 1 if (index.step is None) else index.step + if step > 0: + start = 0 if (index.start is None) else index.start + stop = maxsize if (index.stop is None) else index.stop + elif step < 0: + start = -1 if (index.start is None) else index.start + stop = (-maxsize - 1) if (index.stop is None) else index.stop + else: + raise ValueError('slice step cannot be zero') + + # If either the start or stop index is negative, we'll need to cache + # the rest of the iterable in order to slice from the right side. + if (start < 0) or (stop < 0): + self._cache.extend(self._it) + # Otherwise we'll need to find the rightmost index and cache to that + # point. + else: + n = min(max(start, stop) + 1, maxsize) + cache_len = len(self._cache) + if n >= cache_len: + self._cache.extend(islice(self._it, n - cache_len)) + + return list(self._cache)[index] + + def __getitem__(self, index): + if isinstance(index, slice): + return self._get_slice(index) + + cache_len = len(self._cache) + if index < 0: + self._cache.extend(self._it) + elif index >= cache_len: + self._cache.extend(islice(self._it, index + 1 - cache_len)) + + return self._cache[index] + + +def collate(*iterables, **kwargs): + """Return a sorted merge of the items from each of several already-sorted + *iterables*. + + >>> list(collate('ACDZ', 'AZ', 'JKL')) + ['A', 'A', 'C', 'D', 'J', 'K', 'L', 'Z', 'Z'] + + Works lazily, keeping only the next value from each iterable in memory. Use + :func:`collate` to, for example, perform a n-way mergesort of items that + don't fit in memory. + + If a *key* function is specified, the iterables will be sorted according + to its result: + + >>> key = lambda s: int(s) # Sort by numeric value, not by string + >>> list(collate(['1', '10'], ['2', '11'], key=key)) + ['1', '2', '10', '11'] + + + If the *iterables* are sorted in descending order, set *reverse* to + ``True``: + + >>> list(collate([5, 3, 1], [4, 2, 0], reverse=True)) + [5, 4, 3, 2, 1, 0] + + If the elements of the passed-in iterables are out of order, you might get + unexpected results. + + On Python 3.5+, this function is an alias for :func:`heapq.merge`. + + """ + warnings.warn( + "collate is no longer part of more_itertools, use heapq.merge", + DeprecationWarning, + ) + return merge(*iterables, **kwargs) + + +def consumer(func): + """Decorator that automatically advances a PEP-342-style "reverse iterator" + to its first yield point so you don't have to call ``next()`` on it + manually. + + >>> @consumer + ... def tally(): + ... i = 0 + ... while True: + ... print('Thing number %s is %s.' % (i, (yield))) + ... i += 1 + ... + >>> t = tally() + >>> t.send('red') + Thing number 0 is red. + >>> t.send('fish') + Thing number 1 is fish. + + Without the decorator, you would have to call ``next(t)`` before + ``t.send()`` could be used. + + """ + + @wraps(func) + def wrapper(*args, **kwargs): + gen = func(*args, **kwargs) + next(gen) + return gen + + return wrapper + + +def ilen(iterable): + """Return the number of items in *iterable*. + + >>> ilen(x for x in range(1000000) if x % 3 == 0) + 333334 + + This consumes the iterable, so handle with care. + + """ + # This approach was selected because benchmarks showed it's likely the + # fastest of the known implementations at the time of writing. + # See GitHub tracker: #236, #230. + counter = count() + deque(zip(iterable, counter), maxlen=0) + return next(counter) + + +def iterate(func, start): + """Return ``start``, ``func(start)``, ``func(func(start))``, ... + + >>> from itertools import islice + >>> list(islice(iterate(lambda x: 2*x, 1), 10)) + [1, 2, 4, 8, 16, 32, 64, 128, 256, 512] + + """ + while True: + yield start + start = func(start) + + +def with_iter(context_manager): + """Wrap an iterable in a ``with`` statement, so it closes once exhausted. + + For example, this will close the file when the iterator is exhausted:: + + upper_lines = (line.upper() for line in with_iter(open('foo'))) + + Any context manager which returns an iterable is a candidate for + ``with_iter``. + + """ + with context_manager as iterable: + yield from iterable + + +def one(iterable, too_short=None, too_long=None): + """Return the first item from *iterable*, which is expected to contain only + that item. Raise an exception if *iterable* is empty or has more than one + item. + + :func:`one` is useful for ensuring that an iterable contains only one item. + For example, it can be used to retrieve the result of a database query + that is expected to return a single row. + + If *iterable* is empty, ``ValueError`` will be raised. You may specify a + different exception with the *too_short* keyword: + + >>> it = [] + >>> one(it) # doctest: +IGNORE_EXCEPTION_DETAIL + Traceback (most recent call last): + ... + ValueError: too many items in iterable (expected 1)' + >>> too_short = IndexError('too few items') + >>> one(it, too_short=too_short) # doctest: +IGNORE_EXCEPTION_DETAIL + Traceback (most recent call last): + ... + IndexError: too few items + + Similarly, if *iterable* contains more than one item, ``ValueError`` will + be raised. You may specify a different exception with the *too_long* + keyword: + + >>> it = ['too', 'many'] + >>> one(it) # doctest: +IGNORE_EXCEPTION_DETAIL + Traceback (most recent call last): + ... + ValueError: Expected exactly one item in iterable, but got 'too', + 'many', and perhaps more. + >>> too_long = RuntimeError + >>> one(it, too_long=too_long) # doctest: +IGNORE_EXCEPTION_DETAIL + Traceback (most recent call last): + ... + RuntimeError + + Note that :func:`one` attempts to advance *iterable* twice to ensure there + is only one item. See :func:`spy` or :func:`peekable` to check iterable + contents less destructively. + + """ + it = iter(iterable) + + try: + first_value = next(it) + except StopIteration as e: + raise ( + too_short or ValueError('too few items in iterable (expected 1)') + ) from e + + try: + second_value = next(it) + except StopIteration: + pass + else: + msg = ( + 'Expected exactly one item in iterable, but got {!r}, {!r}, ' + 'and perhaps more.'.format(first_value, second_value) + ) + raise too_long or ValueError(msg) + + return first_value + + +def raise_(exception, *args): + raise exception(*args) + + +def strictly_n(iterable, n, too_short=None, too_long=None): + """Validate that *iterable* has exactly *n* items and return them if + it does. If it has fewer than *n* items, call function *too_short* + with those items. If it has more than *n* items, call function + *too_long* with the first ``n + 1`` items. + + >>> iterable = ['a', 'b', 'c', 'd'] + >>> n = 4 + >>> list(strictly_n(iterable, n)) + ['a', 'b', 'c', 'd'] + + By default, *too_short* and *too_long* are functions that raise + ``ValueError``. + + >>> list(strictly_n('ab', 3)) # doctest: +IGNORE_EXCEPTION_DETAIL + Traceback (most recent call last): + ... + ValueError: too few items in iterable (got 2) + + >>> list(strictly_n('abc', 2)) # doctest: +IGNORE_EXCEPTION_DETAIL + Traceback (most recent call last): + ... + ValueError: too many items in iterable (got at least 3) + + You can instead supply functions that do something else. + *too_short* will be called with the number of items in *iterable*. + *too_long* will be called with `n + 1`. + + >>> def too_short(item_count): + ... raise RuntimeError + >>> it = strictly_n('abcd', 6, too_short=too_short) + >>> list(it) # doctest: +IGNORE_EXCEPTION_DETAIL + Traceback (most recent call last): + ... + RuntimeError + + >>> def too_long(item_count): + ... print('The boss is going to hear about this') + >>> it = strictly_n('abcdef', 4, too_long=too_long) + >>> list(it) + The boss is going to hear about this + ['a', 'b', 'c', 'd'] + + """ + if too_short is None: + too_short = lambda item_count: raise_( + ValueError, + 'Too few items in iterable (got {})'.format(item_count), + ) + + if too_long is None: + too_long = lambda item_count: raise_( + ValueError, + 'Too many items in iterable (got at least {})'.format(item_count), + ) + + it = iter(iterable) + for i in range(n): + try: + item = next(it) + except StopIteration: + too_short(i) + return + else: + yield item + + try: + next(it) + except StopIteration: + pass + else: + too_long(n + 1) + + +def distinct_permutations(iterable, r=None): + """Yield successive distinct permutations of the elements in *iterable*. + + >>> sorted(distinct_permutations([1, 0, 1])) + [(0, 1, 1), (1, 0, 1), (1, 1, 0)] + + Equivalent to ``set(permutations(iterable))``, except duplicates are not + generated and thrown away. For larger input sequences this is much more + efficient. + + Duplicate permutations arise when there are duplicated elements in the + input iterable. The number of items returned is + `n! / (x_1! * x_2! * ... * x_n!)`, where `n` is the total number of + items input, and each `x_i` is the count of a distinct item in the input + sequence. + + If *r* is given, only the *r*-length permutations are yielded. + + >>> sorted(distinct_permutations([1, 0, 1], r=2)) + [(0, 1), (1, 0), (1, 1)] + >>> sorted(distinct_permutations(range(3), r=2)) + [(0, 1), (0, 2), (1, 0), (1, 2), (2, 0), (2, 1)] + + """ + # Algorithm: https://w.wiki/Qai + def _full(A): + while True: + # Yield the permutation we have + yield tuple(A) + + # Find the largest index i such that A[i] < A[i + 1] + for i in range(size - 2, -1, -1): + if A[i] < A[i + 1]: + break + # If no such index exists, this permutation is the last one + else: + return + + # Find the largest index j greater than j such that A[i] < A[j] + for j in range(size - 1, i, -1): + if A[i] < A[j]: + break + + # Swap the value of A[i] with that of A[j], then reverse the + # sequence from A[i + 1] to form the new permutation + A[i], A[j] = A[j], A[i] + A[i + 1 :] = A[: i - size : -1] # A[i + 1:][::-1] + + # Algorithm: modified from the above + def _partial(A, r): + # Split A into the first r items and the last r items + head, tail = A[:r], A[r:] + right_head_indexes = range(r - 1, -1, -1) + left_tail_indexes = range(len(tail)) + + while True: + # Yield the permutation we have + yield tuple(head) + + # Starting from the right, find the first index of the head with + # value smaller than the maximum value of the tail - call it i. + pivot = tail[-1] + for i in right_head_indexes: + if head[i] < pivot: + break + pivot = head[i] + else: + return + + # Starting from the left, find the first value of the tail + # with a value greater than head[i] and swap. + for j in left_tail_indexes: + if tail[j] > head[i]: + head[i], tail[j] = tail[j], head[i] + break + # If we didn't find one, start from the right and find the first + # index of the head with a value greater than head[i] and swap. + else: + for j in right_head_indexes: + if head[j] > head[i]: + head[i], head[j] = head[j], head[i] + break + + # Reverse head[i + 1:] and swap it with tail[:r - (i + 1)] + tail += head[: i - r : -1] # head[i + 1:][::-1] + i += 1 + head[i:], tail[:] = tail[: r - i], tail[r - i :] + + items = sorted(iterable) + + size = len(items) + if r is None: + r = size + + if 0 < r <= size: + return _full(items) if (r == size) else _partial(items, r) + + return iter(() if r else ((),)) + + +def intersperse(e, iterable, n=1): + """Intersperse filler element *e* among the items in *iterable*, leaving + *n* items between each filler element. + + >>> list(intersperse('!', [1, 2, 3, 4, 5])) + [1, '!', 2, '!', 3, '!', 4, '!', 5] + + >>> list(intersperse(None, [1, 2, 3, 4, 5], n=2)) + [1, 2, None, 3, 4, None, 5] + + """ + if n == 0: + raise ValueError('n must be > 0') + elif n == 1: + # interleave(repeat(e), iterable) -> e, x_0, e, x_1, e, x_2... + # islice(..., 1, None) -> x_0, e, x_1, e, x_2... + return islice(interleave(repeat(e), iterable), 1, None) + else: + # interleave(filler, chunks) -> [e], [x_0, x_1], [e], [x_2, x_3]... + # islice(..., 1, None) -> [x_0, x_1], [e], [x_2, x_3]... + # flatten(...) -> x_0, x_1, e, x_2, x_3... + filler = repeat([e]) + chunks = chunked(iterable, n) + return flatten(islice(interleave(filler, chunks), 1, None)) + + +def unique_to_each(*iterables): + """Return the elements from each of the input iterables that aren't in the + other input iterables. + + For example, suppose you have a set of packages, each with a set of + dependencies:: + + {'pkg_1': {'A', 'B'}, 'pkg_2': {'B', 'C'}, 'pkg_3': {'B', 'D'}} + + If you remove one package, which dependencies can also be removed? + + If ``pkg_1`` is removed, then ``A`` is no longer necessary - it is not + associated with ``pkg_2`` or ``pkg_3``. Similarly, ``C`` is only needed for + ``pkg_2``, and ``D`` is only needed for ``pkg_3``:: + + >>> unique_to_each({'A', 'B'}, {'B', 'C'}, {'B', 'D'}) + [['A'], ['C'], ['D']] + + If there are duplicates in one input iterable that aren't in the others + they will be duplicated in the output. Input order is preserved:: + + >>> unique_to_each("mississippi", "missouri") + [['p', 'p'], ['o', 'u', 'r']] + + It is assumed that the elements of each iterable are hashable. + + """ + pool = [list(it) for it in iterables] + counts = Counter(chain.from_iterable(map(set, pool))) + uniques = {element for element in counts if counts[element] == 1} + return [list(filter(uniques.__contains__, it)) for it in pool] + + +def windowed(seq, n, fillvalue=None, step=1): + """Return a sliding window of width *n* over the given iterable. + + >>> all_windows = windowed([1, 2, 3, 4, 5], 3) + >>> list(all_windows) + [(1, 2, 3), (2, 3, 4), (3, 4, 5)] + + When the window is larger than the iterable, *fillvalue* is used in place + of missing values: + + >>> list(windowed([1, 2, 3], 4)) + [(1, 2, 3, None)] + + Each window will advance in increments of *step*: + + >>> list(windowed([1, 2, 3, 4, 5, 6], 3, fillvalue='!', step=2)) + [(1, 2, 3), (3, 4, 5), (5, 6, '!')] + + To slide into the iterable's items, use :func:`chain` to add filler items + to the left: + + >>> iterable = [1, 2, 3, 4] + >>> n = 3 + >>> padding = [None] * (n - 1) + >>> list(windowed(chain(padding, iterable), 3)) + [(None, None, 1), (None, 1, 2), (1, 2, 3), (2, 3, 4)] + """ + if n < 0: + raise ValueError('n must be >= 0') + if n == 0: + yield tuple() + return + if step < 1: + raise ValueError('step must be >= 1') + + window = deque(maxlen=n) + i = n + for _ in map(window.append, seq): + i -= 1 + if not i: + i = step + yield tuple(window) + + size = len(window) + if size < n: + yield tuple(chain(window, repeat(fillvalue, n - size))) + elif 0 < i < min(step, n): + window += (fillvalue,) * i + yield tuple(window) + + +def substrings(iterable): + """Yield all of the substrings of *iterable*. + + >>> [''.join(s) for s in substrings('more')] + ['m', 'o', 'r', 'e', 'mo', 'or', 're', 'mor', 'ore', 'more'] + + Note that non-string iterables can also be subdivided. + + >>> list(substrings([0, 1, 2])) + [(0,), (1,), (2,), (0, 1), (1, 2), (0, 1, 2)] + + """ + # The length-1 substrings + seq = [] + for item in iter(iterable): + seq.append(item) + yield (item,) + seq = tuple(seq) + item_count = len(seq) + + # And the rest + for n in range(2, item_count + 1): + for i in range(item_count - n + 1): + yield seq[i : i + n] + + +def substrings_indexes(seq, reverse=False): + """Yield all substrings and their positions in *seq* + + The items yielded will be a tuple of the form ``(substr, i, j)``, where + ``substr == seq[i:j]``. + + This function only works for iterables that support slicing, such as + ``str`` objects. + + >>> for item in substrings_indexes('more'): + ... print(item) + ('m', 0, 1) + ('o', 1, 2) + ('r', 2, 3) + ('e', 3, 4) + ('mo', 0, 2) + ('or', 1, 3) + ('re', 2, 4) + ('mor', 0, 3) + ('ore', 1, 4) + ('more', 0, 4) + + Set *reverse* to ``True`` to yield the same items in the opposite order. + + + """ + r = range(1, len(seq) + 1) + if reverse: + r = reversed(r) + return ( + (seq[i : i + L], i, i + L) for L in r for i in range(len(seq) - L + 1) + ) + + +class bucket: + """Wrap *iterable* and return an object that buckets it iterable into + child iterables based on a *key* function. + + >>> iterable = ['a1', 'b1', 'c1', 'a2', 'b2', 'c2', 'b3'] + >>> s = bucket(iterable, key=lambda x: x[0]) # Bucket by 1st character + >>> sorted(list(s)) # Get the keys + ['a', 'b', 'c'] + >>> a_iterable = s['a'] + >>> next(a_iterable) + 'a1' + >>> next(a_iterable) + 'a2' + >>> list(s['b']) + ['b1', 'b2', 'b3'] + + The original iterable will be advanced and its items will be cached until + they are used by the child iterables. This may require significant storage. + + By default, attempting to select a bucket to which no items belong will + exhaust the iterable and cache all values. + If you specify a *validator* function, selected buckets will instead be + checked against it. + + >>> from itertools import count + >>> it = count(1, 2) # Infinite sequence of odd numbers + >>> key = lambda x: x % 10 # Bucket by last digit + >>> validator = lambda x: x in {1, 3, 5, 7, 9} # Odd digits only + >>> s = bucket(it, key=key, validator=validator) + >>> 2 in s + False + >>> list(s[2]) + [] + + """ + + def __init__(self, iterable, key, validator=None): + self._it = iter(iterable) + self._key = key + self._cache = defaultdict(deque) + self._validator = validator or (lambda x: True) + + def __contains__(self, value): + if not self._validator(value): + return False + + try: + item = next(self[value]) + except StopIteration: + return False + else: + self._cache[value].appendleft(item) + + return True + + def _get_values(self, value): + """ + Helper to yield items from the parent iterator that match *value*. + Items that don't match are stored in the local cache as they + are encountered. + """ + while True: + # If we've cached some items that match the target value, emit + # the first one and evict it from the cache. + if self._cache[value]: + yield self._cache[value].popleft() + # Otherwise we need to advance the parent iterator to search for + # a matching item, caching the rest. + else: + while True: + try: + item = next(self._it) + except StopIteration: + return + item_value = self._key(item) + if item_value == value: + yield item + break + elif self._validator(item_value): + self._cache[item_value].append(item) + + def __iter__(self): + for item in self._it: + item_value = self._key(item) + if self._validator(item_value): + self._cache[item_value].append(item) + + yield from self._cache.keys() + + def __getitem__(self, value): + if not self._validator(value): + return iter(()) + + return self._get_values(value) + + +def spy(iterable, n=1): + """Return a 2-tuple with a list containing the first *n* elements of + *iterable*, and an iterator with the same items as *iterable*. + This allows you to "look ahead" at the items in the iterable without + advancing it. + + There is one item in the list by default: + + >>> iterable = 'abcdefg' + >>> head, iterable = spy(iterable) + >>> head + ['a'] + >>> list(iterable) + ['a', 'b', 'c', 'd', 'e', 'f', 'g'] + + You may use unpacking to retrieve items instead of lists: + + >>> (head,), iterable = spy('abcdefg') + >>> head + 'a' + >>> (first, second), iterable = spy('abcdefg', 2) + >>> first + 'a' + >>> second + 'b' + + The number of items requested can be larger than the number of items in + the iterable: + + >>> iterable = [1, 2, 3, 4, 5] + >>> head, iterable = spy(iterable, 10) + >>> head + [1, 2, 3, 4, 5] + >>> list(iterable) + [1, 2, 3, 4, 5] + + """ + it = iter(iterable) + head = take(n, it) + + return head.copy(), chain(head, it) + + +def interleave(*iterables): + """Return a new iterable yielding from each iterable in turn, + until the shortest is exhausted. + + >>> list(interleave([1, 2, 3], [4, 5], [6, 7, 8])) + [1, 4, 6, 2, 5, 7] + + For a version that doesn't terminate after the shortest iterable is + exhausted, see :func:`interleave_longest`. + + """ + return chain.from_iterable(zip(*iterables)) + + +def interleave_longest(*iterables): + """Return a new iterable yielding from each iterable in turn, + skipping any that are exhausted. + + >>> list(interleave_longest([1, 2, 3], [4, 5], [6, 7, 8])) + [1, 4, 6, 2, 5, 7, 3, 8] + + This function produces the same output as :func:`roundrobin`, but may + perform better for some inputs (in particular when the number of iterables + is large). + + """ + i = chain.from_iterable(zip_longest(*iterables, fillvalue=_marker)) + return (x for x in i if x is not _marker) + + +def interleave_evenly(iterables, lengths=None): + """ + Interleave multiple iterables so that their elements are evenly distributed + throughout the output sequence. + + >>> iterables = [1, 2, 3, 4, 5], ['a', 'b'] + >>> list(interleave_evenly(iterables)) + [1, 2, 'a', 3, 4, 'b', 5] + + >>> iterables = [[1, 2, 3], [4, 5], [6, 7, 8]] + >>> list(interleave_evenly(iterables)) + [1, 6, 4, 2, 7, 3, 8, 5] + + This function requires iterables of known length. Iterables without + ``__len__()`` can be used by manually specifying lengths with *lengths*: + + >>> from itertools import combinations, repeat + >>> iterables = [combinations(range(4), 2), ['a', 'b', 'c']] + >>> lengths = [4 * (4 - 1) // 2, 3] + >>> list(interleave_evenly(iterables, lengths=lengths)) + [(0, 1), (0, 2), 'a', (0, 3), (1, 2), 'b', (1, 3), (2, 3), 'c'] + + Based on Bresenham's algorithm. + """ + if lengths is None: + try: + lengths = [len(it) for it in iterables] + except TypeError: + raise ValueError( + 'Iterable lengths could not be determined automatically. ' + 'Specify them with the lengths keyword.' + ) + elif len(iterables) != len(lengths): + raise ValueError('Mismatching number of iterables and lengths.') + + dims = len(lengths) + + # sort iterables by length, descending + lengths_permute = sorted( + range(dims), key=lambda i: lengths[i], reverse=True + ) + lengths_desc = [lengths[i] for i in lengths_permute] + iters_desc = [iter(iterables[i]) for i in lengths_permute] + + # the longest iterable is the primary one (Bresenham: the longest + # distance along an axis) + delta_primary, deltas_secondary = lengths_desc[0], lengths_desc[1:] + iter_primary, iters_secondary = iters_desc[0], iters_desc[1:] + errors = [delta_primary // dims] * len(deltas_secondary) + + to_yield = sum(lengths) + while to_yield: + yield next(iter_primary) + to_yield -= 1 + # update errors for each secondary iterable + errors = [e - delta for e, delta in zip(errors, deltas_secondary)] + + # those iterables for which the error is negative are yielded + # ("diagonal step" in Bresenham) + for i, e in enumerate(errors): + if e < 0: + yield next(iters_secondary[i]) + to_yield -= 1 + errors[i] += delta_primary + + +def collapse(iterable, base_type=None, levels=None): + """Flatten an iterable with multiple levels of nesting (e.g., a list of + lists of tuples) into non-iterable types. + + >>> iterable = [(1, 2), ([3, 4], [[5], [6]])] + >>> list(collapse(iterable)) + [1, 2, 3, 4, 5, 6] + + Binary and text strings are not considered iterable and + will not be collapsed. + + To avoid collapsing other types, specify *base_type*: + + >>> iterable = ['ab', ('cd', 'ef'), ['gh', 'ij']] + >>> list(collapse(iterable, base_type=tuple)) + ['ab', ('cd', 'ef'), 'gh', 'ij'] + + Specify *levels* to stop flattening after a certain level: + + >>> iterable = [('a', ['b']), ('c', ['d'])] + >>> list(collapse(iterable)) # Fully flattened + ['a', 'b', 'c', 'd'] + >>> list(collapse(iterable, levels=1)) # Only one level flattened + ['a', ['b'], 'c', ['d']] + + """ + + def walk(node, level): + if ( + ((levels is not None) and (level > levels)) + or isinstance(node, (str, bytes)) + or ((base_type is not None) and isinstance(node, base_type)) + ): + yield node + return + + try: + tree = iter(node) + except TypeError: + yield node + return + else: + for child in tree: + yield from walk(child, level + 1) + + yield from walk(iterable, 0) + + +def side_effect(func, iterable, chunk_size=None, before=None, after=None): + """Invoke *func* on each item in *iterable* (or on each *chunk_size* group + of items) before yielding the item. + + `func` must be a function that takes a single argument. Its return value + will be discarded. + + *before* and *after* are optional functions that take no arguments. They + will be executed before iteration starts and after it ends, respectively. + + `side_effect` can be used for logging, updating progress bars, or anything + that is not functionally "pure." + + Emitting a status message: + + >>> from more_itertools import consume + >>> func = lambda item: print('Received {}'.format(item)) + >>> consume(side_effect(func, range(2))) + Received 0 + Received 1 + + Operating on chunks of items: + + >>> pair_sums = [] + >>> func = lambda chunk: pair_sums.append(sum(chunk)) + >>> list(side_effect(func, [0, 1, 2, 3, 4, 5], 2)) + [0, 1, 2, 3, 4, 5] + >>> list(pair_sums) + [1, 5, 9] + + Writing to a file-like object: + + >>> from io import StringIO + >>> from more_itertools import consume + >>> f = StringIO() + >>> func = lambda x: print(x, file=f) + >>> before = lambda: print(u'HEADER', file=f) + >>> after = f.close + >>> it = [u'a', u'b', u'c'] + >>> consume(side_effect(func, it, before=before, after=after)) + >>> f.closed + True + + """ + try: + if before is not None: + before() + + if chunk_size is None: + for item in iterable: + func(item) + yield item + else: + for chunk in chunked(iterable, chunk_size): + func(chunk) + yield from chunk + finally: + if after is not None: + after() + + +def sliced(seq, n, strict=False): + """Yield slices of length *n* from the sequence *seq*. + + >>> list(sliced((1, 2, 3, 4, 5, 6), 3)) + [(1, 2, 3), (4, 5, 6)] + + By the default, the last yielded slice will have fewer than *n* elements + if the length of *seq* is not divisible by *n*: + + >>> list(sliced((1, 2, 3, 4, 5, 6, 7, 8), 3)) + [(1, 2, 3), (4, 5, 6), (7, 8)] + + If the length of *seq* is not divisible by *n* and *strict* is + ``True``, then ``ValueError`` will be raised before the last + slice is yielded. + + This function will only work for iterables that support slicing. + For non-sliceable iterables, see :func:`chunked`. + + """ + iterator = takewhile(len, (seq[i : i + n] for i in count(0, n))) + if strict: + + def ret(): + for _slice in iterator: + if len(_slice) != n: + raise ValueError("seq is not divisible by n.") + yield _slice + + return iter(ret()) + else: + return iterator + + +def split_at(iterable, pred, maxsplit=-1, keep_separator=False): + """Yield lists of items from *iterable*, where each list is delimited by + an item where callable *pred* returns ``True``. + + >>> list(split_at('abcdcba', lambda x: x == 'b')) + [['a'], ['c', 'd', 'c'], ['a']] + + >>> list(split_at(range(10), lambda n: n % 2 == 1)) + [[0], [2], [4], [6], [8], []] + + At most *maxsplit* splits are done. If *maxsplit* is not specified or -1, + then there is no limit on the number of splits: + + >>> list(split_at(range(10), lambda n: n % 2 == 1, maxsplit=2)) + [[0], [2], [4, 5, 6, 7, 8, 9]] + + By default, the delimiting items are not included in the output. + The include them, set *keep_separator* to ``True``. + + >>> list(split_at('abcdcba', lambda x: x == 'b', keep_separator=True)) + [['a'], ['b'], ['c', 'd', 'c'], ['b'], ['a']] + + """ + if maxsplit == 0: + yield list(iterable) + return + + buf = [] + it = iter(iterable) + for item in it: + if pred(item): + yield buf + if keep_separator: + yield [item] + if maxsplit == 1: + yield list(it) + return + buf = [] + maxsplit -= 1 + else: + buf.append(item) + yield buf + + +def split_before(iterable, pred, maxsplit=-1): + """Yield lists of items from *iterable*, where each list ends just before + an item for which callable *pred* returns ``True``: + + >>> list(split_before('OneTwo', lambda s: s.isupper())) + [['O', 'n', 'e'], ['T', 'w', 'o']] + + >>> list(split_before(range(10), lambda n: n % 3 == 0)) + [[0, 1, 2], [3, 4, 5], [6, 7, 8], [9]] + + At most *maxsplit* splits are done. If *maxsplit* is not specified or -1, + then there is no limit on the number of splits: + + >>> list(split_before(range(10), lambda n: n % 3 == 0, maxsplit=2)) + [[0, 1, 2], [3, 4, 5], [6, 7, 8, 9]] + """ + if maxsplit == 0: + yield list(iterable) + return + + buf = [] + it = iter(iterable) + for item in it: + if pred(item) and buf: + yield buf + if maxsplit == 1: + yield [item] + list(it) + return + buf = [] + maxsplit -= 1 + buf.append(item) + if buf: + yield buf + + +def split_after(iterable, pred, maxsplit=-1): + """Yield lists of items from *iterable*, where each list ends with an + item where callable *pred* returns ``True``: + + >>> list(split_after('one1two2', lambda s: s.isdigit())) + [['o', 'n', 'e', '1'], ['t', 'w', 'o', '2']] + + >>> list(split_after(range(10), lambda n: n % 3 == 0)) + [[0], [1, 2, 3], [4, 5, 6], [7, 8, 9]] + + At most *maxsplit* splits are done. If *maxsplit* is not specified or -1, + then there is no limit on the number of splits: + + >>> list(split_after(range(10), lambda n: n % 3 == 0, maxsplit=2)) + [[0], [1, 2, 3], [4, 5, 6, 7, 8, 9]] + + """ + if maxsplit == 0: + yield list(iterable) + return + + buf = [] + it = iter(iterable) + for item in it: + buf.append(item) + if pred(item) and buf: + yield buf + if maxsplit == 1: + yield list(it) + return + buf = [] + maxsplit -= 1 + if buf: + yield buf + + +def split_when(iterable, pred, maxsplit=-1): + """Split *iterable* into pieces based on the output of *pred*. + *pred* should be a function that takes successive pairs of items and + returns ``True`` if the iterable should be split in between them. + + For example, to find runs of increasing numbers, split the iterable when + element ``i`` is larger than element ``i + 1``: + + >>> list(split_when([1, 2, 3, 3, 2, 5, 2, 4, 2], lambda x, y: x > y)) + [[1, 2, 3, 3], [2, 5], [2, 4], [2]] + + At most *maxsplit* splits are done. If *maxsplit* is not specified or -1, + then there is no limit on the number of splits: + + >>> list(split_when([1, 2, 3, 3, 2, 5, 2, 4, 2], + ... lambda x, y: x > y, maxsplit=2)) + [[1, 2, 3, 3], [2, 5], [2, 4, 2]] + + """ + if maxsplit == 0: + yield list(iterable) + return + + it = iter(iterable) + try: + cur_item = next(it) + except StopIteration: + return + + buf = [cur_item] + for next_item in it: + if pred(cur_item, next_item): + yield buf + if maxsplit == 1: + yield [next_item] + list(it) + return + buf = [] + maxsplit -= 1 + + buf.append(next_item) + cur_item = next_item + + yield buf + + +def split_into(iterable, sizes): + """Yield a list of sequential items from *iterable* of length 'n' for each + integer 'n' in *sizes*. + + >>> list(split_into([1,2,3,4,5,6], [1,2,3])) + [[1], [2, 3], [4, 5, 6]] + + If the sum of *sizes* is smaller than the length of *iterable*, then the + remaining items of *iterable* will not be returned. + + >>> list(split_into([1,2,3,4,5,6], [2,3])) + [[1, 2], [3, 4, 5]] + + If the sum of *sizes* is larger than the length of *iterable*, fewer items + will be returned in the iteration that overruns *iterable* and further + lists will be empty: + + >>> list(split_into([1,2,3,4], [1,2,3,4])) + [[1], [2, 3], [4], []] + + When a ``None`` object is encountered in *sizes*, the returned list will + contain items up to the end of *iterable* the same way that itertools.slice + does: + + >>> list(split_into([1,2,3,4,5,6,7,8,9,0], [2,3,None])) + [[1, 2], [3, 4, 5], [6, 7, 8, 9, 0]] + + :func:`split_into` can be useful for grouping a series of items where the + sizes of the groups are not uniform. An example would be where in a row + from a table, multiple columns represent elements of the same feature + (e.g. a point represented by x,y,z) but, the format is not the same for + all columns. + """ + # convert the iterable argument into an iterator so its contents can + # be consumed by islice in case it is a generator + it = iter(iterable) + + for size in sizes: + if size is None: + yield list(it) + return + else: + yield list(islice(it, size)) + + +def padded(iterable, fillvalue=None, n=None, next_multiple=False): + """Yield the elements from *iterable*, followed by *fillvalue*, such that + at least *n* items are emitted. + + >>> list(padded([1, 2, 3], '?', 5)) + [1, 2, 3, '?', '?'] + + If *next_multiple* is ``True``, *fillvalue* will be emitted until the + number of items emitted is a multiple of *n*:: + + >>> list(padded([1, 2, 3, 4], n=3, next_multiple=True)) + [1, 2, 3, 4, None, None] + + If *n* is ``None``, *fillvalue* will be emitted indefinitely. + + """ + it = iter(iterable) + if n is None: + yield from chain(it, repeat(fillvalue)) + elif n < 1: + raise ValueError('n must be at least 1') + else: + item_count = 0 + for item in it: + yield item + item_count += 1 + + remaining = (n - item_count) % n if next_multiple else n - item_count + for _ in range(remaining): + yield fillvalue + + +def repeat_each(iterable, n=2): + """Repeat each element in *iterable* *n* times. + + >>> list(repeat_each('ABC', 3)) + ['A', 'A', 'A', 'B', 'B', 'B', 'C', 'C', 'C'] + """ + return chain.from_iterable(map(repeat, iterable, repeat(n))) + + +def repeat_last(iterable, default=None): + """After the *iterable* is exhausted, keep yielding its last element. + + >>> list(islice(repeat_last(range(3)), 5)) + [0, 1, 2, 2, 2] + + If the iterable is empty, yield *default* forever:: + + >>> list(islice(repeat_last(range(0), 42), 5)) + [42, 42, 42, 42, 42] + + """ + item = _marker + for item in iterable: + yield item + final = default if item is _marker else item + yield from repeat(final) + + +def distribute(n, iterable): + """Distribute the items from *iterable* among *n* smaller iterables. + + >>> group_1, group_2 = distribute(2, [1, 2, 3, 4, 5, 6]) + >>> list(group_1) + [1, 3, 5] + >>> list(group_2) + [2, 4, 6] + + If the length of *iterable* is not evenly divisible by *n*, then the + length of the returned iterables will not be identical: + + >>> children = distribute(3, [1, 2, 3, 4, 5, 6, 7]) + >>> [list(c) for c in children] + [[1, 4, 7], [2, 5], [3, 6]] + + If the length of *iterable* is smaller than *n*, then the last returned + iterables will be empty: + + >>> children = distribute(5, [1, 2, 3]) + >>> [list(c) for c in children] + [[1], [2], [3], [], []] + + This function uses :func:`itertools.tee` and may require significant + storage. If you need the order items in the smaller iterables to match the + original iterable, see :func:`divide`. + + """ + if n < 1: + raise ValueError('n must be at least 1') + + children = tee(iterable, n) + return [islice(it, index, None, n) for index, it in enumerate(children)] + + +def stagger(iterable, offsets=(-1, 0, 1), longest=False, fillvalue=None): + """Yield tuples whose elements are offset from *iterable*. + The amount by which the `i`-th item in each tuple is offset is given by + the `i`-th item in *offsets*. + + >>> list(stagger([0, 1, 2, 3])) + [(None, 0, 1), (0, 1, 2), (1, 2, 3)] + >>> list(stagger(range(8), offsets=(0, 2, 4))) + [(0, 2, 4), (1, 3, 5), (2, 4, 6), (3, 5, 7)] + + By default, the sequence will end when the final element of a tuple is the + last item in the iterable. To continue until the first element of a tuple + is the last item in the iterable, set *longest* to ``True``:: + + >>> list(stagger([0, 1, 2, 3], longest=True)) + [(None, 0, 1), (0, 1, 2), (1, 2, 3), (2, 3, None), (3, None, None)] + + By default, ``None`` will be used to replace offsets beyond the end of the + sequence. Specify *fillvalue* to use some other value. + + """ + children = tee(iterable, len(offsets)) + + return zip_offset( + *children, offsets=offsets, longest=longest, fillvalue=fillvalue + ) + + +class UnequalIterablesError(ValueError): + def __init__(self, details=None): + msg = 'Iterables have different lengths' + if details is not None: + msg += (': index 0 has length {}; index {} has length {}').format( + *details + ) + + super().__init__(msg) + + +def _zip_equal_generator(iterables): + for combo in zip_longest(*iterables, fillvalue=_marker): + for val in combo: + if val is _marker: + raise UnequalIterablesError() + yield combo + + +def _zip_equal(*iterables): + # Check whether the iterables are all the same size. + try: + first_size = len(iterables[0]) + for i, it in enumerate(iterables[1:], 1): + size = len(it) + if size != first_size: + break + else: + # If we didn't break out, we can use the built-in zip. + return zip(*iterables) + + # If we did break out, there was a mismatch. + raise UnequalIterablesError(details=(first_size, i, size)) + # If any one of the iterables didn't have a length, start reading + # them until one runs out. + except TypeError: + return _zip_equal_generator(iterables) + + +def zip_equal(*iterables): + """``zip`` the input *iterables* together, but raise + ``UnequalIterablesError`` if they aren't all the same length. + + >>> it_1 = range(3) + >>> it_2 = iter('abc') + >>> list(zip_equal(it_1, it_2)) + [(0, 'a'), (1, 'b'), (2, 'c')] + + >>> it_1 = range(3) + >>> it_2 = iter('abcd') + >>> list(zip_equal(it_1, it_2)) # doctest: +IGNORE_EXCEPTION_DETAIL + Traceback (most recent call last): + ... + more_itertools.more.UnequalIterablesError: Iterables have different + lengths + + """ + if hexversion >= 0x30A00A6: + warnings.warn( + ( + 'zip_equal will be removed in a future version of ' + 'more-itertools. Use the builtin zip function with ' + 'strict=True instead.' + ), + DeprecationWarning, + ) + + return _zip_equal(*iterables) + + +def zip_offset(*iterables, offsets, longest=False, fillvalue=None): + """``zip`` the input *iterables* together, but offset the `i`-th iterable + by the `i`-th item in *offsets*. + + >>> list(zip_offset('0123', 'abcdef', offsets=(0, 1))) + [('0', 'b'), ('1', 'c'), ('2', 'd'), ('3', 'e')] + + This can be used as a lightweight alternative to SciPy or pandas to analyze + data sets in which some series have a lead or lag relationship. + + By default, the sequence will end when the shortest iterable is exhausted. + To continue until the longest iterable is exhausted, set *longest* to + ``True``. + + >>> list(zip_offset('0123', 'abcdef', offsets=(0, 1), longest=True)) + [('0', 'b'), ('1', 'c'), ('2', 'd'), ('3', 'e'), (None, 'f')] + + By default, ``None`` will be used to replace offsets beyond the end of the + sequence. Specify *fillvalue* to use some other value. + + """ + if len(iterables) != len(offsets): + raise ValueError("Number of iterables and offsets didn't match") + + staggered = [] + for it, n in zip(iterables, offsets): + if n < 0: + staggered.append(chain(repeat(fillvalue, -n), it)) + elif n > 0: + staggered.append(islice(it, n, None)) + else: + staggered.append(it) + + if longest: + return zip_longest(*staggered, fillvalue=fillvalue) + + return zip(*staggered) + + +def sort_together(iterables, key_list=(0,), key=None, reverse=False): + """Return the input iterables sorted together, with *key_list* as the + priority for sorting. All iterables are trimmed to the length of the + shortest one. + + This can be used like the sorting function in a spreadsheet. If each + iterable represents a column of data, the key list determines which + columns are used for sorting. + + By default, all iterables are sorted using the ``0``-th iterable:: + + >>> iterables = [(4, 3, 2, 1), ('a', 'b', 'c', 'd')] + >>> sort_together(iterables) + [(1, 2, 3, 4), ('d', 'c', 'b', 'a')] + + Set a different key list to sort according to another iterable. + Specifying multiple keys dictates how ties are broken:: + + >>> iterables = [(3, 1, 2), (0, 1, 0), ('c', 'b', 'a')] + >>> sort_together(iterables, key_list=(1, 2)) + [(2, 3, 1), (0, 0, 1), ('a', 'c', 'b')] + + To sort by a function of the elements of the iterable, pass a *key* + function. Its arguments are the elements of the iterables corresponding to + the key list:: + + >>> names = ('a', 'b', 'c') + >>> lengths = (1, 2, 3) + >>> widths = (5, 2, 1) + >>> def area(length, width): + ... return length * width + >>> sort_together([names, lengths, widths], key_list=(1, 2), key=area) + [('c', 'b', 'a'), (3, 2, 1), (1, 2, 5)] + + Set *reverse* to ``True`` to sort in descending order. + + >>> sort_together([(1, 2, 3), ('c', 'b', 'a')], reverse=True) + [(3, 2, 1), ('a', 'b', 'c')] + + """ + if key is None: + # if there is no key function, the key argument to sorted is an + # itemgetter + key_argument = itemgetter(*key_list) + else: + # if there is a key function, call it with the items at the offsets + # specified by the key function as arguments + key_list = list(key_list) + if len(key_list) == 1: + # if key_list contains a single item, pass the item at that offset + # as the only argument to the key function + key_offset = key_list[0] + key_argument = lambda zipped_items: key(zipped_items[key_offset]) + else: + # if key_list contains multiple items, use itemgetter to return a + # tuple of items, which we pass as *args to the key function + get_key_items = itemgetter(*key_list) + key_argument = lambda zipped_items: key( + *get_key_items(zipped_items) + ) + + return list( + zip(*sorted(zip(*iterables), key=key_argument, reverse=reverse)) + ) + + +def unzip(iterable): + """The inverse of :func:`zip`, this function disaggregates the elements + of the zipped *iterable*. + + The ``i``-th iterable contains the ``i``-th element from each element + of the zipped iterable. The first element is used to to determine the + length of the remaining elements. + + >>> iterable = [('a', 1), ('b', 2), ('c', 3), ('d', 4)] + >>> letters, numbers = unzip(iterable) + >>> list(letters) + ['a', 'b', 'c', 'd'] + >>> list(numbers) + [1, 2, 3, 4] + + This is similar to using ``zip(*iterable)``, but it avoids reading + *iterable* into memory. Note, however, that this function uses + :func:`itertools.tee` and thus may require significant storage. + + """ + head, iterable = spy(iter(iterable)) + if not head: + # empty iterable, e.g. zip([], [], []) + return () + # spy returns a one-length iterable as head + head = head[0] + iterables = tee(iterable, len(head)) + + def itemgetter(i): + def getter(obj): + try: + return obj[i] + except IndexError: + # basically if we have an iterable like + # iter([(1, 2, 3), (4, 5), (6,)]) + # the second unzipped iterable would fail at the third tuple + # since it would try to access tup[1] + # same with the third unzipped iterable and the second tuple + # to support these "improperly zipped" iterables, + # we create a custom itemgetter + # which just stops the unzipped iterables + # at first length mismatch + raise StopIteration + + return getter + + return tuple(map(itemgetter(i), it) for i, it in enumerate(iterables)) + + +def divide(n, iterable): + """Divide the elements from *iterable* into *n* parts, maintaining + order. + + >>> group_1, group_2 = divide(2, [1, 2, 3, 4, 5, 6]) + >>> list(group_1) + [1, 2, 3] + >>> list(group_2) + [4, 5, 6] + + If the length of *iterable* is not evenly divisible by *n*, then the + length of the returned iterables will not be identical: + + >>> children = divide(3, [1, 2, 3, 4, 5, 6, 7]) + >>> [list(c) for c in children] + [[1, 2, 3], [4, 5], [6, 7]] + + If the length of the iterable is smaller than n, then the last returned + iterables will be empty: + + >>> children = divide(5, [1, 2, 3]) + >>> [list(c) for c in children] + [[1], [2], [3], [], []] + + This function will exhaust the iterable before returning and may require + significant storage. If order is not important, see :func:`distribute`, + which does not first pull the iterable into memory. + + """ + if n < 1: + raise ValueError('n must be at least 1') + + try: + iterable[:0] + except TypeError: + seq = tuple(iterable) + else: + seq = iterable + + q, r = divmod(len(seq), n) + + ret = [] + stop = 0 + for i in range(1, n + 1): + start = stop + stop += q + 1 if i <= r else q + ret.append(iter(seq[start:stop])) + + return ret + + +def always_iterable(obj, base_type=(str, bytes)): + """If *obj* is iterable, return an iterator over its items:: + + >>> obj = (1, 2, 3) + >>> list(always_iterable(obj)) + [1, 2, 3] + + If *obj* is not iterable, return a one-item iterable containing *obj*:: + + >>> obj = 1 + >>> list(always_iterable(obj)) + [1] + + If *obj* is ``None``, return an empty iterable: + + >>> obj = None + >>> list(always_iterable(None)) + [] + + By default, binary and text strings are not considered iterable:: + + >>> obj = 'foo' + >>> list(always_iterable(obj)) + ['foo'] + + If *base_type* is set, objects for which ``isinstance(obj, base_type)`` + returns ``True`` won't be considered iterable. + + >>> obj = {'a': 1} + >>> list(always_iterable(obj)) # Iterate over the dict's keys + ['a'] + >>> list(always_iterable(obj, base_type=dict)) # Treat dicts as a unit + [{'a': 1}] + + Set *base_type* to ``None`` to avoid any special handling and treat objects + Python considers iterable as iterable: + + >>> obj = 'foo' + >>> list(always_iterable(obj, base_type=None)) + ['f', 'o', 'o'] + """ + if obj is None: + return iter(()) + + if (base_type is not None) and isinstance(obj, base_type): + return iter((obj,)) + + try: + return iter(obj) + except TypeError: + return iter((obj,)) + + +def adjacent(predicate, iterable, distance=1): + """Return an iterable over `(bool, item)` tuples where the `item` is + drawn from *iterable* and the `bool` indicates whether + that item satisfies the *predicate* or is adjacent to an item that does. + + For example, to find whether items are adjacent to a ``3``:: + + >>> list(adjacent(lambda x: x == 3, range(6))) + [(False, 0), (False, 1), (True, 2), (True, 3), (True, 4), (False, 5)] + + Set *distance* to change what counts as adjacent. For example, to find + whether items are two places away from a ``3``: + + >>> list(adjacent(lambda x: x == 3, range(6), distance=2)) + [(False, 0), (True, 1), (True, 2), (True, 3), (True, 4), (True, 5)] + + This is useful for contextualizing the results of a search function. + For example, a code comparison tool might want to identify lines that + have changed, but also surrounding lines to give the viewer of the diff + context. + + The predicate function will only be called once for each item in the + iterable. + + See also :func:`groupby_transform`, which can be used with this function + to group ranges of items with the same `bool` value. + + """ + # Allow distance=0 mainly for testing that it reproduces results with map() + if distance < 0: + raise ValueError('distance must be at least 0') + + i1, i2 = tee(iterable) + padding = [False] * distance + selected = chain(padding, map(predicate, i1), padding) + adjacent_to_selected = map(any, windowed(selected, 2 * distance + 1)) + return zip(adjacent_to_selected, i2) + + +def groupby_transform(iterable, keyfunc=None, valuefunc=None, reducefunc=None): + """An extension of :func:`itertools.groupby` that can apply transformations + to the grouped data. + + * *keyfunc* is a function computing a key value for each item in *iterable* + * *valuefunc* is a function that transforms the individual items from + *iterable* after grouping + * *reducefunc* is a function that transforms each group of items + + >>> iterable = 'aAAbBBcCC' + >>> keyfunc = lambda k: k.upper() + >>> valuefunc = lambda v: v.lower() + >>> reducefunc = lambda g: ''.join(g) + >>> list(groupby_transform(iterable, keyfunc, valuefunc, reducefunc)) + [('A', 'aaa'), ('B', 'bbb'), ('C', 'ccc')] + + Each optional argument defaults to an identity function if not specified. + + :func:`groupby_transform` is useful when grouping elements of an iterable + using a separate iterable as the key. To do this, :func:`zip` the iterables + and pass a *keyfunc* that extracts the first element and a *valuefunc* + that extracts the second element:: + + >>> from operator import itemgetter + >>> keys = [0, 0, 1, 1, 1, 2, 2, 2, 3] + >>> values = 'abcdefghi' + >>> iterable = zip(keys, values) + >>> grouper = groupby_transform(iterable, itemgetter(0), itemgetter(1)) + >>> [(k, ''.join(g)) for k, g in grouper] + [(0, 'ab'), (1, 'cde'), (2, 'fgh'), (3, 'i')] + + Note that the order of items in the iterable is significant. + Only adjacent items are grouped together, so if you don't want any + duplicate groups, you should sort the iterable by the key function. + + """ + ret = groupby(iterable, keyfunc) + if valuefunc: + ret = ((k, map(valuefunc, g)) for k, g in ret) + if reducefunc: + ret = ((k, reducefunc(g)) for k, g in ret) + + return ret + + +class numeric_range(abc.Sequence, abc.Hashable): + """An extension of the built-in ``range()`` function whose arguments can + be any orderable numeric type. + + With only *stop* specified, *start* defaults to ``0`` and *step* + defaults to ``1``. The output items will match the type of *stop*: + + >>> list(numeric_range(3.5)) + [0.0, 1.0, 2.0, 3.0] + + With only *start* and *stop* specified, *step* defaults to ``1``. The + output items will match the type of *start*: + + >>> from decimal import Decimal + >>> start = Decimal('2.1') + >>> stop = Decimal('5.1') + >>> list(numeric_range(start, stop)) + [Decimal('2.1'), Decimal('3.1'), Decimal('4.1')] + + With *start*, *stop*, and *step* specified the output items will match + the type of ``start + step``: + + >>> from fractions import Fraction + >>> start = Fraction(1, 2) # Start at 1/2 + >>> stop = Fraction(5, 2) # End at 5/2 + >>> step = Fraction(1, 2) # Count by 1/2 + >>> list(numeric_range(start, stop, step)) + [Fraction(1, 2), Fraction(1, 1), Fraction(3, 2), Fraction(2, 1)] + + If *step* is zero, ``ValueError`` is raised. Negative steps are supported: + + >>> list(numeric_range(3, -1, -1.0)) + [3.0, 2.0, 1.0, 0.0] + + Be aware of the limitations of floating point numbers; the representation + of the yielded numbers may be surprising. + + ``datetime.datetime`` objects can be used for *start* and *stop*, if *step* + is a ``datetime.timedelta`` object: + + >>> import datetime + >>> start = datetime.datetime(2019, 1, 1) + >>> stop = datetime.datetime(2019, 1, 3) + >>> step = datetime.timedelta(days=1) + >>> items = iter(numeric_range(start, stop, step)) + >>> next(items) + datetime.datetime(2019, 1, 1, 0, 0) + >>> next(items) + datetime.datetime(2019, 1, 2, 0, 0) + + """ + + _EMPTY_HASH = hash(range(0, 0)) + + def __init__(self, *args): + argc = len(args) + if argc == 1: + (self._stop,) = args + self._start = type(self._stop)(0) + self._step = type(self._stop - self._start)(1) + elif argc == 2: + self._start, self._stop = args + self._step = type(self._stop - self._start)(1) + elif argc == 3: + self._start, self._stop, self._step = args + elif argc == 0: + raise TypeError( + 'numeric_range expected at least ' + '1 argument, got {}'.format(argc) + ) + else: + raise TypeError( + 'numeric_range expected at most ' + '3 arguments, got {}'.format(argc) + ) + + self._zero = type(self._step)(0) + if self._step == self._zero: + raise ValueError('numeric_range() arg 3 must not be zero') + self._growing = self._step > self._zero + self._init_len() + + def __bool__(self): + if self._growing: + return self._start < self._stop + else: + return self._start > self._stop + + def __contains__(self, elem): + if self._growing: + if self._start <= elem < self._stop: + return (elem - self._start) % self._step == self._zero + else: + if self._start >= elem > self._stop: + return (self._start - elem) % (-self._step) == self._zero + + return False + + def __eq__(self, other): + if isinstance(other, numeric_range): + empty_self = not bool(self) + empty_other = not bool(other) + if empty_self or empty_other: + return empty_self and empty_other # True if both empty + else: + return ( + self._start == other._start + and self._step == other._step + and self._get_by_index(-1) == other._get_by_index(-1) + ) + else: + return False + + def __getitem__(self, key): + if isinstance(key, int): + return self._get_by_index(key) + elif isinstance(key, slice): + step = self._step if key.step is None else key.step * self._step + + if key.start is None or key.start <= -self._len: + start = self._start + elif key.start >= self._len: + start = self._stop + else: # -self._len < key.start < self._len + start = self._get_by_index(key.start) + + if key.stop is None or key.stop >= self._len: + stop = self._stop + elif key.stop <= -self._len: + stop = self._start + else: # -self._len < key.stop < self._len + stop = self._get_by_index(key.stop) + + return numeric_range(start, stop, step) + else: + raise TypeError( + 'numeric range indices must be ' + 'integers or slices, not {}'.format(type(key).__name__) + ) + + def __hash__(self): + if self: + return hash((self._start, self._get_by_index(-1), self._step)) + else: + return self._EMPTY_HASH + + def __iter__(self): + values = (self._start + (n * self._step) for n in count()) + if self._growing: + return takewhile(partial(gt, self._stop), values) + else: + return takewhile(partial(lt, self._stop), values) + + def __len__(self): + return self._len + + def _init_len(self): + if self._growing: + start = self._start + stop = self._stop + step = self._step + else: + start = self._stop + stop = self._start + step = -self._step + distance = stop - start + if distance <= self._zero: + self._len = 0 + else: # distance > 0 and step > 0: regular euclidean division + q, r = divmod(distance, step) + self._len = int(q) + int(r != self._zero) + + def __reduce__(self): + return numeric_range, (self._start, self._stop, self._step) + + def __repr__(self): + if self._step == 1: + return "numeric_range({}, {})".format( + repr(self._start), repr(self._stop) + ) + else: + return "numeric_range({}, {}, {})".format( + repr(self._start), repr(self._stop), repr(self._step) + ) + + def __reversed__(self): + return iter( + numeric_range( + self._get_by_index(-1), self._start - self._step, -self._step + ) + ) + + def count(self, value): + return int(value in self) + + def index(self, value): + if self._growing: + if self._start <= value < self._stop: + q, r = divmod(value - self._start, self._step) + if r == self._zero: + return int(q) + else: + if self._start >= value > self._stop: + q, r = divmod(self._start - value, -self._step) + if r == self._zero: + return int(q) + + raise ValueError("{} is not in numeric range".format(value)) + + def _get_by_index(self, i): + if i < 0: + i += self._len + if i < 0 or i >= self._len: + raise IndexError("numeric range object index out of range") + return self._start + i * self._step + + +def count_cycle(iterable, n=None): + """Cycle through the items from *iterable* up to *n* times, yielding + the number of completed cycles along with each item. If *n* is omitted the + process repeats indefinitely. + + >>> list(count_cycle('AB', 3)) + [(0, 'A'), (0, 'B'), (1, 'A'), (1, 'B'), (2, 'A'), (2, 'B')] + + """ + iterable = tuple(iterable) + if not iterable: + return iter(()) + counter = count() if n is None else range(n) + return ((i, item) for i in counter for item in iterable) + + +def mark_ends(iterable): + """Yield 3-tuples of the form ``(is_first, is_last, item)``. + + >>> list(mark_ends('ABC')) + [(True, False, 'A'), (False, False, 'B'), (False, True, 'C')] + + Use this when looping over an iterable to take special action on its first + and/or last items: + + >>> iterable = ['Header', 100, 200, 'Footer'] + >>> total = 0 + >>> for is_first, is_last, item in mark_ends(iterable): + ... if is_first: + ... continue # Skip the header + ... if is_last: + ... continue # Skip the footer + ... total += item + >>> print(total) + 300 + """ + it = iter(iterable) + + try: + b = next(it) + except StopIteration: + return + + try: + for i in count(): + a = b + b = next(it) + yield i == 0, False, a + + except StopIteration: + yield i == 0, True, a + + +def locate(iterable, pred=bool, window_size=None): + """Yield the index of each item in *iterable* for which *pred* returns + ``True``. + + *pred* defaults to :func:`bool`, which will select truthy items: + + >>> list(locate([0, 1, 1, 0, 1, 0, 0])) + [1, 2, 4] + + Set *pred* to a custom function to, e.g., find the indexes for a particular + item. + + >>> list(locate(['a', 'b', 'c', 'b'], lambda x: x == 'b')) + [1, 3] + + If *window_size* is given, then the *pred* function will be called with + that many items. This enables searching for sub-sequences: + + >>> iterable = [0, 1, 2, 3, 0, 1, 2, 3, 0, 1, 2, 3] + >>> pred = lambda *args: args == (1, 2, 3) + >>> list(locate(iterable, pred=pred, window_size=3)) + [1, 5, 9] + + Use with :func:`seekable` to find indexes and then retrieve the associated + items: + + >>> from itertools import count + >>> from more_itertools import seekable + >>> source = (3 * n + 1 if (n % 2) else n // 2 for n in count()) + >>> it = seekable(source) + >>> pred = lambda x: x > 100 + >>> indexes = locate(it, pred=pred) + >>> i = next(indexes) + >>> it.seek(i) + >>> next(it) + 106 + + """ + if window_size is None: + return compress(count(), map(pred, iterable)) + + if window_size < 1: + raise ValueError('window size must be at least 1') + + it = windowed(iterable, window_size, fillvalue=_marker) + return compress(count(), starmap(pred, it)) + + +def lstrip(iterable, pred): + """Yield the items from *iterable*, but strip any from the beginning + for which *pred* returns ``True``. + + For example, to remove a set of items from the start of an iterable: + + >>> iterable = (None, False, None, 1, 2, None, 3, False, None) + >>> pred = lambda x: x in {None, False, ''} + >>> list(lstrip(iterable, pred)) + [1, 2, None, 3, False, None] + + This function is analogous to to :func:`str.lstrip`, and is essentially + an wrapper for :func:`itertools.dropwhile`. + + """ + return dropwhile(pred, iterable) + + +def rstrip(iterable, pred): + """Yield the items from *iterable*, but strip any from the end + for which *pred* returns ``True``. + + For example, to remove a set of items from the end of an iterable: + + >>> iterable = (None, False, None, 1, 2, None, 3, False, None) + >>> pred = lambda x: x in {None, False, ''} + >>> list(rstrip(iterable, pred)) + [None, False, None, 1, 2, None, 3] + + This function is analogous to :func:`str.rstrip`. + + """ + cache = [] + cache_append = cache.append + cache_clear = cache.clear + for x in iterable: + if pred(x): + cache_append(x) + else: + yield from cache + cache_clear() + yield x + + +def strip(iterable, pred): + """Yield the items from *iterable*, but strip any from the + beginning and end for which *pred* returns ``True``. + + For example, to remove a set of items from both ends of an iterable: + + >>> iterable = (None, False, None, 1, 2, None, 3, False, None) + >>> pred = lambda x: x in {None, False, ''} + >>> list(strip(iterable, pred)) + [1, 2, None, 3] + + This function is analogous to :func:`str.strip`. + + """ + return rstrip(lstrip(iterable, pred), pred) + + +class islice_extended: + """An extension of :func:`itertools.islice` that supports negative values + for *stop*, *start*, and *step*. + + >>> iterable = iter('abcdefgh') + >>> list(islice_extended(iterable, -4, -1)) + ['e', 'f', 'g'] + + Slices with negative values require some caching of *iterable*, but this + function takes care to minimize the amount of memory required. + + For example, you can use a negative step with an infinite iterator: + + >>> from itertools import count + >>> list(islice_extended(count(), 110, 99, -2)) + [110, 108, 106, 104, 102, 100] + + You can also use slice notation directly: + + >>> iterable = map(str, count()) + >>> it = islice_extended(iterable)[10:20:2] + >>> list(it) + ['10', '12', '14', '16', '18'] + + """ + + def __init__(self, iterable, *args): + it = iter(iterable) + if args: + self._iterable = _islice_helper(it, slice(*args)) + else: + self._iterable = it + + def __iter__(self): + return self + + def __next__(self): + return next(self._iterable) + + def __getitem__(self, key): + if isinstance(key, slice): + return islice_extended(_islice_helper(self._iterable, key)) + + raise TypeError('islice_extended.__getitem__ argument must be a slice') + + +def _islice_helper(it, s): + start = s.start + stop = s.stop + if s.step == 0: + raise ValueError('step argument must be a non-zero integer or None.') + step = s.step or 1 + + if step > 0: + start = 0 if (start is None) else start + + if start < 0: + # Consume all but the last -start items + cache = deque(enumerate(it, 1), maxlen=-start) + len_iter = cache[-1][0] if cache else 0 + + # Adjust start to be positive + i = max(len_iter + start, 0) + + # Adjust stop to be positive + if stop is None: + j = len_iter + elif stop >= 0: + j = min(stop, len_iter) + else: + j = max(len_iter + stop, 0) + + # Slice the cache + n = j - i + if n <= 0: + return + + for index, item in islice(cache, 0, n, step): + yield item + elif (stop is not None) and (stop < 0): + # Advance to the start position + next(islice(it, start, start), None) + + # When stop is negative, we have to carry -stop items while + # iterating + cache = deque(islice(it, -stop), maxlen=-stop) + + for index, item in enumerate(it): + cached_item = cache.popleft() + if index % step == 0: + yield cached_item + cache.append(item) + else: + # When both start and stop are positive we have the normal case + yield from islice(it, start, stop, step) + else: + start = -1 if (start is None) else start + + if (stop is not None) and (stop < 0): + # Consume all but the last items + n = -stop - 1 + cache = deque(enumerate(it, 1), maxlen=n) + len_iter = cache[-1][0] if cache else 0 + + # If start and stop are both negative they are comparable and + # we can just slice. Otherwise we can adjust start to be negative + # and then slice. + if start < 0: + i, j = start, stop + else: + i, j = min(start - len_iter, -1), None + + for index, item in list(cache)[i:j:step]: + yield item + else: + # Advance to the stop position + if stop is not None: + m = stop + 1 + next(islice(it, m, m), None) + + # stop is positive, so if start is negative they are not comparable + # and we need the rest of the items. + if start < 0: + i = start + n = None + # stop is None and start is positive, so we just need items up to + # the start index. + elif stop is None: + i = None + n = start + 1 + # Both stop and start are positive, so they are comparable. + else: + i = None + n = start - stop + if n <= 0: + return + + cache = list(islice(it, n)) + + yield from cache[i::step] + + +def always_reversible(iterable): + """An extension of :func:`reversed` that supports all iterables, not + just those which implement the ``Reversible`` or ``Sequence`` protocols. + + >>> print(*always_reversible(x for x in range(3))) + 2 1 0 + + If the iterable is already reversible, this function returns the + result of :func:`reversed()`. If the iterable is not reversible, + this function will cache the remaining items in the iterable and + yield them in reverse order, which may require significant storage. + """ + try: + return reversed(iterable) + except TypeError: + return reversed(list(iterable)) + + +def consecutive_groups(iterable, ordering=lambda x: x): + """Yield groups of consecutive items using :func:`itertools.groupby`. + The *ordering* function determines whether two items are adjacent by + returning their position. + + By default, the ordering function is the identity function. This is + suitable for finding runs of numbers: + + >>> iterable = [1, 10, 11, 12, 20, 30, 31, 32, 33, 40] + >>> for group in consecutive_groups(iterable): + ... print(list(group)) + [1] + [10, 11, 12] + [20] + [30, 31, 32, 33] + [40] + + For finding runs of adjacent letters, try using the :meth:`index` method + of a string of letters: + + >>> from string import ascii_lowercase + >>> iterable = 'abcdfgilmnop' + >>> ordering = ascii_lowercase.index + >>> for group in consecutive_groups(iterable, ordering): + ... print(list(group)) + ['a', 'b', 'c', 'd'] + ['f', 'g'] + ['i'] + ['l', 'm', 'n', 'o', 'p'] + + Each group of consecutive items is an iterator that shares it source with + *iterable*. When an an output group is advanced, the previous group is + no longer available unless its elements are copied (e.g., into a ``list``). + + >>> iterable = [1, 2, 11, 12, 21, 22] + >>> saved_groups = [] + >>> for group in consecutive_groups(iterable): + ... saved_groups.append(list(group)) # Copy group elements + >>> saved_groups + [[1, 2], [11, 12], [21, 22]] + + """ + for k, g in groupby( + enumerate(iterable), key=lambda x: x[0] - ordering(x[1]) + ): + yield map(itemgetter(1), g) + + +def difference(iterable, func=sub, *, initial=None): + """This function is the inverse of :func:`itertools.accumulate`. By default + it will compute the first difference of *iterable* using + :func:`operator.sub`: + + >>> from itertools import accumulate + >>> iterable = accumulate([0, 1, 2, 3, 4]) # produces 0, 1, 3, 6, 10 + >>> list(difference(iterable)) + [0, 1, 2, 3, 4] + + *func* defaults to :func:`operator.sub`, but other functions can be + specified. They will be applied as follows:: + + A, B, C, D, ... --> A, func(B, A), func(C, B), func(D, C), ... + + For example, to do progressive division: + + >>> iterable = [1, 2, 6, 24, 120] + >>> func = lambda x, y: x // y + >>> list(difference(iterable, func)) + [1, 2, 3, 4, 5] + + If the *initial* keyword is set, the first element will be skipped when + computing successive differences. + + >>> it = [10, 11, 13, 16] # from accumulate([1, 2, 3], initial=10) + >>> list(difference(it, initial=10)) + [1, 2, 3] + + """ + a, b = tee(iterable) + try: + first = [next(b)] + except StopIteration: + return iter([]) + + if initial is not None: + first = [] + + return chain(first, starmap(func, zip(b, a))) + + +class SequenceView(Sequence): + """Return a read-only view of the sequence object *target*. + + :class:`SequenceView` objects are analogous to Python's built-in + "dictionary view" types. They provide a dynamic view of a sequence's items, + meaning that when the sequence updates, so does the view. + + >>> seq = ['0', '1', '2'] + >>> view = SequenceView(seq) + >>> view + SequenceView(['0', '1', '2']) + >>> seq.append('3') + >>> view + SequenceView(['0', '1', '2', '3']) + + Sequence views support indexing, slicing, and length queries. They act + like the underlying sequence, except they don't allow assignment: + + >>> view[1] + '1' + >>> view[1:-1] + ['1', '2'] + >>> len(view) + 4 + + Sequence views are useful as an alternative to copying, as they don't + require (much) extra storage. + + """ + + def __init__(self, target): + if not isinstance(target, Sequence): + raise TypeError + self._target = target + + def __getitem__(self, index): + return self._target[index] + + def __len__(self): + return len(self._target) + + def __repr__(self): + return '{}({})'.format(self.__class__.__name__, repr(self._target)) + + +class seekable: + """Wrap an iterator to allow for seeking backward and forward. This + progressively caches the items in the source iterable so they can be + re-visited. + + Call :meth:`seek` with an index to seek to that position in the source + iterable. + + To "reset" an iterator, seek to ``0``: + + >>> from itertools import count + >>> it = seekable((str(n) for n in count())) + >>> next(it), next(it), next(it) + ('0', '1', '2') + >>> it.seek(0) + >>> next(it), next(it), next(it) + ('0', '1', '2') + >>> next(it) + '3' + + You can also seek forward: + + >>> it = seekable((str(n) for n in range(20))) + >>> it.seek(10) + >>> next(it) + '10' + >>> it.seek(20) # Seeking past the end of the source isn't a problem + >>> list(it) + [] + >>> it.seek(0) # Resetting works even after hitting the end + >>> next(it), next(it), next(it) + ('0', '1', '2') + + Call :meth:`peek` to look ahead one item without advancing the iterator: + + >>> it = seekable('1234') + >>> it.peek() + '1' + >>> list(it) + ['1', '2', '3', '4'] + >>> it.peek(default='empty') + 'empty' + + Before the iterator is at its end, calling :func:`bool` on it will return + ``True``. After it will return ``False``: + + >>> it = seekable('5678') + >>> bool(it) + True + >>> list(it) + ['5', '6', '7', '8'] + >>> bool(it) + False + + You may view the contents of the cache with the :meth:`elements` method. + That returns a :class:`SequenceView`, a view that updates automatically: + + >>> it = seekable((str(n) for n in range(10))) + >>> next(it), next(it), next(it) + ('0', '1', '2') + >>> elements = it.elements() + >>> elements + SequenceView(['0', '1', '2']) + >>> next(it) + '3' + >>> elements + SequenceView(['0', '1', '2', '3']) + + By default, the cache grows as the source iterable progresses, so beware of + wrapping very large or infinite iterables. Supply *maxlen* to limit the + size of the cache (this of course limits how far back you can seek). + + >>> from itertools import count + >>> it = seekable((str(n) for n in count()), maxlen=2) + >>> next(it), next(it), next(it), next(it) + ('0', '1', '2', '3') + >>> list(it.elements()) + ['2', '3'] + >>> it.seek(0) + >>> next(it), next(it), next(it), next(it) + ('2', '3', '4', '5') + >>> next(it) + '6' + + """ + + def __init__(self, iterable, maxlen=None): + self._source = iter(iterable) + if maxlen is None: + self._cache = [] + else: + self._cache = deque([], maxlen) + self._index = None + + def __iter__(self): + return self + + def __next__(self): + if self._index is not None: + try: + item = self._cache[self._index] + except IndexError: + self._index = None + else: + self._index += 1 + return item + + item = next(self._source) + self._cache.append(item) + return item + + def __bool__(self): + try: + self.peek() + except StopIteration: + return False + return True + + def peek(self, default=_marker): + try: + peeked = next(self) + except StopIteration: + if default is _marker: + raise + return default + if self._index is None: + self._index = len(self._cache) + self._index -= 1 + return peeked + + def elements(self): + return SequenceView(self._cache) + + def seek(self, index): + self._index = index + remainder = index - len(self._cache) + if remainder > 0: + consume(self, remainder) + + +class run_length: + """ + :func:`run_length.encode` compresses an iterable with run-length encoding. + It yields groups of repeated items with the count of how many times they + were repeated: + + >>> uncompressed = 'abbcccdddd' + >>> list(run_length.encode(uncompressed)) + [('a', 1), ('b', 2), ('c', 3), ('d', 4)] + + :func:`run_length.decode` decompresses an iterable that was previously + compressed with run-length encoding. It yields the items of the + decompressed iterable: + + >>> compressed = [('a', 1), ('b', 2), ('c', 3), ('d', 4)] + >>> list(run_length.decode(compressed)) + ['a', 'b', 'b', 'c', 'c', 'c', 'd', 'd', 'd', 'd'] + + """ + + @staticmethod + def encode(iterable): + return ((k, ilen(g)) for k, g in groupby(iterable)) + + @staticmethod + def decode(iterable): + return chain.from_iterable(repeat(k, n) for k, n in iterable) + + +def exactly_n(iterable, n, predicate=bool): + """Return ``True`` if exactly ``n`` items in the iterable are ``True`` + according to the *predicate* function. + + >>> exactly_n([True, True, False], 2) + True + >>> exactly_n([True, True, False], 1) + False + >>> exactly_n([0, 1, 2, 3, 4, 5], 3, lambda x: x < 3) + True + + The iterable will be advanced until ``n + 1`` truthy items are encountered, + so avoid calling it on infinite iterables. + + """ + return len(take(n + 1, filter(predicate, iterable))) == n + + +def circular_shifts(iterable): + """Return a list of circular shifts of *iterable*. + + >>> circular_shifts(range(4)) + [(0, 1, 2, 3), (1, 2, 3, 0), (2, 3, 0, 1), (3, 0, 1, 2)] + """ + lst = list(iterable) + return take(len(lst), windowed(cycle(lst), len(lst))) + + +def make_decorator(wrapping_func, result_index=0): + """Return a decorator version of *wrapping_func*, which is a function that + modifies an iterable. *result_index* is the position in that function's + signature where the iterable goes. + + This lets you use itertools on the "production end," i.e. at function + definition. This can augment what the function returns without changing the + function's code. + + For example, to produce a decorator version of :func:`chunked`: + + >>> from more_itertools import chunked + >>> chunker = make_decorator(chunked, result_index=0) + >>> @chunker(3) + ... def iter_range(n): + ... return iter(range(n)) + ... + >>> list(iter_range(9)) + [[0, 1, 2], [3, 4, 5], [6, 7, 8]] + + To only allow truthy items to be returned: + + >>> truth_serum = make_decorator(filter, result_index=1) + >>> @truth_serum(bool) + ... def boolean_test(): + ... return [0, 1, '', ' ', False, True] + ... + >>> list(boolean_test()) + [1, ' ', True] + + The :func:`peekable` and :func:`seekable` wrappers make for practical + decorators: + + >>> from more_itertools import peekable + >>> peekable_function = make_decorator(peekable) + >>> @peekable_function() + ... def str_range(*args): + ... return (str(x) for x in range(*args)) + ... + >>> it = str_range(1, 20, 2) + >>> next(it), next(it), next(it) + ('1', '3', '5') + >>> it.peek() + '7' + >>> next(it) + '7' + + """ + # See https://sites.google.com/site/bbayles/index/decorator_factory for + # notes on how this works. + def decorator(*wrapping_args, **wrapping_kwargs): + def outer_wrapper(f): + def inner_wrapper(*args, **kwargs): + result = f(*args, **kwargs) + wrapping_args_ = list(wrapping_args) + wrapping_args_.insert(result_index, result) + return wrapping_func(*wrapping_args_, **wrapping_kwargs) + + return inner_wrapper + + return outer_wrapper + + return decorator + + +def map_reduce(iterable, keyfunc, valuefunc=None, reducefunc=None): + """Return a dictionary that maps the items in *iterable* to categories + defined by *keyfunc*, transforms them with *valuefunc*, and + then summarizes them by category with *reducefunc*. + + *valuefunc* defaults to the identity function if it is unspecified. + If *reducefunc* is unspecified, no summarization takes place: + + >>> keyfunc = lambda x: x.upper() + >>> result = map_reduce('abbccc', keyfunc) + >>> sorted(result.items()) + [('A', ['a']), ('B', ['b', 'b']), ('C', ['c', 'c', 'c'])] + + Specifying *valuefunc* transforms the categorized items: + + >>> keyfunc = lambda x: x.upper() + >>> valuefunc = lambda x: 1 + >>> result = map_reduce('abbccc', keyfunc, valuefunc) + >>> sorted(result.items()) + [('A', [1]), ('B', [1, 1]), ('C', [1, 1, 1])] + + Specifying *reducefunc* summarizes the categorized items: + + >>> keyfunc = lambda x: x.upper() + >>> valuefunc = lambda x: 1 + >>> reducefunc = sum + >>> result = map_reduce('abbccc', keyfunc, valuefunc, reducefunc) + >>> sorted(result.items()) + [('A', 1), ('B', 2), ('C', 3)] + + You may want to filter the input iterable before applying the map/reduce + procedure: + + >>> all_items = range(30) + >>> items = [x for x in all_items if 10 <= x <= 20] # Filter + >>> keyfunc = lambda x: x % 2 # Evens map to 0; odds to 1 + >>> categories = map_reduce(items, keyfunc=keyfunc) + >>> sorted(categories.items()) + [(0, [10, 12, 14, 16, 18, 20]), (1, [11, 13, 15, 17, 19])] + >>> summaries = map_reduce(items, keyfunc=keyfunc, reducefunc=sum) + >>> sorted(summaries.items()) + [(0, 90), (1, 75)] + + Note that all items in the iterable are gathered into a list before the + summarization step, which may require significant storage. + + The returned object is a :obj:`collections.defaultdict` with the + ``default_factory`` set to ``None``, such that it behaves like a normal + dictionary. + + """ + valuefunc = (lambda x: x) if (valuefunc is None) else valuefunc + + ret = defaultdict(list) + for item in iterable: + key = keyfunc(item) + value = valuefunc(item) + ret[key].append(value) + + if reducefunc is not None: + for key, value_list in ret.items(): + ret[key] = reducefunc(value_list) + + ret.default_factory = None + return ret + + +def rlocate(iterable, pred=bool, window_size=None): + """Yield the index of each item in *iterable* for which *pred* returns + ``True``, starting from the right and moving left. + + *pred* defaults to :func:`bool`, which will select truthy items: + + >>> list(rlocate([0, 1, 1, 0, 1, 0, 0])) # Truthy at 1, 2, and 4 + [4, 2, 1] + + Set *pred* to a custom function to, e.g., find the indexes for a particular + item: + + >>> iterable = iter('abcb') + >>> pred = lambda x: x == 'b' + >>> list(rlocate(iterable, pred)) + [3, 1] + + If *window_size* is given, then the *pred* function will be called with + that many items. This enables searching for sub-sequences: + + >>> iterable = [0, 1, 2, 3, 0, 1, 2, 3, 0, 1, 2, 3] + >>> pred = lambda *args: args == (1, 2, 3) + >>> list(rlocate(iterable, pred=pred, window_size=3)) + [9, 5, 1] + + Beware, this function won't return anything for infinite iterables. + If *iterable* is reversible, ``rlocate`` will reverse it and search from + the right. Otherwise, it will search from the left and return the results + in reverse order. + + See :func:`locate` to for other example applications. + + """ + if window_size is None: + try: + len_iter = len(iterable) + return (len_iter - i - 1 for i in locate(reversed(iterable), pred)) + except TypeError: + pass + + return reversed(list(locate(iterable, pred, window_size))) + + +def replace(iterable, pred, substitutes, count=None, window_size=1): + """Yield the items from *iterable*, replacing the items for which *pred* + returns ``True`` with the items from the iterable *substitutes*. + + >>> iterable = [1, 1, 0, 1, 1, 0, 1, 1] + >>> pred = lambda x: x == 0 + >>> substitutes = (2, 3) + >>> list(replace(iterable, pred, substitutes)) + [1, 1, 2, 3, 1, 1, 2, 3, 1, 1] + + If *count* is given, the number of replacements will be limited: + + >>> iterable = [1, 1, 0, 1, 1, 0, 1, 1, 0] + >>> pred = lambda x: x == 0 + >>> substitutes = [None] + >>> list(replace(iterable, pred, substitutes, count=2)) + [1, 1, None, 1, 1, None, 1, 1, 0] + + Use *window_size* to control the number of items passed as arguments to + *pred*. This allows for locating and replacing subsequences. + + >>> iterable = [0, 1, 2, 5, 0, 1, 2, 5] + >>> window_size = 3 + >>> pred = lambda *args: args == (0, 1, 2) # 3 items passed to pred + >>> substitutes = [3, 4] # Splice in these items + >>> list(replace(iterable, pred, substitutes, window_size=window_size)) + [3, 4, 5, 3, 4, 5] + + """ + if window_size < 1: + raise ValueError('window_size must be at least 1') + + # Save the substitutes iterable, since it's used more than once + substitutes = tuple(substitutes) + + # Add padding such that the number of windows matches the length of the + # iterable + it = chain(iterable, [_marker] * (window_size - 1)) + windows = windowed(it, window_size) + + n = 0 + for w in windows: + # If the current window matches our predicate (and we haven't hit + # our maximum number of replacements), splice in the substitutes + # and then consume the following windows that overlap with this one. + # For example, if the iterable is (0, 1, 2, 3, 4...) + # and the window size is 2, we have (0, 1), (1, 2), (2, 3)... + # If the predicate matches on (0, 1), we need to zap (0, 1) and (1, 2) + if pred(*w): + if (count is None) or (n < count): + n += 1 + yield from substitutes + consume(windows, window_size - 1) + continue + + # If there was no match (or we've reached the replacement limit), + # yield the first item from the window. + if w and (w[0] is not _marker): + yield w[0] + + +def partitions(iterable): + """Yield all possible order-preserving partitions of *iterable*. + + >>> iterable = 'abc' + >>> for part in partitions(iterable): + ... print([''.join(p) for p in part]) + ['abc'] + ['a', 'bc'] + ['ab', 'c'] + ['a', 'b', 'c'] + + This is unrelated to :func:`partition`. + + """ + sequence = list(iterable) + n = len(sequence) + for i in powerset(range(1, n)): + yield [sequence[i:j] for i, j in zip((0,) + i, i + (n,))] + + +def set_partitions(iterable, k=None): + """ + Yield the set partitions of *iterable* into *k* parts. Set partitions are + not order-preserving. + + >>> iterable = 'abc' + >>> for part in set_partitions(iterable, 2): + ... print([''.join(p) for p in part]) + ['a', 'bc'] + ['ab', 'c'] + ['b', 'ac'] + + + If *k* is not given, every set partition is generated. + + >>> iterable = 'abc' + >>> for part in set_partitions(iterable): + ... print([''.join(p) for p in part]) + ['abc'] + ['a', 'bc'] + ['ab', 'c'] + ['b', 'ac'] + ['a', 'b', 'c'] + + """ + L = list(iterable) + n = len(L) + if k is not None: + if k < 1: + raise ValueError( + "Can't partition in a negative or zero number of groups" + ) + elif k > n: + return + + def set_partitions_helper(L, k): + n = len(L) + if k == 1: + yield [L] + elif n == k: + yield [[s] for s in L] + else: + e, *M = L + for p in set_partitions_helper(M, k - 1): + yield [[e], *p] + for p in set_partitions_helper(M, k): + for i in range(len(p)): + yield p[:i] + [[e] + p[i]] + p[i + 1 :] + + if k is None: + for k in range(1, n + 1): + yield from set_partitions_helper(L, k) + else: + yield from set_partitions_helper(L, k) + + +class time_limited: + """ + Yield items from *iterable* until *limit_seconds* have passed. + If the time limit expires before all items have been yielded, the + ``timed_out`` parameter will be set to ``True``. + + >>> from time import sleep + >>> def generator(): + ... yield 1 + ... yield 2 + ... sleep(0.2) + ... yield 3 + >>> iterable = time_limited(0.1, generator()) + >>> list(iterable) + [1, 2] + >>> iterable.timed_out + True + + Note that the time is checked before each item is yielded, and iteration + stops if the time elapsed is greater than *limit_seconds*. If your time + limit is 1 second, but it takes 2 seconds to generate the first item from + the iterable, the function will run for 2 seconds and not yield anything. + + """ + + def __init__(self, limit_seconds, iterable): + if limit_seconds < 0: + raise ValueError('limit_seconds must be positive') + self.limit_seconds = limit_seconds + self._iterable = iter(iterable) + self._start_time = monotonic() + self.timed_out = False + + def __iter__(self): + return self + + def __next__(self): + item = next(self._iterable) + if monotonic() - self._start_time > self.limit_seconds: + self.timed_out = True + raise StopIteration + + return item + + +def only(iterable, default=None, too_long=None): + """If *iterable* has only one item, return it. + If it has zero items, return *default*. + If it has more than one item, raise the exception given by *too_long*, + which is ``ValueError`` by default. + + >>> only([], default='missing') + 'missing' + >>> only([1]) + 1 + >>> only([1, 2]) # doctest: +IGNORE_EXCEPTION_DETAIL + Traceback (most recent call last): + ... + ValueError: Expected exactly one item in iterable, but got 1, 2, + and perhaps more.' + >>> only([1, 2], too_long=TypeError) # doctest: +IGNORE_EXCEPTION_DETAIL + Traceback (most recent call last): + ... + TypeError + + Note that :func:`only` attempts to advance *iterable* twice to ensure there + is only one item. See :func:`spy` or :func:`peekable` to check + iterable contents less destructively. + """ + it = iter(iterable) + first_value = next(it, default) + + try: + second_value = next(it) + except StopIteration: + pass + else: + msg = ( + 'Expected exactly one item in iterable, but got {!r}, {!r}, ' + 'and perhaps more.'.format(first_value, second_value) + ) + raise too_long or ValueError(msg) + + return first_value + + +def ichunked(iterable, n): + """Break *iterable* into sub-iterables with *n* elements each. + :func:`ichunked` is like :func:`chunked`, but it yields iterables + instead of lists. + + If the sub-iterables are read in order, the elements of *iterable* + won't be stored in memory. + If they are read out of order, :func:`itertools.tee` is used to cache + elements as necessary. + + >>> from itertools import count + >>> all_chunks = ichunked(count(), 4) + >>> c_1, c_2, c_3 = next(all_chunks), next(all_chunks), next(all_chunks) + >>> list(c_2) # c_1's elements have been cached; c_3's haven't been + [4, 5, 6, 7] + >>> list(c_1) + [0, 1, 2, 3] + >>> list(c_3) + [8, 9, 10, 11] + + """ + source = iter(iterable) + + while True: + # Check to see whether we're at the end of the source iterable + item = next(source, _marker) + if item is _marker: + return + + # Clone the source and yield an n-length slice + source, it = tee(chain([item], source)) + yield islice(it, n) + + # Advance the source iterable + consume(source, n) + + +def distinct_combinations(iterable, r): + """Yield the distinct combinations of *r* items taken from *iterable*. + + >>> list(distinct_combinations([0, 0, 1], 2)) + [(0, 0), (0, 1)] + + Equivalent to ``set(combinations(iterable))``, except duplicates are not + generated and thrown away. For larger input sequences this is much more + efficient. + + """ + if r < 0: + raise ValueError('r must be non-negative') + elif r == 0: + yield () + return + pool = tuple(iterable) + generators = [unique_everseen(enumerate(pool), key=itemgetter(1))] + current_combo = [None] * r + level = 0 + while generators: + try: + cur_idx, p = next(generators[-1]) + except StopIteration: + generators.pop() + level -= 1 + continue + current_combo[level] = p + if level + 1 == r: + yield tuple(current_combo) + else: + generators.append( + unique_everseen( + enumerate(pool[cur_idx + 1 :], cur_idx + 1), + key=itemgetter(1), + ) + ) + level += 1 + + +def filter_except(validator, iterable, *exceptions): + """Yield the items from *iterable* for which the *validator* function does + not raise one of the specified *exceptions*. + + *validator* is called for each item in *iterable*. + It should be a function that accepts one argument and raises an exception + if that item is not valid. + + >>> iterable = ['1', '2', 'three', '4', None] + >>> list(filter_except(int, iterable, ValueError, TypeError)) + ['1', '2', '4'] + + If an exception other than one given by *exceptions* is raised by + *validator*, it is raised like normal. + """ + for item in iterable: + try: + validator(item) + except exceptions: + pass + else: + yield item + + +def map_except(function, iterable, *exceptions): + """Transform each item from *iterable* with *function* and yield the + result, unless *function* raises one of the specified *exceptions*. + + *function* is called to transform each item in *iterable*. + It should accept one argument. + + >>> iterable = ['1', '2', 'three', '4', None] + >>> list(map_except(int, iterable, ValueError, TypeError)) + [1, 2, 4] + + If an exception other than one given by *exceptions* is raised by + *function*, it is raised like normal. + """ + for item in iterable: + try: + yield function(item) + except exceptions: + pass + + +def map_if(iterable, pred, func, func_else=lambda x: x): + """Evaluate each item from *iterable* using *pred*. If the result is + equivalent to ``True``, transform the item with *func* and yield it. + Otherwise, transform the item with *func_else* and yield it. + + *pred*, *func*, and *func_else* should each be functions that accept + one argument. By default, *func_else* is the identity function. + + >>> from math import sqrt + >>> iterable = list(range(-5, 5)) + >>> iterable + [-5, -4, -3, -2, -1, 0, 1, 2, 3, 4] + >>> list(map_if(iterable, lambda x: x > 3, lambda x: 'toobig')) + [-5, -4, -3, -2, -1, 0, 1, 2, 3, 'toobig'] + >>> list(map_if(iterable, lambda x: x >= 0, + ... lambda x: f'{sqrt(x):.2f}', lambda x: None)) + [None, None, None, None, None, '0.00', '1.00', '1.41', '1.73', '2.00'] + """ + for item in iterable: + yield func(item) if pred(item) else func_else(item) + + +def _sample_unweighted(iterable, k): + # Implementation of "Algorithm L" from the 1994 paper by Kim-Hung Li: + # "Reservoir-Sampling Algorithms of Time Complexity O(n(1+log(N/n)))". + + # Fill up the reservoir (collection of samples) with the first `k` samples + reservoir = take(k, iterable) + + # Generate random number that's the largest in a sample of k U(0,1) numbers + # Largest order statistic: https://en.wikipedia.org/wiki/Order_statistic + W = exp(log(random()) / k) + + # The number of elements to skip before changing the reservoir is a random + # number with a geometric distribution. Sample it using random() and logs. + next_index = k + floor(log(random()) / log(1 - W)) + + for index, element in enumerate(iterable, k): + + if index == next_index: + reservoir[randrange(k)] = element + # The new W is the largest in a sample of k U(0, `old_W`) numbers + W *= exp(log(random()) / k) + next_index += floor(log(random()) / log(1 - W)) + 1 + + return reservoir + + +def _sample_weighted(iterable, k, weights): + # Implementation of "A-ExpJ" from the 2006 paper by Efraimidis et al. : + # "Weighted random sampling with a reservoir". + + # Log-transform for numerical stability for weights that are small/large + weight_keys = (log(random()) / weight for weight in weights) + + # Fill up the reservoir (collection of samples) with the first `k` + # weight-keys and elements, then heapify the list. + reservoir = take(k, zip(weight_keys, iterable)) + heapify(reservoir) + + # The number of jumps before changing the reservoir is a random variable + # with an exponential distribution. Sample it using random() and logs. + smallest_weight_key, _ = reservoir[0] + weights_to_skip = log(random()) / smallest_weight_key + + for weight, element in zip(weights, iterable): + if weight >= weights_to_skip: + # The notation here is consistent with the paper, but we store + # the weight-keys in log-space for better numerical stability. + smallest_weight_key, _ = reservoir[0] + t_w = exp(weight * smallest_weight_key) + r_2 = uniform(t_w, 1) # generate U(t_w, 1) + weight_key = log(r_2) / weight + heapreplace(reservoir, (weight_key, element)) + smallest_weight_key, _ = reservoir[0] + weights_to_skip = log(random()) / smallest_weight_key + else: + weights_to_skip -= weight + + # Equivalent to [element for weight_key, element in sorted(reservoir)] + return [heappop(reservoir)[1] for _ in range(k)] + + +def sample(iterable, k, weights=None): + """Return a *k*-length list of elements chosen (without replacement) + from the *iterable*. Like :func:`random.sample`, but works on iterables + of unknown length. + + >>> iterable = range(100) + >>> sample(iterable, 5) # doctest: +SKIP + [81, 60, 96, 16, 4] + + An iterable with *weights* may also be given: + + >>> iterable = range(100) + >>> weights = (i * i + 1 for i in range(100)) + >>> sampled = sample(iterable, 5, weights=weights) # doctest: +SKIP + [79, 67, 74, 66, 78] + + The algorithm can also be used to generate weighted random permutations. + The relative weight of each item determines the probability that it + appears late in the permutation. + + >>> data = "abcdefgh" + >>> weights = range(1, len(data) + 1) + >>> sample(data, k=len(data), weights=weights) # doctest: +SKIP + ['c', 'a', 'b', 'e', 'g', 'd', 'h', 'f'] + """ + if k == 0: + return [] + + iterable = iter(iterable) + if weights is None: + return _sample_unweighted(iterable, k) + else: + weights = iter(weights) + return _sample_weighted(iterable, k, weights) + + +def is_sorted(iterable, key=None, reverse=False, strict=False): + """Returns ``True`` if the items of iterable are in sorted order, and + ``False`` otherwise. *key* and *reverse* have the same meaning that they do + in the built-in :func:`sorted` function. + + >>> is_sorted(['1', '2', '3', '4', '5'], key=int) + True + >>> is_sorted([5, 4, 3, 1, 2], reverse=True) + False + + If *strict*, tests for strict sorting, that is, returns ``False`` if equal + elements are found: + + >>> is_sorted([1, 2, 2]) + True + >>> is_sorted([1, 2, 2], strict=True) + False + + The function returns ``False`` after encountering the first out-of-order + item. If there are no out-of-order items, the iterable is exhausted. + """ + + compare = (le if reverse else ge) if strict else (lt if reverse else gt) + it = iterable if key is None else map(key, iterable) + return not any(starmap(compare, pairwise(it))) + + +class AbortThread(BaseException): + pass + + +class callback_iter: + """Convert a function that uses callbacks to an iterator. + + Let *func* be a function that takes a `callback` keyword argument. + For example: + + >>> def func(callback=None): + ... for i, c in [(1, 'a'), (2, 'b'), (3, 'c')]: + ... if callback: + ... callback(i, c) + ... return 4 + + + Use ``with callback_iter(func)`` to get an iterator over the parameters + that are delivered to the callback. + + >>> with callback_iter(func) as it: + ... for args, kwargs in it: + ... print(args) + (1, 'a') + (2, 'b') + (3, 'c') + + The function will be called in a background thread. The ``done`` property + indicates whether it has completed execution. + + >>> it.done + True + + If it completes successfully, its return value will be available + in the ``result`` property. + + >>> it.result + 4 + + Notes: + + * If the function uses some keyword argument besides ``callback``, supply + *callback_kwd*. + * If it finished executing, but raised an exception, accessing the + ``result`` property will raise the same exception. + * If it hasn't finished executing, accessing the ``result`` + property from within the ``with`` block will raise ``RuntimeError``. + * If it hasn't finished executing, accessing the ``result`` property from + outside the ``with`` block will raise a + ``more_itertools.AbortThread`` exception. + * Provide *wait_seconds* to adjust how frequently the it is polled for + output. + + """ + + def __init__(self, func, callback_kwd='callback', wait_seconds=0.1): + self._func = func + self._callback_kwd = callback_kwd + self._aborted = False + self._future = None + self._wait_seconds = wait_seconds + self._executor = __import__("concurrent.futures").futures.ThreadPoolExecutor(max_workers=1) + self._iterator = self._reader() + + def __enter__(self): + return self + + def __exit__(self, exc_type, exc_value, traceback): + self._aborted = True + self._executor.shutdown() + + def __iter__(self): + return self + + def __next__(self): + return next(self._iterator) + + @property + def done(self): + if self._future is None: + return False + return self._future.done() + + @property + def result(self): + if not self.done: + raise RuntimeError('Function has not yet completed') + + return self._future.result() + + def _reader(self): + q = Queue() + + def callback(*args, **kwargs): + if self._aborted: + raise AbortThread('canceled by user') + + q.put((args, kwargs)) + + self._future = self._executor.submit( + self._func, **{self._callback_kwd: callback} + ) + + while True: + try: + item = q.get(timeout=self._wait_seconds) + except Empty: + pass + else: + q.task_done() + yield item + + if self._future.done(): + break + + remaining = [] + while True: + try: + item = q.get_nowait() + except Empty: + break + else: + q.task_done() + remaining.append(item) + q.join() + yield from remaining + + +def windowed_complete(iterable, n): + """ + Yield ``(beginning, middle, end)`` tuples, where: + + * Each ``middle`` has *n* items from *iterable* + * Each ``beginning`` has the items before the ones in ``middle`` + * Each ``end`` has the items after the ones in ``middle`` + + >>> iterable = range(7) + >>> n = 3 + >>> for beginning, middle, end in windowed_complete(iterable, n): + ... print(beginning, middle, end) + () (0, 1, 2) (3, 4, 5, 6) + (0,) (1, 2, 3) (4, 5, 6) + (0, 1) (2, 3, 4) (5, 6) + (0, 1, 2) (3, 4, 5) (6,) + (0, 1, 2, 3) (4, 5, 6) () + + Note that *n* must be at least 0 and most equal to the length of + *iterable*. + + This function will exhaust the iterable and may require significant + storage. + """ + if n < 0: + raise ValueError('n must be >= 0') + + seq = tuple(iterable) + size = len(seq) + + if n > size: + raise ValueError('n must be <= len(seq)') + + for i in range(size - n + 1): + beginning = seq[:i] + middle = seq[i : i + n] + end = seq[i + n :] + yield beginning, middle, end + + +def all_unique(iterable, key=None): + """ + Returns ``True`` if all the elements of *iterable* are unique (no two + elements are equal). + + >>> all_unique('ABCB') + False + + If a *key* function is specified, it will be used to make comparisons. + + >>> all_unique('ABCb') + True + >>> all_unique('ABCb', str.lower) + False + + The function returns as soon as the first non-unique element is + encountered. Iterables with a mix of hashable and unhashable items can + be used, but the function will be slower for unhashable items. + """ + seenset = set() + seenset_add = seenset.add + seenlist = [] + seenlist_add = seenlist.append + for element in map(key, iterable) if key else iterable: + try: + if element in seenset: + return False + seenset_add(element) + except TypeError: + if element in seenlist: + return False + seenlist_add(element) + return True + + +def nth_product(index, *args): + """Equivalent to ``list(product(*args))[index]``. + + The products of *args* can be ordered lexicographically. + :func:`nth_product` computes the product at sort position *index* without + computing the previous products. + + >>> nth_product(8, range(2), range(2), range(2), range(2)) + (1, 0, 0, 0) + + ``IndexError`` will be raised if the given *index* is invalid. + """ + pools = list(map(tuple, reversed(args))) + ns = list(map(len, pools)) + + c = reduce(mul, ns) + + if index < 0: + index += c + + if not 0 <= index < c: + raise IndexError + + result = [] + for pool, n in zip(pools, ns): + result.append(pool[index % n]) + index //= n + + return tuple(reversed(result)) + + +def nth_permutation(iterable, r, index): + """Equivalent to ``list(permutations(iterable, r))[index]``` + + The subsequences of *iterable* that are of length *r* where order is + important can be ordered lexicographically. :func:`nth_permutation` + computes the subsequence at sort position *index* directly, without + computing the previous subsequences. + + >>> nth_permutation('ghijk', 2, 5) + ('h', 'i') + + ``ValueError`` will be raised If *r* is negative or greater than the length + of *iterable*. + ``IndexError`` will be raised if the given *index* is invalid. + """ + pool = list(iterable) + n = len(pool) + + if r is None or r == n: + r, c = n, factorial(n) + elif not 0 <= r < n: + raise ValueError + else: + c = factorial(n) // factorial(n - r) + + if index < 0: + index += c + + if not 0 <= index < c: + raise IndexError + + if c == 0: + return tuple() + + result = [0] * r + q = index * factorial(n) // c if r < n else index + for d in range(1, n + 1): + q, i = divmod(q, d) + if 0 <= n - d < r: + result[n - d] = i + if q == 0: + break + + return tuple(map(pool.pop, result)) + + +def value_chain(*args): + """Yield all arguments passed to the function in the same order in which + they were passed. If an argument itself is iterable then iterate over its + values. + + >>> list(value_chain(1, 2, 3, [4, 5, 6])) + [1, 2, 3, 4, 5, 6] + + Binary and text strings are not considered iterable and are emitted + as-is: + + >>> list(value_chain('12', '34', ['56', '78'])) + ['12', '34', '56', '78'] + + + Multiple levels of nesting are not flattened. + + """ + for value in args: + if isinstance(value, (str, bytes)): + yield value + continue + try: + yield from value + except TypeError: + yield value + + +def product_index(element, *args): + """Equivalent to ``list(product(*args)).index(element)`` + + The products of *args* can be ordered lexicographically. + :func:`product_index` computes the first index of *element* without + computing the previous products. + + >>> product_index([8, 2], range(10), range(5)) + 42 + + ``ValueError`` will be raised if the given *element* isn't in the product + of *args*. + """ + index = 0 + + for x, pool in zip_longest(element, args, fillvalue=_marker): + if x is _marker or pool is _marker: + raise ValueError('element is not a product of args') + + pool = tuple(pool) + index = index * len(pool) + pool.index(x) + + return index + + +def combination_index(element, iterable): + """Equivalent to ``list(combinations(iterable, r)).index(element)`` + + The subsequences of *iterable* that are of length *r* can be ordered + lexicographically. :func:`combination_index` computes the index of the + first *element*, without computing the previous combinations. + + >>> combination_index('adf', 'abcdefg') + 10 + + ``ValueError`` will be raised if the given *element* isn't one of the + combinations of *iterable*. + """ + element = enumerate(element) + k, y = next(element, (None, None)) + if k is None: + return 0 + + indexes = [] + pool = enumerate(iterable) + for n, x in pool: + if x == y: + indexes.append(n) + tmp, y = next(element, (None, None)) + if tmp is None: + break + else: + k = tmp + else: + raise ValueError('element is not a combination of iterable') + + n, _ = last(pool, default=(n, None)) + + # Python versiosn below 3.8 don't have math.comb + index = 1 + for i, j in enumerate(reversed(indexes), start=1): + j = n - j + if i <= j: + index += factorial(j) // (factorial(i) * factorial(j - i)) + + return factorial(n + 1) // (factorial(k + 1) * factorial(n - k)) - index + + +def permutation_index(element, iterable): + """Equivalent to ``list(permutations(iterable, r)).index(element)``` + + The subsequences of *iterable* that are of length *r* where order is + important can be ordered lexicographically. :func:`permutation_index` + computes the index of the first *element* directly, without computing + the previous permutations. + + >>> permutation_index([1, 3, 2], range(5)) + 19 + + ``ValueError`` will be raised if the given *element* isn't one of the + permutations of *iterable*. + """ + index = 0 + pool = list(iterable) + for i, x in zip(range(len(pool), -1, -1), element): + r = pool.index(x) + index = index * i + r + del pool[r] + + return index + + +class countable: + """Wrap *iterable* and keep a count of how many items have been consumed. + + The ``items_seen`` attribute starts at ``0`` and increments as the iterable + is consumed: + + >>> iterable = map(str, range(10)) + >>> it = countable(iterable) + >>> it.items_seen + 0 + >>> next(it), next(it) + ('0', '1') + >>> list(it) + ['2', '3', '4', '5', '6', '7', '8', '9'] + >>> it.items_seen + 10 + """ + + def __init__(self, iterable): + self._it = iter(iterable) + self.items_seen = 0 + + def __iter__(self): + return self + + def __next__(self): + item = next(self._it) + self.items_seen += 1 + + return item + + +def chunked_even(iterable, n): + """Break *iterable* into lists of approximately length *n*. + Items are distributed such the lengths of the lists differ by at most + 1 item. + + >>> iterable = [1, 2, 3, 4, 5, 6, 7] + >>> n = 3 + >>> list(chunked_even(iterable, n)) # List lengths: 3, 2, 2 + [[1, 2, 3], [4, 5], [6, 7]] + >>> list(chunked(iterable, n)) # List lengths: 3, 3, 1 + [[1, 2, 3], [4, 5, 6], [7]] + + """ + + len_method = getattr(iterable, '__len__', None) + + if len_method is None: + return _chunked_even_online(iterable, n) + else: + return _chunked_even_finite(iterable, len_method(), n) + + +def _chunked_even_online(iterable, n): + buffer = [] + maxbuf = n + (n - 2) * (n - 1) + for x in iterable: + buffer.append(x) + if len(buffer) == maxbuf: + yield buffer[:n] + buffer = buffer[n:] + yield from _chunked_even_finite(buffer, len(buffer), n) + + +def _chunked_even_finite(iterable, N, n): + if N < 1: + return + + # Lists are either size `full_size <= n` or `partial_size = full_size - 1` + q, r = divmod(N, n) + num_lists = q + (1 if r > 0 else 0) + q, r = divmod(N, num_lists) + full_size = q + (1 if r > 0 else 0) + partial_size = full_size - 1 + num_full = N - partial_size * num_lists + num_partial = num_lists - num_full + + buffer = [] + iterator = iter(iterable) + + # Yield num_full lists of full_size + for x in iterator: + buffer.append(x) + if len(buffer) == full_size: + yield buffer + buffer = [] + num_full -= 1 + if num_full <= 0: + break + + # Yield num_partial lists of partial_size + for x in iterator: + buffer.append(x) + if len(buffer) == partial_size: + yield buffer + buffer = [] + num_partial -= 1 + + +def zip_broadcast(*objects, scalar_types=(str, bytes), strict=False): + """A version of :func:`zip` that "broadcasts" any scalar + (i.e., non-iterable) items into output tuples. + + >>> iterable_1 = [1, 2, 3] + >>> iterable_2 = ['a', 'b', 'c'] + >>> scalar = '_' + >>> list(zip_broadcast(iterable_1, iterable_2, scalar)) + [(1, 'a', '_'), (2, 'b', '_'), (3, 'c', '_')] + + The *scalar_types* keyword argument determines what types are considered + scalar. It is set to ``(str, bytes)`` by default. Set it to ``None`` to + treat strings and byte strings as iterable: + + >>> list(zip_broadcast('abc', 0, 'xyz', scalar_types=None)) + [('a', 0, 'x'), ('b', 0, 'y'), ('c', 0, 'z')] + + If the *strict* keyword argument is ``True``, then + ``UnequalIterablesError`` will be raised if any of the iterables have + different lengthss. + """ + + def is_scalar(obj): + if scalar_types and isinstance(obj, scalar_types): + return True + try: + iter(obj) + except TypeError: + return True + else: + return False + + size = len(objects) + if not size: + return + + iterables, iterable_positions = [], [] + scalars, scalar_positions = [], [] + for i, obj in enumerate(objects): + if is_scalar(obj): + scalars.append(obj) + scalar_positions.append(i) + else: + iterables.append(iter(obj)) + iterable_positions.append(i) + + if len(scalars) == size: + yield tuple(objects) + return + + zipper = _zip_equal if strict else zip + for item in zipper(*iterables): + new_item = [None] * size + + for i, elem in zip(iterable_positions, item): + new_item[i] = elem + + for i, elem in zip(scalar_positions, scalars): + new_item[i] = elem + + yield tuple(new_item) + + +def unique_in_window(iterable, n, key=None): + """Yield the items from *iterable* that haven't been seen recently. + *n* is the size of the lookback window. + + >>> iterable = [0, 1, 0, 2, 3, 0] + >>> n = 3 + >>> list(unique_in_window(iterable, n)) + [0, 1, 2, 3, 0] + + The *key* function, if provided, will be used to determine uniqueness: + + >>> list(unique_in_window('abAcda', 3, key=lambda x: x.lower())) + ['a', 'b', 'c', 'd', 'a'] + + The items in *iterable* must be hashable. + + """ + if n <= 0: + raise ValueError('n must be greater than 0') + + window = deque(maxlen=n) + uniques = set() + use_key = key is not None + + for item in iterable: + k = key(item) if use_key else item + if k in uniques: + continue + + if len(uniques) == n: + uniques.discard(window[0]) + + uniques.add(k) + window.append(k) + + yield item + + +def duplicates_everseen(iterable, key=None): + """Yield duplicate elements after their first appearance. + + >>> list(duplicates_everseen('mississippi')) + ['s', 'i', 's', 's', 'i', 'p', 'i'] + >>> list(duplicates_everseen('AaaBbbCccAaa', str.lower)) + ['a', 'a', 'b', 'b', 'c', 'c', 'A', 'a', 'a'] + + This function is analagous to :func:`unique_everseen` and is subject to + the same performance considerations. + + """ + seen_set = set() + seen_list = [] + use_key = key is not None + + for element in iterable: + k = key(element) if use_key else element + try: + if k not in seen_set: + seen_set.add(k) + else: + yield element + except TypeError: + if k not in seen_list: + seen_list.append(k) + else: + yield element + + +def duplicates_justseen(iterable, key=None): + """Yields serially-duplicate elements after their first appearance. + + >>> list(duplicates_justseen('mississippi')) + ['s', 's', 'p'] + >>> list(duplicates_justseen('AaaBbbCccAaa', str.lower)) + ['a', 'a', 'b', 'b', 'c', 'c', 'a', 'a'] + + This function is analagous to :func:`unique_justseen`. + + """ + return flatten( + map( + lambda group_tuple: islice_extended(group_tuple[1])[1:], + groupby(iterable, key), + ) + ) + + +def minmax(iterable_or_value, *others, key=None, default=_marker): + """Returns both the smallest and largest items in an iterable + or the largest of two or more arguments. + + >>> minmax([3, 1, 5]) + (1, 5) + + >>> minmax(4, 2, 6) + (2, 6) + + If a *key* function is provided, it will be used to transform the input + items for comparison. + + >>> minmax([5, 30], key=str) # '30' sorts before '5' + (30, 5) + + If a *default* value is provided, it will be returned if there are no + input items. + + >>> minmax([], default=(0, 0)) + (0, 0) + + Otherwise ``ValueError`` is raised. + + This function is based on the + `recipe <http://code.activestate.com/recipes/577916/>`__ by + Raymond Hettinger and takes care to minimize the number of comparisons + performed. + """ + iterable = (iterable_or_value, *others) if others else iterable_or_value + + it = iter(iterable) + + try: + lo = hi = next(it) + except StopIteration as e: + if default is _marker: + raise ValueError( + '`minmax()` argument is an empty iterable. ' + 'Provide a `default` value to suppress this error.' + ) from e + return default + + # Different branches depending on the presence of key. This saves a lot + # of unimportant copies which would slow the "key=None" branch + # significantly down. + if key is None: + for x, y in zip_longest(it, it, fillvalue=lo): + if y < x: + x, y = y, x + if x < lo: + lo = x + if hi < y: + hi = y + + else: + lo_key = hi_key = key(lo) + + for x, y in zip_longest(it, it, fillvalue=lo): + + x_key, y_key = key(x), key(y) + + if y_key < x_key: + x, y, x_key, y_key = y, x, y_key, x_key + if x_key < lo_key: + lo, lo_key = x, x_key + if hi_key < y_key: + hi, hi_key = y, y_key + + return lo, hi diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/recipes.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/recipes.py new file mode 100644 index 0000000..a259642 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/more_itertools/recipes.py @@ -0,0 +1,698 @@ +"""Imported from the recipes section of the itertools documentation. + +All functions taken from the recipes section of the itertools library docs +[1]_. +Some backward-compatible usability improvements have been made. + +.. [1] http://docs.python.org/library/itertools.html#recipes + +""" +import warnings +from collections import deque +from itertools import ( + chain, + combinations, + count, + cycle, + groupby, + islice, + repeat, + starmap, + tee, + zip_longest, +) +import operator +from random import randrange, sample, choice + +__all__ = [ + 'all_equal', + 'before_and_after', + 'consume', + 'convolve', + 'dotproduct', + 'first_true', + 'flatten', + 'grouper', + 'iter_except', + 'ncycles', + 'nth', + 'nth_combination', + 'padnone', + 'pad_none', + 'pairwise', + 'partition', + 'powerset', + 'prepend', + 'quantify', + 'random_combination_with_replacement', + 'random_combination', + 'random_permutation', + 'random_product', + 'repeatfunc', + 'roundrobin', + 'sliding_window', + 'tabulate', + 'tail', + 'take', + 'triplewise', + 'unique_everseen', + 'unique_justseen', +] + + +def take(n, iterable): + """Return first *n* items of the iterable as a list. + + >>> take(3, range(10)) + [0, 1, 2] + + If there are fewer than *n* items in the iterable, all of them are + returned. + + >>> take(10, range(3)) + [0, 1, 2] + + """ + return list(islice(iterable, n)) + + +def tabulate(function, start=0): + """Return an iterator over the results of ``func(start)``, + ``func(start + 1)``, ``func(start + 2)``... + + *func* should be a function that accepts one integer argument. + + If *start* is not specified it defaults to 0. It will be incremented each + time the iterator is advanced. + + >>> square = lambda x: x ** 2 + >>> iterator = tabulate(square, -3) + >>> take(4, iterator) + [9, 4, 1, 0] + + """ + return map(function, count(start)) + + +def tail(n, iterable): + """Return an iterator over the last *n* items of *iterable*. + + >>> t = tail(3, 'ABCDEFG') + >>> list(t) + ['E', 'F', 'G'] + + """ + return iter(deque(iterable, maxlen=n)) + + +def consume(iterator, n=None): + """Advance *iterable* by *n* steps. If *n* is ``None``, consume it + entirely. + + Efficiently exhausts an iterator without returning values. Defaults to + consuming the whole iterator, but an optional second argument may be + provided to limit consumption. + + >>> i = (x for x in range(10)) + >>> next(i) + 0 + >>> consume(i, 3) + >>> next(i) + 4 + >>> consume(i) + >>> next(i) + Traceback (most recent call last): + File "<stdin>", line 1, in <module> + StopIteration + + If the iterator has fewer items remaining than the provided limit, the + whole iterator will be consumed. + + >>> i = (x for x in range(3)) + >>> consume(i, 5) + >>> next(i) + Traceback (most recent call last): + File "<stdin>", line 1, in <module> + StopIteration + + """ + # Use functions that consume iterators at C speed. + if n is None: + # feed the entire iterator into a zero-length deque + deque(iterator, maxlen=0) + else: + # advance to the empty slice starting at position n + next(islice(iterator, n, n), None) + + +def nth(iterable, n, default=None): + """Returns the nth item or a default value. + + >>> l = range(10) + >>> nth(l, 3) + 3 + >>> nth(l, 20, "zebra") + 'zebra' + + """ + return next(islice(iterable, n, None), default) + + +def all_equal(iterable): + """ + Returns ``True`` if all the elements are equal to each other. + + >>> all_equal('aaaa') + True + >>> all_equal('aaab') + False + + """ + g = groupby(iterable) + return next(g, True) and not next(g, False) + + +def quantify(iterable, pred=bool): + """Return the how many times the predicate is true. + + >>> quantify([True, False, True]) + 2 + + """ + return sum(map(pred, iterable)) + + +def pad_none(iterable): + """Returns the sequence of elements and then returns ``None`` indefinitely. + + >>> take(5, pad_none(range(3))) + [0, 1, 2, None, None] + + Useful for emulating the behavior of the built-in :func:`map` function. + + See also :func:`padded`. + + """ + return chain(iterable, repeat(None)) + + +padnone = pad_none + + +def ncycles(iterable, n): + """Returns the sequence elements *n* times + + >>> list(ncycles(["a", "b"], 3)) + ['a', 'b', 'a', 'b', 'a', 'b'] + + """ + return chain.from_iterable(repeat(tuple(iterable), n)) + + +def dotproduct(vec1, vec2): + """Returns the dot product of the two iterables. + + >>> dotproduct([10, 10], [20, 20]) + 400 + + """ + return sum(map(operator.mul, vec1, vec2)) + + +def flatten(listOfLists): + """Return an iterator flattening one level of nesting in a list of lists. + + >>> list(flatten([[0, 1], [2, 3]])) + [0, 1, 2, 3] + + See also :func:`collapse`, which can flatten multiple levels of nesting. + + """ + return chain.from_iterable(listOfLists) + + +def repeatfunc(func, times=None, *args): + """Call *func* with *args* repeatedly, returning an iterable over the + results. + + If *times* is specified, the iterable will terminate after that many + repetitions: + + >>> from operator import add + >>> times = 4 + >>> args = 3, 5 + >>> list(repeatfunc(add, times, *args)) + [8, 8, 8, 8] + + If *times* is ``None`` the iterable will not terminate: + + >>> from random import randrange + >>> times = None + >>> args = 1, 11 + >>> take(6, repeatfunc(randrange, times, *args)) # doctest:+SKIP + [2, 4, 8, 1, 8, 4] + + """ + if times is None: + return starmap(func, repeat(args)) + return starmap(func, repeat(args, times)) + + +def _pairwise(iterable): + """Returns an iterator of paired items, overlapping, from the original + + >>> take(4, pairwise(count())) + [(0, 1), (1, 2), (2, 3), (3, 4)] + + On Python 3.10 and above, this is an alias for :func:`itertools.pairwise`. + + """ + a, b = tee(iterable) + next(b, None) + yield from zip(a, b) + + +try: + from itertools import pairwise as itertools_pairwise +except ImportError: + pairwise = _pairwise +else: + + def pairwise(iterable): + yield from itertools_pairwise(iterable) + + pairwise.__doc__ = _pairwise.__doc__ + + +def grouper(iterable, n, fillvalue=None): + """Collect data into fixed-length chunks or blocks. + + >>> list(grouper('ABCDEFG', 3, 'x')) + [('A', 'B', 'C'), ('D', 'E', 'F'), ('G', 'x', 'x')] + + """ + if isinstance(iterable, int): + warnings.warn( + "grouper expects iterable as first parameter", DeprecationWarning + ) + n, iterable = iterable, n + args = [iter(iterable)] * n + return zip_longest(fillvalue=fillvalue, *args) + + +def roundrobin(*iterables): + """Yields an item from each iterable, alternating between them. + + >>> list(roundrobin('ABC', 'D', 'EF')) + ['A', 'D', 'E', 'B', 'F', 'C'] + + This function produces the same output as :func:`interleave_longest`, but + may perform better for some inputs (in particular when the number of + iterables is small). + + """ + # Recipe credited to George Sakkis + pending = len(iterables) + nexts = cycle(iter(it).__next__ for it in iterables) + while pending: + try: + for next in nexts: + yield next() + except StopIteration: + pending -= 1 + nexts = cycle(islice(nexts, pending)) + + +def partition(pred, iterable): + """ + Returns a 2-tuple of iterables derived from the input iterable. + The first yields the items that have ``pred(item) == False``. + The second yields the items that have ``pred(item) == True``. + + >>> is_odd = lambda x: x % 2 != 0 + >>> iterable = range(10) + >>> even_items, odd_items = partition(is_odd, iterable) + >>> list(even_items), list(odd_items) + ([0, 2, 4, 6, 8], [1, 3, 5, 7, 9]) + + If *pred* is None, :func:`bool` is used. + + >>> iterable = [0, 1, False, True, '', ' '] + >>> false_items, true_items = partition(None, iterable) + >>> list(false_items), list(true_items) + ([0, False, ''], [1, True, ' ']) + + """ + if pred is None: + pred = bool + + evaluations = ((pred(x), x) for x in iterable) + t1, t2 = tee(evaluations) + return ( + (x for (cond, x) in t1 if not cond), + (x for (cond, x) in t2 if cond), + ) + + +def powerset(iterable): + """Yields all possible subsets of the iterable. + + >>> list(powerset([1, 2, 3])) + [(), (1,), (2,), (3,), (1, 2), (1, 3), (2, 3), (1, 2, 3)] + + :func:`powerset` will operate on iterables that aren't :class:`set` + instances, so repeated elements in the input will produce repeated elements + in the output. Use :func:`unique_everseen` on the input to avoid generating + duplicates: + + >>> seq = [1, 1, 0] + >>> list(powerset(seq)) + [(), (1,), (1,), (0,), (1, 1), (1, 0), (1, 0), (1, 1, 0)] + >>> from more_itertools import unique_everseen + >>> list(powerset(unique_everseen(seq))) + [(), (1,), (0,), (1, 0)] + + """ + s = list(iterable) + return chain.from_iterable(combinations(s, r) for r in range(len(s) + 1)) + + +def unique_everseen(iterable, key=None): + """ + Yield unique elements, preserving order. + + >>> list(unique_everseen('AAAABBBCCDAABBB')) + ['A', 'B', 'C', 'D'] + >>> list(unique_everseen('ABBCcAD', str.lower)) + ['A', 'B', 'C', 'D'] + + Sequences with a mix of hashable and unhashable items can be used. + The function will be slower (i.e., `O(n^2)`) for unhashable items. + + Remember that ``list`` objects are unhashable - you can use the *key* + parameter to transform the list to a tuple (which is hashable) to + avoid a slowdown. + + >>> iterable = ([1, 2], [2, 3], [1, 2]) + >>> list(unique_everseen(iterable)) # Slow + [[1, 2], [2, 3]] + >>> list(unique_everseen(iterable, key=tuple)) # Faster + [[1, 2], [2, 3]] + + Similary, you may want to convert unhashable ``set`` objects with + ``key=frozenset``. For ``dict`` objects, + ``key=lambda x: frozenset(x.items())`` can be used. + + """ + seenset = set() + seenset_add = seenset.add + seenlist = [] + seenlist_add = seenlist.append + use_key = key is not None + + for element in iterable: + k = key(element) if use_key else element + try: + if k not in seenset: + seenset_add(k) + yield element + except TypeError: + if k not in seenlist: + seenlist_add(k) + yield element + + +def unique_justseen(iterable, key=None): + """Yields elements in order, ignoring serial duplicates + + >>> list(unique_justseen('AAAABBBCCDAABBB')) + ['A', 'B', 'C', 'D', 'A', 'B'] + >>> list(unique_justseen('ABBCcAD', str.lower)) + ['A', 'B', 'C', 'A', 'D'] + + """ + return map(next, map(operator.itemgetter(1), groupby(iterable, key))) + + +def iter_except(func, exception, first=None): + """Yields results from a function repeatedly until an exception is raised. + + Converts a call-until-exception interface to an iterator interface. + Like ``iter(func, sentinel)``, but uses an exception instead of a sentinel + to end the loop. + + >>> l = [0, 1, 2] + >>> list(iter_except(l.pop, IndexError)) + [2, 1, 0] + + Multiple exceptions can be specified as a stopping condition: + + >>> l = [1, 2, 3, '...', 4, 5, 6] + >>> list(iter_except(lambda: 1 + l.pop(), (IndexError, TypeError))) + [7, 6, 5] + >>> list(iter_except(lambda: 1 + l.pop(), (IndexError, TypeError))) + [4, 3, 2] + >>> list(iter_except(lambda: 1 + l.pop(), (IndexError, TypeError))) + [] + + """ + try: + if first is not None: + yield first() + while 1: + yield func() + except exception: + pass + + +def first_true(iterable, default=None, pred=None): + """ + Returns the first true value in the iterable. + + If no true value is found, returns *default* + + If *pred* is not None, returns the first item for which + ``pred(item) == True`` . + + >>> first_true(range(10)) + 1 + >>> first_true(range(10), pred=lambda x: x > 5) + 6 + >>> first_true(range(10), default='missing', pred=lambda x: x > 9) + 'missing' + + """ + return next(filter(pred, iterable), default) + + +def random_product(*args, repeat=1): + """Draw an item at random from each of the input iterables. + + >>> random_product('abc', range(4), 'XYZ') # doctest:+SKIP + ('c', 3, 'Z') + + If *repeat* is provided as a keyword argument, that many items will be + drawn from each iterable. + + >>> random_product('abcd', range(4), repeat=2) # doctest:+SKIP + ('a', 2, 'd', 3) + + This equivalent to taking a random selection from + ``itertools.product(*args, **kwarg)``. + + """ + pools = [tuple(pool) for pool in args] * repeat + return tuple(choice(pool) for pool in pools) + + +def random_permutation(iterable, r=None): + """Return a random *r* length permutation of the elements in *iterable*. + + If *r* is not specified or is ``None``, then *r* defaults to the length of + *iterable*. + + >>> random_permutation(range(5)) # doctest:+SKIP + (3, 4, 0, 1, 2) + + This equivalent to taking a random selection from + ``itertools.permutations(iterable, r)``. + + """ + pool = tuple(iterable) + r = len(pool) if r is None else r + return tuple(sample(pool, r)) + + +def random_combination(iterable, r): + """Return a random *r* length subsequence of the elements in *iterable*. + + >>> random_combination(range(5), 3) # doctest:+SKIP + (2, 3, 4) + + This equivalent to taking a random selection from + ``itertools.combinations(iterable, r)``. + + """ + pool = tuple(iterable) + n = len(pool) + indices = sorted(sample(range(n), r)) + return tuple(pool[i] for i in indices) + + +def random_combination_with_replacement(iterable, r): + """Return a random *r* length subsequence of elements in *iterable*, + allowing individual elements to be repeated. + + >>> random_combination_with_replacement(range(3), 5) # doctest:+SKIP + (0, 0, 1, 2, 2) + + This equivalent to taking a random selection from + ``itertools.combinations_with_replacement(iterable, r)``. + + """ + pool = tuple(iterable) + n = len(pool) + indices = sorted(randrange(n) for i in range(r)) + return tuple(pool[i] for i in indices) + + +def nth_combination(iterable, r, index): + """Equivalent to ``list(combinations(iterable, r))[index]``. + + The subsequences of *iterable* that are of length *r* can be ordered + lexicographically. :func:`nth_combination` computes the subsequence at + sort position *index* directly, without computing the previous + subsequences. + + >>> nth_combination(range(5), 3, 5) + (0, 3, 4) + + ``ValueError`` will be raised If *r* is negative or greater than the length + of *iterable*. + ``IndexError`` will be raised if the given *index* is invalid. + """ + pool = tuple(iterable) + n = len(pool) + if (r < 0) or (r > n): + raise ValueError + + c = 1 + k = min(r, n - r) + for i in range(1, k + 1): + c = c * (n - k + i) // i + + if index < 0: + index += c + + if (index < 0) or (index >= c): + raise IndexError + + result = [] + while r: + c, n, r = c * r // n, n - 1, r - 1 + while index >= c: + index -= c + c, n = c * (n - r) // n, n - 1 + result.append(pool[-1 - n]) + + return tuple(result) + + +def prepend(value, iterator): + """Yield *value*, followed by the elements in *iterator*. + + >>> value = '0' + >>> iterator = ['1', '2', '3'] + >>> list(prepend(value, iterator)) + ['0', '1', '2', '3'] + + To prepend multiple values, see :func:`itertools.chain` + or :func:`value_chain`. + + """ + return chain([value], iterator) + + +def convolve(signal, kernel): + """Convolve the iterable *signal* with the iterable *kernel*. + + >>> signal = (1, 2, 3, 4, 5) + >>> kernel = [3, 2, 1] + >>> list(convolve(signal, kernel)) + [3, 8, 14, 20, 26, 14, 5] + + Note: the input arguments are not interchangeable, as the *kernel* + is immediately consumed and stored. + + """ + kernel = tuple(kernel)[::-1] + n = len(kernel) + window = deque([0], maxlen=n) * n + for x in chain(signal, repeat(0, n - 1)): + window.append(x) + yield sum(map(operator.mul, kernel, window)) + + +def before_and_after(predicate, it): + """A variant of :func:`takewhile` that allows complete access to the + remainder of the iterator. + + >>> it = iter('ABCdEfGhI') + >>> all_upper, remainder = before_and_after(str.isupper, it) + >>> ''.join(all_upper) + 'ABC' + >>> ''.join(remainder) # takewhile() would lose the 'd' + 'dEfGhI' + + Note that the first iterator must be fully consumed before the second + iterator can generate valid results. + """ + it = iter(it) + transition = [] + + def true_iterator(): + for elem in it: + if predicate(elem): + yield elem + else: + transition.append(elem) + return + + def remainder_iterator(): + yield from transition + yield from it + + return true_iterator(), remainder_iterator() + + +def triplewise(iterable): + """Return overlapping triplets from *iterable*. + + >>> list(triplewise('ABCDE')) + [('A', 'B', 'C'), ('B', 'C', 'D'), ('C', 'D', 'E')] + + """ + for (a, _), (b, c) in pairwise(pairwise(iterable)): + yield a, b, c + + +def sliding_window(iterable, n): + """Return a sliding window of width *n* over *iterable*. + + >>> list(sliding_window(range(6), 4)) + [(0, 1, 2, 3), (1, 2, 3, 4), (2, 3, 4, 5)] + + If *iterable* has fewer than *n* items, then nothing is yielded: + + >>> list(sliding_window(range(3), 4)) + [] + + For a variant with more features, see :func:`windowed`. + """ + it = iter(iterable) + window = deque(islice(it, n), maxlen=n) + if len(window) == n: + yield tuple(window) + for x in it: + window.append(x) + yield tuple(window) diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__about__.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__about__.py new file mode 100644 index 0000000..3551bc2 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__about__.py @@ -0,0 +1,26 @@ +# This file is dual licensed under the terms of the Apache License, Version +# 2.0, and the BSD License. See the LICENSE file in the root of this repository +# for complete details. + +__all__ = [ + "__title__", + "__summary__", + "__uri__", + "__version__", + "__author__", + "__email__", + "__license__", + "__copyright__", +] + +__title__ = "packaging" +__summary__ = "Core utilities for Python packages" +__uri__ = "https://github.com/pypa/packaging" + +__version__ = "21.3" + +__author__ = "Donald Stufft and individual contributors" +__email__ = "donald@stufft.io" + +__license__ = "BSD-2-Clause or Apache-2.0" +__copyright__ = "2014-2019 %s" % __author__ diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__init__.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__init__.py new file mode 100644 index 0000000..3c50c5d --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__init__.py @@ -0,0 +1,25 @@ +# This file is dual licensed under the terms of the Apache License, Version +# 2.0, and the BSD License. See the LICENSE file in the root of this repository +# for complete details. + +from .__about__ import ( + __author__, + __copyright__, + __email__, + __license__, + __summary__, + __title__, + __uri__, + __version__, +) + +__all__ = [ + "__title__", + "__summary__", + "__uri__", + "__version__", + "__author__", + "__email__", + "__license__", + "__copyright__", +] diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/__about__.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/__about__.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..a7f1c60 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/__about__.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/__init__.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/__init__.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..a2ad76a --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/__init__.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/_manylinux.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/_manylinux.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..6d95b1a --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/_manylinux.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/_musllinux.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/_musllinux.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..e1f5562 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/_musllinux.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/_structures.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/_structures.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..16345f2 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/_structures.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/markers.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/markers.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..c8143d6 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/markers.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/requirements.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/requirements.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..1e094ae --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/requirements.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/specifiers.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/specifiers.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..5d5516e --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/specifiers.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/tags.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/tags.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..d7db1fe --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/tags.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/utils.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/utils.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..e952206 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/utils.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/version.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/version.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..abb1fec --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/__pycache__/version.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/_manylinux.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/_manylinux.py new file mode 100644 index 0000000..4c379aa --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/_manylinux.py @@ -0,0 +1,301 @@ +import collections +import functools +import os +import re +import struct +import sys +import warnings +from typing import IO, Dict, Iterator, NamedTuple, Optional, Tuple + + +# Python does not provide platform information at sufficient granularity to +# identify the architecture of the running executable in some cases, so we +# determine it dynamically by reading the information from the running +# process. This only applies on Linux, which uses the ELF format. +class _ELFFileHeader: + # https://en.wikipedia.org/wiki/Executable_and_Linkable_Format#File_header + class _InvalidELFFileHeader(ValueError): + """ + An invalid ELF file header was found. + """ + + ELF_MAGIC_NUMBER = 0x7F454C46 + ELFCLASS32 = 1 + ELFCLASS64 = 2 + ELFDATA2LSB = 1 + ELFDATA2MSB = 2 + EM_386 = 3 + EM_S390 = 22 + EM_ARM = 40 + EM_X86_64 = 62 + EF_ARM_ABIMASK = 0xFF000000 + EF_ARM_ABI_VER5 = 0x05000000 + EF_ARM_ABI_FLOAT_HARD = 0x00000400 + + def __init__(self, file: IO[bytes]) -> None: + def unpack(fmt: str) -> int: + try: + data = file.read(struct.calcsize(fmt)) + result: Tuple[int, ...] = struct.unpack(fmt, data) + except struct.error: + raise _ELFFileHeader._InvalidELFFileHeader() + return result[0] + + self.e_ident_magic = unpack(">I") + if self.e_ident_magic != self.ELF_MAGIC_NUMBER: + raise _ELFFileHeader._InvalidELFFileHeader() + self.e_ident_class = unpack("B") + if self.e_ident_class not in {self.ELFCLASS32, self.ELFCLASS64}: + raise _ELFFileHeader._InvalidELFFileHeader() + self.e_ident_data = unpack("B") + if self.e_ident_data not in {self.ELFDATA2LSB, self.ELFDATA2MSB}: + raise _ELFFileHeader._InvalidELFFileHeader() + self.e_ident_version = unpack("B") + self.e_ident_osabi = unpack("B") + self.e_ident_abiversion = unpack("B") + self.e_ident_pad = file.read(7) + format_h = "<H" if self.e_ident_data == self.ELFDATA2LSB else ">H" + format_i = "<I" if self.e_ident_data == self.ELFDATA2LSB else ">I" + format_q = "<Q" if self.e_ident_data == self.ELFDATA2LSB else ">Q" + format_p = format_i if self.e_ident_class == self.ELFCLASS32 else format_q + self.e_type = unpack(format_h) + self.e_machine = unpack(format_h) + self.e_version = unpack(format_i) + self.e_entry = unpack(format_p) + self.e_phoff = unpack(format_p) + self.e_shoff = unpack(format_p) + self.e_flags = unpack(format_i) + self.e_ehsize = unpack(format_h) + self.e_phentsize = unpack(format_h) + self.e_phnum = unpack(format_h) + self.e_shentsize = unpack(format_h) + self.e_shnum = unpack(format_h) + self.e_shstrndx = unpack(format_h) + + +def _get_elf_header() -> Optional[_ELFFileHeader]: + try: + with open(sys.executable, "rb") as f: + elf_header = _ELFFileHeader(f) + except (OSError, TypeError, _ELFFileHeader._InvalidELFFileHeader): + return None + return elf_header + + +def _is_linux_armhf() -> bool: + # hard-float ABI can be detected from the ELF header of the running + # process + # https://static.docs.arm.com/ihi0044/g/aaelf32.pdf + elf_header = _get_elf_header() + if elf_header is None: + return False + result = elf_header.e_ident_class == elf_header.ELFCLASS32 + result &= elf_header.e_ident_data == elf_header.ELFDATA2LSB + result &= elf_header.e_machine == elf_header.EM_ARM + result &= ( + elf_header.e_flags & elf_header.EF_ARM_ABIMASK + ) == elf_header.EF_ARM_ABI_VER5 + result &= ( + elf_header.e_flags & elf_header.EF_ARM_ABI_FLOAT_HARD + ) == elf_header.EF_ARM_ABI_FLOAT_HARD + return result + + +def _is_linux_i686() -> bool: + elf_header = _get_elf_header() + if elf_header is None: + return False + result = elf_header.e_ident_class == elf_header.ELFCLASS32 + result &= elf_header.e_ident_data == elf_header.ELFDATA2LSB + result &= elf_header.e_machine == elf_header.EM_386 + return result + + +def _have_compatible_abi(arch: str) -> bool: + if arch == "armv7l": + return _is_linux_armhf() + if arch == "i686": + return _is_linux_i686() + return arch in {"x86_64", "aarch64", "ppc64", "ppc64le", "s390x"} + + +# If glibc ever changes its major version, we need to know what the last +# minor version was, so we can build the complete list of all versions. +# For now, guess what the highest minor version might be, assume it will +# be 50 for testing. Once this actually happens, update the dictionary +# with the actual value. +_LAST_GLIBC_MINOR: Dict[int, int] = collections.defaultdict(lambda: 50) + + +class _GLibCVersion(NamedTuple): + major: int + minor: int + + +def _glibc_version_string_confstr() -> Optional[str]: + """ + Primary implementation of glibc_version_string using os.confstr. + """ + # os.confstr is quite a bit faster than ctypes.DLL. It's also less likely + # to be broken or missing. This strategy is used in the standard library + # platform module. + # https://github.com/python/cpython/blob/fcf1d003bf4f0100c/Lib/platform.py#L175-L183 + try: + # os.confstr("CS_GNU_LIBC_VERSION") returns a string like "glibc 2.17". + version_string = os.confstr("CS_GNU_LIBC_VERSION") + assert version_string is not None + _, version = version_string.split() + except (AssertionError, AttributeError, OSError, ValueError): + # os.confstr() or CS_GNU_LIBC_VERSION not available (or a bad value)... + return None + return version + + +def _glibc_version_string_ctypes() -> Optional[str]: + """ + Fallback implementation of glibc_version_string using ctypes. + """ + try: + import ctypes + except ImportError: + return None + + # ctypes.CDLL(None) internally calls dlopen(NULL), and as the dlopen + # manpage says, "If filename is NULL, then the returned handle is for the + # main program". This way we can let the linker do the work to figure out + # which libc our process is actually using. + # + # We must also handle the special case where the executable is not a + # dynamically linked executable. This can occur when using musl libc, + # for example. In this situation, dlopen() will error, leading to an + # OSError. Interestingly, at least in the case of musl, there is no + # errno set on the OSError. The single string argument used to construct + # OSError comes from libc itself and is therefore not portable to + # hard code here. In any case, failure to call dlopen() means we + # can proceed, so we bail on our attempt. + try: + process_namespace = ctypes.CDLL(None) + except OSError: + return None + + try: + gnu_get_libc_version = process_namespace.gnu_get_libc_version + except AttributeError: + # Symbol doesn't exist -> therefore, we are not linked to + # glibc. + return None + + # Call gnu_get_libc_version, which returns a string like "2.5" + gnu_get_libc_version.restype = ctypes.c_char_p + version_str: str = gnu_get_libc_version() + # py2 / py3 compatibility: + if not isinstance(version_str, str): + version_str = version_str.decode("ascii") + + return version_str + + +def _glibc_version_string() -> Optional[str]: + """Returns glibc version string, or None if not using glibc.""" + return _glibc_version_string_confstr() or _glibc_version_string_ctypes() + + +def _parse_glibc_version(version_str: str) -> Tuple[int, int]: + """Parse glibc version. + + We use a regexp instead of str.split because we want to discard any + random junk that might come after the minor version -- this might happen + in patched/forked versions of glibc (e.g. Linaro's version of glibc + uses version strings like "2.20-2014.11"). See gh-3588. + """ + m = re.match(r"(?P<major>[0-9]+)\.(?P<minor>[0-9]+)", version_str) + if not m: + warnings.warn( + "Expected glibc version with 2 components major.minor," + " got: %s" % version_str, + RuntimeWarning, + ) + return -1, -1 + return int(m.group("major")), int(m.group("minor")) + + +@functools.lru_cache() +def _get_glibc_version() -> Tuple[int, int]: + version_str = _glibc_version_string() + if version_str is None: + return (-1, -1) + return _parse_glibc_version(version_str) + + +# From PEP 513, PEP 600 +def _is_compatible(name: str, arch: str, version: _GLibCVersion) -> bool: + sys_glibc = _get_glibc_version() + if sys_glibc < version: + return False + # Check for presence of _manylinux module. + try: + import _manylinux # noqa + except ImportError: + return True + if hasattr(_manylinux, "manylinux_compatible"): + result = _manylinux.manylinux_compatible(version[0], version[1], arch) + if result is not None: + return bool(result) + return True + if version == _GLibCVersion(2, 5): + if hasattr(_manylinux, "manylinux1_compatible"): + return bool(_manylinux.manylinux1_compatible) + if version == _GLibCVersion(2, 12): + if hasattr(_manylinux, "manylinux2010_compatible"): + return bool(_manylinux.manylinux2010_compatible) + if version == _GLibCVersion(2, 17): + if hasattr(_manylinux, "manylinux2014_compatible"): + return bool(_manylinux.manylinux2014_compatible) + return True + + +_LEGACY_MANYLINUX_MAP = { + # CentOS 7 w/ glibc 2.17 (PEP 599) + (2, 17): "manylinux2014", + # CentOS 6 w/ glibc 2.12 (PEP 571) + (2, 12): "manylinux2010", + # CentOS 5 w/ glibc 2.5 (PEP 513) + (2, 5): "manylinux1", +} + + +def platform_tags(linux: str, arch: str) -> Iterator[str]: + if not _have_compatible_abi(arch): + return + # Oldest glibc to be supported regardless of architecture is (2, 17). + too_old_glibc2 = _GLibCVersion(2, 16) + if arch in {"x86_64", "i686"}: + # On x86/i686 also oldest glibc to be supported is (2, 5). + too_old_glibc2 = _GLibCVersion(2, 4) + current_glibc = _GLibCVersion(*_get_glibc_version()) + glibc_max_list = [current_glibc] + # We can assume compatibility across glibc major versions. + # https://sourceware.org/bugzilla/show_bug.cgi?id=24636 + # + # Build a list of maximum glibc versions so that we can + # output the canonical list of all glibc from current_glibc + # down to too_old_glibc2, including all intermediary versions. + for glibc_major in range(current_glibc.major - 1, 1, -1): + glibc_minor = _LAST_GLIBC_MINOR[glibc_major] + glibc_max_list.append(_GLibCVersion(glibc_major, glibc_minor)) + for glibc_max in glibc_max_list: + if glibc_max.major == too_old_glibc2.major: + min_minor = too_old_glibc2.minor + else: + # For other glibc major versions oldest supported is (x, 0). + min_minor = -1 + for glibc_minor in range(glibc_max.minor, min_minor, -1): + glibc_version = _GLibCVersion(glibc_max.major, glibc_minor) + tag = "manylinux_{}_{}".format(*glibc_version) + if _is_compatible(tag, arch, glibc_version): + yield linux.replace("linux", tag) + # Handle the legacy manylinux1, manylinux2010, manylinux2014 tags. + if glibc_version in _LEGACY_MANYLINUX_MAP: + legacy_tag = _LEGACY_MANYLINUX_MAP[glibc_version] + if _is_compatible(legacy_tag, arch, glibc_version): + yield linux.replace("linux", legacy_tag) diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/_musllinux.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/_musllinux.py new file mode 100644 index 0000000..8ac3059 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/_musllinux.py @@ -0,0 +1,136 @@ +"""PEP 656 support. + +This module implements logic to detect if the currently running Python is +linked against musl, and what musl version is used. +""" + +import contextlib +import functools +import operator +import os +import re +import struct +import subprocess +import sys +from typing import IO, Iterator, NamedTuple, Optional, Tuple + + +def _read_unpacked(f: IO[bytes], fmt: str) -> Tuple[int, ...]: + return struct.unpack(fmt, f.read(struct.calcsize(fmt))) + + +def _parse_ld_musl_from_elf(f: IO[bytes]) -> Optional[str]: + """Detect musl libc location by parsing the Python executable. + + Based on: https://gist.github.com/lyssdod/f51579ae8d93c8657a5564aefc2ffbca + ELF header: https://refspecs.linuxfoundation.org/elf/gabi4+/ch4.eheader.html + """ + f.seek(0) + try: + ident = _read_unpacked(f, "16B") + except struct.error: + return None + if ident[:4] != tuple(b"\x7fELF"): # Invalid magic, not ELF. + return None + f.seek(struct.calcsize("HHI"), 1) # Skip file type, machine, and version. + + try: + # e_fmt: Format for program header. + # p_fmt: Format for section header. + # p_idx: Indexes to find p_type, p_offset, and p_filesz. + e_fmt, p_fmt, p_idx = { + 1: ("IIIIHHH", "IIIIIIII", (0, 1, 4)), # 32-bit. + 2: ("QQQIHHH", "IIQQQQQQ", (0, 2, 5)), # 64-bit. + }[ident[4]] + except KeyError: + return None + else: + p_get = operator.itemgetter(*p_idx) + + # Find the interpreter section and return its content. + try: + _, e_phoff, _, _, _, e_phentsize, e_phnum = _read_unpacked(f, e_fmt) + except struct.error: + return None + for i in range(e_phnum + 1): + f.seek(e_phoff + e_phentsize * i) + try: + p_type, p_offset, p_filesz = p_get(_read_unpacked(f, p_fmt)) + except struct.error: + return None + if p_type != 3: # Not PT_INTERP. + continue + f.seek(p_offset) + interpreter = os.fsdecode(f.read(p_filesz)).strip("\0") + if "musl" not in interpreter: + return None + return interpreter + return None + + +class _MuslVersion(NamedTuple): + major: int + minor: int + + +def _parse_musl_version(output: str) -> Optional[_MuslVersion]: + lines = [n for n in (n.strip() for n in output.splitlines()) if n] + if len(lines) < 2 or lines[0][:4] != "musl": + return None + m = re.match(r"Version (\d+)\.(\d+)", lines[1]) + if not m: + return None + return _MuslVersion(major=int(m.group(1)), minor=int(m.group(2))) + + +@functools.lru_cache() +def _get_musl_version(executable: str) -> Optional[_MuslVersion]: + """Detect currently-running musl runtime version. + + This is done by checking the specified executable's dynamic linking + information, and invoking the loader to parse its output for a version + string. If the loader is musl, the output would be something like:: + + musl libc (x86_64) + Version 1.2.2 + Dynamic Program Loader + """ + with contextlib.ExitStack() as stack: + try: + f = stack.enter_context(open(executable, "rb")) + except OSError: + return None + ld = _parse_ld_musl_from_elf(f) + if not ld: + return None + proc = subprocess.run([ld], stderr=subprocess.PIPE, universal_newlines=True) + return _parse_musl_version(proc.stderr) + + +def platform_tags(arch: str) -> Iterator[str]: + """Generate musllinux tags compatible to the current platform. + + :param arch: Should be the part of platform tag after the ``linux_`` + prefix, e.g. ``x86_64``. The ``linux_`` prefix is assumed as a + prerequisite for the current platform to be musllinux-compatible. + + :returns: An iterator of compatible musllinux tags. + """ + sys_musl = _get_musl_version(sys.executable) + if sys_musl is None: # Python not dynamically linked against musl. + return + for minor in range(sys_musl.minor, -1, -1): + yield f"musllinux_{sys_musl.major}_{minor}_{arch}" + + +if __name__ == "__main__": # pragma: no cover + import sysconfig + + plat = sysconfig.get_platform() + assert plat.startswith("linux-"), "not linux" + + print("plat:", plat) + print("musl:", _get_musl_version(sys.executable)) + print("tags:", end=" ") + for t in platform_tags(re.sub(r"[.-]", "_", plat.split("-", 1)[-1])): + print(t, end="\n ") diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/_structures.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/_structures.py new file mode 100644 index 0000000..90a6465 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/_structures.py @@ -0,0 +1,61 @@ +# This file is dual licensed under the terms of the Apache License, Version +# 2.0, and the BSD License. See the LICENSE file in the root of this repository +# for complete details. + + +class InfinityType: + def __repr__(self) -> str: + return "Infinity" + + def __hash__(self) -> int: + return hash(repr(self)) + + def __lt__(self, other: object) -> bool: + return False + + def __le__(self, other: object) -> bool: + return False + + def __eq__(self, other: object) -> bool: + return isinstance(other, self.__class__) + + def __gt__(self, other: object) -> bool: + return True + + def __ge__(self, other: object) -> bool: + return True + + def __neg__(self: object) -> "NegativeInfinityType": + return NegativeInfinity + + +Infinity = InfinityType() + + +class NegativeInfinityType: + def __repr__(self) -> str: + return "-Infinity" + + def __hash__(self) -> int: + return hash(repr(self)) + + def __lt__(self, other: object) -> bool: + return True + + def __le__(self, other: object) -> bool: + return True + + def __eq__(self, other: object) -> bool: + return isinstance(other, self.__class__) + + def __gt__(self, other: object) -> bool: + return False + + def __ge__(self, other: object) -> bool: + return False + + def __neg__(self: object) -> InfinityType: + return Infinity + + +NegativeInfinity = NegativeInfinityType() diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/markers.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/markers.py new file mode 100644 index 0000000..18769b0 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/markers.py @@ -0,0 +1,304 @@ +# This file is dual licensed under the terms of the Apache License, Version +# 2.0, and the BSD License. See the LICENSE file in the root of this repository +# for complete details. + +import operator +import os +import platform +import sys +from typing import Any, Callable, Dict, List, Optional, Tuple, Union + +from pkg_resources.extern.pyparsing import ( # noqa: N817 + Forward, + Group, + Literal as L, + ParseException, + ParseResults, + QuotedString, + ZeroOrMore, + stringEnd, + stringStart, +) + +from .specifiers import InvalidSpecifier, Specifier + +__all__ = [ + "InvalidMarker", + "UndefinedComparison", + "UndefinedEnvironmentName", + "Marker", + "default_environment", +] + +Operator = Callable[[str, str], bool] + + +class InvalidMarker(ValueError): + """ + An invalid marker was found, users should refer to PEP 508. + """ + + +class UndefinedComparison(ValueError): + """ + An invalid operation was attempted on a value that doesn't support it. + """ + + +class UndefinedEnvironmentName(ValueError): + """ + A name was attempted to be used that does not exist inside of the + environment. + """ + + +class Node: + def __init__(self, value: Any) -> None: + self.value = value + + def __str__(self) -> str: + return str(self.value) + + def __repr__(self) -> str: + return f"<{self.__class__.__name__}('{self}')>" + + def serialize(self) -> str: + raise NotImplementedError + + +class Variable(Node): + def serialize(self) -> str: + return str(self) + + +class Value(Node): + def serialize(self) -> str: + return f'"{self}"' + + +class Op(Node): + def serialize(self) -> str: + return str(self) + + +VARIABLE = ( + L("implementation_version") + | L("platform_python_implementation") + | L("implementation_name") + | L("python_full_version") + | L("platform_release") + | L("platform_version") + | L("platform_machine") + | L("platform_system") + | L("python_version") + | L("sys_platform") + | L("os_name") + | L("os.name") # PEP-345 + | L("sys.platform") # PEP-345 + | L("platform.version") # PEP-345 + | L("platform.machine") # PEP-345 + | L("platform.python_implementation") # PEP-345 + | L("python_implementation") # undocumented setuptools legacy + | L("extra") # PEP-508 +) +ALIASES = { + "os.name": "os_name", + "sys.platform": "sys_platform", + "platform.version": "platform_version", + "platform.machine": "platform_machine", + "platform.python_implementation": "platform_python_implementation", + "python_implementation": "platform_python_implementation", +} +VARIABLE.setParseAction(lambda s, l, t: Variable(ALIASES.get(t[0], t[0]))) + +VERSION_CMP = ( + L("===") | L("==") | L(">=") | L("<=") | L("!=") | L("~=") | L(">") | L("<") +) + +MARKER_OP = VERSION_CMP | L("not in") | L("in") +MARKER_OP.setParseAction(lambda s, l, t: Op(t[0])) + +MARKER_VALUE = QuotedString("'") | QuotedString('"') +MARKER_VALUE.setParseAction(lambda s, l, t: Value(t[0])) + +BOOLOP = L("and") | L("or") + +MARKER_VAR = VARIABLE | MARKER_VALUE + +MARKER_ITEM = Group(MARKER_VAR + MARKER_OP + MARKER_VAR) +MARKER_ITEM.setParseAction(lambda s, l, t: tuple(t[0])) + +LPAREN = L("(").suppress() +RPAREN = L(")").suppress() + +MARKER_EXPR = Forward() +MARKER_ATOM = MARKER_ITEM | Group(LPAREN + MARKER_EXPR + RPAREN) +MARKER_EXPR << MARKER_ATOM + ZeroOrMore(BOOLOP + MARKER_EXPR) + +MARKER = stringStart + MARKER_EXPR + stringEnd + + +def _coerce_parse_result(results: Union[ParseResults, List[Any]]) -> List[Any]: + if isinstance(results, ParseResults): + return [_coerce_parse_result(i) for i in results] + else: + return results + + +def _format_marker( + marker: Union[List[str], Tuple[Node, ...], str], first: Optional[bool] = True +) -> str: + + assert isinstance(marker, (list, tuple, str)) + + # Sometimes we have a structure like [[...]] which is a single item list + # where the single item is itself it's own list. In that case we want skip + # the rest of this function so that we don't get extraneous () on the + # outside. + if ( + isinstance(marker, list) + and len(marker) == 1 + and isinstance(marker[0], (list, tuple)) + ): + return _format_marker(marker[0]) + + if isinstance(marker, list): + inner = (_format_marker(m, first=False) for m in marker) + if first: + return " ".join(inner) + else: + return "(" + " ".join(inner) + ")" + elif isinstance(marker, tuple): + return " ".join([m.serialize() for m in marker]) + else: + return marker + + +_operators: Dict[str, Operator] = { + "in": lambda lhs, rhs: lhs in rhs, + "not in": lambda lhs, rhs: lhs not in rhs, + "<": operator.lt, + "<=": operator.le, + "==": operator.eq, + "!=": operator.ne, + ">=": operator.ge, + ">": operator.gt, +} + + +def _eval_op(lhs: str, op: Op, rhs: str) -> bool: + try: + spec = Specifier("".join([op.serialize(), rhs])) + except InvalidSpecifier: + pass + else: + return spec.contains(lhs) + + oper: Optional[Operator] = _operators.get(op.serialize()) + if oper is None: + raise UndefinedComparison(f"Undefined {op!r} on {lhs!r} and {rhs!r}.") + + return oper(lhs, rhs) + + +class Undefined: + pass + + +_undefined = Undefined() + + +def _get_env(environment: Dict[str, str], name: str) -> str: + value: Union[str, Undefined] = environment.get(name, _undefined) + + if isinstance(value, Undefined): + raise UndefinedEnvironmentName( + f"{name!r} does not exist in evaluation environment." + ) + + return value + + +def _evaluate_markers(markers: List[Any], environment: Dict[str, str]) -> bool: + groups: List[List[bool]] = [[]] + + for marker in markers: + assert isinstance(marker, (list, tuple, str)) + + if isinstance(marker, list): + groups[-1].append(_evaluate_markers(marker, environment)) + elif isinstance(marker, tuple): + lhs, op, rhs = marker + + if isinstance(lhs, Variable): + lhs_value = _get_env(environment, lhs.value) + rhs_value = rhs.value + else: + lhs_value = lhs.value + rhs_value = _get_env(environment, rhs.value) + + groups[-1].append(_eval_op(lhs_value, op, rhs_value)) + else: + assert marker in ["and", "or"] + if marker == "or": + groups.append([]) + + return any(all(item) for item in groups) + + +def format_full_version(info: "sys._version_info") -> str: + version = "{0.major}.{0.minor}.{0.micro}".format(info) + kind = info.releaselevel + if kind != "final": + version += kind[0] + str(info.serial) + return version + + +def default_environment() -> Dict[str, str]: + iver = format_full_version(sys.implementation.version) + implementation_name = sys.implementation.name + return { + "implementation_name": implementation_name, + "implementation_version": iver, + "os_name": os.name, + "platform_machine": platform.machine(), + "platform_release": platform.release(), + "platform_system": platform.system(), + "platform_version": platform.version(), + "python_full_version": platform.python_version(), + "platform_python_implementation": platform.python_implementation(), + "python_version": ".".join(platform.python_version_tuple()[:2]), + "sys_platform": sys.platform, + } + + +class Marker: + def __init__(self, marker: str) -> None: + try: + self._markers = _coerce_parse_result(MARKER.parseString(marker)) + except ParseException as e: + raise InvalidMarker( + f"Invalid marker: {marker!r}, parse error at " + f"{marker[e.loc : e.loc + 8]!r}" + ) + + def __str__(self) -> str: + return _format_marker(self._markers) + + def __repr__(self) -> str: + return f"<Marker('{self}')>" + + def evaluate(self, environment: Optional[Dict[str, str]] = None) -> bool: + """Evaluate a marker. + + Return the boolean from evaluating the given marker against the + environment. environment is an optional argument to override all or + part of the determined environment. + + The environment is determined from the current Python process. + """ + current_environment = default_environment() + if environment is not None: + current_environment.update(environment) + + return _evaluate_markers(self._markers, current_environment) diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/requirements.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/requirements.py new file mode 100644 index 0000000..6af14ec --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/requirements.py @@ -0,0 +1,146 @@ +# This file is dual licensed under the terms of the Apache License, Version +# 2.0, and the BSD License. See the LICENSE file in the root of this repository +# for complete details. + +import re +import string +import urllib.parse +from typing import List, Optional as TOptional, Set + +from pkg_resources.extern.pyparsing import ( # noqa + Combine, + Literal as L, + Optional, + ParseException, + Regex, + Word, + ZeroOrMore, + originalTextFor, + stringEnd, + stringStart, +) + +from .markers import MARKER_EXPR, Marker +from .specifiers import LegacySpecifier, Specifier, SpecifierSet + + +class InvalidRequirement(ValueError): + """ + An invalid requirement was found, users should refer to PEP 508. + """ + + +ALPHANUM = Word(string.ascii_letters + string.digits) + +LBRACKET = L("[").suppress() +RBRACKET = L("]").suppress() +LPAREN = L("(").suppress() +RPAREN = L(")").suppress() +COMMA = L(",").suppress() +SEMICOLON = L(";").suppress() +AT = L("@").suppress() + +PUNCTUATION = Word("-_.") +IDENTIFIER_END = ALPHANUM | (ZeroOrMore(PUNCTUATION) + ALPHANUM) +IDENTIFIER = Combine(ALPHANUM + ZeroOrMore(IDENTIFIER_END)) + +NAME = IDENTIFIER("name") +EXTRA = IDENTIFIER + +URI = Regex(r"[^ ]+")("url") +URL = AT + URI + +EXTRAS_LIST = EXTRA + ZeroOrMore(COMMA + EXTRA) +EXTRAS = (LBRACKET + Optional(EXTRAS_LIST) + RBRACKET)("extras") + +VERSION_PEP440 = Regex(Specifier._regex_str, re.VERBOSE | re.IGNORECASE) +VERSION_LEGACY = Regex(LegacySpecifier._regex_str, re.VERBOSE | re.IGNORECASE) + +VERSION_ONE = VERSION_PEP440 ^ VERSION_LEGACY +VERSION_MANY = Combine( + VERSION_ONE + ZeroOrMore(COMMA + VERSION_ONE), joinString=",", adjacent=False +)("_raw_spec") +_VERSION_SPEC = Optional((LPAREN + VERSION_MANY + RPAREN) | VERSION_MANY) +_VERSION_SPEC.setParseAction(lambda s, l, t: t._raw_spec or "") + +VERSION_SPEC = originalTextFor(_VERSION_SPEC)("specifier") +VERSION_SPEC.setParseAction(lambda s, l, t: t[1]) + +MARKER_EXPR = originalTextFor(MARKER_EXPR())("marker") +MARKER_EXPR.setParseAction( + lambda s, l, t: Marker(s[t._original_start : t._original_end]) +) +MARKER_SEPARATOR = SEMICOLON +MARKER = MARKER_SEPARATOR + MARKER_EXPR + +VERSION_AND_MARKER = VERSION_SPEC + Optional(MARKER) +URL_AND_MARKER = URL + Optional(MARKER) + +NAMED_REQUIREMENT = NAME + Optional(EXTRAS) + (URL_AND_MARKER | VERSION_AND_MARKER) + +REQUIREMENT = stringStart + NAMED_REQUIREMENT + stringEnd +# pkg_resources.extern.pyparsing isn't thread safe during initialization, so we do it eagerly, see +# issue #104 +REQUIREMENT.parseString("x[]") + + +class Requirement: + """Parse a requirement. + + Parse a given requirement string into its parts, such as name, specifier, + URL, and extras. Raises InvalidRequirement on a badly-formed requirement + string. + """ + + # TODO: Can we test whether something is contained within a requirement? + # If so how do we do that? Do we need to test against the _name_ of + # the thing as well as the version? What about the markers? + # TODO: Can we normalize the name and extra name? + + def __init__(self, requirement_string: str) -> None: + try: + req = REQUIREMENT.parseString(requirement_string) + except ParseException as e: + raise InvalidRequirement( + f'Parse error at "{ requirement_string[e.loc : e.loc + 8]!r}": {e.msg}' + ) + + self.name: str = req.name + if req.url: + parsed_url = urllib.parse.urlparse(req.url) + if parsed_url.scheme == "file": + if urllib.parse.urlunparse(parsed_url) != req.url: + raise InvalidRequirement("Invalid URL given") + elif not (parsed_url.scheme and parsed_url.netloc) or ( + not parsed_url.scheme and not parsed_url.netloc + ): + raise InvalidRequirement(f"Invalid URL: {req.url}") + self.url: TOptional[str] = req.url + else: + self.url = None + self.extras: Set[str] = set(req.extras.asList() if req.extras else []) + self.specifier: SpecifierSet = SpecifierSet(req.specifier) + self.marker: TOptional[Marker] = req.marker if req.marker else None + + def __str__(self) -> str: + parts: List[str] = [self.name] + + if self.extras: + formatted_extras = ",".join(sorted(self.extras)) + parts.append(f"[{formatted_extras}]") + + if self.specifier: + parts.append(str(self.specifier)) + + if self.url: + parts.append(f"@ {self.url}") + if self.marker: + parts.append(" ") + + if self.marker: + parts.append(f"; {self.marker}") + + return "".join(parts) + + def __repr__(self) -> str: + return f"<Requirement('{self}')>" diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/specifiers.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/specifiers.py new file mode 100644 index 0000000..0e218a6 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/specifiers.py @@ -0,0 +1,802 @@ +# This file is dual licensed under the terms of the Apache License, Version +# 2.0, and the BSD License. See the LICENSE file in the root of this repository +# for complete details. + +import abc +import functools +import itertools +import re +import warnings +from typing import ( + Callable, + Dict, + Iterable, + Iterator, + List, + Optional, + Pattern, + Set, + Tuple, + TypeVar, + Union, +) + +from .utils import canonicalize_version +from .version import LegacyVersion, Version, parse + +ParsedVersion = Union[Version, LegacyVersion] +UnparsedVersion = Union[Version, LegacyVersion, str] +VersionTypeVar = TypeVar("VersionTypeVar", bound=UnparsedVersion) +CallableOperator = Callable[[ParsedVersion, str], bool] + + +class InvalidSpecifier(ValueError): + """ + An invalid specifier was found, users should refer to PEP 440. + """ + + +class BaseSpecifier(metaclass=abc.ABCMeta): + @abc.abstractmethod + def __str__(self) -> str: + """ + Returns the str representation of this Specifier like object. This + should be representative of the Specifier itself. + """ + + @abc.abstractmethod + def __hash__(self) -> int: + """ + Returns a hash value for this Specifier like object. + """ + + @abc.abstractmethod + def __eq__(self, other: object) -> bool: + """ + Returns a boolean representing whether or not the two Specifier like + objects are equal. + """ + + @abc.abstractproperty + def prereleases(self) -> Optional[bool]: + """ + Returns whether or not pre-releases as a whole are allowed by this + specifier. + """ + + @prereleases.setter + def prereleases(self, value: bool) -> None: + """ + Sets whether or not pre-releases as a whole are allowed by this + specifier. + """ + + @abc.abstractmethod + def contains(self, item: str, prereleases: Optional[bool] = None) -> bool: + """ + Determines if the given item is contained within this specifier. + """ + + @abc.abstractmethod + def filter( + self, iterable: Iterable[VersionTypeVar], prereleases: Optional[bool] = None + ) -> Iterable[VersionTypeVar]: + """ + Takes an iterable of items and filters them so that only items which + are contained within this specifier are allowed in it. + """ + + +class _IndividualSpecifier(BaseSpecifier): + + _operators: Dict[str, str] = {} + _regex: Pattern[str] + + def __init__(self, spec: str = "", prereleases: Optional[bool] = None) -> None: + match = self._regex.search(spec) + if not match: + raise InvalidSpecifier(f"Invalid specifier: '{spec}'") + + self._spec: Tuple[str, str] = ( + match.group("operator").strip(), + match.group("version").strip(), + ) + + # Store whether or not this Specifier should accept prereleases + self._prereleases = prereleases + + def __repr__(self) -> str: + pre = ( + f", prereleases={self.prereleases!r}" + if self._prereleases is not None + else "" + ) + + return f"<{self.__class__.__name__}({str(self)!r}{pre})>" + + def __str__(self) -> str: + return "{}{}".format(*self._spec) + + @property + def _canonical_spec(self) -> Tuple[str, str]: + return self._spec[0], canonicalize_version(self._spec[1]) + + def __hash__(self) -> int: + return hash(self._canonical_spec) + + def __eq__(self, other: object) -> bool: + if isinstance(other, str): + try: + other = self.__class__(str(other)) + except InvalidSpecifier: + return NotImplemented + elif not isinstance(other, self.__class__): + return NotImplemented + + return self._canonical_spec == other._canonical_spec + + def _get_operator(self, op: str) -> CallableOperator: + operator_callable: CallableOperator = getattr( + self, f"_compare_{self._operators[op]}" + ) + return operator_callable + + def _coerce_version(self, version: UnparsedVersion) -> ParsedVersion: + if not isinstance(version, (LegacyVersion, Version)): + version = parse(version) + return version + + @property + def operator(self) -> str: + return self._spec[0] + + @property + def version(self) -> str: + return self._spec[1] + + @property + def prereleases(self) -> Optional[bool]: + return self._prereleases + + @prereleases.setter + def prereleases(self, value: bool) -> None: + self._prereleases = value + + def __contains__(self, item: str) -> bool: + return self.contains(item) + + def contains( + self, item: UnparsedVersion, prereleases: Optional[bool] = None + ) -> bool: + + # Determine if prereleases are to be allowed or not. + if prereleases is None: + prereleases = self.prereleases + + # Normalize item to a Version or LegacyVersion, this allows us to have + # a shortcut for ``"2.0" in Specifier(">=2") + normalized_item = self._coerce_version(item) + + # Determine if we should be supporting prereleases in this specifier + # or not, if we do not support prereleases than we can short circuit + # logic if this version is a prereleases. + if normalized_item.is_prerelease and not prereleases: + return False + + # Actually do the comparison to determine if this item is contained + # within this Specifier or not. + operator_callable: CallableOperator = self._get_operator(self.operator) + return operator_callable(normalized_item, self.version) + + def filter( + self, iterable: Iterable[VersionTypeVar], prereleases: Optional[bool] = None + ) -> Iterable[VersionTypeVar]: + + yielded = False + found_prereleases = [] + + kw = {"prereleases": prereleases if prereleases is not None else True} + + # Attempt to iterate over all the values in the iterable and if any of + # them match, yield them. + for version in iterable: + parsed_version = self._coerce_version(version) + + if self.contains(parsed_version, **kw): + # If our version is a prerelease, and we were not set to allow + # prereleases, then we'll store it for later in case nothing + # else matches this specifier. + if parsed_version.is_prerelease and not ( + prereleases or self.prereleases + ): + found_prereleases.append(version) + # Either this is not a prerelease, or we should have been + # accepting prereleases from the beginning. + else: + yielded = True + yield version + + # Now that we've iterated over everything, determine if we've yielded + # any values, and if we have not and we have any prereleases stored up + # then we will go ahead and yield the prereleases. + if not yielded and found_prereleases: + for version in found_prereleases: + yield version + + +class LegacySpecifier(_IndividualSpecifier): + + _regex_str = r""" + (?P<operator>(==|!=|<=|>=|<|>)) + \s* + (?P<version> + [^,;\s)]* # Since this is a "legacy" specifier, and the version + # string can be just about anything, we match everything + # except for whitespace, a semi-colon for marker support, + # a closing paren since versions can be enclosed in + # them, and a comma since it's a version separator. + ) + """ + + _regex = re.compile(r"^\s*" + _regex_str + r"\s*$", re.VERBOSE | re.IGNORECASE) + + _operators = { + "==": "equal", + "!=": "not_equal", + "<=": "less_than_equal", + ">=": "greater_than_equal", + "<": "less_than", + ">": "greater_than", + } + + def __init__(self, spec: str = "", prereleases: Optional[bool] = None) -> None: + super().__init__(spec, prereleases) + + warnings.warn( + "Creating a LegacyVersion has been deprecated and will be " + "removed in the next major release", + DeprecationWarning, + ) + + def _coerce_version(self, version: UnparsedVersion) -> LegacyVersion: + if not isinstance(version, LegacyVersion): + version = LegacyVersion(str(version)) + return version + + def _compare_equal(self, prospective: LegacyVersion, spec: str) -> bool: + return prospective == self._coerce_version(spec) + + def _compare_not_equal(self, prospective: LegacyVersion, spec: str) -> bool: + return prospective != self._coerce_version(spec) + + def _compare_less_than_equal(self, prospective: LegacyVersion, spec: str) -> bool: + return prospective <= self._coerce_version(spec) + + def _compare_greater_than_equal( + self, prospective: LegacyVersion, spec: str + ) -> bool: + return prospective >= self._coerce_version(spec) + + def _compare_less_than(self, prospective: LegacyVersion, spec: str) -> bool: + return prospective < self._coerce_version(spec) + + def _compare_greater_than(self, prospective: LegacyVersion, spec: str) -> bool: + return prospective > self._coerce_version(spec) + + +def _require_version_compare( + fn: Callable[["Specifier", ParsedVersion, str], bool] +) -> Callable[["Specifier", ParsedVersion, str], bool]: + @functools.wraps(fn) + def wrapped(self: "Specifier", prospective: ParsedVersion, spec: str) -> bool: + if not isinstance(prospective, Version): + return False + return fn(self, prospective, spec) + + return wrapped + + +class Specifier(_IndividualSpecifier): + + _regex_str = r""" + (?P<operator>(~=|==|!=|<=|>=|<|>|===)) + (?P<version> + (?: + # The identity operators allow for an escape hatch that will + # do an exact string match of the version you wish to install. + # This will not be parsed by PEP 440 and we cannot determine + # any semantic meaning from it. This operator is discouraged + # but included entirely as an escape hatch. + (?<====) # Only match for the identity operator + \s* + [^\s]* # We just match everything, except for whitespace + # since we are only testing for strict identity. + ) + | + (?: + # The (non)equality operators allow for wild card and local + # versions to be specified so we have to define these two + # operators separately to enable that. + (?<===|!=) # Only match for equals and not equals + + \s* + v? + (?:[0-9]+!)? # epoch + [0-9]+(?:\.[0-9]+)* # release + (?: # pre release + [-_\.]? + (a|b|c|rc|alpha|beta|pre|preview) + [-_\.]? + [0-9]* + )? + (?: # post release + (?:-[0-9]+)|(?:[-_\.]?(post|rev|r)[-_\.]?[0-9]*) + )? + + # You cannot use a wild card and a dev or local version + # together so group them with a | and make them optional. + (?: + (?:[-_\.]?dev[-_\.]?[0-9]*)? # dev release + (?:\+[a-z0-9]+(?:[-_\.][a-z0-9]+)*)? # local + | + \.\* # Wild card syntax of .* + )? + ) + | + (?: + # The compatible operator requires at least two digits in the + # release segment. + (?<=~=) # Only match for the compatible operator + + \s* + v? + (?:[0-9]+!)? # epoch + [0-9]+(?:\.[0-9]+)+ # release (We have a + instead of a *) + (?: # pre release + [-_\.]? + (a|b|c|rc|alpha|beta|pre|preview) + [-_\.]? + [0-9]* + )? + (?: # post release + (?:-[0-9]+)|(?:[-_\.]?(post|rev|r)[-_\.]?[0-9]*) + )? + (?:[-_\.]?dev[-_\.]?[0-9]*)? # dev release + ) + | + (?: + # All other operators only allow a sub set of what the + # (non)equality operators do. Specifically they do not allow + # local versions to be specified nor do they allow the prefix + # matching wild cards. + (?<!==|!=|~=) # We have special cases for these + # operators so we want to make sure they + # don't match here. + + \s* + v? + (?:[0-9]+!)? # epoch + [0-9]+(?:\.[0-9]+)* # release + (?: # pre release + [-_\.]? + (a|b|c|rc|alpha|beta|pre|preview) + [-_\.]? + [0-9]* + )? + (?: # post release + (?:-[0-9]+)|(?:[-_\.]?(post|rev|r)[-_\.]?[0-9]*) + )? + (?:[-_\.]?dev[-_\.]?[0-9]*)? # dev release + ) + ) + """ + + _regex = re.compile(r"^\s*" + _regex_str + r"\s*$", re.VERBOSE | re.IGNORECASE) + + _operators = { + "~=": "compatible", + "==": "equal", + "!=": "not_equal", + "<=": "less_than_equal", + ">=": "greater_than_equal", + "<": "less_than", + ">": "greater_than", + "===": "arbitrary", + } + + @_require_version_compare + def _compare_compatible(self, prospective: ParsedVersion, spec: str) -> bool: + + # Compatible releases have an equivalent combination of >= and ==. That + # is that ~=2.2 is equivalent to >=2.2,==2.*. This allows us to + # implement this in terms of the other specifiers instead of + # implementing it ourselves. The only thing we need to do is construct + # the other specifiers. + + # We want everything but the last item in the version, but we want to + # ignore suffix segments. + prefix = ".".join( + list(itertools.takewhile(_is_not_suffix, _version_split(spec)))[:-1] + ) + + # Add the prefix notation to the end of our string + prefix += ".*" + + return self._get_operator(">=")(prospective, spec) and self._get_operator("==")( + prospective, prefix + ) + + @_require_version_compare + def _compare_equal(self, prospective: ParsedVersion, spec: str) -> bool: + + # We need special logic to handle prefix matching + if spec.endswith(".*"): + # In the case of prefix matching we want to ignore local segment. + prospective = Version(prospective.public) + # Split the spec out by dots, and pretend that there is an implicit + # dot in between a release segment and a pre-release segment. + split_spec = _version_split(spec[:-2]) # Remove the trailing .* + + # Split the prospective version out by dots, and pretend that there + # is an implicit dot in between a release segment and a pre-release + # segment. + split_prospective = _version_split(str(prospective)) + + # Shorten the prospective version to be the same length as the spec + # so that we can determine if the specifier is a prefix of the + # prospective version or not. + shortened_prospective = split_prospective[: len(split_spec)] + + # Pad out our two sides with zeros so that they both equal the same + # length. + padded_spec, padded_prospective = _pad_version( + split_spec, shortened_prospective + ) + + return padded_prospective == padded_spec + else: + # Convert our spec string into a Version + spec_version = Version(spec) + + # If the specifier does not have a local segment, then we want to + # act as if the prospective version also does not have a local + # segment. + if not spec_version.local: + prospective = Version(prospective.public) + + return prospective == spec_version + + @_require_version_compare + def _compare_not_equal(self, prospective: ParsedVersion, spec: str) -> bool: + return not self._compare_equal(prospective, spec) + + @_require_version_compare + def _compare_less_than_equal(self, prospective: ParsedVersion, spec: str) -> bool: + + # NB: Local version identifiers are NOT permitted in the version + # specifier, so local version labels can be universally removed from + # the prospective version. + return Version(prospective.public) <= Version(spec) + + @_require_version_compare + def _compare_greater_than_equal( + self, prospective: ParsedVersion, spec: str + ) -> bool: + + # NB: Local version identifiers are NOT permitted in the version + # specifier, so local version labels can be universally removed from + # the prospective version. + return Version(prospective.public) >= Version(spec) + + @_require_version_compare + def _compare_less_than(self, prospective: ParsedVersion, spec_str: str) -> bool: + + # Convert our spec to a Version instance, since we'll want to work with + # it as a version. + spec = Version(spec_str) + + # Check to see if the prospective version is less than the spec + # version. If it's not we can short circuit and just return False now + # instead of doing extra unneeded work. + if not prospective < spec: + return False + + # This special case is here so that, unless the specifier itself + # includes is a pre-release version, that we do not accept pre-release + # versions for the version mentioned in the specifier (e.g. <3.1 should + # not match 3.1.dev0, but should match 3.0.dev0). + if not spec.is_prerelease and prospective.is_prerelease: + if Version(prospective.base_version) == Version(spec.base_version): + return False + + # If we've gotten to here, it means that prospective version is both + # less than the spec version *and* it's not a pre-release of the same + # version in the spec. + return True + + @_require_version_compare + def _compare_greater_than(self, prospective: ParsedVersion, spec_str: str) -> bool: + + # Convert our spec to a Version instance, since we'll want to work with + # it as a version. + spec = Version(spec_str) + + # Check to see if the prospective version is greater than the spec + # version. If it's not we can short circuit and just return False now + # instead of doing extra unneeded work. + if not prospective > spec: + return False + + # This special case is here so that, unless the specifier itself + # includes is a post-release version, that we do not accept + # post-release versions for the version mentioned in the specifier + # (e.g. >3.1 should not match 3.0.post0, but should match 3.2.post0). + if not spec.is_postrelease and prospective.is_postrelease: + if Version(prospective.base_version) == Version(spec.base_version): + return False + + # Ensure that we do not allow a local version of the version mentioned + # in the specifier, which is technically greater than, to match. + if prospective.local is not None: + if Version(prospective.base_version) == Version(spec.base_version): + return False + + # If we've gotten to here, it means that prospective version is both + # greater than the spec version *and* it's not a pre-release of the + # same version in the spec. + return True + + def _compare_arbitrary(self, prospective: Version, spec: str) -> bool: + return str(prospective).lower() == str(spec).lower() + + @property + def prereleases(self) -> bool: + + # If there is an explicit prereleases set for this, then we'll just + # blindly use that. + if self._prereleases is not None: + return self._prereleases + + # Look at all of our specifiers and determine if they are inclusive + # operators, and if they are if they are including an explicit + # prerelease. + operator, version = self._spec + if operator in ["==", ">=", "<=", "~=", "==="]: + # The == specifier can include a trailing .*, if it does we + # want to remove before parsing. + if operator == "==" and version.endswith(".*"): + version = version[:-2] + + # Parse the version, and if it is a pre-release than this + # specifier allows pre-releases. + if parse(version).is_prerelease: + return True + + return False + + @prereleases.setter + def prereleases(self, value: bool) -> None: + self._prereleases = value + + +_prefix_regex = re.compile(r"^([0-9]+)((?:a|b|c|rc)[0-9]+)$") + + +def _version_split(version: str) -> List[str]: + result: List[str] = [] + for item in version.split("."): + match = _prefix_regex.search(item) + if match: + result.extend(match.groups()) + else: + result.append(item) + return result + + +def _is_not_suffix(segment: str) -> bool: + return not any( + segment.startswith(prefix) for prefix in ("dev", "a", "b", "rc", "post") + ) + + +def _pad_version(left: List[str], right: List[str]) -> Tuple[List[str], List[str]]: + left_split, right_split = [], [] + + # Get the release segment of our versions + left_split.append(list(itertools.takewhile(lambda x: x.isdigit(), left))) + right_split.append(list(itertools.takewhile(lambda x: x.isdigit(), right))) + + # Get the rest of our versions + left_split.append(left[len(left_split[0]) :]) + right_split.append(right[len(right_split[0]) :]) + + # Insert our padding + left_split.insert(1, ["0"] * max(0, len(right_split[0]) - len(left_split[0]))) + right_split.insert(1, ["0"] * max(0, len(left_split[0]) - len(right_split[0]))) + + return (list(itertools.chain(*left_split)), list(itertools.chain(*right_split))) + + +class SpecifierSet(BaseSpecifier): + def __init__( + self, specifiers: str = "", prereleases: Optional[bool] = None + ) -> None: + + # Split on , to break each individual specifier into it's own item, and + # strip each item to remove leading/trailing whitespace. + split_specifiers = [s.strip() for s in specifiers.split(",") if s.strip()] + + # Parsed each individual specifier, attempting first to make it a + # Specifier and falling back to a LegacySpecifier. + parsed: Set[_IndividualSpecifier] = set() + for specifier in split_specifiers: + try: + parsed.add(Specifier(specifier)) + except InvalidSpecifier: + parsed.add(LegacySpecifier(specifier)) + + # Turn our parsed specifiers into a frozen set and save them for later. + self._specs = frozenset(parsed) + + # Store our prereleases value so we can use it later to determine if + # we accept prereleases or not. + self._prereleases = prereleases + + def __repr__(self) -> str: + pre = ( + f", prereleases={self.prereleases!r}" + if self._prereleases is not None + else "" + ) + + return f"<SpecifierSet({str(self)!r}{pre})>" + + def __str__(self) -> str: + return ",".join(sorted(str(s) for s in self._specs)) + + def __hash__(self) -> int: + return hash(self._specs) + + def __and__(self, other: Union["SpecifierSet", str]) -> "SpecifierSet": + if isinstance(other, str): + other = SpecifierSet(other) + elif not isinstance(other, SpecifierSet): + return NotImplemented + + specifier = SpecifierSet() + specifier._specs = frozenset(self._specs | other._specs) + + if self._prereleases is None and other._prereleases is not None: + specifier._prereleases = other._prereleases + elif self._prereleases is not None and other._prereleases is None: + specifier._prereleases = self._prereleases + elif self._prereleases == other._prereleases: + specifier._prereleases = self._prereleases + else: + raise ValueError( + "Cannot combine SpecifierSets with True and False prerelease " + "overrides." + ) + + return specifier + + def __eq__(self, other: object) -> bool: + if isinstance(other, (str, _IndividualSpecifier)): + other = SpecifierSet(str(other)) + elif not isinstance(other, SpecifierSet): + return NotImplemented + + return self._specs == other._specs + + def __len__(self) -> int: + return len(self._specs) + + def __iter__(self) -> Iterator[_IndividualSpecifier]: + return iter(self._specs) + + @property + def prereleases(self) -> Optional[bool]: + + # If we have been given an explicit prerelease modifier, then we'll + # pass that through here. + if self._prereleases is not None: + return self._prereleases + + # If we don't have any specifiers, and we don't have a forced value, + # then we'll just return None since we don't know if this should have + # pre-releases or not. + if not self._specs: + return None + + # Otherwise we'll see if any of the given specifiers accept + # prereleases, if any of them do we'll return True, otherwise False. + return any(s.prereleases for s in self._specs) + + @prereleases.setter + def prereleases(self, value: bool) -> None: + self._prereleases = value + + def __contains__(self, item: UnparsedVersion) -> bool: + return self.contains(item) + + def contains( + self, item: UnparsedVersion, prereleases: Optional[bool] = None + ) -> bool: + + # Ensure that our item is a Version or LegacyVersion instance. + if not isinstance(item, (LegacyVersion, Version)): + item = parse(item) + + # Determine if we're forcing a prerelease or not, if we're not forcing + # one for this particular filter call, then we'll use whatever the + # SpecifierSet thinks for whether or not we should support prereleases. + if prereleases is None: + prereleases = self.prereleases + + # We can determine if we're going to allow pre-releases by looking to + # see if any of the underlying items supports them. If none of them do + # and this item is a pre-release then we do not allow it and we can + # short circuit that here. + # Note: This means that 1.0.dev1 would not be contained in something + # like >=1.0.devabc however it would be in >=1.0.debabc,>0.0.dev0 + if not prereleases and item.is_prerelease: + return False + + # We simply dispatch to the underlying specs here to make sure that the + # given version is contained within all of them. + # Note: This use of all() here means that an empty set of specifiers + # will always return True, this is an explicit design decision. + return all(s.contains(item, prereleases=prereleases) for s in self._specs) + + def filter( + self, iterable: Iterable[VersionTypeVar], prereleases: Optional[bool] = None + ) -> Iterable[VersionTypeVar]: + + # Determine if we're forcing a prerelease or not, if we're not forcing + # one for this particular filter call, then we'll use whatever the + # SpecifierSet thinks for whether or not we should support prereleases. + if prereleases is None: + prereleases = self.prereleases + + # If we have any specifiers, then we want to wrap our iterable in the + # filter method for each one, this will act as a logical AND amongst + # each specifier. + if self._specs: + for spec in self._specs: + iterable = spec.filter(iterable, prereleases=bool(prereleases)) + return iterable + # If we do not have any specifiers, then we need to have a rough filter + # which will filter out any pre-releases, unless there are no final + # releases, and which will filter out LegacyVersion in general. + else: + filtered: List[VersionTypeVar] = [] + found_prereleases: List[VersionTypeVar] = [] + + item: UnparsedVersion + parsed_version: Union[Version, LegacyVersion] + + for item in iterable: + # Ensure that we some kind of Version class for this item. + if not isinstance(item, (LegacyVersion, Version)): + parsed_version = parse(item) + else: + parsed_version = item + + # Filter out any item which is parsed as a LegacyVersion + if isinstance(parsed_version, LegacyVersion): + continue + + # Store any item which is a pre-release for later unless we've + # already found a final version or we are accepting prereleases + if parsed_version.is_prerelease and not prereleases: + if not filtered: + found_prereleases.append(item) + else: + filtered.append(item) + + # If we've found no items except for pre-releases, then we'll go + # ahead and use the pre-releases + if not filtered and found_prereleases and prereleases is None: + return found_prereleases + + return filtered diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/tags.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/tags.py new file mode 100644 index 0000000..9a3d25a --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/tags.py @@ -0,0 +1,487 @@ +# This file is dual licensed under the terms of the Apache License, Version +# 2.0, and the BSD License. See the LICENSE file in the root of this repository +# for complete details. + +import logging +import platform +import sys +import sysconfig +from importlib.machinery import EXTENSION_SUFFIXES +from typing import ( + Dict, + FrozenSet, + Iterable, + Iterator, + List, + Optional, + Sequence, + Tuple, + Union, + cast, +) + +from . import _manylinux, _musllinux + +logger = logging.getLogger(__name__) + +PythonVersion = Sequence[int] +MacVersion = Tuple[int, int] + +INTERPRETER_SHORT_NAMES: Dict[str, str] = { + "python": "py", # Generic. + "cpython": "cp", + "pypy": "pp", + "ironpython": "ip", + "jython": "jy", +} + + +_32_BIT_INTERPRETER = sys.maxsize <= 2 ** 32 + + +class Tag: + """ + A representation of the tag triple for a wheel. + + Instances are considered immutable and thus are hashable. Equality checking + is also supported. + """ + + __slots__ = ["_interpreter", "_abi", "_platform", "_hash"] + + def __init__(self, interpreter: str, abi: str, platform: str) -> None: + self._interpreter = interpreter.lower() + self._abi = abi.lower() + self._platform = platform.lower() + # The __hash__ of every single element in a Set[Tag] will be evaluated each time + # that a set calls its `.disjoint()` method, which may be called hundreds of + # times when scanning a page of links for packages with tags matching that + # Set[Tag]. Pre-computing the value here produces significant speedups for + # downstream consumers. + self._hash = hash((self._interpreter, self._abi, self._platform)) + + @property + def interpreter(self) -> str: + return self._interpreter + + @property + def abi(self) -> str: + return self._abi + + @property + def platform(self) -> str: + return self._platform + + def __eq__(self, other: object) -> bool: + if not isinstance(other, Tag): + return NotImplemented + + return ( + (self._hash == other._hash) # Short-circuit ASAP for perf reasons. + and (self._platform == other._platform) + and (self._abi == other._abi) + and (self._interpreter == other._interpreter) + ) + + def __hash__(self) -> int: + return self._hash + + def __str__(self) -> str: + return f"{self._interpreter}-{self._abi}-{self._platform}" + + def __repr__(self) -> str: + return f"<{self} @ {id(self)}>" + + +def parse_tag(tag: str) -> FrozenSet[Tag]: + """ + Parses the provided tag (e.g. `py3-none-any`) into a frozenset of Tag instances. + + Returning a set is required due to the possibility that the tag is a + compressed tag set. + """ + tags = set() + interpreters, abis, platforms = tag.split("-") + for interpreter in interpreters.split("."): + for abi in abis.split("."): + for platform_ in platforms.split("."): + tags.add(Tag(interpreter, abi, platform_)) + return frozenset(tags) + + +def _get_config_var(name: str, warn: bool = False) -> Union[int, str, None]: + value = sysconfig.get_config_var(name) + if value is None and warn: + logger.debug( + "Config variable '%s' is unset, Python ABI tag may be incorrect", name + ) + return value + + +def _normalize_string(string: str) -> str: + return string.replace(".", "_").replace("-", "_") + + +def _abi3_applies(python_version: PythonVersion) -> bool: + """ + Determine if the Python version supports abi3. + + PEP 384 was first implemented in Python 3.2. + """ + return len(python_version) > 1 and tuple(python_version) >= (3, 2) + + +def _cpython_abis(py_version: PythonVersion, warn: bool = False) -> List[str]: + py_version = tuple(py_version) # To allow for version comparison. + abis = [] + version = _version_nodot(py_version[:2]) + debug = pymalloc = ucs4 = "" + with_debug = _get_config_var("Py_DEBUG", warn) + has_refcount = hasattr(sys, "gettotalrefcount") + # Windows doesn't set Py_DEBUG, so checking for support of debug-compiled + # extension modules is the best option. + # https://github.com/pypa/pip/issues/3383#issuecomment-173267692 + has_ext = "_d.pyd" in EXTENSION_SUFFIXES + if with_debug or (with_debug is None and (has_refcount or has_ext)): + debug = "d" + if py_version < (3, 8): + with_pymalloc = _get_config_var("WITH_PYMALLOC", warn) + if with_pymalloc or with_pymalloc is None: + pymalloc = "m" + if py_version < (3, 3): + unicode_size = _get_config_var("Py_UNICODE_SIZE", warn) + if unicode_size == 4 or ( + unicode_size is None and sys.maxunicode == 0x10FFFF + ): + ucs4 = "u" + elif debug: + # Debug builds can also load "normal" extension modules. + # We can also assume no UCS-4 or pymalloc requirement. + abis.append(f"cp{version}") + abis.insert( + 0, + "cp{version}{debug}{pymalloc}{ucs4}".format( + version=version, debug=debug, pymalloc=pymalloc, ucs4=ucs4 + ), + ) + return abis + + +def cpython_tags( + python_version: Optional[PythonVersion] = None, + abis: Optional[Iterable[str]] = None, + platforms: Optional[Iterable[str]] = None, + *, + warn: bool = False, +) -> Iterator[Tag]: + """ + Yields the tags for a CPython interpreter. + + The tags consist of: + - cp<python_version>-<abi>-<platform> + - cp<python_version>-abi3-<platform> + - cp<python_version>-none-<platform> + - cp<less than python_version>-abi3-<platform> # Older Python versions down to 3.2. + + If python_version only specifies a major version then user-provided ABIs and + the 'none' ABItag will be used. + + If 'abi3' or 'none' are specified in 'abis' then they will be yielded at + their normal position and not at the beginning. + """ + if not python_version: + python_version = sys.version_info[:2] + + interpreter = f"cp{_version_nodot(python_version[:2])}" + + if abis is None: + if len(python_version) > 1: + abis = _cpython_abis(python_version, warn) + else: + abis = [] + abis = list(abis) + # 'abi3' and 'none' are explicitly handled later. + for explicit_abi in ("abi3", "none"): + try: + abis.remove(explicit_abi) + except ValueError: + pass + + platforms = list(platforms or platform_tags()) + for abi in abis: + for platform_ in platforms: + yield Tag(interpreter, abi, platform_) + if _abi3_applies(python_version): + yield from (Tag(interpreter, "abi3", platform_) for platform_ in platforms) + yield from (Tag(interpreter, "none", platform_) for platform_ in platforms) + + if _abi3_applies(python_version): + for minor_version in range(python_version[1] - 1, 1, -1): + for platform_ in platforms: + interpreter = "cp{version}".format( + version=_version_nodot((python_version[0], minor_version)) + ) + yield Tag(interpreter, "abi3", platform_) + + +def _generic_abi() -> Iterator[str]: + abi = sysconfig.get_config_var("SOABI") + if abi: + yield _normalize_string(abi) + + +def generic_tags( + interpreter: Optional[str] = None, + abis: Optional[Iterable[str]] = None, + platforms: Optional[Iterable[str]] = None, + *, + warn: bool = False, +) -> Iterator[Tag]: + """ + Yields the tags for a generic interpreter. + + The tags consist of: + - <interpreter>-<abi>-<platform> + + The "none" ABI will be added if it was not explicitly provided. + """ + if not interpreter: + interp_name = interpreter_name() + interp_version = interpreter_version(warn=warn) + interpreter = "".join([interp_name, interp_version]) + if abis is None: + abis = _generic_abi() + platforms = list(platforms or platform_tags()) + abis = list(abis) + if "none" not in abis: + abis.append("none") + for abi in abis: + for platform_ in platforms: + yield Tag(interpreter, abi, platform_) + + +def _py_interpreter_range(py_version: PythonVersion) -> Iterator[str]: + """ + Yields Python versions in descending order. + + After the latest version, the major-only version will be yielded, and then + all previous versions of that major version. + """ + if len(py_version) > 1: + yield f"py{_version_nodot(py_version[:2])}" + yield f"py{py_version[0]}" + if len(py_version) > 1: + for minor in range(py_version[1] - 1, -1, -1): + yield f"py{_version_nodot((py_version[0], minor))}" + + +def compatible_tags( + python_version: Optional[PythonVersion] = None, + interpreter: Optional[str] = None, + platforms: Optional[Iterable[str]] = None, +) -> Iterator[Tag]: + """ + Yields the sequence of tags that are compatible with a specific version of Python. + + The tags consist of: + - py*-none-<platform> + - <interpreter>-none-any # ... if `interpreter` is provided. + - py*-none-any + """ + if not python_version: + python_version = sys.version_info[:2] + platforms = list(platforms or platform_tags()) + for version in _py_interpreter_range(python_version): + for platform_ in platforms: + yield Tag(version, "none", platform_) + if interpreter: + yield Tag(interpreter, "none", "any") + for version in _py_interpreter_range(python_version): + yield Tag(version, "none", "any") + + +def _mac_arch(arch: str, is_32bit: bool = _32_BIT_INTERPRETER) -> str: + if not is_32bit: + return arch + + if arch.startswith("ppc"): + return "ppc" + + return "i386" + + +def _mac_binary_formats(version: MacVersion, cpu_arch: str) -> List[str]: + formats = [cpu_arch] + if cpu_arch == "x86_64": + if version < (10, 4): + return [] + formats.extend(["intel", "fat64", "fat32"]) + + elif cpu_arch == "i386": + if version < (10, 4): + return [] + formats.extend(["intel", "fat32", "fat"]) + + elif cpu_arch == "ppc64": + # TODO: Need to care about 32-bit PPC for ppc64 through 10.2? + if version > (10, 5) or version < (10, 4): + return [] + formats.append("fat64") + + elif cpu_arch == "ppc": + if version > (10, 6): + return [] + formats.extend(["fat32", "fat"]) + + if cpu_arch in {"arm64", "x86_64"}: + formats.append("universal2") + + if cpu_arch in {"x86_64", "i386", "ppc64", "ppc", "intel"}: + formats.append("universal") + + return formats + + +def mac_platforms( + version: Optional[MacVersion] = None, arch: Optional[str] = None +) -> Iterator[str]: + """ + Yields the platform tags for a macOS system. + + The `version` parameter is a two-item tuple specifying the macOS version to + generate platform tags for. The `arch` parameter is the CPU architecture to + generate platform tags for. Both parameters default to the appropriate value + for the current system. + """ + version_str, _, cpu_arch = platform.mac_ver() + if version is None: + version = cast("MacVersion", tuple(map(int, version_str.split(".")[:2]))) + else: + version = version + if arch is None: + arch = _mac_arch(cpu_arch) + else: + arch = arch + + if (10, 0) <= version and version < (11, 0): + # Prior to Mac OS 11, each yearly release of Mac OS bumped the + # "minor" version number. The major version was always 10. + for minor_version in range(version[1], -1, -1): + compat_version = 10, minor_version + binary_formats = _mac_binary_formats(compat_version, arch) + for binary_format in binary_formats: + yield "macosx_{major}_{minor}_{binary_format}".format( + major=10, minor=minor_version, binary_format=binary_format + ) + + if version >= (11, 0): + # Starting with Mac OS 11, each yearly release bumps the major version + # number. The minor versions are now the midyear updates. + for major_version in range(version[0], 10, -1): + compat_version = major_version, 0 + binary_formats = _mac_binary_formats(compat_version, arch) + for binary_format in binary_formats: + yield "macosx_{major}_{minor}_{binary_format}".format( + major=major_version, minor=0, binary_format=binary_format + ) + + if version >= (11, 0): + # Mac OS 11 on x86_64 is compatible with binaries from previous releases. + # Arm64 support was introduced in 11.0, so no Arm binaries from previous + # releases exist. + # + # However, the "universal2" binary format can have a + # macOS version earlier than 11.0 when the x86_64 part of the binary supports + # that version of macOS. + if arch == "x86_64": + for minor_version in range(16, 3, -1): + compat_version = 10, minor_version + binary_formats = _mac_binary_formats(compat_version, arch) + for binary_format in binary_formats: + yield "macosx_{major}_{minor}_{binary_format}".format( + major=compat_version[0], + minor=compat_version[1], + binary_format=binary_format, + ) + else: + for minor_version in range(16, 3, -1): + compat_version = 10, minor_version + binary_format = "universal2" + yield "macosx_{major}_{minor}_{binary_format}".format( + major=compat_version[0], + minor=compat_version[1], + binary_format=binary_format, + ) + + +def _linux_platforms(is_32bit: bool = _32_BIT_INTERPRETER) -> Iterator[str]: + linux = _normalize_string(sysconfig.get_platform()) + if is_32bit: + if linux == "linux_x86_64": + linux = "linux_i686" + elif linux == "linux_aarch64": + linux = "linux_armv7l" + _, arch = linux.split("_", 1) + yield from _manylinux.platform_tags(linux, arch) + yield from _musllinux.platform_tags(arch) + yield linux + + +def _generic_platforms() -> Iterator[str]: + yield _normalize_string(sysconfig.get_platform()) + + +def platform_tags() -> Iterator[str]: + """ + Provides the platform tags for this installation. + """ + if platform.system() == "Darwin": + return mac_platforms() + elif platform.system() == "Linux": + return _linux_platforms() + else: + return _generic_platforms() + + +def interpreter_name() -> str: + """ + Returns the name of the running interpreter. + """ + name = sys.implementation.name + return INTERPRETER_SHORT_NAMES.get(name) or name + + +def interpreter_version(*, warn: bool = False) -> str: + """ + Returns the version of the running interpreter. + """ + version = _get_config_var("py_version_nodot", warn=warn) + if version: + version = str(version) + else: + version = _version_nodot(sys.version_info[:2]) + return version + + +def _version_nodot(version: PythonVersion) -> str: + return "".join(map(str, version)) + + +def sys_tags(*, warn: bool = False) -> Iterator[Tag]: + """ + Returns the sequence of tag triples for the running interpreter. + + The order of the sequence corresponds to priority order for the + interpreter, from most to least important. + """ + + interp_name = interpreter_name() + if interp_name == "cp": + yield from cpython_tags(warn=warn) + else: + yield from generic_tags() + + if interp_name == "pp": + yield from compatible_tags(interpreter="pp3") + else: + yield from compatible_tags() diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/utils.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/utils.py new file mode 100644 index 0000000..bab11b8 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/utils.py @@ -0,0 +1,136 @@ +# This file is dual licensed under the terms of the Apache License, Version +# 2.0, and the BSD License. See the LICENSE file in the root of this repository +# for complete details. + +import re +from typing import FrozenSet, NewType, Tuple, Union, cast + +from .tags import Tag, parse_tag +from .version import InvalidVersion, Version + +BuildTag = Union[Tuple[()], Tuple[int, str]] +NormalizedName = NewType("NormalizedName", str) + + +class InvalidWheelFilename(ValueError): + """ + An invalid wheel filename was found, users should refer to PEP 427. + """ + + +class InvalidSdistFilename(ValueError): + """ + An invalid sdist filename was found, users should refer to the packaging user guide. + """ + + +_canonicalize_regex = re.compile(r"[-_.]+") +# PEP 427: The build number must start with a digit. +_build_tag_regex = re.compile(r"(\d+)(.*)") + + +def canonicalize_name(name: str) -> NormalizedName: + # This is taken from PEP 503. + value = _canonicalize_regex.sub("-", name).lower() + return cast(NormalizedName, value) + + +def canonicalize_version(version: Union[Version, str]) -> str: + """ + This is very similar to Version.__str__, but has one subtle difference + with the way it handles the release segment. + """ + if isinstance(version, str): + try: + parsed = Version(version) + except InvalidVersion: + # Legacy versions cannot be normalized + return version + else: + parsed = version + + parts = [] + + # Epoch + if parsed.epoch != 0: + parts.append(f"{parsed.epoch}!") + + # Release segment + # NB: This strips trailing '.0's to normalize + parts.append(re.sub(r"(\.0)+$", "", ".".join(str(x) for x in parsed.release))) + + # Pre-release + if parsed.pre is not None: + parts.append("".join(str(x) for x in parsed.pre)) + + # Post-release + if parsed.post is not None: + parts.append(f".post{parsed.post}") + + # Development release + if parsed.dev is not None: + parts.append(f".dev{parsed.dev}") + + # Local version segment + if parsed.local is not None: + parts.append(f"+{parsed.local}") + + return "".join(parts) + + +def parse_wheel_filename( + filename: str, +) -> Tuple[NormalizedName, Version, BuildTag, FrozenSet[Tag]]: + if not filename.endswith(".whl"): + raise InvalidWheelFilename( + f"Invalid wheel filename (extension must be '.whl'): {filename}" + ) + + filename = filename[:-4] + dashes = filename.count("-") + if dashes not in (4, 5): + raise InvalidWheelFilename( + f"Invalid wheel filename (wrong number of parts): {filename}" + ) + + parts = filename.split("-", dashes - 2) + name_part = parts[0] + # See PEP 427 for the rules on escaping the project name + if "__" in name_part or re.match(r"^[\w\d._]*$", name_part, re.UNICODE) is None: + raise InvalidWheelFilename(f"Invalid project name: {filename}") + name = canonicalize_name(name_part) + version = Version(parts[1]) + if dashes == 5: + build_part = parts[2] + build_match = _build_tag_regex.match(build_part) + if build_match is None: + raise InvalidWheelFilename( + f"Invalid build number: {build_part} in '{filename}'" + ) + build = cast(BuildTag, (int(build_match.group(1)), build_match.group(2))) + else: + build = () + tags = parse_tag(parts[-1]) + return (name, version, build, tags) + + +def parse_sdist_filename(filename: str) -> Tuple[NormalizedName, Version]: + if filename.endswith(".tar.gz"): + file_stem = filename[: -len(".tar.gz")] + elif filename.endswith(".zip"): + file_stem = filename[: -len(".zip")] + else: + raise InvalidSdistFilename( + f"Invalid sdist filename (extension must be '.tar.gz' or '.zip'):" + f" {filename}" + ) + + # We are requiring a PEP 440 version, which cannot contain dashes, + # so we split on the last dash. + name_part, sep, version_part = file_stem.rpartition("-") + if not sep: + raise InvalidSdistFilename(f"Invalid sdist filename: {filename}") + + name = canonicalize_name(name_part) + version = Version(version_part) + return (name, version) diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/version.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/version.py new file mode 100644 index 0000000..de9a09a --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/packaging/version.py @@ -0,0 +1,504 @@ +# This file is dual licensed under the terms of the Apache License, Version +# 2.0, and the BSD License. See the LICENSE file in the root of this repository +# for complete details. + +import collections +import itertools +import re +import warnings +from typing import Callable, Iterator, List, Optional, SupportsInt, Tuple, Union + +from ._structures import Infinity, InfinityType, NegativeInfinity, NegativeInfinityType + +__all__ = ["parse", "Version", "LegacyVersion", "InvalidVersion", "VERSION_PATTERN"] + +InfiniteTypes = Union[InfinityType, NegativeInfinityType] +PrePostDevType = Union[InfiniteTypes, Tuple[str, int]] +SubLocalType = Union[InfiniteTypes, int, str] +LocalType = Union[ + NegativeInfinityType, + Tuple[ + Union[ + SubLocalType, + Tuple[SubLocalType, str], + Tuple[NegativeInfinityType, SubLocalType], + ], + ..., + ], +] +CmpKey = Tuple[ + int, Tuple[int, ...], PrePostDevType, PrePostDevType, PrePostDevType, LocalType +] +LegacyCmpKey = Tuple[int, Tuple[str, ...]] +VersionComparisonMethod = Callable[ + [Union[CmpKey, LegacyCmpKey], Union[CmpKey, LegacyCmpKey]], bool +] + +_Version = collections.namedtuple( + "_Version", ["epoch", "release", "dev", "pre", "post", "local"] +) + + +def parse(version: str) -> Union["LegacyVersion", "Version"]: + """ + Parse the given version string and return either a :class:`Version` object + or a :class:`LegacyVersion` object depending on if the given version is + a valid PEP 440 version or a legacy version. + """ + try: + return Version(version) + except InvalidVersion: + return LegacyVersion(version) + + +class InvalidVersion(ValueError): + """ + An invalid version was found, users should refer to PEP 440. + """ + + +class _BaseVersion: + _key: Union[CmpKey, LegacyCmpKey] + + def __hash__(self) -> int: + return hash(self._key) + + # Please keep the duplicated `isinstance` check + # in the six comparisons hereunder + # unless you find a way to avoid adding overhead function calls. + def __lt__(self, other: "_BaseVersion") -> bool: + if not isinstance(other, _BaseVersion): + return NotImplemented + + return self._key < other._key + + def __le__(self, other: "_BaseVersion") -> bool: + if not isinstance(other, _BaseVersion): + return NotImplemented + + return self._key <= other._key + + def __eq__(self, other: object) -> bool: + if not isinstance(other, _BaseVersion): + return NotImplemented + + return self._key == other._key + + def __ge__(self, other: "_BaseVersion") -> bool: + if not isinstance(other, _BaseVersion): + return NotImplemented + + return self._key >= other._key + + def __gt__(self, other: "_BaseVersion") -> bool: + if not isinstance(other, _BaseVersion): + return NotImplemented + + return self._key > other._key + + def __ne__(self, other: object) -> bool: + if not isinstance(other, _BaseVersion): + return NotImplemented + + return self._key != other._key + + +class LegacyVersion(_BaseVersion): + def __init__(self, version: str) -> None: + self._version = str(version) + self._key = _legacy_cmpkey(self._version) + + warnings.warn( + "Creating a LegacyVersion has been deprecated and will be " + "removed in the next major release", + DeprecationWarning, + ) + + def __str__(self) -> str: + return self._version + + def __repr__(self) -> str: + return f"<LegacyVersion('{self}')>" + + @property + def public(self) -> str: + return self._version + + @property + def base_version(self) -> str: + return self._version + + @property + def epoch(self) -> int: + return -1 + + @property + def release(self) -> None: + return None + + @property + def pre(self) -> None: + return None + + @property + def post(self) -> None: + return None + + @property + def dev(self) -> None: + return None + + @property + def local(self) -> None: + return None + + @property + def is_prerelease(self) -> bool: + return False + + @property + def is_postrelease(self) -> bool: + return False + + @property + def is_devrelease(self) -> bool: + return False + + +_legacy_version_component_re = re.compile(r"(\d+ | [a-z]+ | \.| -)", re.VERBOSE) + +_legacy_version_replacement_map = { + "pre": "c", + "preview": "c", + "-": "final-", + "rc": "c", + "dev": "@", +} + + +def _parse_version_parts(s: str) -> Iterator[str]: + for part in _legacy_version_component_re.split(s): + part = _legacy_version_replacement_map.get(part, part) + + if not part or part == ".": + continue + + if part[:1] in "0123456789": + # pad for numeric comparison + yield part.zfill(8) + else: + yield "*" + part + + # ensure that alpha/beta/candidate are before final + yield "*final" + + +def _legacy_cmpkey(version: str) -> LegacyCmpKey: + + # We hardcode an epoch of -1 here. A PEP 440 version can only have a epoch + # greater than or equal to 0. This will effectively put the LegacyVersion, + # which uses the defacto standard originally implemented by setuptools, + # as before all PEP 440 versions. + epoch = -1 + + # This scheme is taken from pkg_resources.parse_version setuptools prior to + # it's adoption of the packaging library. + parts: List[str] = [] + for part in _parse_version_parts(version.lower()): + if part.startswith("*"): + # remove "-" before a prerelease tag + if part < "*final": + while parts and parts[-1] == "*final-": + parts.pop() + + # remove trailing zeros from each series of numeric parts + while parts and parts[-1] == "00000000": + parts.pop() + + parts.append(part) + + return epoch, tuple(parts) + + +# Deliberately not anchored to the start and end of the string, to make it +# easier for 3rd party code to reuse +VERSION_PATTERN = r""" + v? + (?: + (?:(?P<epoch>[0-9]+)!)? # epoch + (?P<release>[0-9]+(?:\.[0-9]+)*) # release segment + (?P<pre> # pre-release + [-_\.]? + (?P<pre_l>(a|b|c|rc|alpha|beta|pre|preview)) + [-_\.]? + (?P<pre_n>[0-9]+)? + )? + (?P<post> # post release + (?:-(?P<post_n1>[0-9]+)) + | + (?: + [-_\.]? + (?P<post_l>post|rev|r) + [-_\.]? + (?P<post_n2>[0-9]+)? + ) + )? + (?P<dev> # dev release + [-_\.]? + (?P<dev_l>dev) + [-_\.]? + (?P<dev_n>[0-9]+)? + )? + ) + (?:\+(?P<local>[a-z0-9]+(?:[-_\.][a-z0-9]+)*))? # local version +""" + + +class Version(_BaseVersion): + + _regex = re.compile(r"^\s*" + VERSION_PATTERN + r"\s*$", re.VERBOSE | re.IGNORECASE) + + def __init__(self, version: str) -> None: + + # Validate the version and parse it into pieces + match = self._regex.search(version) + if not match: + raise InvalidVersion(f"Invalid version: '{version}'") + + # Store the parsed out pieces of the version + self._version = _Version( + epoch=int(match.group("epoch")) if match.group("epoch") else 0, + release=tuple(int(i) for i in match.group("release").split(".")), + pre=_parse_letter_version(match.group("pre_l"), match.group("pre_n")), + post=_parse_letter_version( + match.group("post_l"), match.group("post_n1") or match.group("post_n2") + ), + dev=_parse_letter_version(match.group("dev_l"), match.group("dev_n")), + local=_parse_local_version(match.group("local")), + ) + + # Generate a key which will be used for sorting + self._key = _cmpkey( + self._version.epoch, + self._version.release, + self._version.pre, + self._version.post, + self._version.dev, + self._version.local, + ) + + def __repr__(self) -> str: + return f"<Version('{self}')>" + + def __str__(self) -> str: + parts = [] + + # Epoch + if self.epoch != 0: + parts.append(f"{self.epoch}!") + + # Release segment + parts.append(".".join(str(x) for x in self.release)) + + # Pre-release + if self.pre is not None: + parts.append("".join(str(x) for x in self.pre)) + + # Post-release + if self.post is not None: + parts.append(f".post{self.post}") + + # Development release + if self.dev is not None: + parts.append(f".dev{self.dev}") + + # Local version segment + if self.local is not None: + parts.append(f"+{self.local}") + + return "".join(parts) + + @property + def epoch(self) -> int: + _epoch: int = self._version.epoch + return _epoch + + @property + def release(self) -> Tuple[int, ...]: + _release: Tuple[int, ...] = self._version.release + return _release + + @property + def pre(self) -> Optional[Tuple[str, int]]: + _pre: Optional[Tuple[str, int]] = self._version.pre + return _pre + + @property + def post(self) -> Optional[int]: + return self._version.post[1] if self._version.post else None + + @property + def dev(self) -> Optional[int]: + return self._version.dev[1] if self._version.dev else None + + @property + def local(self) -> Optional[str]: + if self._version.local: + return ".".join(str(x) for x in self._version.local) + else: + return None + + @property + def public(self) -> str: + return str(self).split("+", 1)[0] + + @property + def base_version(self) -> str: + parts = [] + + # Epoch + if self.epoch != 0: + parts.append(f"{self.epoch}!") + + # Release segment + parts.append(".".join(str(x) for x in self.release)) + + return "".join(parts) + + @property + def is_prerelease(self) -> bool: + return self.dev is not None or self.pre is not None + + @property + def is_postrelease(self) -> bool: + return self.post is not None + + @property + def is_devrelease(self) -> bool: + return self.dev is not None + + @property + def major(self) -> int: + return self.release[0] if len(self.release) >= 1 else 0 + + @property + def minor(self) -> int: + return self.release[1] if len(self.release) >= 2 else 0 + + @property + def micro(self) -> int: + return self.release[2] if len(self.release) >= 3 else 0 + + +def _parse_letter_version( + letter: str, number: Union[str, bytes, SupportsInt] +) -> Optional[Tuple[str, int]]: + + if letter: + # We consider there to be an implicit 0 in a pre-release if there is + # not a numeral associated with it. + if number is None: + number = 0 + + # We normalize any letters to their lower case form + letter = letter.lower() + + # We consider some words to be alternate spellings of other words and + # in those cases we want to normalize the spellings to our preferred + # spelling. + if letter == "alpha": + letter = "a" + elif letter == "beta": + letter = "b" + elif letter in ["c", "pre", "preview"]: + letter = "rc" + elif letter in ["rev", "r"]: + letter = "post" + + return letter, int(number) + if not letter and number: + # We assume if we are given a number, but we are not given a letter + # then this is using the implicit post release syntax (e.g. 1.0-1) + letter = "post" + + return letter, int(number) + + return None + + +_local_version_separators = re.compile(r"[\._-]") + + +def _parse_local_version(local: str) -> Optional[LocalType]: + """ + Takes a string like abc.1.twelve and turns it into ("abc", 1, "twelve"). + """ + if local is not None: + return tuple( + part.lower() if not part.isdigit() else int(part) + for part in _local_version_separators.split(local) + ) + return None + + +def _cmpkey( + epoch: int, + release: Tuple[int, ...], + pre: Optional[Tuple[str, int]], + post: Optional[Tuple[str, int]], + dev: Optional[Tuple[str, int]], + local: Optional[Tuple[SubLocalType]], +) -> CmpKey: + + # When we compare a release version, we want to compare it with all of the + # trailing zeros removed. So we'll use a reverse the list, drop all the now + # leading zeros until we come to something non zero, then take the rest + # re-reverse it back into the correct order and make it a tuple and use + # that for our sorting key. + _release = tuple( + reversed(list(itertools.dropwhile(lambda x: x == 0, reversed(release)))) + ) + + # We need to "trick" the sorting algorithm to put 1.0.dev0 before 1.0a0. + # We'll do this by abusing the pre segment, but we _only_ want to do this + # if there is not a pre or a post segment. If we have one of those then + # the normal sorting rules will handle this case correctly. + if pre is None and post is None and dev is not None: + _pre: PrePostDevType = NegativeInfinity + # Versions without a pre-release (except as noted above) should sort after + # those with one. + elif pre is None: + _pre = Infinity + else: + _pre = pre + + # Versions without a post segment should sort before those with one. + if post is None: + _post: PrePostDevType = NegativeInfinity + + else: + _post = post + + # Versions without a development segment should sort after those with one. + if dev is None: + _dev: PrePostDevType = Infinity + + else: + _dev = dev + + if local is None: + # Versions without a local segment should sort before those with one. + _local: LocalType = NegativeInfinity + else: + # Versions with a local segment need that segment parsed to implement + # the sorting rules in PEP440. + # - Alpha numeric segments sort before numeric segments + # - Alpha numeric segments sort lexicographically + # - Numeric segments sort numerically + # - Shorter versions sort before longer versions when the prefixes + # match exactly + _local = tuple( + (i, "") if isinstance(i, int) else (NegativeInfinity, i) for i in local + ) + + return epoch, _release, _pre, _post, _dev, _local diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__init__.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__init__.py new file mode 100644 index 0000000..7802ff1 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__init__.py @@ -0,0 +1,331 @@ +# module pyparsing.py +# +# Copyright (c) 2003-2022 Paul T. McGuire +# +# Permission is hereby granted, free of charge, to any person obtaining +# a copy of this software and associated documentation files (the +# "Software"), to deal in the Software without restriction, including +# without limitation the rights to use, copy, modify, merge, publish, +# distribute, sublicense, and/or sell copies of the Software, and to +# permit persons to whom the Software is furnished to do so, subject to +# the following conditions: +# +# The above copyright notice and this permission notice shall be +# included in all copies or substantial portions of the Software. +# +# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. +# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY +# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, +# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE +# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. +# + +__doc__ = """ +pyparsing module - Classes and methods to define and execute parsing grammars +============================================================================= + +The pyparsing module is an alternative approach to creating and +executing simple grammars, vs. the traditional lex/yacc approach, or the +use of regular expressions. With pyparsing, you don't need to learn +a new syntax for defining grammars or matching expressions - the parsing +module provides a library of classes that you use to construct the +grammar directly in Python. + +Here is a program to parse "Hello, World!" (or any greeting of the form +``"<salutation>, <addressee>!"``), built up using :class:`Word`, +:class:`Literal`, and :class:`And` elements +(the :meth:`'+'<ParserElement.__add__>` operators create :class:`And` expressions, +and the strings are auto-converted to :class:`Literal` expressions):: + + from pyparsing import Word, alphas + + # define grammar of a greeting + greet = Word(alphas) + "," + Word(alphas) + "!" + + hello = "Hello, World!" + print(hello, "->", greet.parse_string(hello)) + +The program outputs the following:: + + Hello, World! -> ['Hello', ',', 'World', '!'] + +The Python representation of the grammar is quite readable, owing to the +self-explanatory class names, and the use of :class:`'+'<And>`, +:class:`'|'<MatchFirst>`, :class:`'^'<Or>` and :class:`'&'<Each>` operators. + +The :class:`ParseResults` object returned from +:class:`ParserElement.parseString` can be +accessed as a nested list, a dictionary, or an object with named +attributes. + +The pyparsing module handles some of the problems that are typically +vexing when writing text parsers: + + - extra or missing whitespace (the above program will also handle + "Hello,World!", "Hello , World !", etc.) + - quoted strings + - embedded comments + + +Getting Started - +----------------- +Visit the classes :class:`ParserElement` and :class:`ParseResults` to +see the base classes that most other pyparsing +classes inherit from. Use the docstrings for examples of how to: + + - construct literal match expressions from :class:`Literal` and + :class:`CaselessLiteral` classes + - construct character word-group expressions using the :class:`Word` + class + - see how to create repetitive expressions using :class:`ZeroOrMore` + and :class:`OneOrMore` classes + - use :class:`'+'<And>`, :class:`'|'<MatchFirst>`, :class:`'^'<Or>`, + and :class:`'&'<Each>` operators to combine simple expressions into + more complex ones + - associate names with your parsed results using + :class:`ParserElement.setResultsName` + - access the parsed data, which is returned as a :class:`ParseResults` + object + - find some helpful expression short-cuts like :class:`delimitedList` + and :class:`oneOf` + - find more useful common expressions in the :class:`pyparsing_common` + namespace class +""" +from typing import NamedTuple + + +class version_info(NamedTuple): + major: int + minor: int + micro: int + releaselevel: str + serial: int + + @property + def __version__(self): + return ( + "{}.{}.{}".format(self.major, self.minor, self.micro) + + ( + "{}{}{}".format( + "r" if self.releaselevel[0] == "c" else "", + self.releaselevel[0], + self.serial, + ), + "", + )[self.releaselevel == "final"] + ) + + def __str__(self): + return "{} {} / {}".format(__name__, self.__version__, __version_time__) + + def __repr__(self): + return "{}.{}({})".format( + __name__, + type(self).__name__, + ", ".join("{}={!r}".format(*nv) for nv in zip(self._fields, self)), + ) + + +__version_info__ = version_info(3, 0, 9, "final", 0) +__version_time__ = "05 May 2022 07:02 UTC" +__version__ = __version_info__.__version__ +__versionTime__ = __version_time__ +__author__ = "Paul McGuire <ptmcg.gm+pyparsing@gmail.com>" + +from .util import * +from .exceptions import * +from .actions import * +from .core import __diag__, __compat__ +from .results import * +from .core import * +from .core import _builtin_exprs as core_builtin_exprs +from .helpers import * +from .helpers import _builtin_exprs as helper_builtin_exprs + +from .unicode import unicode_set, UnicodeRangeList, pyparsing_unicode as unicode +from .testing import pyparsing_test as testing +from .common import ( + pyparsing_common as common, + _builtin_exprs as common_builtin_exprs, +) + +# define backward compat synonyms +if "pyparsing_unicode" not in globals(): + pyparsing_unicode = unicode +if "pyparsing_common" not in globals(): + pyparsing_common = common +if "pyparsing_test" not in globals(): + pyparsing_test = testing + +core_builtin_exprs += common_builtin_exprs + helper_builtin_exprs + + +__all__ = [ + "__version__", + "__version_time__", + "__author__", + "__compat__", + "__diag__", + "And", + "AtLineStart", + "AtStringStart", + "CaselessKeyword", + "CaselessLiteral", + "CharsNotIn", + "Combine", + "Dict", + "Each", + "Empty", + "FollowedBy", + "Forward", + "GoToColumn", + "Group", + "IndentedBlock", + "Keyword", + "LineEnd", + "LineStart", + "Literal", + "Located", + "PrecededBy", + "MatchFirst", + "NoMatch", + "NotAny", + "OneOrMore", + "OnlyOnce", + "OpAssoc", + "Opt", + "Optional", + "Or", + "ParseBaseException", + "ParseElementEnhance", + "ParseException", + "ParseExpression", + "ParseFatalException", + "ParseResults", + "ParseSyntaxException", + "ParserElement", + "PositionToken", + "QuotedString", + "RecursiveGrammarException", + "Regex", + "SkipTo", + "StringEnd", + "StringStart", + "Suppress", + "Token", + "TokenConverter", + "White", + "Word", + "WordEnd", + "WordStart", + "ZeroOrMore", + "Char", + "alphanums", + "alphas", + "alphas8bit", + "any_close_tag", + "any_open_tag", + "c_style_comment", + "col", + "common_html_entity", + "counted_array", + "cpp_style_comment", + "dbl_quoted_string", + "dbl_slash_comment", + "delimited_list", + "dict_of", + "empty", + "hexnums", + "html_comment", + "identchars", + "identbodychars", + "java_style_comment", + "line", + "line_end", + "line_start", + "lineno", + "make_html_tags", + "make_xml_tags", + "match_only_at_col", + "match_previous_expr", + "match_previous_literal", + "nested_expr", + "null_debug_action", + "nums", + "one_of", + "printables", + "punc8bit", + "python_style_comment", + "quoted_string", + "remove_quotes", + "replace_with", + "replace_html_entity", + "rest_of_line", + "sgl_quoted_string", + "srange", + "string_end", + "string_start", + "trace_parse_action", + "unicode_string", + "with_attribute", + "indentedBlock", + "original_text_for", + "ungroup", + "infix_notation", + "locatedExpr", + "with_class", + "CloseMatch", + "token_map", + "pyparsing_common", + "pyparsing_unicode", + "unicode_set", + "condition_as_parse_action", + "pyparsing_test", + # pre-PEP8 compatibility names + "__versionTime__", + "anyCloseTag", + "anyOpenTag", + "cStyleComment", + "commonHTMLEntity", + "countedArray", + "cppStyleComment", + "dblQuotedString", + "dblSlashComment", + "delimitedList", + "dictOf", + "htmlComment", + "javaStyleComment", + "lineEnd", + "lineStart", + "makeHTMLTags", + "makeXMLTags", + "matchOnlyAtCol", + "matchPreviousExpr", + "matchPreviousLiteral", + "nestedExpr", + "nullDebugAction", + "oneOf", + "opAssoc", + "pythonStyleComment", + "quotedString", + "removeQuotes", + "replaceHTMLEntity", + "replaceWith", + "restOfLine", + "sglQuotedString", + "stringEnd", + "stringStart", + "traceParseAction", + "unicodeString", + "withAttribute", + "indentedBlock", + "originalTextFor", + "infixNotation", + "locatedExpr", + "withClass", + "tokenMap", + "conditionAsParseAction", + "autoname_elements", +] diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/__init__.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/__init__.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..79df265 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/__init__.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/actions.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/actions.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..b2a8844 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/actions.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/common.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/common.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..b402053 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/common.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/core.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/core.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..a488b56 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/core.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/exceptions.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/exceptions.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..37db7cb --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/exceptions.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/helpers.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/helpers.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..b6087d5 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/helpers.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/results.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/results.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..2a9ea97 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/results.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/testing.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/testing.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..9b71599 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/testing.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/unicode.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/unicode.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..54f9f66 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/unicode.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/util.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/util.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..217bc34 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/__pycache__/util.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/actions.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/actions.py new file mode 100644 index 0000000..f72c66e --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/actions.py @@ -0,0 +1,207 @@ +# actions.py + +from .exceptions import ParseException +from .util import col + + +class OnlyOnce: + """ + Wrapper for parse actions, to ensure they are only called once. + """ + + def __init__(self, method_call): + from .core import _trim_arity + + self.callable = _trim_arity(method_call) + self.called = False + + def __call__(self, s, l, t): + if not self.called: + results = self.callable(s, l, t) + self.called = True + return results + raise ParseException(s, l, "OnlyOnce obj called multiple times w/out reset") + + def reset(self): + """ + Allow the associated parse action to be called once more. + """ + + self.called = False + + +def match_only_at_col(n): + """ + Helper method for defining parse actions that require matching at + a specific column in the input text. + """ + + def verify_col(strg, locn, toks): + if col(locn, strg) != n: + raise ParseException(strg, locn, "matched token not at column {}".format(n)) + + return verify_col + + +def replace_with(repl_str): + """ + Helper method for common parse actions that simply return + a literal value. Especially useful when used with + :class:`transform_string<ParserElement.transform_string>` (). + + Example:: + + num = Word(nums).set_parse_action(lambda toks: int(toks[0])) + na = one_of("N/A NA").set_parse_action(replace_with(math.nan)) + term = na | num + + term[1, ...].parse_string("324 234 N/A 234") # -> [324, 234, nan, 234] + """ + return lambda s, l, t: [repl_str] + + +def remove_quotes(s, l, t): + """ + Helper parse action for removing quotation marks from parsed + quoted strings. + + Example:: + + # by default, quotation marks are included in parsed results + quoted_string.parse_string("'Now is the Winter of our Discontent'") # -> ["'Now is the Winter of our Discontent'"] + + # use remove_quotes to strip quotation marks from parsed results + quoted_string.set_parse_action(remove_quotes) + quoted_string.parse_string("'Now is the Winter of our Discontent'") # -> ["Now is the Winter of our Discontent"] + """ + return t[0][1:-1] + + +def with_attribute(*args, **attr_dict): + """ + Helper to create a validating parse action to be used with start + tags created with :class:`make_xml_tags` or + :class:`make_html_tags`. Use ``with_attribute`` to qualify + a starting tag with a required attribute value, to avoid false + matches on common tags such as ``<TD>`` or ``<DIV>``. + + Call ``with_attribute`` with a series of attribute names and + values. Specify the list of filter attributes names and values as: + + - keyword arguments, as in ``(align="right")``, or + - as an explicit dict with ``**`` operator, when an attribute + name is also a Python reserved word, as in ``**{"class":"Customer", "align":"right"}`` + - a list of name-value tuples, as in ``(("ns1:class", "Customer"), ("ns2:align", "right"))`` + + For attribute names with a namespace prefix, you must use the second + form. Attribute names are matched insensitive to upper/lower case. + + If just testing for ``class`` (with or without a namespace), use + :class:`with_class`. + + To verify that the attribute exists, but without specifying a value, + pass ``with_attribute.ANY_VALUE`` as the value. + + Example:: + + html = ''' + <div> + Some text + <div type="grid">1 4 0 1 0</div> + <div type="graph">1,3 2,3 1,1</div> + <div>this has no type</div> + </div> + + ''' + div,div_end = make_html_tags("div") + + # only match div tag having a type attribute with value "grid" + div_grid = div().set_parse_action(with_attribute(type="grid")) + grid_expr = div_grid + SkipTo(div | div_end)("body") + for grid_header in grid_expr.search_string(html): + print(grid_header.body) + + # construct a match with any div tag having a type attribute, regardless of the value + div_any_type = div().set_parse_action(with_attribute(type=with_attribute.ANY_VALUE)) + div_expr = div_any_type + SkipTo(div | div_end)("body") + for div_header in div_expr.search_string(html): + print(div_header.body) + + prints:: + + 1 4 0 1 0 + + 1 4 0 1 0 + 1,3 2,3 1,1 + """ + if args: + attrs = args[:] + else: + attrs = attr_dict.items() + attrs = [(k, v) for k, v in attrs] + + def pa(s, l, tokens): + for attrName, attrValue in attrs: + if attrName not in tokens: + raise ParseException(s, l, "no matching attribute " + attrName) + if attrValue != with_attribute.ANY_VALUE and tokens[attrName] != attrValue: + raise ParseException( + s, + l, + "attribute {!r} has value {!r}, must be {!r}".format( + attrName, tokens[attrName], attrValue + ), + ) + + return pa + + +with_attribute.ANY_VALUE = object() + + +def with_class(classname, namespace=""): + """ + Simplified version of :class:`with_attribute` when + matching on a div class - made difficult because ``class`` is + a reserved word in Python. + + Example:: + + html = ''' + <div> + Some text + <div class="grid">1 4 0 1 0</div> + <div class="graph">1,3 2,3 1,1</div> + <div>this <div> has no class</div> + </div> + + ''' + div,div_end = make_html_tags("div") + div_grid = div().set_parse_action(with_class("grid")) + + grid_expr = div_grid + SkipTo(div | div_end)("body") + for grid_header in grid_expr.search_string(html): + print(grid_header.body) + + div_any_type = div().set_parse_action(with_class(withAttribute.ANY_VALUE)) + div_expr = div_any_type + SkipTo(div | div_end)("body") + for div_header in div_expr.search_string(html): + print(div_header.body) + + prints:: + + 1 4 0 1 0 + + 1 4 0 1 0 + 1,3 2,3 1,1 + """ + classattr = "{}:class".format(namespace) if namespace else "class" + return with_attribute(**{classattr: classname}) + + +# pre-PEP8 compatibility symbols +replaceWith = replace_with +removeQuotes = remove_quotes +withAttribute = with_attribute +withClass = with_class +matchOnlyAtCol = match_only_at_col diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/common.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/common.py new file mode 100644 index 0000000..1859fb7 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/common.py @@ -0,0 +1,424 @@ +# common.py +from .core import * +from .helpers import delimited_list, any_open_tag, any_close_tag +from datetime import datetime + + +# some other useful expressions - using lower-case class name since we are really using this as a namespace +class pyparsing_common: + """Here are some common low-level expressions that may be useful in + jump-starting parser development: + + - numeric forms (:class:`integers<integer>`, :class:`reals<real>`, + :class:`scientific notation<sci_real>`) + - common :class:`programming identifiers<identifier>` + - network addresses (:class:`MAC<mac_address>`, + :class:`IPv4<ipv4_address>`, :class:`IPv6<ipv6_address>`) + - ISO8601 :class:`dates<iso8601_date>` and + :class:`datetime<iso8601_datetime>` + - :class:`UUID<uuid>` + - :class:`comma-separated list<comma_separated_list>` + - :class:`url` + + Parse actions: + + - :class:`convertToInteger` + - :class:`convertToFloat` + - :class:`convertToDate` + - :class:`convertToDatetime` + - :class:`stripHTMLTags` + - :class:`upcaseTokens` + - :class:`downcaseTokens` + + Example:: + + pyparsing_common.number.runTests(''' + # any int or real number, returned as the appropriate type + 100 + -100 + +100 + 3.14159 + 6.02e23 + 1e-12 + ''') + + pyparsing_common.fnumber.runTests(''' + # any int or real number, returned as float + 100 + -100 + +100 + 3.14159 + 6.02e23 + 1e-12 + ''') + + pyparsing_common.hex_integer.runTests(''' + # hex numbers + 100 + FF + ''') + + pyparsing_common.fraction.runTests(''' + # fractions + 1/2 + -3/4 + ''') + + pyparsing_common.mixed_integer.runTests(''' + # mixed fractions + 1 + 1/2 + -3/4 + 1-3/4 + ''') + + import uuid + pyparsing_common.uuid.setParseAction(tokenMap(uuid.UUID)) + pyparsing_common.uuid.runTests(''' + # uuid + 12345678-1234-5678-1234-567812345678 + ''') + + prints:: + + # any int or real number, returned as the appropriate type + 100 + [100] + + -100 + [-100] + + +100 + [100] + + 3.14159 + [3.14159] + + 6.02e23 + [6.02e+23] + + 1e-12 + [1e-12] + + # any int or real number, returned as float + 100 + [100.0] + + -100 + [-100.0] + + +100 + [100.0] + + 3.14159 + [3.14159] + + 6.02e23 + [6.02e+23] + + 1e-12 + [1e-12] + + # hex numbers + 100 + [256] + + FF + [255] + + # fractions + 1/2 + [0.5] + + -3/4 + [-0.75] + + # mixed fractions + 1 + [1] + + 1/2 + [0.5] + + -3/4 + [-0.75] + + 1-3/4 + [1.75] + + # uuid + 12345678-1234-5678-1234-567812345678 + [UUID('12345678-1234-5678-1234-567812345678')] + """ + + convert_to_integer = token_map(int) + """ + Parse action for converting parsed integers to Python int + """ + + convert_to_float = token_map(float) + """ + Parse action for converting parsed numbers to Python float + """ + + integer = Word(nums).set_name("integer").set_parse_action(convert_to_integer) + """expression that parses an unsigned integer, returns an int""" + + hex_integer = ( + Word(hexnums).set_name("hex integer").set_parse_action(token_map(int, 16)) + ) + """expression that parses a hexadecimal integer, returns an int""" + + signed_integer = ( + Regex(r"[+-]?\d+") + .set_name("signed integer") + .set_parse_action(convert_to_integer) + ) + """expression that parses an integer with optional leading sign, returns an int""" + + fraction = ( + signed_integer().set_parse_action(convert_to_float) + + "/" + + signed_integer().set_parse_action(convert_to_float) + ).set_name("fraction") + """fractional expression of an integer divided by an integer, returns a float""" + fraction.add_parse_action(lambda tt: tt[0] / tt[-1]) + + mixed_integer = ( + fraction | signed_integer + Opt(Opt("-").suppress() + fraction) + ).set_name("fraction or mixed integer-fraction") + """mixed integer of the form 'integer - fraction', with optional leading integer, returns float""" + mixed_integer.add_parse_action(sum) + + real = ( + Regex(r"[+-]?(?:\d+\.\d*|\.\d+)") + .set_name("real number") + .set_parse_action(convert_to_float) + ) + """expression that parses a floating point number and returns a float""" + + sci_real = ( + Regex(r"[+-]?(?:\d+(?:[eE][+-]?\d+)|(?:\d+\.\d*|\.\d+)(?:[eE][+-]?\d+)?)") + .set_name("real number with scientific notation") + .set_parse_action(convert_to_float) + ) + """expression that parses a floating point number with optional + scientific notation and returns a float""" + + # streamlining this expression makes the docs nicer-looking + number = (sci_real | real | signed_integer).setName("number").streamline() + """any numeric expression, returns the corresponding Python type""" + + fnumber = ( + Regex(r"[+-]?\d+\.?\d*([eE][+-]?\d+)?") + .set_name("fnumber") + .set_parse_action(convert_to_float) + ) + """any int or real number, returned as float""" + + identifier = Word(identchars, identbodychars).set_name("identifier") + """typical code identifier (leading alpha or '_', followed by 0 or more alphas, nums, or '_')""" + + ipv4_address = Regex( + r"(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})(\.(25[0-5]|2[0-4][0-9]|1?[0-9]{1,2})){3}" + ).set_name("IPv4 address") + "IPv4 address (``0.0.0.0 - 255.255.255.255``)" + + _ipv6_part = Regex(r"[0-9a-fA-F]{1,4}").set_name("hex_integer") + _full_ipv6_address = (_ipv6_part + (":" + _ipv6_part) * 7).set_name( + "full IPv6 address" + ) + _short_ipv6_address = ( + Opt(_ipv6_part + (":" + _ipv6_part) * (0, 6)) + + "::" + + Opt(_ipv6_part + (":" + _ipv6_part) * (0, 6)) + ).set_name("short IPv6 address") + _short_ipv6_address.add_condition( + lambda t: sum(1 for tt in t if pyparsing_common._ipv6_part.matches(tt)) < 8 + ) + _mixed_ipv6_address = ("::ffff:" + ipv4_address).set_name("mixed IPv6 address") + ipv6_address = Combine( + (_full_ipv6_address | _mixed_ipv6_address | _short_ipv6_address).set_name( + "IPv6 address" + ) + ).set_name("IPv6 address") + "IPv6 address (long, short, or mixed form)" + + mac_address = Regex( + r"[0-9a-fA-F]{2}([:.-])[0-9a-fA-F]{2}(?:\1[0-9a-fA-F]{2}){4}" + ).set_name("MAC address") + "MAC address xx:xx:xx:xx:xx (may also have '-' or '.' delimiters)" + + @staticmethod + def convert_to_date(fmt: str = "%Y-%m-%d"): + """ + Helper to create a parse action for converting parsed date string to Python datetime.date + + Params - + - fmt - format to be passed to datetime.strptime (default= ``"%Y-%m-%d"``) + + Example:: + + date_expr = pyparsing_common.iso8601_date.copy() + date_expr.setParseAction(pyparsing_common.convertToDate()) + print(date_expr.parseString("1999-12-31")) + + prints:: + + [datetime.date(1999, 12, 31)] + """ + + def cvt_fn(ss, ll, tt): + try: + return datetime.strptime(tt[0], fmt).date() + except ValueError as ve: + raise ParseException(ss, ll, str(ve)) + + return cvt_fn + + @staticmethod + def convert_to_datetime(fmt: str = "%Y-%m-%dT%H:%M:%S.%f"): + """Helper to create a parse action for converting parsed + datetime string to Python datetime.datetime + + Params - + - fmt - format to be passed to datetime.strptime (default= ``"%Y-%m-%dT%H:%M:%S.%f"``) + + Example:: + + dt_expr = pyparsing_common.iso8601_datetime.copy() + dt_expr.setParseAction(pyparsing_common.convertToDatetime()) + print(dt_expr.parseString("1999-12-31T23:59:59.999")) + + prints:: + + [datetime.datetime(1999, 12, 31, 23, 59, 59, 999000)] + """ + + def cvt_fn(s, l, t): + try: + return datetime.strptime(t[0], fmt) + except ValueError as ve: + raise ParseException(s, l, str(ve)) + + return cvt_fn + + iso8601_date = Regex( + r"(?P<year>\d{4})(?:-(?P<month>\d\d)(?:-(?P<day>\d\d))?)?" + ).set_name("ISO8601 date") + "ISO8601 date (``yyyy-mm-dd``)" + + iso8601_datetime = Regex( + r"(?P<year>\d{4})-(?P<month>\d\d)-(?P<day>\d\d)[T ](?P<hour>\d\d):(?P<minute>\d\d)(:(?P<second>\d\d(\.\d*)?)?)?(?P<tz>Z|[+-]\d\d:?\d\d)?" + ).set_name("ISO8601 datetime") + "ISO8601 datetime (``yyyy-mm-ddThh:mm:ss.s(Z|+-00:00)``) - trailing seconds, milliseconds, and timezone optional; accepts separating ``'T'`` or ``' '``" + + uuid = Regex(r"[0-9a-fA-F]{8}(-[0-9a-fA-F]{4}){3}-[0-9a-fA-F]{12}").set_name("UUID") + "UUID (``xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx``)" + + _html_stripper = any_open_tag.suppress() | any_close_tag.suppress() + + @staticmethod + def strip_html_tags(s: str, l: int, tokens: ParseResults): + """Parse action to remove HTML tags from web page HTML source + + Example:: + + # strip HTML links from normal text + text = '<td>More info at the <a href="https://github.com/pyparsing/pyparsing/wiki">pyparsing</a> wiki page</td>' + td, td_end = makeHTMLTags("TD") + table_text = td + SkipTo(td_end).setParseAction(pyparsing_common.stripHTMLTags)("body") + td_end + print(table_text.parseString(text).body) + + Prints:: + + More info at the pyparsing wiki page + """ + return pyparsing_common._html_stripper.transform_string(tokens[0]) + + _commasepitem = ( + Combine( + OneOrMore( + ~Literal(",") + + ~LineEnd() + + Word(printables, exclude_chars=",") + + Opt(White(" \t") + ~FollowedBy(LineEnd() | ",")) + ) + ) + .streamline() + .set_name("commaItem") + ) + comma_separated_list = delimited_list( + Opt(quoted_string.copy() | _commasepitem, default="") + ).set_name("comma separated list") + """Predefined expression of 1 or more printable words or quoted strings, separated by commas.""" + + upcase_tokens = staticmethod(token_map(lambda t: t.upper())) + """Parse action to convert tokens to upper case.""" + + downcase_tokens = staticmethod(token_map(lambda t: t.lower())) + """Parse action to convert tokens to lower case.""" + + # fmt: off + url = Regex( + # https://mathiasbynens.be/demo/url-regex + # https://gist.github.com/dperini/729294 + r"^" + + # protocol identifier (optional) + # short syntax // still required + r"(?:(?:(?P<scheme>https?|ftp):)?\/\/)" + + # user:pass BasicAuth (optional) + r"(?:(?P<auth>\S+(?::\S*)?)@)?" + + r"(?P<host>" + + # IP address exclusion + # private & local networks + r"(?!(?:10|127)(?:\.\d{1,3}){3})" + + r"(?!(?:169\.254|192\.168)(?:\.\d{1,3}){2})" + + r"(?!172\.(?:1[6-9]|2\d|3[0-1])(?:\.\d{1,3}){2})" + + # IP address dotted notation octets + # excludes loopback network 0.0.0.0 + # excludes reserved space >= 224.0.0.0 + # excludes network & broadcast addresses + # (first & last IP address of each class) + r"(?:[1-9]\d?|1\d\d|2[01]\d|22[0-3])" + + r"(?:\.(?:1?\d{1,2}|2[0-4]\d|25[0-5])){2}" + + r"(?:\.(?:[1-9]\d?|1\d\d|2[0-4]\d|25[0-4]))" + + r"|" + + # host & domain names, may end with dot + # can be replaced by a shortest alternative + # (?![-_])(?:[-\w\u00a1-\uffff]{0,63}[^-_]\.)+ + r"(?:" + + r"(?:" + + r"[a-z0-9\u00a1-\uffff]" + + r"[a-z0-9\u00a1-\uffff_-]{0,62}" + + r")?" + + r"[a-z0-9\u00a1-\uffff]\." + + r")+" + + # TLD identifier name, may end with dot + r"(?:[a-z\u00a1-\uffff]{2,}\.?)" + + r")" + + # port number (optional) + r"(:(?P<port>\d{2,5}))?" + + # resource path (optional) + r"(?P<path>\/[^?# ]*)?" + + # query string (optional) + r"(\?(?P<query>[^#]*))?" + + # fragment (optional) + r"(#(?P<fragment>\S*))?" + + r"$" + ).set_name("url") + # fmt: on + + # pre-PEP8 compatibility names + convertToInteger = convert_to_integer + convertToFloat = convert_to_float + convertToDate = convert_to_date + convertToDatetime = convert_to_datetime + stripHTMLTags = strip_html_tags + upcaseTokens = upcase_tokens + downcaseTokens = downcase_tokens + + +_builtin_exprs = [ + v for v in vars(pyparsing_common).values() if isinstance(v, ParserElement) +] diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/core.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/core.py new file mode 100644 index 0000000..9acba3f --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/core.py @@ -0,0 +1,5814 @@ +# +# core.py +# +import os +import typing +from typing import ( + NamedTuple, + Union, + Callable, + Any, + Generator, + Tuple, + List, + TextIO, + Set, + Sequence, +) +from abc import ABC, abstractmethod +from enum import Enum +import string +import copy +import warnings +import re +import sys +from collections.abc import Iterable +import traceback +import types +from operator import itemgetter +from functools import wraps +from threading import RLock +from pathlib import Path + +from .util import ( + _FifoCache, + _UnboundedCache, + __config_flags, + _collapse_string_to_ranges, + _escape_regex_range_chars, + _bslash, + _flatten, + LRUMemo as _LRUMemo, + UnboundedMemo as _UnboundedMemo, +) +from .exceptions import * +from .actions import * +from .results import ParseResults, _ParseResultsWithOffset +from .unicode import pyparsing_unicode + +_MAX_INT = sys.maxsize +str_type: Tuple[type, ...] = (str, bytes) + +# +# Copyright (c) 2003-2022 Paul T. McGuire +# +# Permission is hereby granted, free of charge, to any person obtaining +# a copy of this software and associated documentation files (the +# "Software"), to deal in the Software without restriction, including +# without limitation the rights to use, copy, modify, merge, publish, +# distribute, sublicense, and/or sell copies of the Software, and to +# permit persons to whom the Software is furnished to do so, subject to +# the following conditions: +# +# The above copyright notice and this permission notice shall be +# included in all copies or substantial portions of the Software. +# +# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, +# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. +# IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY +# CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, +# TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE +# SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. +# + + +if sys.version_info >= (3, 8): + from functools import cached_property +else: + + class cached_property: + def __init__(self, func): + self._func = func + + def __get__(self, instance, owner=None): + ret = instance.__dict__[self._func.__name__] = self._func(instance) + return ret + + +class __compat__(__config_flags): + """ + A cross-version compatibility configuration for pyparsing features that will be + released in a future version. By setting values in this configuration to True, + those features can be enabled in prior versions for compatibility development + and testing. + + - ``collect_all_And_tokens`` - flag to enable fix for Issue #63 that fixes erroneous grouping + of results names when an :class:`And` expression is nested within an :class:`Or` or :class:`MatchFirst`; + maintained for compatibility, but setting to ``False`` no longer restores pre-2.3.1 + behavior + """ + + _type_desc = "compatibility" + + collect_all_And_tokens = True + + _all_names = [__ for __ in locals() if not __.startswith("_")] + _fixed_names = """ + collect_all_And_tokens + """.split() + + +class __diag__(__config_flags): + _type_desc = "diagnostic" + + warn_multiple_tokens_in_named_alternation = False + warn_ungrouped_named_tokens_in_collection = False + warn_name_set_on_empty_Forward = False + warn_on_parse_using_empty_Forward = False + warn_on_assignment_to_Forward = False + warn_on_multiple_string_args_to_oneof = False + warn_on_match_first_with_lshift_operator = False + enable_debug_on_named_expressions = False + + _all_names = [__ for __ in locals() if not __.startswith("_")] + _warning_names = [name for name in _all_names if name.startswith("warn")] + _debug_names = [name for name in _all_names if name.startswith("enable_debug")] + + @classmethod + def enable_all_warnings(cls) -> None: + for name in cls._warning_names: + cls.enable(name) + + +class Diagnostics(Enum): + """ + Diagnostic configuration (all default to disabled) + - ``warn_multiple_tokens_in_named_alternation`` - flag to enable warnings when a results + name is defined on a :class:`MatchFirst` or :class:`Or` expression with one or more :class:`And` subexpressions + - ``warn_ungrouped_named_tokens_in_collection`` - flag to enable warnings when a results + name is defined on a containing expression with ungrouped subexpressions that also + have results names + - ``warn_name_set_on_empty_Forward`` - flag to enable warnings when a :class:`Forward` is defined + with a results name, but has no contents defined + - ``warn_on_parse_using_empty_Forward`` - flag to enable warnings when a :class:`Forward` is + defined in a grammar but has never had an expression attached to it + - ``warn_on_assignment_to_Forward`` - flag to enable warnings when a :class:`Forward` is defined + but is overwritten by assigning using ``'='`` instead of ``'<<='`` or ``'<<'`` + - ``warn_on_multiple_string_args_to_oneof`` - flag to enable warnings when :class:`one_of` is + incorrectly called with multiple str arguments + - ``enable_debug_on_named_expressions`` - flag to auto-enable debug on all subsequent + calls to :class:`ParserElement.set_name` + + Diagnostics are enabled/disabled by calling :class:`enable_diag` and :class:`disable_diag`. + All warnings can be enabled by calling :class:`enable_all_warnings`. + """ + + warn_multiple_tokens_in_named_alternation = 0 + warn_ungrouped_named_tokens_in_collection = 1 + warn_name_set_on_empty_Forward = 2 + warn_on_parse_using_empty_Forward = 3 + warn_on_assignment_to_Forward = 4 + warn_on_multiple_string_args_to_oneof = 5 + warn_on_match_first_with_lshift_operator = 6 + enable_debug_on_named_expressions = 7 + + +def enable_diag(diag_enum: Diagnostics) -> None: + """ + Enable a global pyparsing diagnostic flag (see :class:`Diagnostics`). + """ + __diag__.enable(diag_enum.name) + + +def disable_diag(diag_enum: Diagnostics) -> None: + """ + Disable a global pyparsing diagnostic flag (see :class:`Diagnostics`). + """ + __diag__.disable(diag_enum.name) + + +def enable_all_warnings() -> None: + """ + Enable all global pyparsing diagnostic warnings (see :class:`Diagnostics`). + """ + __diag__.enable_all_warnings() + + +# hide abstract class +del __config_flags + + +def _should_enable_warnings( + cmd_line_warn_options: typing.Iterable[str], warn_env_var: typing.Optional[str] +) -> bool: + enable = bool(warn_env_var) + for warn_opt in cmd_line_warn_options: + w_action, w_message, w_category, w_module, w_line = (warn_opt + "::::").split( + ":" + )[:5] + if not w_action.lower().startswith("i") and ( + not (w_message or w_category or w_module) or w_module == "pyparsing" + ): + enable = True + elif w_action.lower().startswith("i") and w_module in ("pyparsing", ""): + enable = False + return enable + + +if _should_enable_warnings( + sys.warnoptions, os.environ.get("PYPARSINGENABLEALLWARNINGS") +): + enable_all_warnings() + + +# build list of single arg builtins, that can be used as parse actions +_single_arg_builtins = { + sum, + len, + sorted, + reversed, + list, + tuple, + set, + any, + all, + min, + max, +} + +_generatorType = types.GeneratorType +ParseAction = Union[ + Callable[[], Any], + Callable[[ParseResults], Any], + Callable[[int, ParseResults], Any], + Callable[[str, int, ParseResults], Any], +] +ParseCondition = Union[ + Callable[[], bool], + Callable[[ParseResults], bool], + Callable[[int, ParseResults], bool], + Callable[[str, int, ParseResults], bool], +] +ParseFailAction = Callable[[str, int, "ParserElement", Exception], None] +DebugStartAction = Callable[[str, int, "ParserElement", bool], None] +DebugSuccessAction = Callable[ + [str, int, int, "ParserElement", ParseResults, bool], None +] +DebugExceptionAction = Callable[[str, int, "ParserElement", Exception, bool], None] + + +alphas = string.ascii_uppercase + string.ascii_lowercase +identchars = pyparsing_unicode.Latin1.identchars +identbodychars = pyparsing_unicode.Latin1.identbodychars +nums = "0123456789" +hexnums = nums + "ABCDEFabcdef" +alphanums = alphas + nums +printables = "".join([c for c in string.printable if c not in string.whitespace]) + +_trim_arity_call_line: traceback.StackSummary = None + + +def _trim_arity(func, max_limit=3): + """decorator to trim function calls to match the arity of the target""" + global _trim_arity_call_line + + if func in _single_arg_builtins: + return lambda s, l, t: func(t) + + limit = 0 + found_arity = False + + def extract_tb(tb, limit=0): + frames = traceback.extract_tb(tb, limit=limit) + frame_summary = frames[-1] + return [frame_summary[:2]] + + # synthesize what would be returned by traceback.extract_stack at the call to + # user's parse action 'func', so that we don't incur call penalty at parse time + + # fmt: off + LINE_DIFF = 7 + # IF ANY CODE CHANGES, EVEN JUST COMMENTS OR BLANK LINES, BETWEEN THE NEXT LINE AND + # THE CALL TO FUNC INSIDE WRAPPER, LINE_DIFF MUST BE MODIFIED!!!! + _trim_arity_call_line = (_trim_arity_call_line or traceback.extract_stack(limit=2)[-1]) + pa_call_line_synth = (_trim_arity_call_line[0], _trim_arity_call_line[1] + LINE_DIFF) + + def wrapper(*args): + nonlocal found_arity, limit + while 1: + try: + ret = func(*args[limit:]) + found_arity = True + return ret + except TypeError as te: + # re-raise TypeErrors if they did not come from our arity testing + if found_arity: + raise + else: + tb = te.__traceback__ + trim_arity_type_error = ( + extract_tb(tb, limit=2)[-1][:2] == pa_call_line_synth + ) + del tb + + if trim_arity_type_error: + if limit < max_limit: + limit += 1 + continue + + raise + # fmt: on + + # copy func name to wrapper for sensible debug output + # (can't use functools.wraps, since that messes with function signature) + func_name = getattr(func, "__name__", getattr(func, "__class__").__name__) + wrapper.__name__ = func_name + wrapper.__doc__ = func.__doc__ + + return wrapper + + +def condition_as_parse_action( + fn: ParseCondition, message: str = None, fatal: bool = False +) -> ParseAction: + """ + Function to convert a simple predicate function that returns ``True`` or ``False`` + into a parse action. Can be used in places when a parse action is required + and :class:`ParserElement.add_condition` cannot be used (such as when adding a condition + to an operator level in :class:`infix_notation`). + + Optional keyword arguments: + + - ``message`` - define a custom message to be used in the raised exception + - ``fatal`` - if True, will raise :class:`ParseFatalException` to stop parsing immediately; + otherwise will raise :class:`ParseException` + + """ + msg = message if message is not None else "failed user-defined condition" + exc_type = ParseFatalException if fatal else ParseException + fn = _trim_arity(fn) + + @wraps(fn) + def pa(s, l, t): + if not bool(fn(s, l, t)): + raise exc_type(s, l, msg) + + return pa + + +def _default_start_debug_action( + instring: str, loc: int, expr: "ParserElement", cache_hit: bool = False +): + cache_hit_str = "*" if cache_hit else "" + print( + ( + "{}Match {} at loc {}({},{})\n {}\n {}^".format( + cache_hit_str, + expr, + loc, + lineno(loc, instring), + col(loc, instring), + line(loc, instring), + " " * (col(loc, instring) - 1), + ) + ) + ) + + +def _default_success_debug_action( + instring: str, + startloc: int, + endloc: int, + expr: "ParserElement", + toks: ParseResults, + cache_hit: bool = False, +): + cache_hit_str = "*" if cache_hit else "" + print("{}Matched {} -> {}".format(cache_hit_str, expr, toks.as_list())) + + +def _default_exception_debug_action( + instring: str, + loc: int, + expr: "ParserElement", + exc: Exception, + cache_hit: bool = False, +): + cache_hit_str = "*" if cache_hit else "" + print( + "{}Match {} failed, {} raised: {}".format( + cache_hit_str, expr, type(exc).__name__, exc + ) + ) + + +def null_debug_action(*args): + """'Do-nothing' debug action, to suppress debugging output during parsing.""" + + +class ParserElement(ABC): + """Abstract base level parser element class.""" + + DEFAULT_WHITE_CHARS: str = " \n\t\r" + verbose_stacktrace: bool = False + _literalStringClass: typing.Optional[type] = None + + @staticmethod + def set_default_whitespace_chars(chars: str) -> None: + r""" + Overrides the default whitespace chars + + Example:: + + # default whitespace chars are space, <TAB> and newline + Word(alphas)[1, ...].parse_string("abc def\nghi jkl") # -> ['abc', 'def', 'ghi', 'jkl'] + + # change to just treat newline as significant + ParserElement.set_default_whitespace_chars(" \t") + Word(alphas)[1, ...].parse_string("abc def\nghi jkl") # -> ['abc', 'def'] + """ + ParserElement.DEFAULT_WHITE_CHARS = chars + + # update whitespace all parse expressions defined in this module + for expr in _builtin_exprs: + if expr.copyDefaultWhiteChars: + expr.whiteChars = set(chars) + + @staticmethod + def inline_literals_using(cls: type) -> None: + """ + Set class to be used for inclusion of string literals into a parser. + + Example:: + + # default literal class used is Literal + integer = Word(nums) + date_str = integer("year") + '/' + integer("month") + '/' + integer("day") + + date_str.parse_string("1999/12/31") # -> ['1999', '/', '12', '/', '31'] + + + # change to Suppress + ParserElement.inline_literals_using(Suppress) + date_str = integer("year") + '/' + integer("month") + '/' + integer("day") + + date_str.parse_string("1999/12/31") # -> ['1999', '12', '31'] + """ + ParserElement._literalStringClass = cls + + class DebugActions(NamedTuple): + debug_try: typing.Optional[DebugStartAction] + debug_match: typing.Optional[DebugSuccessAction] + debug_fail: typing.Optional[DebugExceptionAction] + + def __init__(self, savelist: bool = False): + self.parseAction: List[ParseAction] = list() + self.failAction: typing.Optional[ParseFailAction] = None + self.customName = None + self._defaultName = None + self.resultsName = None + self.saveAsList = savelist + self.skipWhitespace = True + self.whiteChars = set(ParserElement.DEFAULT_WHITE_CHARS) + self.copyDefaultWhiteChars = True + # used when checking for left-recursion + self.mayReturnEmpty = False + self.keepTabs = False + self.ignoreExprs: List["ParserElement"] = list() + self.debug = False + self.streamlined = False + # optimize exception handling for subclasses that don't advance parse index + self.mayIndexError = True + self.errmsg = "" + # mark results names as modal (report only last) or cumulative (list all) + self.modalResults = True + # custom debug actions + self.debugActions = self.DebugActions(None, None, None) + # avoid redundant calls to preParse + self.callPreparse = True + self.callDuringTry = False + self.suppress_warnings_: List[Diagnostics] = [] + + def suppress_warning(self, warning_type: Diagnostics) -> "ParserElement": + """ + Suppress warnings emitted for a particular diagnostic on this expression. + + Example:: + + base = pp.Forward() + base.suppress_warning(Diagnostics.warn_on_parse_using_empty_Forward) + + # statement would normally raise a warning, but is now suppressed + print(base.parseString("x")) + + """ + self.suppress_warnings_.append(warning_type) + return self + + def copy(self) -> "ParserElement": + """ + Make a copy of this :class:`ParserElement`. Useful for defining + different parse actions for the same parsing pattern, using copies of + the original parse element. + + Example:: + + integer = Word(nums).set_parse_action(lambda toks: int(toks[0])) + integerK = integer.copy().add_parse_action(lambda toks: toks[0] * 1024) + Suppress("K") + integerM = integer.copy().add_parse_action(lambda toks: toks[0] * 1024 * 1024) + Suppress("M") + + print((integerK | integerM | integer)[1, ...].parse_string("5K 100 640K 256M")) + + prints:: + + [5120, 100, 655360, 268435456] + + Equivalent form of ``expr.copy()`` is just ``expr()``:: + + integerM = integer().add_parse_action(lambda toks: toks[0] * 1024 * 1024) + Suppress("M") + """ + cpy = copy.copy(self) + cpy.parseAction = self.parseAction[:] + cpy.ignoreExprs = self.ignoreExprs[:] + if self.copyDefaultWhiteChars: + cpy.whiteChars = set(ParserElement.DEFAULT_WHITE_CHARS) + return cpy + + def set_results_name( + self, name: str, list_all_matches: bool = False, *, listAllMatches: bool = False + ) -> "ParserElement": + """ + Define name for referencing matching tokens as a nested attribute + of the returned parse results. + + Normally, results names are assigned as you would assign keys in a dict: + any existing value is overwritten by later values. If it is necessary to + keep all values captured for a particular results name, call ``set_results_name`` + with ``list_all_matches`` = True. + + NOTE: ``set_results_name`` returns a *copy* of the original :class:`ParserElement` object; + this is so that the client can define a basic element, such as an + integer, and reference it in multiple places with different names. + + You can also set results names using the abbreviated syntax, + ``expr("name")`` in place of ``expr.set_results_name("name")`` + - see :class:`__call__`. If ``list_all_matches`` is required, use + ``expr("name*")``. + + Example:: + + date_str = (integer.set_results_name("year") + '/' + + integer.set_results_name("month") + '/' + + integer.set_results_name("day")) + + # equivalent form: + date_str = integer("year") + '/' + integer("month") + '/' + integer("day") + """ + listAllMatches = listAllMatches or list_all_matches + return self._setResultsName(name, listAllMatches) + + def _setResultsName(self, name, listAllMatches=False): + if name is None: + return self + newself = self.copy() + if name.endswith("*"): + name = name[:-1] + listAllMatches = True + newself.resultsName = name + newself.modalResults = not listAllMatches + return newself + + def set_break(self, break_flag: bool = True) -> "ParserElement": + """ + Method to invoke the Python pdb debugger when this element is + about to be parsed. Set ``break_flag`` to ``True`` to enable, ``False`` to + disable. + """ + if break_flag: + _parseMethod = self._parse + + def breaker(instring, loc, doActions=True, callPreParse=True): + import pdb + + # this call to pdb.set_trace() is intentional, not a checkin error + pdb.set_trace() + return _parseMethod(instring, loc, doActions, callPreParse) + + breaker._originalParseMethod = _parseMethod + self._parse = breaker + else: + if hasattr(self._parse, "_originalParseMethod"): + self._parse = self._parse._originalParseMethod + return self + + def set_parse_action(self, *fns: ParseAction, **kwargs) -> "ParserElement": + """ + Define one or more actions to perform when successfully matching parse element definition. + + Parse actions can be called to perform data conversions, do extra validation, + update external data structures, or enhance or replace the parsed tokens. + Each parse action ``fn`` is a callable method with 0-3 arguments, called as + ``fn(s, loc, toks)`` , ``fn(loc, toks)`` , ``fn(toks)`` , or just ``fn()`` , where: + + - s = the original string being parsed (see note below) + - loc = the location of the matching substring + - toks = a list of the matched tokens, packaged as a :class:`ParseResults` object + + The parsed tokens are passed to the parse action as ParseResults. They can be + modified in place using list-style append, extend, and pop operations to update + the parsed list elements; and with dictionary-style item set and del operations + to add, update, or remove any named results. If the tokens are modified in place, + it is not necessary to return them with a return statement. + + Parse actions can also completely replace the given tokens, with another ``ParseResults`` + object, or with some entirely different object (common for parse actions that perform data + conversions). A convenient way to build a new parse result is to define the values + using a dict, and then create the return value using :class:`ParseResults.from_dict`. + + If None is passed as the ``fn`` parse action, all previously added parse actions for this + expression are cleared. + + Optional keyword arguments: + + - call_during_try = (default= ``False``) indicate if parse action should be run during + lookaheads and alternate testing. For parse actions that have side effects, it is + important to only call the parse action once it is determined that it is being + called as part of a successful parse. For parse actions that perform additional + validation, then call_during_try should be passed as True, so that the validation + code is included in the preliminary "try" parses. + + Note: the default parsing behavior is to expand tabs in the input string + before starting the parsing process. See :class:`parse_string` for more + information on parsing strings containing ``<TAB>`` s, and suggested + methods to maintain a consistent view of the parsed string, the parse + location, and line and column positions within the parsed string. + + Example:: + + # parse dates in the form YYYY/MM/DD + + # use parse action to convert toks from str to int at parse time + def convert_to_int(toks): + return int(toks[0]) + + # use a parse action to verify that the date is a valid date + def is_valid_date(instring, loc, toks): + from datetime import date + year, month, day = toks[::2] + try: + date(year, month, day) + except ValueError: + raise ParseException(instring, loc, "invalid date given") + + integer = Word(nums) + date_str = integer + '/' + integer + '/' + integer + + # add parse actions + integer.set_parse_action(convert_to_int) + date_str.set_parse_action(is_valid_date) + + # note that integer fields are now ints, not strings + date_str.run_tests(''' + # successful parse - note that integer fields were converted to ints + 1999/12/31 + + # fail - invalid date + 1999/13/31 + ''') + """ + if list(fns) == [None]: + self.parseAction = [] + else: + if not all(callable(fn) for fn in fns): + raise TypeError("parse actions must be callable") + self.parseAction = [_trim_arity(fn) for fn in fns] + self.callDuringTry = kwargs.get( + "call_during_try", kwargs.get("callDuringTry", False) + ) + return self + + def add_parse_action(self, *fns: ParseAction, **kwargs) -> "ParserElement": + """ + Add one or more parse actions to expression's list of parse actions. See :class:`set_parse_action`. + + See examples in :class:`copy`. + """ + self.parseAction += [_trim_arity(fn) for fn in fns] + self.callDuringTry = self.callDuringTry or kwargs.get( + "call_during_try", kwargs.get("callDuringTry", False) + ) + return self + + def add_condition(self, *fns: ParseCondition, **kwargs) -> "ParserElement": + """Add a boolean predicate function to expression's list of parse actions. See + :class:`set_parse_action` for function call signatures. Unlike ``set_parse_action``, + functions passed to ``add_condition`` need to return boolean success/fail of the condition. + + Optional keyword arguments: + + - message = define a custom message to be used in the raised exception + - fatal = if True, will raise ParseFatalException to stop parsing immediately; otherwise will raise + ParseException + - call_during_try = boolean to indicate if this method should be called during internal tryParse calls, + default=False + + Example:: + + integer = Word(nums).set_parse_action(lambda toks: int(toks[0])) + year_int = integer.copy() + year_int.add_condition(lambda toks: toks[0] >= 2000, message="Only support years 2000 and later") + date_str = year_int + '/' + integer + '/' + integer + + result = date_str.parse_string("1999/12/31") # -> Exception: Only support years 2000 and later (at char 0), + (line:1, col:1) + """ + for fn in fns: + self.parseAction.append( + condition_as_parse_action( + fn, message=kwargs.get("message"), fatal=kwargs.get("fatal", False) + ) + ) + + self.callDuringTry = self.callDuringTry or kwargs.get( + "call_during_try", kwargs.get("callDuringTry", False) + ) + return self + + def set_fail_action(self, fn: ParseFailAction) -> "ParserElement": + """ + Define action to perform if parsing fails at this expression. + Fail acton fn is a callable function that takes the arguments + ``fn(s, loc, expr, err)`` where: + + - s = string being parsed + - loc = location where expression match was attempted and failed + - expr = the parse expression that failed + - err = the exception thrown + + The function returns no value. It may throw :class:`ParseFatalException` + if it is desired to stop parsing immediately.""" + self.failAction = fn + return self + + def _skipIgnorables(self, instring, loc): + exprsFound = True + while exprsFound: + exprsFound = False + for e in self.ignoreExprs: + try: + while 1: + loc, dummy = e._parse(instring, loc) + exprsFound = True + except ParseException: + pass + return loc + + def preParse(self, instring, loc): + if self.ignoreExprs: + loc = self._skipIgnorables(instring, loc) + + if self.skipWhitespace: + instrlen = len(instring) + white_chars = self.whiteChars + while loc < instrlen and instring[loc] in white_chars: + loc += 1 + + return loc + + def parseImpl(self, instring, loc, doActions=True): + return loc, [] + + def postParse(self, instring, loc, tokenlist): + return tokenlist + + # @profile + def _parseNoCache( + self, instring, loc, doActions=True, callPreParse=True + ) -> Tuple[int, ParseResults]: + TRY, MATCH, FAIL = 0, 1, 2 + debugging = self.debug # and doActions) + len_instring = len(instring) + + if debugging or self.failAction: + # print("Match {} at loc {}({}, {})".format(self, loc, lineno(loc, instring), col(loc, instring))) + try: + if callPreParse and self.callPreparse: + pre_loc = self.preParse(instring, loc) + else: + pre_loc = loc + tokens_start = pre_loc + if self.debugActions.debug_try: + self.debugActions.debug_try(instring, tokens_start, self, False) + if self.mayIndexError or pre_loc >= len_instring: + try: + loc, tokens = self.parseImpl(instring, pre_loc, doActions) + except IndexError: + raise ParseException(instring, len_instring, self.errmsg, self) + else: + loc, tokens = self.parseImpl(instring, pre_loc, doActions) + except Exception as err: + # print("Exception raised:", err) + if self.debugActions.debug_fail: + self.debugActions.debug_fail( + instring, tokens_start, self, err, False + ) + if self.failAction: + self.failAction(instring, tokens_start, self, err) + raise + else: + if callPreParse and self.callPreparse: + pre_loc = self.preParse(instring, loc) + else: + pre_loc = loc + tokens_start = pre_loc + if self.mayIndexError or pre_loc >= len_instring: + try: + loc, tokens = self.parseImpl(instring, pre_loc, doActions) + except IndexError: + raise ParseException(instring, len_instring, self.errmsg, self) + else: + loc, tokens = self.parseImpl(instring, pre_loc, doActions) + + tokens = self.postParse(instring, loc, tokens) + + ret_tokens = ParseResults( + tokens, self.resultsName, asList=self.saveAsList, modal=self.modalResults + ) + if self.parseAction and (doActions or self.callDuringTry): + if debugging: + try: + for fn in self.parseAction: + try: + tokens = fn(instring, tokens_start, ret_tokens) + except IndexError as parse_action_exc: + exc = ParseException("exception raised in parse action") + raise exc from parse_action_exc + + if tokens is not None and tokens is not ret_tokens: + ret_tokens = ParseResults( + tokens, + self.resultsName, + asList=self.saveAsList + and isinstance(tokens, (ParseResults, list)), + modal=self.modalResults, + ) + except Exception as err: + # print "Exception raised in user parse action:", err + if self.debugActions.debug_fail: + self.debugActions.debug_fail( + instring, tokens_start, self, err, False + ) + raise + else: + for fn in self.parseAction: + try: + tokens = fn(instring, tokens_start, ret_tokens) + except IndexError as parse_action_exc: + exc = ParseException("exception raised in parse action") + raise exc from parse_action_exc + + if tokens is not None and tokens is not ret_tokens: + ret_tokens = ParseResults( + tokens, + self.resultsName, + asList=self.saveAsList + and isinstance(tokens, (ParseResults, list)), + modal=self.modalResults, + ) + if debugging: + # print("Matched", self, "->", ret_tokens.as_list()) + if self.debugActions.debug_match: + self.debugActions.debug_match( + instring, tokens_start, loc, self, ret_tokens, False + ) + + return loc, ret_tokens + + def try_parse(self, instring: str, loc: int, raise_fatal: bool = False) -> int: + try: + return self._parse(instring, loc, doActions=False)[0] + except ParseFatalException: + if raise_fatal: + raise + raise ParseException(instring, loc, self.errmsg, self) + + def can_parse_next(self, instring: str, loc: int) -> bool: + try: + self.try_parse(instring, loc) + except (ParseException, IndexError): + return False + else: + return True + + # cache for left-recursion in Forward references + recursion_lock = RLock() + recursion_memos: typing.Dict[ + Tuple[int, "Forward", bool], Tuple[int, Union[ParseResults, Exception]] + ] = {} + + # argument cache for optimizing repeated calls when backtracking through recursive expressions + packrat_cache = ( + {} + ) # this is set later by enabled_packrat(); this is here so that reset_cache() doesn't fail + packrat_cache_lock = RLock() + packrat_cache_stats = [0, 0] + + # this method gets repeatedly called during backtracking with the same arguments - + # we can cache these arguments and save ourselves the trouble of re-parsing the contained expression + def _parseCache( + self, instring, loc, doActions=True, callPreParse=True + ) -> Tuple[int, ParseResults]: + HIT, MISS = 0, 1 + TRY, MATCH, FAIL = 0, 1, 2 + lookup = (self, instring, loc, callPreParse, doActions) + with ParserElement.packrat_cache_lock: + cache = ParserElement.packrat_cache + value = cache.get(lookup) + if value is cache.not_in_cache: + ParserElement.packrat_cache_stats[MISS] += 1 + try: + value = self._parseNoCache(instring, loc, doActions, callPreParse) + except ParseBaseException as pe: + # cache a copy of the exception, without the traceback + cache.set(lookup, pe.__class__(*pe.args)) + raise + else: + cache.set(lookup, (value[0], value[1].copy(), loc)) + return value + else: + ParserElement.packrat_cache_stats[HIT] += 1 + if self.debug and self.debugActions.debug_try: + try: + self.debugActions.debug_try(instring, loc, self, cache_hit=True) + except TypeError: + pass + if isinstance(value, Exception): + if self.debug and self.debugActions.debug_fail: + try: + self.debugActions.debug_fail( + instring, loc, self, value, cache_hit=True + ) + except TypeError: + pass + raise value + + loc_, result, endloc = value[0], value[1].copy(), value[2] + if self.debug and self.debugActions.debug_match: + try: + self.debugActions.debug_match( + instring, loc_, endloc, self, result, cache_hit=True + ) + except TypeError: + pass + + return loc_, result + + _parse = _parseNoCache + + @staticmethod + def reset_cache() -> None: + ParserElement.packrat_cache.clear() + ParserElement.packrat_cache_stats[:] = [0] * len( + ParserElement.packrat_cache_stats + ) + ParserElement.recursion_memos.clear() + + _packratEnabled = False + _left_recursion_enabled = False + + @staticmethod + def disable_memoization() -> None: + """ + Disables active Packrat or Left Recursion parsing and their memoization + + This method also works if neither Packrat nor Left Recursion are enabled. + This makes it safe to call before activating Packrat nor Left Recursion + to clear any previous settings. + """ + ParserElement.reset_cache() + ParserElement._left_recursion_enabled = False + ParserElement._packratEnabled = False + ParserElement._parse = ParserElement._parseNoCache + + @staticmethod + def enable_left_recursion( + cache_size_limit: typing.Optional[int] = None, *, force=False + ) -> None: + """ + Enables "bounded recursion" parsing, which allows for both direct and indirect + left-recursion. During parsing, left-recursive :class:`Forward` elements are + repeatedly matched with a fixed recursion depth that is gradually increased + until finding the longest match. + + Example:: + + import pyparsing as pp + pp.ParserElement.enable_left_recursion() + + E = pp.Forward("E") + num = pp.Word(pp.nums) + # match `num`, or `num '+' num`, or `num '+' num '+' num`, ... + E <<= E + '+' - num | num + + print(E.parse_string("1+2+3")) + + Recursion search naturally memoizes matches of ``Forward`` elements and may + thus skip reevaluation of parse actions during backtracking. This may break + programs with parse actions which rely on strict ordering of side-effects. + + Parameters: + + - cache_size_limit - (default=``None``) - memoize at most this many + ``Forward`` elements during matching; if ``None`` (the default), + memoize all ``Forward`` elements. + + Bounded Recursion parsing works similar but not identical to Packrat parsing, + thus the two cannot be used together. Use ``force=True`` to disable any + previous, conflicting settings. + """ + if force: + ParserElement.disable_memoization() + elif ParserElement._packratEnabled: + raise RuntimeError("Packrat and Bounded Recursion are not compatible") + if cache_size_limit is None: + ParserElement.recursion_memos = _UnboundedMemo() + elif cache_size_limit > 0: + ParserElement.recursion_memos = _LRUMemo(capacity=cache_size_limit) + else: + raise NotImplementedError("Memo size of %s" % cache_size_limit) + ParserElement._left_recursion_enabled = True + + @staticmethod + def enable_packrat(cache_size_limit: int = 128, *, force: bool = False) -> None: + """ + Enables "packrat" parsing, which adds memoizing to the parsing logic. + Repeated parse attempts at the same string location (which happens + often in many complex grammars) can immediately return a cached value, + instead of re-executing parsing/validating code. Memoizing is done of + both valid results and parsing exceptions. + + Parameters: + + - cache_size_limit - (default= ``128``) - if an integer value is provided + will limit the size of the packrat cache; if None is passed, then + the cache size will be unbounded; if 0 is passed, the cache will + be effectively disabled. + + This speedup may break existing programs that use parse actions that + have side-effects. For this reason, packrat parsing is disabled when + you first import pyparsing. To activate the packrat feature, your + program must call the class method :class:`ParserElement.enable_packrat`. + For best results, call ``enable_packrat()`` immediately after + importing pyparsing. + + Example:: + + import pyparsing + pyparsing.ParserElement.enable_packrat() + + Packrat parsing works similar but not identical to Bounded Recursion parsing, + thus the two cannot be used together. Use ``force=True`` to disable any + previous, conflicting settings. + """ + if force: + ParserElement.disable_memoization() + elif ParserElement._left_recursion_enabled: + raise RuntimeError("Packrat and Bounded Recursion are not compatible") + if not ParserElement._packratEnabled: + ParserElement._packratEnabled = True + if cache_size_limit is None: + ParserElement.packrat_cache = _UnboundedCache() + else: + ParserElement.packrat_cache = _FifoCache(cache_size_limit) + ParserElement._parse = ParserElement._parseCache + + def parse_string( + self, instring: str, parse_all: bool = False, *, parseAll: bool = False + ) -> ParseResults: + """ + Parse a string with respect to the parser definition. This function is intended as the primary interface to the + client code. + + :param instring: The input string to be parsed. + :param parse_all: If set, the entire input string must match the grammar. + :param parseAll: retained for pre-PEP8 compatibility, will be removed in a future release. + :raises ParseException: Raised if ``parse_all`` is set and the input string does not match the whole grammar. + :returns: the parsed data as a :class:`ParseResults` object, which may be accessed as a `list`, a `dict`, or + an object with attributes if the given parser includes results names. + + If the input string is required to match the entire grammar, ``parse_all`` flag must be set to ``True``. This + is also equivalent to ending the grammar with :class:`StringEnd`(). + + To report proper column numbers, ``parse_string`` operates on a copy of the input string where all tabs are + converted to spaces (8 spaces per tab, as per the default in ``string.expandtabs``). If the input string + contains tabs and the grammar uses parse actions that use the ``loc`` argument to index into the string + being parsed, one can ensure a consistent view of the input string by doing one of the following: + + - calling ``parse_with_tabs`` on your grammar before calling ``parse_string`` (see :class:`parse_with_tabs`), + - define your parse action using the full ``(s,loc,toks)`` signature, and reference the input string using the + parse action's ``s`` argument, or + - explicitly expand the tabs in your input string before calling ``parse_string``. + + Examples: + + By default, partial matches are OK. + + >>> res = Word('a').parse_string('aaaaabaaa') + >>> print(res) + ['aaaaa'] + + The parsing behavior varies by the inheriting class of this abstract class. Please refer to the children + directly to see more examples. + + It raises an exception if parse_all flag is set and instring does not match the whole grammar. + + >>> res = Word('a').parse_string('aaaaabaaa', parse_all=True) + Traceback (most recent call last): + ... + pyparsing.ParseException: Expected end of text, found 'b' (at char 5), (line:1, col:6) + """ + parseAll = parse_all or parseAll + + ParserElement.reset_cache() + if not self.streamlined: + self.streamline() + for e in self.ignoreExprs: + e.streamline() + if not self.keepTabs: + instring = instring.expandtabs() + try: + loc, tokens = self._parse(instring, 0) + if parseAll: + loc = self.preParse(instring, loc) + se = Empty() + StringEnd() + se._parse(instring, loc) + except ParseBaseException as exc: + if ParserElement.verbose_stacktrace: + raise + else: + # catch and re-raise exception from here, clearing out pyparsing internal stack trace + raise exc.with_traceback(None) + else: + return tokens + + def scan_string( + self, + instring: str, + max_matches: int = _MAX_INT, + overlap: bool = False, + *, + debug: bool = False, + maxMatches: int = _MAX_INT, + ) -> Generator[Tuple[ParseResults, int, int], None, None]: + """ + Scan the input string for expression matches. Each match will return the + matching tokens, start location, and end location. May be called with optional + ``max_matches`` argument, to clip scanning after 'n' matches are found. If + ``overlap`` is specified, then overlapping matches will be reported. + + Note that the start and end locations are reported relative to the string + being parsed. See :class:`parse_string` for more information on parsing + strings with embedded tabs. + + Example:: + + source = "sldjf123lsdjjkf345sldkjf879lkjsfd987" + print(source) + for tokens, start, end in Word(alphas).scan_string(source): + print(' '*start + '^'*(end-start)) + print(' '*start + tokens[0]) + + prints:: + + sldjf123lsdjjkf345sldkjf879lkjsfd987 + ^^^^^ + sldjf + ^^^^^^^ + lsdjjkf + ^^^^^^ + sldkjf + ^^^^^^ + lkjsfd + """ + maxMatches = min(maxMatches, max_matches) + if not self.streamlined: + self.streamline() + for e in self.ignoreExprs: + e.streamline() + + if not self.keepTabs: + instring = str(instring).expandtabs() + instrlen = len(instring) + loc = 0 + preparseFn = self.preParse + parseFn = self._parse + ParserElement.resetCache() + matches = 0 + try: + while loc <= instrlen and matches < maxMatches: + try: + preloc = preparseFn(instring, loc) + nextLoc, tokens = parseFn(instring, preloc, callPreParse=False) + except ParseException: + loc = preloc + 1 + else: + if nextLoc > loc: + matches += 1 + if debug: + print( + { + "tokens": tokens.asList(), + "start": preloc, + "end": nextLoc, + } + ) + yield tokens, preloc, nextLoc + if overlap: + nextloc = preparseFn(instring, loc) + if nextloc > loc: + loc = nextLoc + else: + loc += 1 + else: + loc = nextLoc + else: + loc = preloc + 1 + except ParseBaseException as exc: + if ParserElement.verbose_stacktrace: + raise + else: + # catch and re-raise exception from here, clears out pyparsing internal stack trace + raise exc.with_traceback(None) + + def transform_string(self, instring: str, *, debug: bool = False) -> str: + """ + Extension to :class:`scan_string`, to modify matching text with modified tokens that may + be returned from a parse action. To use ``transform_string``, define a grammar and + attach a parse action to it that modifies the returned token list. + Invoking ``transform_string()`` on a target string will then scan for matches, + and replace the matched text patterns according to the logic in the parse + action. ``transform_string()`` returns the resulting transformed string. + + Example:: + + wd = Word(alphas) + wd.set_parse_action(lambda toks: toks[0].title()) + + print(wd.transform_string("now is the winter of our discontent made glorious summer by this sun of york.")) + + prints:: + + Now Is The Winter Of Our Discontent Made Glorious Summer By This Sun Of York. + """ + out: List[str] = [] + lastE = 0 + # force preservation of <TAB>s, to minimize unwanted transformation of string, and to + # keep string locs straight between transform_string and scan_string + self.keepTabs = True + try: + for t, s, e in self.scan_string(instring, debug=debug): + out.append(instring[lastE:s]) + if t: + if isinstance(t, ParseResults): + out += t.as_list() + elif isinstance(t, Iterable) and not isinstance(t, str_type): + out.extend(t) + else: + out.append(t) + lastE = e + out.append(instring[lastE:]) + out = [o for o in out if o] + return "".join([str(s) for s in _flatten(out)]) + except ParseBaseException as exc: + if ParserElement.verbose_stacktrace: + raise + else: + # catch and re-raise exception from here, clears out pyparsing internal stack trace + raise exc.with_traceback(None) + + def search_string( + self, + instring: str, + max_matches: int = _MAX_INT, + *, + debug: bool = False, + maxMatches: int = _MAX_INT, + ) -> ParseResults: + """ + Another extension to :class:`scan_string`, simplifying the access to the tokens found + to match the given parse expression. May be called with optional + ``max_matches`` argument, to clip searching after 'n' matches are found. + + Example:: + + # a capitalized word starts with an uppercase letter, followed by zero or more lowercase letters + cap_word = Word(alphas.upper(), alphas.lower()) + + print(cap_word.search_string("More than Iron, more than Lead, more than Gold I need Electricity")) + + # the sum() builtin can be used to merge results into a single ParseResults object + print(sum(cap_word.search_string("More than Iron, more than Lead, more than Gold I need Electricity"))) + + prints:: + + [['More'], ['Iron'], ['Lead'], ['Gold'], ['I'], ['Electricity']] + ['More', 'Iron', 'Lead', 'Gold', 'I', 'Electricity'] + """ + maxMatches = min(maxMatches, max_matches) + try: + return ParseResults( + [t for t, s, e in self.scan_string(instring, maxMatches, debug=debug)] + ) + except ParseBaseException as exc: + if ParserElement.verbose_stacktrace: + raise + else: + # catch and re-raise exception from here, clears out pyparsing internal stack trace + raise exc.with_traceback(None) + + def split( + self, + instring: str, + maxsplit: int = _MAX_INT, + include_separators: bool = False, + *, + includeSeparators=False, + ) -> Generator[str, None, None]: + """ + Generator method to split a string using the given expression as a separator. + May be called with optional ``maxsplit`` argument, to limit the number of splits; + and the optional ``include_separators`` argument (default= ``False``), if the separating + matching text should be included in the split results. + + Example:: + + punc = one_of(list(".,;:/-!?")) + print(list(punc.split("This, this?, this sentence, is badly punctuated!"))) + + prints:: + + ['This', ' this', '', ' this sentence', ' is badly punctuated', ''] + """ + includeSeparators = includeSeparators or include_separators + last = 0 + for t, s, e in self.scan_string(instring, max_matches=maxsplit): + yield instring[last:s] + if includeSeparators: + yield t[0] + last = e + yield instring[last:] + + def __add__(self, other) -> "ParserElement": + """ + Implementation of ``+`` operator - returns :class:`And`. Adding strings to a :class:`ParserElement` + converts them to :class:`Literal`s by default. + + Example:: + + greet = Word(alphas) + "," + Word(alphas) + "!" + hello = "Hello, World!" + print(hello, "->", greet.parse_string(hello)) + + prints:: + + Hello, World! -> ['Hello', ',', 'World', '!'] + + ``...`` may be used as a parse expression as a short form of :class:`SkipTo`. + + Literal('start') + ... + Literal('end') + + is equivalent to: + + Literal('start') + SkipTo('end')("_skipped*") + Literal('end') + + Note that the skipped text is returned with '_skipped' as a results name, + and to support having multiple skips in the same parser, the value returned is + a list of all skipped text. + """ + if other is Ellipsis: + return _PendingSkip(self) + + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return And([self, other]) + + def __radd__(self, other) -> "ParserElement": + """ + Implementation of ``+`` operator when left operand is not a :class:`ParserElement` + """ + if other is Ellipsis: + return SkipTo(self)("_skipped*") + self + + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return other + self + + def __sub__(self, other) -> "ParserElement": + """ + Implementation of ``-`` operator, returns :class:`And` with error stop + """ + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return self + And._ErrorStop() + other + + def __rsub__(self, other) -> "ParserElement": + """ + Implementation of ``-`` operator when left operand is not a :class:`ParserElement` + """ + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return other - self + + def __mul__(self, other) -> "ParserElement": + """ + Implementation of ``*`` operator, allows use of ``expr * 3`` in place of + ``expr + expr + expr``. Expressions may also be multiplied by a 2-integer + tuple, similar to ``{min, max}`` multipliers in regular expressions. Tuples + may also include ``None`` as in: + - ``expr*(n, None)`` or ``expr*(n, )`` is equivalent + to ``expr*n + ZeroOrMore(expr)`` + (read as "at least n instances of ``expr``") + - ``expr*(None, n)`` is equivalent to ``expr*(0, n)`` + (read as "0 to n instances of ``expr``") + - ``expr*(None, None)`` is equivalent to ``ZeroOrMore(expr)`` + - ``expr*(1, None)`` is equivalent to ``OneOrMore(expr)`` + + Note that ``expr*(None, n)`` does not raise an exception if + more than n exprs exist in the input stream; that is, + ``expr*(None, n)`` does not enforce a maximum number of expr + occurrences. If this behavior is desired, then write + ``expr*(None, n) + ~expr`` + """ + if other is Ellipsis: + other = (0, None) + elif isinstance(other, tuple) and other[:1] == (Ellipsis,): + other = ((0,) + other[1:] + (None,))[:2] + + if isinstance(other, int): + minElements, optElements = other, 0 + elif isinstance(other, tuple): + other = tuple(o if o is not Ellipsis else None for o in other) + other = (other + (None, None))[:2] + if other[0] is None: + other = (0, other[1]) + if isinstance(other[0], int) and other[1] is None: + if other[0] == 0: + return ZeroOrMore(self) + if other[0] == 1: + return OneOrMore(self) + else: + return self * other[0] + ZeroOrMore(self) + elif isinstance(other[0], int) and isinstance(other[1], int): + minElements, optElements = other + optElements -= minElements + else: + raise TypeError( + "cannot multiply ParserElement and ({}) objects".format( + ",".join(type(item).__name__ for item in other) + ) + ) + else: + raise TypeError( + "cannot multiply ParserElement and {} objects".format( + type(other).__name__ + ) + ) + + if minElements < 0: + raise ValueError("cannot multiply ParserElement by negative value") + if optElements < 0: + raise ValueError( + "second tuple value must be greater or equal to first tuple value" + ) + if minElements == optElements == 0: + return And([]) + + if optElements: + + def makeOptionalList(n): + if n > 1: + return Opt(self + makeOptionalList(n - 1)) + else: + return Opt(self) + + if minElements: + if minElements == 1: + ret = self + makeOptionalList(optElements) + else: + ret = And([self] * minElements) + makeOptionalList(optElements) + else: + ret = makeOptionalList(optElements) + else: + if minElements == 1: + ret = self + else: + ret = And([self] * minElements) + return ret + + def __rmul__(self, other) -> "ParserElement": + return self.__mul__(other) + + def __or__(self, other) -> "ParserElement": + """ + Implementation of ``|`` operator - returns :class:`MatchFirst` + """ + if other is Ellipsis: + return _PendingSkip(self, must_skip=True) + + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return MatchFirst([self, other]) + + def __ror__(self, other) -> "ParserElement": + """ + Implementation of ``|`` operator when left operand is not a :class:`ParserElement` + """ + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return other | self + + def __xor__(self, other) -> "ParserElement": + """ + Implementation of ``^`` operator - returns :class:`Or` + """ + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return Or([self, other]) + + def __rxor__(self, other) -> "ParserElement": + """ + Implementation of ``^`` operator when left operand is not a :class:`ParserElement` + """ + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return other ^ self + + def __and__(self, other) -> "ParserElement": + """ + Implementation of ``&`` operator - returns :class:`Each` + """ + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return Each([self, other]) + + def __rand__(self, other) -> "ParserElement": + """ + Implementation of ``&`` operator when left operand is not a :class:`ParserElement` + """ + if isinstance(other, str_type): + other = self._literalStringClass(other) + if not isinstance(other, ParserElement): + raise TypeError( + "Cannot combine element of type {} with ParserElement".format( + type(other).__name__ + ) + ) + return other & self + + def __invert__(self) -> "ParserElement": + """ + Implementation of ``~`` operator - returns :class:`NotAny` + """ + return NotAny(self) + + # disable __iter__ to override legacy use of sequential access to __getitem__ to + # iterate over a sequence + __iter__ = None + + def __getitem__(self, key): + """ + use ``[]`` indexing notation as a short form for expression repetition: + + - ``expr[n]`` is equivalent to ``expr*n`` + - ``expr[m, n]`` is equivalent to ``expr*(m, n)`` + - ``expr[n, ...]`` or ``expr[n,]`` is equivalent + to ``expr*n + ZeroOrMore(expr)`` + (read as "at least n instances of ``expr``") + - ``expr[..., n]`` is equivalent to ``expr*(0, n)`` + (read as "0 to n instances of ``expr``") + - ``expr[...]`` and ``expr[0, ...]`` are equivalent to ``ZeroOrMore(expr)`` + - ``expr[1, ...]`` is equivalent to ``OneOrMore(expr)`` + + ``None`` may be used in place of ``...``. + + Note that ``expr[..., n]`` and ``expr[m, n]``do not raise an exception + if more than ``n`` ``expr``s exist in the input stream. If this behavior is + desired, then write ``expr[..., n] + ~expr``. + """ + + # convert single arg keys to tuples + try: + if isinstance(key, str_type): + key = (key,) + iter(key) + except TypeError: + key = (key, key) + + if len(key) > 2: + raise TypeError( + "only 1 or 2 index arguments supported ({}{})".format( + key[:5], "... [{}]".format(len(key)) if len(key) > 5 else "" + ) + ) + + # clip to 2 elements + ret = self * tuple(key[:2]) + return ret + + def __call__(self, name: str = None) -> "ParserElement": + """ + Shortcut for :class:`set_results_name`, with ``list_all_matches=False``. + + If ``name`` is given with a trailing ``'*'`` character, then ``list_all_matches`` will be + passed as ``True``. + + If ``name` is omitted, same as calling :class:`copy`. + + Example:: + + # these are equivalent + userdata = Word(alphas).set_results_name("name") + Word(nums + "-").set_results_name("socsecno") + userdata = Word(alphas)("name") + Word(nums + "-")("socsecno") + """ + if name is not None: + return self._setResultsName(name) + else: + return self.copy() + + def suppress(self) -> "ParserElement": + """ + Suppresses the output of this :class:`ParserElement`; useful to keep punctuation from + cluttering up returned output. + """ + return Suppress(self) + + def ignore_whitespace(self, recursive: bool = True) -> "ParserElement": + """ + Enables the skipping of whitespace before matching the characters in the + :class:`ParserElement`'s defined pattern. + + :param recursive: If ``True`` (the default), also enable whitespace skipping in child elements (if any) + """ + self.skipWhitespace = True + return self + + def leave_whitespace(self, recursive: bool = True) -> "ParserElement": + """ + Disables the skipping of whitespace before matching the characters in the + :class:`ParserElement`'s defined pattern. This is normally only used internally by + the pyparsing module, but may be needed in some whitespace-sensitive grammars. + + :param recursive: If true (the default), also disable whitespace skipping in child elements (if any) + """ + self.skipWhitespace = False + return self + + def set_whitespace_chars( + self, chars: Union[Set[str], str], copy_defaults: bool = False + ) -> "ParserElement": + """ + Overrides the default whitespace chars + """ + self.skipWhitespace = True + self.whiteChars = set(chars) + self.copyDefaultWhiteChars = copy_defaults + return self + + def parse_with_tabs(self) -> "ParserElement": + """ + Overrides default behavior to expand ``<TAB>`` s to spaces before parsing the input string. + Must be called before ``parse_string`` when the input grammar contains elements that + match ``<TAB>`` characters. + """ + self.keepTabs = True + return self + + def ignore(self, other: "ParserElement") -> "ParserElement": + """ + Define expression to be ignored (e.g., comments) while doing pattern + matching; may be called repeatedly, to define multiple comment or other + ignorable patterns. + + Example:: + + patt = Word(alphas)[1, ...] + patt.parse_string('ablaj /* comment */ lskjd') + # -> ['ablaj'] + + patt.ignore(c_style_comment) + patt.parse_string('ablaj /* comment */ lskjd') + # -> ['ablaj', 'lskjd'] + """ + import typing + + if isinstance(other, str_type): + other = Suppress(other) + + if isinstance(other, Suppress): + if other not in self.ignoreExprs: + self.ignoreExprs.append(other) + else: + self.ignoreExprs.append(Suppress(other.copy())) + return self + + def set_debug_actions( + self, + start_action: DebugStartAction, + success_action: DebugSuccessAction, + exception_action: DebugExceptionAction, + ) -> "ParserElement": + """ + Customize display of debugging messages while doing pattern matching: + + - ``start_action`` - method to be called when an expression is about to be parsed; + should have the signature ``fn(input_string: str, location: int, expression: ParserElement, cache_hit: bool)`` + + - ``success_action`` - method to be called when an expression has successfully parsed; + should have the signature ``fn(input_string: str, start_location: int, end_location: int, expression: ParserELement, parsed_tokens: ParseResults, cache_hit: bool)`` + + - ``exception_action`` - method to be called when expression fails to parse; + should have the signature ``fn(input_string: str, location: int, expression: ParserElement, exception: Exception, cache_hit: bool)`` + """ + self.debugActions = self.DebugActions( + start_action or _default_start_debug_action, + success_action or _default_success_debug_action, + exception_action or _default_exception_debug_action, + ) + self.debug = True + return self + + def set_debug(self, flag: bool = True) -> "ParserElement": + """ + Enable display of debugging messages while doing pattern matching. + Set ``flag`` to ``True`` to enable, ``False`` to disable. + + Example:: + + wd = Word(alphas).set_name("alphaword") + integer = Word(nums).set_name("numword") + term = wd | integer + + # turn on debugging for wd + wd.set_debug() + + term[1, ...].parse_string("abc 123 xyz 890") + + prints:: + + Match alphaword at loc 0(1,1) + Matched alphaword -> ['abc'] + Match alphaword at loc 3(1,4) + Exception raised:Expected alphaword (at char 4), (line:1, col:5) + Match alphaword at loc 7(1,8) + Matched alphaword -> ['xyz'] + Match alphaword at loc 11(1,12) + Exception raised:Expected alphaword (at char 12), (line:1, col:13) + Match alphaword at loc 15(1,16) + Exception raised:Expected alphaword (at char 15), (line:1, col:16) + + The output shown is that produced by the default debug actions - custom debug actions can be + specified using :class:`set_debug_actions`. Prior to attempting + to match the ``wd`` expression, the debugging message ``"Match <exprname> at loc <n>(<line>,<col>)"`` + is shown. Then if the parse succeeds, a ``"Matched"`` message is shown, or an ``"Exception raised"`` + message is shown. Also note the use of :class:`set_name` to assign a human-readable name to the expression, + which makes debugging and exception messages easier to understand - for instance, the default + name created for the :class:`Word` expression without calling ``set_name`` is ``"W:(A-Za-z)"``. + """ + if flag: + self.set_debug_actions( + _default_start_debug_action, + _default_success_debug_action, + _default_exception_debug_action, + ) + else: + self.debug = False + return self + + @property + def default_name(self) -> str: + if self._defaultName is None: + self._defaultName = self._generateDefaultName() + return self._defaultName + + @abstractmethod + def _generateDefaultName(self): + """ + Child classes must define this method, which defines how the ``default_name`` is set. + """ + + def set_name(self, name: str) -> "ParserElement": + """ + Define name for this expression, makes debugging and exception messages clearer. + Example:: + Word(nums).parse_string("ABC") # -> Exception: Expected W:(0-9) (at char 0), (line:1, col:1) + Word(nums).set_name("integer").parse_string("ABC") # -> Exception: Expected integer (at char 0), (line:1, col:1) + """ + self.customName = name + self.errmsg = "Expected " + self.name + if __diag__.enable_debug_on_named_expressions: + self.set_debug() + return self + + @property + def name(self) -> str: + # This will use a user-defined name if available, but otherwise defaults back to the auto-generated name + return self.customName if self.customName is not None else self.default_name + + def __str__(self) -> str: + return self.name + + def __repr__(self) -> str: + return str(self) + + def streamline(self) -> "ParserElement": + self.streamlined = True + self._defaultName = None + return self + + def recurse(self) -> Sequence["ParserElement"]: + return [] + + def _checkRecursion(self, parseElementList): + subRecCheckList = parseElementList[:] + [self] + for e in self.recurse(): + e._checkRecursion(subRecCheckList) + + def validate(self, validateTrace=None) -> None: + """ + Check defined expressions for valid structure, check for infinite recursive definitions. + """ + self._checkRecursion([]) + + def parse_file( + self, + file_or_filename: Union[str, Path, TextIO], + encoding: str = "utf-8", + parse_all: bool = False, + *, + parseAll: bool = False, + ) -> ParseResults: + """ + Execute the parse expression on the given file or filename. + If a filename is specified (instead of a file object), + the entire file is opened, read, and closed before parsing. + """ + parseAll = parseAll or parse_all + try: + file_contents = file_or_filename.read() + except AttributeError: + with open(file_or_filename, "r", encoding=encoding) as f: + file_contents = f.read() + try: + return self.parse_string(file_contents, parseAll) + except ParseBaseException as exc: + if ParserElement.verbose_stacktrace: + raise + else: + # catch and re-raise exception from here, clears out pyparsing internal stack trace + raise exc.with_traceback(None) + + def __eq__(self, other): + if self is other: + return True + elif isinstance(other, str_type): + return self.matches(other, parse_all=True) + elif isinstance(other, ParserElement): + return vars(self) == vars(other) + return False + + def __hash__(self): + return id(self) + + def matches( + self, test_string: str, parse_all: bool = True, *, parseAll: bool = True + ) -> bool: + """ + Method for quick testing of a parser against a test string. Good for simple + inline microtests of sub expressions while building up larger parser. + + Parameters: + - ``test_string`` - to test against this expression for a match + - ``parse_all`` - (default= ``True``) - flag to pass to :class:`parse_string` when running tests + + Example:: + + expr = Word(nums) + assert expr.matches("100") + """ + parseAll = parseAll and parse_all + try: + self.parse_string(str(test_string), parse_all=parseAll) + return True + except ParseBaseException: + return False + + def run_tests( + self, + tests: Union[str, List[str]], + parse_all: bool = True, + comment: typing.Optional[Union["ParserElement", str]] = "#", + full_dump: bool = True, + print_results: bool = True, + failure_tests: bool = False, + post_parse: Callable[[str, ParseResults], str] = None, + file: typing.Optional[TextIO] = None, + with_line_numbers: bool = False, + *, + parseAll: bool = True, + fullDump: bool = True, + printResults: bool = True, + failureTests: bool = False, + postParse: Callable[[str, ParseResults], str] = None, + ) -> Tuple[bool, List[Tuple[str, Union[ParseResults, Exception]]]]: + """ + Execute the parse expression on a series of test strings, showing each + test, the parsed results or where the parse failed. Quick and easy way to + run a parse expression against a list of sample strings. + + Parameters: + - ``tests`` - a list of separate test strings, or a multiline string of test strings + - ``parse_all`` - (default= ``True``) - flag to pass to :class:`parse_string` when running tests + - ``comment`` - (default= ``'#'``) - expression for indicating embedded comments in the test + string; pass None to disable comment filtering + - ``full_dump`` - (default= ``True``) - dump results as list followed by results names in nested outline; + if False, only dump nested list + - ``print_results`` - (default= ``True``) prints test output to stdout + - ``failure_tests`` - (default= ``False``) indicates if these tests are expected to fail parsing + - ``post_parse`` - (default= ``None``) optional callback for successful parse results; called as + `fn(test_string, parse_results)` and returns a string to be added to the test output + - ``file`` - (default= ``None``) optional file-like object to which test output will be written; + if None, will default to ``sys.stdout`` + - ``with_line_numbers`` - default= ``False``) show test strings with line and column numbers + + Returns: a (success, results) tuple, where success indicates that all tests succeeded + (or failed if ``failure_tests`` is True), and the results contain a list of lines of each + test's output + + Example:: + + number_expr = pyparsing_common.number.copy() + + result = number_expr.run_tests(''' + # unsigned integer + 100 + # negative integer + -100 + # float with scientific notation + 6.02e23 + # integer with scientific notation + 1e-12 + ''') + print("Success" if result[0] else "Failed!") + + result = number_expr.run_tests(''' + # stray character + 100Z + # missing leading digit before '.' + -.100 + # too many '.' + 3.14.159 + ''', failure_tests=True) + print("Success" if result[0] else "Failed!") + + prints:: + + # unsigned integer + 100 + [100] + + # negative integer + -100 + [-100] + + # float with scientific notation + 6.02e23 + [6.02e+23] + + # integer with scientific notation + 1e-12 + [1e-12] + + Success + + # stray character + 100Z + ^ + FAIL: Expected end of text (at char 3), (line:1, col:4) + + # missing leading digit before '.' + -.100 + ^ + FAIL: Expected {real number with scientific notation | real number | signed integer} (at char 0), (line:1, col:1) + + # too many '.' + 3.14.159 + ^ + FAIL: Expected end of text (at char 4), (line:1, col:5) + + Success + + Each test string must be on a single line. If you want to test a string that spans multiple + lines, create a test like this:: + + expr.run_tests(r"this is a test\\n of strings that spans \\n 3 lines") + + (Note that this is a raw string literal, you must include the leading ``'r'``.) + """ + from .testing import pyparsing_test + + parseAll = parseAll and parse_all + fullDump = fullDump and full_dump + printResults = printResults and print_results + failureTests = failureTests or failure_tests + postParse = postParse or post_parse + if isinstance(tests, str_type): + line_strip = type(tests).strip + tests = [line_strip(test_line) for test_line in tests.rstrip().splitlines()] + if isinstance(comment, str_type): + comment = Literal(comment) + if file is None: + file = sys.stdout + print_ = file.write + + result: Union[ParseResults, Exception] + allResults = [] + comments = [] + success = True + NL = Literal(r"\n").add_parse_action(replace_with("\n")).ignore(quoted_string) + BOM = "\ufeff" + for t in tests: + if comment is not None and comment.matches(t, False) or comments and not t: + comments.append( + pyparsing_test.with_line_numbers(t) if with_line_numbers else t + ) + continue + if not t: + continue + out = [ + "\n" + "\n".join(comments) if comments else "", + pyparsing_test.with_line_numbers(t) if with_line_numbers else t, + ] + comments = [] + try: + # convert newline marks to actual newlines, and strip leading BOM if present + t = NL.transform_string(t.lstrip(BOM)) + result = self.parse_string(t, parse_all=parseAll) + except ParseBaseException as pe: + fatal = "(FATAL)" if isinstance(pe, ParseFatalException) else "" + out.append(pe.explain()) + out.append("FAIL: " + str(pe)) + if ParserElement.verbose_stacktrace: + out.extend(traceback.format_tb(pe.__traceback__)) + success = success and failureTests + result = pe + except Exception as exc: + out.append("FAIL-EXCEPTION: {}: {}".format(type(exc).__name__, exc)) + if ParserElement.verbose_stacktrace: + out.extend(traceback.format_tb(exc.__traceback__)) + success = success and failureTests + result = exc + else: + success = success and not failureTests + if postParse is not None: + try: + pp_value = postParse(t, result) + if pp_value is not None: + if isinstance(pp_value, ParseResults): + out.append(pp_value.dump()) + else: + out.append(str(pp_value)) + else: + out.append(result.dump()) + except Exception as e: + out.append(result.dump(full=fullDump)) + out.append( + "{} failed: {}: {}".format( + postParse.__name__, type(e).__name__, e + ) + ) + else: + out.append(result.dump(full=fullDump)) + out.append("") + + if printResults: + print_("\n".join(out)) + + allResults.append((t, result)) + + return success, allResults + + def create_diagram( + self, + output_html: Union[TextIO, Path, str], + vertical: int = 3, + show_results_names: bool = False, + show_groups: bool = False, + **kwargs, + ) -> None: + """ + Create a railroad diagram for the parser. + + Parameters: + - output_html (str or file-like object) - output target for generated + diagram HTML + - vertical (int) - threshold for formatting multiple alternatives vertically + instead of horizontally (default=3) + - show_results_names - bool flag whether diagram should show annotations for + defined results names + - show_groups - bool flag whether groups should be highlighted with an unlabeled surrounding box + Additional diagram-formatting keyword arguments can also be included; + see railroad.Diagram class. + """ + + try: + from .diagram import to_railroad, railroad_to_html + except ImportError as ie: + raise Exception( + "must ``pip install pyparsing[diagrams]`` to generate parser railroad diagrams" + ) from ie + + self.streamline() + + railroad = to_railroad( + self, + vertical=vertical, + show_results_names=show_results_names, + show_groups=show_groups, + diagram_kwargs=kwargs, + ) + if isinstance(output_html, (str, Path)): + with open(output_html, "w", encoding="utf-8") as diag_file: + diag_file.write(railroad_to_html(railroad)) + else: + # we were passed a file-like object, just write to it + output_html.write(railroad_to_html(railroad)) + + setDefaultWhitespaceChars = set_default_whitespace_chars + inlineLiteralsUsing = inline_literals_using + setResultsName = set_results_name + setBreak = set_break + setParseAction = set_parse_action + addParseAction = add_parse_action + addCondition = add_condition + setFailAction = set_fail_action + tryParse = try_parse + canParseNext = can_parse_next + resetCache = reset_cache + enableLeftRecursion = enable_left_recursion + enablePackrat = enable_packrat + parseString = parse_string + scanString = scan_string + searchString = search_string + transformString = transform_string + setWhitespaceChars = set_whitespace_chars + parseWithTabs = parse_with_tabs + setDebugActions = set_debug_actions + setDebug = set_debug + defaultName = default_name + setName = set_name + parseFile = parse_file + runTests = run_tests + ignoreWhitespace = ignore_whitespace + leaveWhitespace = leave_whitespace + + +class _PendingSkip(ParserElement): + # internal placeholder class to hold a place were '...' is added to a parser element, + # once another ParserElement is added, this placeholder will be replaced with a SkipTo + def __init__(self, expr: ParserElement, must_skip: bool = False): + super().__init__() + self.anchor = expr + self.must_skip = must_skip + + def _generateDefaultName(self): + return str(self.anchor + Empty()).replace("Empty", "...") + + def __add__(self, other) -> "ParserElement": + skipper = SkipTo(other).set_name("...")("_skipped*") + if self.must_skip: + + def must_skip(t): + if not t._skipped or t._skipped.as_list() == [""]: + del t[0] + t.pop("_skipped", None) + + def show_skip(t): + if t._skipped.as_list()[-1:] == [""]: + t.pop("_skipped") + t["_skipped"] = "missing <" + repr(self.anchor) + ">" + + return ( + self.anchor + skipper().add_parse_action(must_skip) + | skipper().add_parse_action(show_skip) + ) + other + + return self.anchor + skipper + other + + def __repr__(self): + return self.defaultName + + def parseImpl(self, *args): + raise Exception( + "use of `...` expression without following SkipTo target expression" + ) + + +class Token(ParserElement): + """Abstract :class:`ParserElement` subclass, for defining atomic + matching patterns. + """ + + def __init__(self): + super().__init__(savelist=False) + + def _generateDefaultName(self): + return type(self).__name__ + + +class Empty(Token): + """ + An empty token, will always match. + """ + + def __init__(self): + super().__init__() + self.mayReturnEmpty = True + self.mayIndexError = False + + +class NoMatch(Token): + """ + A token that will never match. + """ + + def __init__(self): + super().__init__() + self.mayReturnEmpty = True + self.mayIndexError = False + self.errmsg = "Unmatchable token" + + def parseImpl(self, instring, loc, doActions=True): + raise ParseException(instring, loc, self.errmsg, self) + + +class Literal(Token): + """ + Token to exactly match a specified string. + + Example:: + + Literal('blah').parse_string('blah') # -> ['blah'] + Literal('blah').parse_string('blahfooblah') # -> ['blah'] + Literal('blah').parse_string('bla') # -> Exception: Expected "blah" + + For case-insensitive matching, use :class:`CaselessLiteral`. + + For keyword matching (force word break before and after the matched string), + use :class:`Keyword` or :class:`CaselessKeyword`. + """ + + def __init__(self, match_string: str = "", *, matchString: str = ""): + super().__init__() + match_string = matchString or match_string + self.match = match_string + self.matchLen = len(match_string) + try: + self.firstMatchChar = match_string[0] + except IndexError: + raise ValueError("null string passed to Literal; use Empty() instead") + self.errmsg = "Expected " + self.name + self.mayReturnEmpty = False + self.mayIndexError = False + + # Performance tuning: modify __class__ to select + # a parseImpl optimized for single-character check + if self.matchLen == 1 and type(self) is Literal: + self.__class__ = _SingleCharLiteral + + def _generateDefaultName(self): + return repr(self.match) + + def parseImpl(self, instring, loc, doActions=True): + if instring[loc] == self.firstMatchChar and instring.startswith( + self.match, loc + ): + return loc + self.matchLen, self.match + raise ParseException(instring, loc, self.errmsg, self) + + +class _SingleCharLiteral(Literal): + def parseImpl(self, instring, loc, doActions=True): + if instring[loc] == self.firstMatchChar: + return loc + 1, self.match + raise ParseException(instring, loc, self.errmsg, self) + + +ParserElement._literalStringClass = Literal + + +class Keyword(Token): + """ + Token to exactly match a specified string as a keyword, that is, + it must be immediately followed by a non-keyword character. Compare + with :class:`Literal`: + + - ``Literal("if")`` will match the leading ``'if'`` in + ``'ifAndOnlyIf'``. + - ``Keyword("if")`` will not; it will only match the leading + ``'if'`` in ``'if x=1'``, or ``'if(y==2)'`` + + Accepts two optional constructor arguments in addition to the + keyword string: + + - ``identChars`` is a string of characters that would be valid + identifier characters, defaulting to all alphanumerics + "_" and + "$" + - ``caseless`` allows case-insensitive matching, default is ``False``. + + Example:: + + Keyword("start").parse_string("start") # -> ['start'] + Keyword("start").parse_string("starting") # -> Exception + + For case-insensitive matching, use :class:`CaselessKeyword`. + """ + + DEFAULT_KEYWORD_CHARS = alphanums + "_$" + + def __init__( + self, + match_string: str = "", + ident_chars: typing.Optional[str] = None, + caseless: bool = False, + *, + matchString: str = "", + identChars: typing.Optional[str] = None, + ): + super().__init__() + identChars = identChars or ident_chars + if identChars is None: + identChars = Keyword.DEFAULT_KEYWORD_CHARS + match_string = matchString or match_string + self.match = match_string + self.matchLen = len(match_string) + try: + self.firstMatchChar = match_string[0] + except IndexError: + raise ValueError("null string passed to Keyword; use Empty() instead") + self.errmsg = "Expected {} {}".format(type(self).__name__, self.name) + self.mayReturnEmpty = False + self.mayIndexError = False + self.caseless = caseless + if caseless: + self.caselessmatch = match_string.upper() + identChars = identChars.upper() + self.identChars = set(identChars) + + def _generateDefaultName(self): + return repr(self.match) + + def parseImpl(self, instring, loc, doActions=True): + errmsg = self.errmsg + errloc = loc + if self.caseless: + if instring[loc : loc + self.matchLen].upper() == self.caselessmatch: + if loc == 0 or instring[loc - 1].upper() not in self.identChars: + if ( + loc >= len(instring) - self.matchLen + or instring[loc + self.matchLen].upper() not in self.identChars + ): + return loc + self.matchLen, self.match + else: + # followed by keyword char + errmsg += ", was immediately followed by keyword character" + errloc = loc + self.matchLen + else: + # preceded by keyword char + errmsg += ", keyword was immediately preceded by keyword character" + errloc = loc - 1 + # else no match just raise plain exception + + else: + if ( + instring[loc] == self.firstMatchChar + and self.matchLen == 1 + or instring.startswith(self.match, loc) + ): + if loc == 0 or instring[loc - 1] not in self.identChars: + if ( + loc >= len(instring) - self.matchLen + or instring[loc + self.matchLen] not in self.identChars + ): + return loc + self.matchLen, self.match + else: + # followed by keyword char + errmsg += ( + ", keyword was immediately followed by keyword character" + ) + errloc = loc + self.matchLen + else: + # preceded by keyword char + errmsg += ", keyword was immediately preceded by keyword character" + errloc = loc - 1 + # else no match just raise plain exception + + raise ParseException(instring, errloc, errmsg, self) + + @staticmethod + def set_default_keyword_chars(chars) -> None: + """ + Overrides the default characters used by :class:`Keyword` expressions. + """ + Keyword.DEFAULT_KEYWORD_CHARS = chars + + setDefaultKeywordChars = set_default_keyword_chars + + +class CaselessLiteral(Literal): + """ + Token to match a specified string, ignoring case of letters. + Note: the matched results will always be in the case of the given + match string, NOT the case of the input text. + + Example:: + + CaselessLiteral("CMD")[1, ...].parse_string("cmd CMD Cmd10") + # -> ['CMD', 'CMD', 'CMD'] + + (Contrast with example for :class:`CaselessKeyword`.) + """ + + def __init__(self, match_string: str = "", *, matchString: str = ""): + match_string = matchString or match_string + super().__init__(match_string.upper()) + # Preserve the defining literal. + self.returnString = match_string + self.errmsg = "Expected " + self.name + + def parseImpl(self, instring, loc, doActions=True): + if instring[loc : loc + self.matchLen].upper() == self.match: + return loc + self.matchLen, self.returnString + raise ParseException(instring, loc, self.errmsg, self) + + +class CaselessKeyword(Keyword): + """ + Caseless version of :class:`Keyword`. + + Example:: + + CaselessKeyword("CMD")[1, ...].parse_string("cmd CMD Cmd10") + # -> ['CMD', 'CMD'] + + (Contrast with example for :class:`CaselessLiteral`.) + """ + + def __init__( + self, + match_string: str = "", + ident_chars: typing.Optional[str] = None, + *, + matchString: str = "", + identChars: typing.Optional[str] = None, + ): + identChars = identChars or ident_chars + match_string = matchString or match_string + super().__init__(match_string, identChars, caseless=True) + + +class CloseMatch(Token): + """A variation on :class:`Literal` which matches "close" matches, + that is, strings with at most 'n' mismatching characters. + :class:`CloseMatch` takes parameters: + + - ``match_string`` - string to be matched + - ``caseless`` - a boolean indicating whether to ignore casing when comparing characters + - ``max_mismatches`` - (``default=1``) maximum number of + mismatches allowed to count as a match + + The results from a successful parse will contain the matched text + from the input string and the following named results: + + - ``mismatches`` - a list of the positions within the + match_string where mismatches were found + - ``original`` - the original match_string used to compare + against the input string + + If ``mismatches`` is an empty list, then the match was an exact + match. + + Example:: + + patt = CloseMatch("ATCATCGAATGGA") + patt.parse_string("ATCATCGAAXGGA") # -> (['ATCATCGAAXGGA'], {'mismatches': [[9]], 'original': ['ATCATCGAATGGA']}) + patt.parse_string("ATCAXCGAAXGGA") # -> Exception: Expected 'ATCATCGAATGGA' (with up to 1 mismatches) (at char 0), (line:1, col:1) + + # exact match + patt.parse_string("ATCATCGAATGGA") # -> (['ATCATCGAATGGA'], {'mismatches': [[]], 'original': ['ATCATCGAATGGA']}) + + # close match allowing up to 2 mismatches + patt = CloseMatch("ATCATCGAATGGA", max_mismatches=2) + patt.parse_string("ATCAXCGAAXGGA") # -> (['ATCAXCGAAXGGA'], {'mismatches': [[4, 9]], 'original': ['ATCATCGAATGGA']}) + """ + + def __init__( + self, + match_string: str, + max_mismatches: int = None, + *, + maxMismatches: int = 1, + caseless=False, + ): + maxMismatches = max_mismatches if max_mismatches is not None else maxMismatches + super().__init__() + self.match_string = match_string + self.maxMismatches = maxMismatches + self.errmsg = "Expected {!r} (with up to {} mismatches)".format( + self.match_string, self.maxMismatches + ) + self.caseless = caseless + self.mayIndexError = False + self.mayReturnEmpty = False + + def _generateDefaultName(self): + return "{}:{!r}".format(type(self).__name__, self.match_string) + + def parseImpl(self, instring, loc, doActions=True): + start = loc + instrlen = len(instring) + maxloc = start + len(self.match_string) + + if maxloc <= instrlen: + match_string = self.match_string + match_stringloc = 0 + mismatches = [] + maxMismatches = self.maxMismatches + + for match_stringloc, s_m in enumerate( + zip(instring[loc:maxloc], match_string) + ): + src, mat = s_m + if self.caseless: + src, mat = src.lower(), mat.lower() + + if src != mat: + mismatches.append(match_stringloc) + if len(mismatches) > maxMismatches: + break + else: + loc = start + match_stringloc + 1 + results = ParseResults([instring[start:loc]]) + results["original"] = match_string + results["mismatches"] = mismatches + return loc, results + + raise ParseException(instring, loc, self.errmsg, self) + + +class Word(Token): + """Token for matching words composed of allowed character sets. + Parameters: + - ``init_chars`` - string of all characters that should be used to + match as a word; "ABC" will match "AAA", "ABAB", "CBAC", etc.; + if ``body_chars`` is also specified, then this is the string of + initial characters + - ``body_chars`` - string of characters that + can be used for matching after a matched initial character as + given in ``init_chars``; if omitted, same as the initial characters + (default=``None``) + - ``min`` - minimum number of characters to match (default=1) + - ``max`` - maximum number of characters to match (default=0) + - ``exact`` - exact number of characters to match (default=0) + - ``as_keyword`` - match as a keyword (default=``False``) + - ``exclude_chars`` - characters that might be + found in the input ``body_chars`` string but which should not be + accepted for matching ;useful to define a word of all + printables except for one or two characters, for instance + (default=``None``) + + :class:`srange` is useful for defining custom character set strings + for defining :class:`Word` expressions, using range notation from + regular expression character sets. + + A common mistake is to use :class:`Word` to match a specific literal + string, as in ``Word("Address")``. Remember that :class:`Word` + uses the string argument to define *sets* of matchable characters. + This expression would match "Add", "AAA", "dAred", or any other word + made up of the characters 'A', 'd', 'r', 'e', and 's'. To match an + exact literal string, use :class:`Literal` or :class:`Keyword`. + + pyparsing includes helper strings for building Words: + + - :class:`alphas` + - :class:`nums` + - :class:`alphanums` + - :class:`hexnums` + - :class:`alphas8bit` (alphabetic characters in ASCII range 128-255 + - accented, tilded, umlauted, etc.) + - :class:`punc8bit` (non-alphabetic characters in ASCII range + 128-255 - currency, symbols, superscripts, diacriticals, etc.) + - :class:`printables` (any non-whitespace character) + + ``alphas``, ``nums``, and ``printables`` are also defined in several + Unicode sets - see :class:`pyparsing_unicode``. + + Example:: + + # a word composed of digits + integer = Word(nums) # equivalent to Word("0123456789") or Word(srange("0-9")) + + # a word with a leading capital, and zero or more lowercase + capital_word = Word(alphas.upper(), alphas.lower()) + + # hostnames are alphanumeric, with leading alpha, and '-' + hostname = Word(alphas, alphanums + '-') + + # roman numeral (not a strict parser, accepts invalid mix of characters) + roman = Word("IVXLCDM") + + # any string of non-whitespace characters, except for ',' + csv_value = Word(printables, exclude_chars=",") + """ + + def __init__( + self, + init_chars: str = "", + body_chars: typing.Optional[str] = None, + min: int = 1, + max: int = 0, + exact: int = 0, + as_keyword: bool = False, + exclude_chars: typing.Optional[str] = None, + *, + initChars: typing.Optional[str] = None, + bodyChars: typing.Optional[str] = None, + asKeyword: bool = False, + excludeChars: typing.Optional[str] = None, + ): + initChars = initChars or init_chars + bodyChars = bodyChars or body_chars + asKeyword = asKeyword or as_keyword + excludeChars = excludeChars or exclude_chars + super().__init__() + if not initChars: + raise ValueError( + "invalid {}, initChars cannot be empty string".format( + type(self).__name__ + ) + ) + + initChars = set(initChars) + self.initChars = initChars + if excludeChars: + excludeChars = set(excludeChars) + initChars -= excludeChars + if bodyChars: + bodyChars = set(bodyChars) - excludeChars + self.initCharsOrig = "".join(sorted(initChars)) + + if bodyChars: + self.bodyCharsOrig = "".join(sorted(bodyChars)) + self.bodyChars = set(bodyChars) + else: + self.bodyCharsOrig = "".join(sorted(initChars)) + self.bodyChars = set(initChars) + + self.maxSpecified = max > 0 + + if min < 1: + raise ValueError( + "cannot specify a minimum length < 1; use Opt(Word()) if zero-length word is permitted" + ) + + self.minLen = min + + if max > 0: + self.maxLen = max + else: + self.maxLen = _MAX_INT + + if exact > 0: + self.maxLen = exact + self.minLen = exact + + self.errmsg = "Expected " + self.name + self.mayIndexError = False + self.asKeyword = asKeyword + + # see if we can make a regex for this Word + if " " not in self.initChars | self.bodyChars and (min == 1 and exact == 0): + if self.bodyChars == self.initChars: + if max == 0: + repeat = "+" + elif max == 1: + repeat = "" + else: + repeat = "{{{},{}}}".format( + self.minLen, "" if self.maxLen == _MAX_INT else self.maxLen + ) + self.reString = "[{}]{}".format( + _collapse_string_to_ranges(self.initChars), + repeat, + ) + elif len(self.initChars) == 1: + if max == 0: + repeat = "*" + else: + repeat = "{{0,{}}}".format(max - 1) + self.reString = "{}[{}]{}".format( + re.escape(self.initCharsOrig), + _collapse_string_to_ranges(self.bodyChars), + repeat, + ) + else: + if max == 0: + repeat = "*" + elif max == 2: + repeat = "" + else: + repeat = "{{0,{}}}".format(max - 1) + self.reString = "[{}][{}]{}".format( + _collapse_string_to_ranges(self.initChars), + _collapse_string_to_ranges(self.bodyChars), + repeat, + ) + if self.asKeyword: + self.reString = r"\b" + self.reString + r"\b" + + try: + self.re = re.compile(self.reString) + except re.error: + self.re = None + else: + self.re_match = self.re.match + self.__class__ = _WordRegex + + def _generateDefaultName(self): + def charsAsStr(s): + max_repr_len = 16 + s = _collapse_string_to_ranges(s, re_escape=False) + if len(s) > max_repr_len: + return s[: max_repr_len - 3] + "..." + else: + return s + + if self.initChars != self.bodyChars: + base = "W:({}, {})".format( + charsAsStr(self.initChars), charsAsStr(self.bodyChars) + ) + else: + base = "W:({})".format(charsAsStr(self.initChars)) + + # add length specification + if self.minLen > 1 or self.maxLen != _MAX_INT: + if self.minLen == self.maxLen: + if self.minLen == 1: + return base[2:] + else: + return base + "{{{}}}".format(self.minLen) + elif self.maxLen == _MAX_INT: + return base + "{{{},...}}".format(self.minLen) + else: + return base + "{{{},{}}}".format(self.minLen, self.maxLen) + return base + + def parseImpl(self, instring, loc, doActions=True): + if instring[loc] not in self.initChars: + raise ParseException(instring, loc, self.errmsg, self) + + start = loc + loc += 1 + instrlen = len(instring) + bodychars = self.bodyChars + maxloc = start + self.maxLen + maxloc = min(maxloc, instrlen) + while loc < maxloc and instring[loc] in bodychars: + loc += 1 + + throwException = False + if loc - start < self.minLen: + throwException = True + elif self.maxSpecified and loc < instrlen and instring[loc] in bodychars: + throwException = True + elif self.asKeyword: + if ( + start > 0 + and instring[start - 1] in bodychars + or loc < instrlen + and instring[loc] in bodychars + ): + throwException = True + + if throwException: + raise ParseException(instring, loc, self.errmsg, self) + + return loc, instring[start:loc] + + +class _WordRegex(Word): + def parseImpl(self, instring, loc, doActions=True): + result = self.re_match(instring, loc) + if not result: + raise ParseException(instring, loc, self.errmsg, self) + + loc = result.end() + return loc, result.group() + + +class Char(_WordRegex): + """A short-cut class for defining :class:`Word` ``(characters, exact=1)``, + when defining a match of any single character in a string of + characters. + """ + + def __init__( + self, + charset: str, + as_keyword: bool = False, + exclude_chars: typing.Optional[str] = None, + *, + asKeyword: bool = False, + excludeChars: typing.Optional[str] = None, + ): + asKeyword = asKeyword or as_keyword + excludeChars = excludeChars or exclude_chars + super().__init__( + charset, exact=1, asKeyword=asKeyword, excludeChars=excludeChars + ) + self.reString = "[{}]".format(_collapse_string_to_ranges(self.initChars)) + if asKeyword: + self.reString = r"\b{}\b".format(self.reString) + self.re = re.compile(self.reString) + self.re_match = self.re.match + + +class Regex(Token): + r"""Token for matching strings that match a given regular + expression. Defined with string specifying the regular expression in + a form recognized by the stdlib Python `re module <https://docs.python.org/3/library/re.html>`_. + If the given regex contains named groups (defined using ``(?P<name>...)``), + these will be preserved as named :class:`ParseResults`. + + If instead of the Python stdlib ``re`` module you wish to use a different RE module + (such as the ``regex`` module), you can do so by building your ``Regex`` object with + a compiled RE that was compiled using ``regex``. + + Example:: + + realnum = Regex(r"[+-]?\d+\.\d*") + # ref: https://stackoverflow.com/questions/267399/how-do-you-match-only-valid-roman-numerals-with-a-regular-expression + roman = Regex(r"M{0,4}(CM|CD|D?{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})") + + # named fields in a regex will be returned as named results + date = Regex(r'(?P<year>\d{4})-(?P<month>\d\d?)-(?P<day>\d\d?)') + + # the Regex class will accept re's compiled using the regex module + import regex + parser = pp.Regex(regex.compile(r'[0-9]')) + """ + + def __init__( + self, + pattern: Any, + flags: Union[re.RegexFlag, int] = 0, + as_group_list: bool = False, + as_match: bool = False, + *, + asGroupList: bool = False, + asMatch: bool = False, + ): + """The parameters ``pattern`` and ``flags`` are passed + to the ``re.compile()`` function as-is. See the Python + `re module <https://docs.python.org/3/library/re.html>`_ module for an + explanation of the acceptable patterns and flags. + """ + super().__init__() + asGroupList = asGroupList or as_group_list + asMatch = asMatch or as_match + + if isinstance(pattern, str_type): + if not pattern: + raise ValueError("null string passed to Regex; use Empty() instead") + + self._re = None + self.reString = self.pattern = pattern + self.flags = flags + + elif hasattr(pattern, "pattern") and hasattr(pattern, "match"): + self._re = pattern + self.pattern = self.reString = pattern.pattern + self.flags = flags + + else: + raise TypeError( + "Regex may only be constructed with a string or a compiled RE object" + ) + + self.errmsg = "Expected " + self.name + self.mayIndexError = False + self.asGroupList = asGroupList + self.asMatch = asMatch + if self.asGroupList: + self.parseImpl = self.parseImplAsGroupList + if self.asMatch: + self.parseImpl = self.parseImplAsMatch + + @cached_property + def re(self): + if self._re: + return self._re + else: + try: + return re.compile(self.pattern, self.flags) + except re.error: + raise ValueError( + "invalid pattern ({!r}) passed to Regex".format(self.pattern) + ) + + @cached_property + def re_match(self): + return self.re.match + + @cached_property + def mayReturnEmpty(self): + return self.re_match("") is not None + + def _generateDefaultName(self): + return "Re:({})".format(repr(self.pattern).replace("\\\\", "\\")) + + def parseImpl(self, instring, loc, doActions=True): + result = self.re_match(instring, loc) + if not result: + raise ParseException(instring, loc, self.errmsg, self) + + loc = result.end() + ret = ParseResults(result.group()) + d = result.groupdict() + if d: + for k, v in d.items(): + ret[k] = v + return loc, ret + + def parseImplAsGroupList(self, instring, loc, doActions=True): + result = self.re_match(instring, loc) + if not result: + raise ParseException(instring, loc, self.errmsg, self) + + loc = result.end() + ret = result.groups() + return loc, ret + + def parseImplAsMatch(self, instring, loc, doActions=True): + result = self.re_match(instring, loc) + if not result: + raise ParseException(instring, loc, self.errmsg, self) + + loc = result.end() + ret = result + return loc, ret + + def sub(self, repl: str) -> ParserElement: + r""" + Return :class:`Regex` with an attached parse action to transform the parsed + result as if called using `re.sub(expr, repl, string) <https://docs.python.org/3/library/re.html#re.sub>`_. + + Example:: + + make_html = Regex(r"(\w+):(.*?):").sub(r"<\1>\2</\1>") + print(make_html.transform_string("h1:main title:")) + # prints "<h1>main title</h1>" + """ + if self.asGroupList: + raise TypeError("cannot use sub() with Regex(asGroupList=True)") + + if self.asMatch and callable(repl): + raise TypeError("cannot use sub() with a callable with Regex(asMatch=True)") + + if self.asMatch: + + def pa(tokens): + return tokens[0].expand(repl) + + else: + + def pa(tokens): + return self.re.sub(repl, tokens[0]) + + return self.add_parse_action(pa) + + +class QuotedString(Token): + r""" + Token for matching strings that are delimited by quoting characters. + + Defined with the following parameters: + + - ``quote_char`` - string of one or more characters defining the + quote delimiting string + - ``esc_char`` - character to re_escape quotes, typically backslash + (default= ``None``) + - ``esc_quote`` - special quote sequence to re_escape an embedded quote + string (such as SQL's ``""`` to re_escape an embedded ``"``) + (default= ``None``) + - ``multiline`` - boolean indicating whether quotes can span + multiple lines (default= ``False``) + - ``unquote_results`` - boolean indicating whether the matched text + should be unquoted (default= ``True``) + - ``end_quote_char`` - string of one or more characters defining the + end of the quote delimited string (default= ``None`` => same as + quote_char) + - ``convert_whitespace_escapes`` - convert escaped whitespace + (``'\t'``, ``'\n'``, etc.) to actual whitespace + (default= ``True``) + + Example:: + + qs = QuotedString('"') + print(qs.search_string('lsjdf "This is the quote" sldjf')) + complex_qs = QuotedString('{{', end_quote_char='}}') + print(complex_qs.search_string('lsjdf {{This is the "quote"}} sldjf')) + sql_qs = QuotedString('"', esc_quote='""') + print(sql_qs.search_string('lsjdf "This is the quote with ""embedded"" quotes" sldjf')) + + prints:: + + [['This is the quote']] + [['This is the "quote"']] + [['This is the quote with "embedded" quotes']] + """ + ws_map = ((r"\t", "\t"), (r"\n", "\n"), (r"\f", "\f"), (r"\r", "\r")) + + def __init__( + self, + quote_char: str = "", + esc_char: typing.Optional[str] = None, + esc_quote: typing.Optional[str] = None, + multiline: bool = False, + unquote_results: bool = True, + end_quote_char: typing.Optional[str] = None, + convert_whitespace_escapes: bool = True, + *, + quoteChar: str = "", + escChar: typing.Optional[str] = None, + escQuote: typing.Optional[str] = None, + unquoteResults: bool = True, + endQuoteChar: typing.Optional[str] = None, + convertWhitespaceEscapes: bool = True, + ): + super().__init__() + escChar = escChar or esc_char + escQuote = escQuote or esc_quote + unquoteResults = unquoteResults and unquote_results + endQuoteChar = endQuoteChar or end_quote_char + convertWhitespaceEscapes = ( + convertWhitespaceEscapes and convert_whitespace_escapes + ) + quote_char = quoteChar or quote_char + + # remove white space from quote chars - wont work anyway + quote_char = quote_char.strip() + if not quote_char: + raise ValueError("quote_char cannot be the empty string") + + if endQuoteChar is None: + endQuoteChar = quote_char + else: + endQuoteChar = endQuoteChar.strip() + if not endQuoteChar: + raise ValueError("endQuoteChar cannot be the empty string") + + self.quoteChar = quote_char + self.quoteCharLen = len(quote_char) + self.firstQuoteChar = quote_char[0] + self.endQuoteChar = endQuoteChar + self.endQuoteCharLen = len(endQuoteChar) + self.escChar = escChar + self.escQuote = escQuote + self.unquoteResults = unquoteResults + self.convertWhitespaceEscapes = convertWhitespaceEscapes + + sep = "" + inner_pattern = "" + + if escQuote: + inner_pattern += r"{}(?:{})".format(sep, re.escape(escQuote)) + sep = "|" + + if escChar: + inner_pattern += r"{}(?:{}.)".format(sep, re.escape(escChar)) + sep = "|" + self.escCharReplacePattern = re.escape(self.escChar) + "(.)" + + if len(self.endQuoteChar) > 1: + inner_pattern += ( + "{}(?:".format(sep) + + "|".join( + "(?:{}(?!{}))".format( + re.escape(self.endQuoteChar[:i]), + re.escape(self.endQuoteChar[i:]), + ) + for i in range(len(self.endQuoteChar) - 1, 0, -1) + ) + + ")" + ) + sep = "|" + + if multiline: + self.flags = re.MULTILINE | re.DOTALL + inner_pattern += r"{}(?:[^{}{}])".format( + sep, + _escape_regex_range_chars(self.endQuoteChar[0]), + (_escape_regex_range_chars(escChar) if escChar is not None else ""), + ) + else: + self.flags = 0 + inner_pattern += r"{}(?:[^{}\n\r{}])".format( + sep, + _escape_regex_range_chars(self.endQuoteChar[0]), + (_escape_regex_range_chars(escChar) if escChar is not None else ""), + ) + + self.pattern = "".join( + [ + re.escape(self.quoteChar), + "(?:", + inner_pattern, + ")*", + re.escape(self.endQuoteChar), + ] + ) + + try: + self.re = re.compile(self.pattern, self.flags) + self.reString = self.pattern + self.re_match = self.re.match + except re.error: + raise ValueError( + "invalid pattern {!r} passed to Regex".format(self.pattern) + ) + + self.errmsg = "Expected " + self.name + self.mayIndexError = False + self.mayReturnEmpty = True + + def _generateDefaultName(self): + if self.quoteChar == self.endQuoteChar and isinstance(self.quoteChar, str_type): + return "string enclosed in {!r}".format(self.quoteChar) + + return "quoted string, starting with {} ending with {}".format( + self.quoteChar, self.endQuoteChar + ) + + def parseImpl(self, instring, loc, doActions=True): + result = ( + instring[loc] == self.firstQuoteChar + and self.re_match(instring, loc) + or None + ) + if not result: + raise ParseException(instring, loc, self.errmsg, self) + + loc = result.end() + ret = result.group() + + if self.unquoteResults: + + # strip off quotes + ret = ret[self.quoteCharLen : -self.endQuoteCharLen] + + if isinstance(ret, str_type): + # replace escaped whitespace + if "\\" in ret and self.convertWhitespaceEscapes: + for wslit, wschar in self.ws_map: + ret = ret.replace(wslit, wschar) + + # replace escaped characters + if self.escChar: + ret = re.sub(self.escCharReplacePattern, r"\g<1>", ret) + + # replace escaped quotes + if self.escQuote: + ret = ret.replace(self.escQuote, self.endQuoteChar) + + return loc, ret + + +class CharsNotIn(Token): + """Token for matching words composed of characters *not* in a given + set (will include whitespace in matched characters if not listed in + the provided exclusion set - see example). Defined with string + containing all disallowed characters, and an optional minimum, + maximum, and/or exact length. The default value for ``min`` is + 1 (a minimum value < 1 is not valid); the default values for + ``max`` and ``exact`` are 0, meaning no maximum or exact + length restriction. + + Example:: + + # define a comma-separated-value as anything that is not a ',' + csv_value = CharsNotIn(',') + print(delimited_list(csv_value).parse_string("dkls,lsdkjf,s12 34,@!#,213")) + + prints:: + + ['dkls', 'lsdkjf', 's12 34', '@!#', '213'] + """ + + def __init__( + self, + not_chars: str = "", + min: int = 1, + max: int = 0, + exact: int = 0, + *, + notChars: str = "", + ): + super().__init__() + self.skipWhitespace = False + self.notChars = not_chars or notChars + self.notCharsSet = set(self.notChars) + + if min < 1: + raise ValueError( + "cannot specify a minimum length < 1; use " + "Opt(CharsNotIn()) if zero-length char group is permitted" + ) + + self.minLen = min + + if max > 0: + self.maxLen = max + else: + self.maxLen = _MAX_INT + + if exact > 0: + self.maxLen = exact + self.minLen = exact + + self.errmsg = "Expected " + self.name + self.mayReturnEmpty = self.minLen == 0 + self.mayIndexError = False + + def _generateDefaultName(self): + not_chars_str = _collapse_string_to_ranges(self.notChars) + if len(not_chars_str) > 16: + return "!W:({}...)".format(self.notChars[: 16 - 3]) + else: + return "!W:({})".format(self.notChars) + + def parseImpl(self, instring, loc, doActions=True): + notchars = self.notCharsSet + if instring[loc] in notchars: + raise ParseException(instring, loc, self.errmsg, self) + + start = loc + loc += 1 + maxlen = min(start + self.maxLen, len(instring)) + while loc < maxlen and instring[loc] not in notchars: + loc += 1 + + if loc - start < self.minLen: + raise ParseException(instring, loc, self.errmsg, self) + + return loc, instring[start:loc] + + +class White(Token): + """Special matching class for matching whitespace. Normally, + whitespace is ignored by pyparsing grammars. This class is included + when some whitespace structures are significant. Define with + a string containing the whitespace characters to be matched; default + is ``" \\t\\r\\n"``. Also takes optional ``min``, + ``max``, and ``exact`` arguments, as defined for the + :class:`Word` class. + """ + + whiteStrs = { + " ": "<SP>", + "\t": "<TAB>", + "\n": "<LF>", + "\r": "<CR>", + "\f": "<FF>", + "\u00A0": "<NBSP>", + "\u1680": "<OGHAM_SPACE_MARK>", + "\u180E": "<MONGOLIAN_VOWEL_SEPARATOR>", + "\u2000": "<EN_QUAD>", + "\u2001": "<EM_QUAD>", + "\u2002": "<EN_SPACE>", + "\u2003": "<EM_SPACE>", + "\u2004": "<THREE-PER-EM_SPACE>", + "\u2005": "<FOUR-PER-EM_SPACE>", + "\u2006": "<SIX-PER-EM_SPACE>", + "\u2007": "<FIGURE_SPACE>", + "\u2008": "<PUNCTUATION_SPACE>", + "\u2009": "<THIN_SPACE>", + "\u200A": "<HAIR_SPACE>", + "\u200B": "<ZERO_WIDTH_SPACE>", + "\u202F": "<NNBSP>", + "\u205F": "<MMSP>", + "\u3000": "<IDEOGRAPHIC_SPACE>", + } + + def __init__(self, ws: str = " \t\r\n", min: int = 1, max: int = 0, exact: int = 0): + super().__init__() + self.matchWhite = ws + self.set_whitespace_chars( + "".join(c for c in self.whiteStrs if c not in self.matchWhite), + copy_defaults=True, + ) + # self.leave_whitespace() + self.mayReturnEmpty = True + self.errmsg = "Expected " + self.name + + self.minLen = min + + if max > 0: + self.maxLen = max + else: + self.maxLen = _MAX_INT + + if exact > 0: + self.maxLen = exact + self.minLen = exact + + def _generateDefaultName(self): + return "".join(White.whiteStrs[c] for c in self.matchWhite) + + def parseImpl(self, instring, loc, doActions=True): + if instring[loc] not in self.matchWhite: + raise ParseException(instring, loc, self.errmsg, self) + start = loc + loc += 1 + maxloc = start + self.maxLen + maxloc = min(maxloc, len(instring)) + while loc < maxloc and instring[loc] in self.matchWhite: + loc += 1 + + if loc - start < self.minLen: + raise ParseException(instring, loc, self.errmsg, self) + + return loc, instring[start:loc] + + +class PositionToken(Token): + def __init__(self): + super().__init__() + self.mayReturnEmpty = True + self.mayIndexError = False + + +class GoToColumn(PositionToken): + """Token to advance to a specific column of input text; useful for + tabular report scraping. + """ + + def __init__(self, colno: int): + super().__init__() + self.col = colno + + def preParse(self, instring, loc): + if col(loc, instring) != self.col: + instrlen = len(instring) + if self.ignoreExprs: + loc = self._skipIgnorables(instring, loc) + while ( + loc < instrlen + and instring[loc].isspace() + and col(loc, instring) != self.col + ): + loc += 1 + return loc + + def parseImpl(self, instring, loc, doActions=True): + thiscol = col(loc, instring) + if thiscol > self.col: + raise ParseException(instring, loc, "Text not in expected column", self) + newloc = loc + self.col - thiscol + ret = instring[loc:newloc] + return newloc, ret + + +class LineStart(PositionToken): + r"""Matches if current position is at the beginning of a line within + the parse string + + Example:: + + test = '''\ + AAA this line + AAA and this line + AAA but not this one + B AAA and definitely not this one + ''' + + for t in (LineStart() + 'AAA' + restOfLine).search_string(test): + print(t) + + prints:: + + ['AAA', ' this line'] + ['AAA', ' and this line'] + + """ + + def __init__(self): + super().__init__() + self.leave_whitespace() + self.orig_whiteChars = set() | self.whiteChars + self.whiteChars.discard("\n") + self.skipper = Empty().set_whitespace_chars(self.whiteChars) + self.errmsg = "Expected start of line" + + def preParse(self, instring, loc): + if loc == 0: + return loc + else: + ret = self.skipper.preParse(instring, loc) + if "\n" in self.orig_whiteChars: + while instring[ret : ret + 1] == "\n": + ret = self.skipper.preParse(instring, ret + 1) + return ret + + def parseImpl(self, instring, loc, doActions=True): + if col(loc, instring) == 1: + return loc, [] + raise ParseException(instring, loc, self.errmsg, self) + + +class LineEnd(PositionToken): + """Matches if current position is at the end of a line within the + parse string + """ + + def __init__(self): + super().__init__() + self.whiteChars.discard("\n") + self.set_whitespace_chars(self.whiteChars, copy_defaults=False) + self.errmsg = "Expected end of line" + + def parseImpl(self, instring, loc, doActions=True): + if loc < len(instring): + if instring[loc] == "\n": + return loc + 1, "\n" + else: + raise ParseException(instring, loc, self.errmsg, self) + elif loc == len(instring): + return loc + 1, [] + else: + raise ParseException(instring, loc, self.errmsg, self) + + +class StringStart(PositionToken): + """Matches if current position is at the beginning of the parse + string + """ + + def __init__(self): + super().__init__() + self.errmsg = "Expected start of text" + + def parseImpl(self, instring, loc, doActions=True): + if loc != 0: + # see if entire string up to here is just whitespace and ignoreables + if loc != self.preParse(instring, 0): + raise ParseException(instring, loc, self.errmsg, self) + return loc, [] + + +class StringEnd(PositionToken): + """ + Matches if current position is at the end of the parse string + """ + + def __init__(self): + super().__init__() + self.errmsg = "Expected end of text" + + def parseImpl(self, instring, loc, doActions=True): + if loc < len(instring): + raise ParseException(instring, loc, self.errmsg, self) + elif loc == len(instring): + return loc + 1, [] + elif loc > len(instring): + return loc, [] + else: + raise ParseException(instring, loc, self.errmsg, self) + + +class WordStart(PositionToken): + """Matches if the current position is at the beginning of a + :class:`Word`, and is not preceded by any character in a given + set of ``word_chars`` (default= ``printables``). To emulate the + ``\b`` behavior of regular expressions, use + ``WordStart(alphanums)``. ``WordStart`` will also match at + the beginning of the string being parsed, or at the beginning of + a line. + """ + + def __init__(self, word_chars: str = printables, *, wordChars: str = printables): + wordChars = word_chars if wordChars == printables else wordChars + super().__init__() + self.wordChars = set(wordChars) + self.errmsg = "Not at the start of a word" + + def parseImpl(self, instring, loc, doActions=True): + if loc != 0: + if ( + instring[loc - 1] in self.wordChars + or instring[loc] not in self.wordChars + ): + raise ParseException(instring, loc, self.errmsg, self) + return loc, [] + + +class WordEnd(PositionToken): + """Matches if the current position is at the end of a :class:`Word`, + and is not followed by any character in a given set of ``word_chars`` + (default= ``printables``). To emulate the ``\b`` behavior of + regular expressions, use ``WordEnd(alphanums)``. ``WordEnd`` + will also match at the end of the string being parsed, or at the end + of a line. + """ + + def __init__(self, word_chars: str = printables, *, wordChars: str = printables): + wordChars = word_chars if wordChars == printables else wordChars + super().__init__() + self.wordChars = set(wordChars) + self.skipWhitespace = False + self.errmsg = "Not at the end of a word" + + def parseImpl(self, instring, loc, doActions=True): + instrlen = len(instring) + if instrlen > 0 and loc < instrlen: + if ( + instring[loc] in self.wordChars + or instring[loc - 1] not in self.wordChars + ): + raise ParseException(instring, loc, self.errmsg, self) + return loc, [] + + +class ParseExpression(ParserElement): + """Abstract subclass of ParserElement, for combining and + post-processing parsed tokens. + """ + + def __init__(self, exprs: typing.Iterable[ParserElement], savelist: bool = False): + super().__init__(savelist) + self.exprs: List[ParserElement] + if isinstance(exprs, _generatorType): + exprs = list(exprs) + + if isinstance(exprs, str_type): + self.exprs = [self._literalStringClass(exprs)] + elif isinstance(exprs, ParserElement): + self.exprs = [exprs] + elif isinstance(exprs, Iterable): + exprs = list(exprs) + # if sequence of strings provided, wrap with Literal + if any(isinstance(expr, str_type) for expr in exprs): + exprs = ( + self._literalStringClass(e) if isinstance(e, str_type) else e + for e in exprs + ) + self.exprs = list(exprs) + else: + try: + self.exprs = list(exprs) + except TypeError: + self.exprs = [exprs] + self.callPreparse = False + + def recurse(self) -> Sequence[ParserElement]: + return self.exprs[:] + + def append(self, other) -> ParserElement: + self.exprs.append(other) + self._defaultName = None + return self + + def leave_whitespace(self, recursive: bool = True) -> ParserElement: + """ + Extends ``leave_whitespace`` defined in base class, and also invokes ``leave_whitespace`` on + all contained expressions. + """ + super().leave_whitespace(recursive) + + if recursive: + self.exprs = [e.copy() for e in self.exprs] + for e in self.exprs: + e.leave_whitespace(recursive) + return self + + def ignore_whitespace(self, recursive: bool = True) -> ParserElement: + """ + Extends ``ignore_whitespace`` defined in base class, and also invokes ``leave_whitespace`` on + all contained expressions. + """ + super().ignore_whitespace(recursive) + if recursive: + self.exprs = [e.copy() for e in self.exprs] + for e in self.exprs: + e.ignore_whitespace(recursive) + return self + + def ignore(self, other) -> ParserElement: + if isinstance(other, Suppress): + if other not in self.ignoreExprs: + super().ignore(other) + for e in self.exprs: + e.ignore(self.ignoreExprs[-1]) + else: + super().ignore(other) + for e in self.exprs: + e.ignore(self.ignoreExprs[-1]) + return self + + def _generateDefaultName(self): + return "{}:({})".format(self.__class__.__name__, str(self.exprs)) + + def streamline(self) -> ParserElement: + if self.streamlined: + return self + + super().streamline() + + for e in self.exprs: + e.streamline() + + # collapse nested :class:`And`'s of the form ``And(And(And(a, b), c), d)`` to ``And(a, b, c, d)`` + # but only if there are no parse actions or resultsNames on the nested And's + # (likewise for :class:`Or`'s and :class:`MatchFirst`'s) + if len(self.exprs) == 2: + other = self.exprs[0] + if ( + isinstance(other, self.__class__) + and not other.parseAction + and other.resultsName is None + and not other.debug + ): + self.exprs = other.exprs[:] + [self.exprs[1]] + self._defaultName = None + self.mayReturnEmpty |= other.mayReturnEmpty + self.mayIndexError |= other.mayIndexError + + other = self.exprs[-1] + if ( + isinstance(other, self.__class__) + and not other.parseAction + and other.resultsName is None + and not other.debug + ): + self.exprs = self.exprs[:-1] + other.exprs[:] + self._defaultName = None + self.mayReturnEmpty |= other.mayReturnEmpty + self.mayIndexError |= other.mayIndexError + + self.errmsg = "Expected " + str(self) + + return self + + def validate(self, validateTrace=None) -> None: + tmp = (validateTrace if validateTrace is not None else [])[:] + [self] + for e in self.exprs: + e.validate(tmp) + self._checkRecursion([]) + + def copy(self) -> ParserElement: + ret = super().copy() + ret.exprs = [e.copy() for e in self.exprs] + return ret + + def _setResultsName(self, name, listAllMatches=False): + if ( + __diag__.warn_ungrouped_named_tokens_in_collection + and Diagnostics.warn_ungrouped_named_tokens_in_collection + not in self.suppress_warnings_ + ): + for e in self.exprs: + if ( + isinstance(e, ParserElement) + and e.resultsName + and Diagnostics.warn_ungrouped_named_tokens_in_collection + not in e.suppress_warnings_ + ): + warnings.warn( + "{}: setting results name {!r} on {} expression " + "collides with {!r} on contained expression".format( + "warn_ungrouped_named_tokens_in_collection", + name, + type(self).__name__, + e.resultsName, + ), + stacklevel=3, + ) + + return super()._setResultsName(name, listAllMatches) + + ignoreWhitespace = ignore_whitespace + leaveWhitespace = leave_whitespace + + +class And(ParseExpression): + """ + Requires all given :class:`ParseExpression` s to be found in the given order. + Expressions may be separated by whitespace. + May be constructed using the ``'+'`` operator. + May also be constructed using the ``'-'`` operator, which will + suppress backtracking. + + Example:: + + integer = Word(nums) + name_expr = Word(alphas)[1, ...] + + expr = And([integer("id"), name_expr("name"), integer("age")]) + # more easily written as: + expr = integer("id") + name_expr("name") + integer("age") + """ + + class _ErrorStop(Empty): + def __init__(self, *args, **kwargs): + super().__init__(*args, **kwargs) + self.leave_whitespace() + + def _generateDefaultName(self): + return "-" + + def __init__( + self, exprs_arg: typing.Iterable[ParserElement], savelist: bool = True + ): + exprs: List[ParserElement] = list(exprs_arg) + if exprs and Ellipsis in exprs: + tmp = [] + for i, expr in enumerate(exprs): + if expr is Ellipsis: + if i < len(exprs) - 1: + skipto_arg: ParserElement = (Empty() + exprs[i + 1]).exprs[-1] + tmp.append(SkipTo(skipto_arg)("_skipped*")) + else: + raise Exception( + "cannot construct And with sequence ending in ..." + ) + else: + tmp.append(expr) + exprs[:] = tmp + super().__init__(exprs, savelist) + if self.exprs: + self.mayReturnEmpty = all(e.mayReturnEmpty for e in self.exprs) + if not isinstance(self.exprs[0], White): + self.set_whitespace_chars( + self.exprs[0].whiteChars, + copy_defaults=self.exprs[0].copyDefaultWhiteChars, + ) + self.skipWhitespace = self.exprs[0].skipWhitespace + else: + self.skipWhitespace = False + else: + self.mayReturnEmpty = True + self.callPreparse = True + + def streamline(self) -> ParserElement: + # collapse any _PendingSkip's + if self.exprs: + if any( + isinstance(e, ParseExpression) + and e.exprs + and isinstance(e.exprs[-1], _PendingSkip) + for e in self.exprs[:-1] + ): + for i, e in enumerate(self.exprs[:-1]): + if e is None: + continue + if ( + isinstance(e, ParseExpression) + and e.exprs + and isinstance(e.exprs[-1], _PendingSkip) + ): + e.exprs[-1] = e.exprs[-1] + self.exprs[i + 1] + self.exprs[i + 1] = None + self.exprs = [e for e in self.exprs if e is not None] + + super().streamline() + + # link any IndentedBlocks to the prior expression + for prev, cur in zip(self.exprs, self.exprs[1:]): + # traverse cur or any first embedded expr of cur looking for an IndentedBlock + # (but watch out for recursive grammar) + seen = set() + while cur: + if id(cur) in seen: + break + seen.add(id(cur)) + if isinstance(cur, IndentedBlock): + prev.add_parse_action( + lambda s, l, t, cur_=cur: setattr( + cur_, "parent_anchor", col(l, s) + ) + ) + break + subs = cur.recurse() + cur = next(iter(subs), None) + + self.mayReturnEmpty = all(e.mayReturnEmpty for e in self.exprs) + return self + + def parseImpl(self, instring, loc, doActions=True): + # pass False as callPreParse arg to _parse for first element, since we already + # pre-parsed the string as part of our And pre-parsing + loc, resultlist = self.exprs[0]._parse( + instring, loc, doActions, callPreParse=False + ) + errorStop = False + for e in self.exprs[1:]: + # if isinstance(e, And._ErrorStop): + if type(e) is And._ErrorStop: + errorStop = True + continue + if errorStop: + try: + loc, exprtokens = e._parse(instring, loc, doActions) + except ParseSyntaxException: + raise + except ParseBaseException as pe: + pe.__traceback__ = None + raise ParseSyntaxException._from_exception(pe) + except IndexError: + raise ParseSyntaxException( + instring, len(instring), self.errmsg, self + ) + else: + loc, exprtokens = e._parse(instring, loc, doActions) + if exprtokens or exprtokens.haskeys(): + resultlist += exprtokens + return loc, resultlist + + def __iadd__(self, other): + if isinstance(other, str_type): + other = self._literalStringClass(other) + return self.append(other) # And([self, other]) + + def _checkRecursion(self, parseElementList): + subRecCheckList = parseElementList[:] + [self] + for e in self.exprs: + e._checkRecursion(subRecCheckList) + if not e.mayReturnEmpty: + break + + def _generateDefaultName(self): + inner = " ".join(str(e) for e in self.exprs) + # strip off redundant inner {}'s + while len(inner) > 1 and inner[0 :: len(inner) - 1] == "{}": + inner = inner[1:-1] + return "{" + inner + "}" + + +class Or(ParseExpression): + """Requires that at least one :class:`ParseExpression` is found. If + two expressions match, the expression that matches the longest + string will be used. May be constructed using the ``'^'`` + operator. + + Example:: + + # construct Or using '^' operator + + number = Word(nums) ^ Combine(Word(nums) + '.' + Word(nums)) + print(number.search_string("123 3.1416 789")) + + prints:: + + [['123'], ['3.1416'], ['789']] + """ + + def __init__(self, exprs: typing.Iterable[ParserElement], savelist: bool = False): + super().__init__(exprs, savelist) + if self.exprs: + self.mayReturnEmpty = any(e.mayReturnEmpty for e in self.exprs) + self.skipWhitespace = all(e.skipWhitespace for e in self.exprs) + else: + self.mayReturnEmpty = True + + def streamline(self) -> ParserElement: + super().streamline() + if self.exprs: + self.mayReturnEmpty = any(e.mayReturnEmpty for e in self.exprs) + self.saveAsList = any(e.saveAsList for e in self.exprs) + self.skipWhitespace = all( + e.skipWhitespace and not isinstance(e, White) for e in self.exprs + ) + else: + self.saveAsList = False + return self + + def parseImpl(self, instring, loc, doActions=True): + maxExcLoc = -1 + maxException = None + matches = [] + fatals = [] + if all(e.callPreparse for e in self.exprs): + loc = self.preParse(instring, loc) + for e in self.exprs: + try: + loc2 = e.try_parse(instring, loc, raise_fatal=True) + except ParseFatalException as pfe: + pfe.__traceback__ = None + pfe.parserElement = e + fatals.append(pfe) + maxException = None + maxExcLoc = -1 + except ParseException as err: + if not fatals: + err.__traceback__ = None + if err.loc > maxExcLoc: + maxException = err + maxExcLoc = err.loc + except IndexError: + if len(instring) > maxExcLoc: + maxException = ParseException( + instring, len(instring), e.errmsg, self + ) + maxExcLoc = len(instring) + else: + # save match among all matches, to retry longest to shortest + matches.append((loc2, e)) + + if matches: + # re-evaluate all matches in descending order of length of match, in case attached actions + # might change whether or how much they match of the input. + matches.sort(key=itemgetter(0), reverse=True) + + if not doActions: + # no further conditions or parse actions to change the selection of + # alternative, so the first match will be the best match + best_expr = matches[0][1] + return best_expr._parse(instring, loc, doActions) + + longest = -1, None + for loc1, expr1 in matches: + if loc1 <= longest[0]: + # already have a longer match than this one will deliver, we are done + return longest + + try: + loc2, toks = expr1._parse(instring, loc, doActions) + except ParseException as err: + err.__traceback__ = None + if err.loc > maxExcLoc: + maxException = err + maxExcLoc = err.loc + else: + if loc2 >= loc1: + return loc2, toks + # didn't match as much as before + elif loc2 > longest[0]: + longest = loc2, toks + + if longest != (-1, None): + return longest + + if fatals: + if len(fatals) > 1: + fatals.sort(key=lambda e: -e.loc) + if fatals[0].loc == fatals[1].loc: + fatals.sort(key=lambda e: (-e.loc, -len(str(e.parserElement)))) + max_fatal = fatals[0] + raise max_fatal + + if maxException is not None: + maxException.msg = self.errmsg + raise maxException + else: + raise ParseException( + instring, loc, "no defined alternatives to match", self + ) + + def __ixor__(self, other): + if isinstance(other, str_type): + other = self._literalStringClass(other) + return self.append(other) # Or([self, other]) + + def _generateDefaultName(self): + return "{" + " ^ ".join(str(e) for e in self.exprs) + "}" + + def _setResultsName(self, name, listAllMatches=False): + if ( + __diag__.warn_multiple_tokens_in_named_alternation + and Diagnostics.warn_multiple_tokens_in_named_alternation + not in self.suppress_warnings_ + ): + if any( + isinstance(e, And) + and Diagnostics.warn_multiple_tokens_in_named_alternation + not in e.suppress_warnings_ + for e in self.exprs + ): + warnings.warn( + "{}: setting results name {!r} on {} expression " + "will return a list of all parsed tokens in an And alternative, " + "in prior versions only the first token was returned; enclose " + "contained argument in Group".format( + "warn_multiple_tokens_in_named_alternation", + name, + type(self).__name__, + ), + stacklevel=3, + ) + + return super()._setResultsName(name, listAllMatches) + + +class MatchFirst(ParseExpression): + """Requires that at least one :class:`ParseExpression` is found. If + more than one expression matches, the first one listed is the one that will + match. May be constructed using the ``'|'`` operator. + + Example:: + + # construct MatchFirst using '|' operator + + # watch the order of expressions to match + number = Word(nums) | Combine(Word(nums) + '.' + Word(nums)) + print(number.search_string("123 3.1416 789")) # Fail! -> [['123'], ['3'], ['1416'], ['789']] + + # put more selective expression first + number = Combine(Word(nums) + '.' + Word(nums)) | Word(nums) + print(number.search_string("123 3.1416 789")) # Better -> [['123'], ['3.1416'], ['789']] + """ + + def __init__(self, exprs: typing.Iterable[ParserElement], savelist: bool = False): + super().__init__(exprs, savelist) + if self.exprs: + self.mayReturnEmpty = any(e.mayReturnEmpty for e in self.exprs) + self.skipWhitespace = all(e.skipWhitespace for e in self.exprs) + else: + self.mayReturnEmpty = True + + def streamline(self) -> ParserElement: + if self.streamlined: + return self + + super().streamline() + if self.exprs: + self.saveAsList = any(e.saveAsList for e in self.exprs) + self.mayReturnEmpty = any(e.mayReturnEmpty for e in self.exprs) + self.skipWhitespace = all( + e.skipWhitespace and not isinstance(e, White) for e in self.exprs + ) + else: + self.saveAsList = False + self.mayReturnEmpty = True + return self + + def parseImpl(self, instring, loc, doActions=True): + maxExcLoc = -1 + maxException = None + + for e in self.exprs: + try: + return e._parse( + instring, + loc, + doActions, + ) + except ParseFatalException as pfe: + pfe.__traceback__ = None + pfe.parserElement = e + raise + except ParseException as err: + if err.loc > maxExcLoc: + maxException = err + maxExcLoc = err.loc + except IndexError: + if len(instring) > maxExcLoc: + maxException = ParseException( + instring, len(instring), e.errmsg, self + ) + maxExcLoc = len(instring) + + if maxException is not None: + maxException.msg = self.errmsg + raise maxException + else: + raise ParseException( + instring, loc, "no defined alternatives to match", self + ) + + def __ior__(self, other): + if isinstance(other, str_type): + other = self._literalStringClass(other) + return self.append(other) # MatchFirst([self, other]) + + def _generateDefaultName(self): + return "{" + " | ".join(str(e) for e in self.exprs) + "}" + + def _setResultsName(self, name, listAllMatches=False): + if ( + __diag__.warn_multiple_tokens_in_named_alternation + and Diagnostics.warn_multiple_tokens_in_named_alternation + not in self.suppress_warnings_ + ): + if any( + isinstance(e, And) + and Diagnostics.warn_multiple_tokens_in_named_alternation + not in e.suppress_warnings_ + for e in self.exprs + ): + warnings.warn( + "{}: setting results name {!r} on {} expression " + "will return a list of all parsed tokens in an And alternative, " + "in prior versions only the first token was returned; enclose " + "contained argument in Group".format( + "warn_multiple_tokens_in_named_alternation", + name, + type(self).__name__, + ), + stacklevel=3, + ) + + return super()._setResultsName(name, listAllMatches) + + +class Each(ParseExpression): + """Requires all given :class:`ParseExpression` s to be found, but in + any order. Expressions may be separated by whitespace. + + May be constructed using the ``'&'`` operator. + + Example:: + + color = one_of("RED ORANGE YELLOW GREEN BLUE PURPLE BLACK WHITE BROWN") + shape_type = one_of("SQUARE CIRCLE TRIANGLE STAR HEXAGON OCTAGON") + integer = Word(nums) + shape_attr = "shape:" + shape_type("shape") + posn_attr = "posn:" + Group(integer("x") + ',' + integer("y"))("posn") + color_attr = "color:" + color("color") + size_attr = "size:" + integer("size") + + # use Each (using operator '&') to accept attributes in any order + # (shape and posn are required, color and size are optional) + shape_spec = shape_attr & posn_attr & Opt(color_attr) & Opt(size_attr) + + shape_spec.run_tests(''' + shape: SQUARE color: BLACK posn: 100, 120 + shape: CIRCLE size: 50 color: BLUE posn: 50,80 + color:GREEN size:20 shape:TRIANGLE posn:20,40 + ''' + ) + + prints:: + + shape: SQUARE color: BLACK posn: 100, 120 + ['shape:', 'SQUARE', 'color:', 'BLACK', 'posn:', ['100', ',', '120']] + - color: BLACK + - posn: ['100', ',', '120'] + - x: 100 + - y: 120 + - shape: SQUARE + + + shape: CIRCLE size: 50 color: BLUE posn: 50,80 + ['shape:', 'CIRCLE', 'size:', '50', 'color:', 'BLUE', 'posn:', ['50', ',', '80']] + - color: BLUE + - posn: ['50', ',', '80'] + - x: 50 + - y: 80 + - shape: CIRCLE + - size: 50 + + + color: GREEN size: 20 shape: TRIANGLE posn: 20,40 + ['color:', 'GREEN', 'size:', '20', 'shape:', 'TRIANGLE', 'posn:', ['20', ',', '40']] + - color: GREEN + - posn: ['20', ',', '40'] + - x: 20 + - y: 40 + - shape: TRIANGLE + - size: 20 + """ + + def __init__(self, exprs: typing.Iterable[ParserElement], savelist: bool = True): + super().__init__(exprs, savelist) + if self.exprs: + self.mayReturnEmpty = all(e.mayReturnEmpty for e in self.exprs) + else: + self.mayReturnEmpty = True + self.skipWhitespace = True + self.initExprGroups = True + self.saveAsList = True + + def streamline(self) -> ParserElement: + super().streamline() + if self.exprs: + self.mayReturnEmpty = all(e.mayReturnEmpty for e in self.exprs) + else: + self.mayReturnEmpty = True + return self + + def parseImpl(self, instring, loc, doActions=True): + if self.initExprGroups: + self.opt1map = dict( + (id(e.expr), e) for e in self.exprs if isinstance(e, Opt) + ) + opt1 = [e.expr for e in self.exprs if isinstance(e, Opt)] + opt2 = [ + e + for e in self.exprs + if e.mayReturnEmpty and not isinstance(e, (Opt, Regex, ZeroOrMore)) + ] + self.optionals = opt1 + opt2 + self.multioptionals = [ + e.expr.set_results_name(e.resultsName, list_all_matches=True) + for e in self.exprs + if isinstance(e, _MultipleMatch) + ] + self.multirequired = [ + e.expr.set_results_name(e.resultsName, list_all_matches=True) + for e in self.exprs + if isinstance(e, OneOrMore) + ] + self.required = [ + e for e in self.exprs if not isinstance(e, (Opt, ZeroOrMore, OneOrMore)) + ] + self.required += self.multirequired + self.initExprGroups = False + + tmpLoc = loc + tmpReqd = self.required[:] + tmpOpt = self.optionals[:] + multis = self.multioptionals[:] + matchOrder = [] + + keepMatching = True + failed = [] + fatals = [] + while keepMatching: + tmpExprs = tmpReqd + tmpOpt + multis + failed.clear() + fatals.clear() + for e in tmpExprs: + try: + tmpLoc = e.try_parse(instring, tmpLoc, raise_fatal=True) + except ParseFatalException as pfe: + pfe.__traceback__ = None + pfe.parserElement = e + fatals.append(pfe) + failed.append(e) + except ParseException: + failed.append(e) + else: + matchOrder.append(self.opt1map.get(id(e), e)) + if e in tmpReqd: + tmpReqd.remove(e) + elif e in tmpOpt: + tmpOpt.remove(e) + if len(failed) == len(tmpExprs): + keepMatching = False + + # look for any ParseFatalExceptions + if fatals: + if len(fatals) > 1: + fatals.sort(key=lambda e: -e.loc) + if fatals[0].loc == fatals[1].loc: + fatals.sort(key=lambda e: (-e.loc, -len(str(e.parserElement)))) + max_fatal = fatals[0] + raise max_fatal + + if tmpReqd: + missing = ", ".join([str(e) for e in tmpReqd]) + raise ParseException( + instring, + loc, + "Missing one or more required elements ({})".format(missing), + ) + + # add any unmatched Opts, in case they have default values defined + matchOrder += [e for e in self.exprs if isinstance(e, Opt) and e.expr in tmpOpt] + + total_results = ParseResults([]) + for e in matchOrder: + loc, results = e._parse(instring, loc, doActions) + total_results += results + + return loc, total_results + + def _generateDefaultName(self): + return "{" + " & ".join(str(e) for e in self.exprs) + "}" + + +class ParseElementEnhance(ParserElement): + """Abstract subclass of :class:`ParserElement`, for combining and + post-processing parsed tokens. + """ + + def __init__(self, expr: Union[ParserElement, str], savelist: bool = False): + super().__init__(savelist) + if isinstance(expr, str_type): + if issubclass(self._literalStringClass, Token): + expr = self._literalStringClass(expr) + elif issubclass(type(self), self._literalStringClass): + expr = Literal(expr) + else: + expr = self._literalStringClass(Literal(expr)) + self.expr = expr + if expr is not None: + self.mayIndexError = expr.mayIndexError + self.mayReturnEmpty = expr.mayReturnEmpty + self.set_whitespace_chars( + expr.whiteChars, copy_defaults=expr.copyDefaultWhiteChars + ) + self.skipWhitespace = expr.skipWhitespace + self.saveAsList = expr.saveAsList + self.callPreparse = expr.callPreparse + self.ignoreExprs.extend(expr.ignoreExprs) + + def recurse(self) -> Sequence[ParserElement]: + return [self.expr] if self.expr is not None else [] + + def parseImpl(self, instring, loc, doActions=True): + if self.expr is not None: + return self.expr._parse(instring, loc, doActions, callPreParse=False) + else: + raise ParseException(instring, loc, "No expression defined", self) + + def leave_whitespace(self, recursive: bool = True) -> ParserElement: + super().leave_whitespace(recursive) + + if recursive: + self.expr = self.expr.copy() + if self.expr is not None: + self.expr.leave_whitespace(recursive) + return self + + def ignore_whitespace(self, recursive: bool = True) -> ParserElement: + super().ignore_whitespace(recursive) + + if recursive: + self.expr = self.expr.copy() + if self.expr is not None: + self.expr.ignore_whitespace(recursive) + return self + + def ignore(self, other) -> ParserElement: + if isinstance(other, Suppress): + if other not in self.ignoreExprs: + super().ignore(other) + if self.expr is not None: + self.expr.ignore(self.ignoreExprs[-1]) + else: + super().ignore(other) + if self.expr is not None: + self.expr.ignore(self.ignoreExprs[-1]) + return self + + def streamline(self) -> ParserElement: + super().streamline() + if self.expr is not None: + self.expr.streamline() + return self + + def _checkRecursion(self, parseElementList): + if self in parseElementList: + raise RecursiveGrammarException(parseElementList + [self]) + subRecCheckList = parseElementList[:] + [self] + if self.expr is not None: + self.expr._checkRecursion(subRecCheckList) + + def validate(self, validateTrace=None) -> None: + if validateTrace is None: + validateTrace = [] + tmp = validateTrace[:] + [self] + if self.expr is not None: + self.expr.validate(tmp) + self._checkRecursion([]) + + def _generateDefaultName(self): + return "{}:({})".format(self.__class__.__name__, str(self.expr)) + + ignoreWhitespace = ignore_whitespace + leaveWhitespace = leave_whitespace + + +class IndentedBlock(ParseElementEnhance): + """ + Expression to match one or more expressions at a given indentation level. + Useful for parsing text where structure is implied by indentation (like Python source code). + """ + + class _Indent(Empty): + def __init__(self, ref_col: int): + super().__init__() + self.errmsg = "expected indent at column {}".format(ref_col) + self.add_condition(lambda s, l, t: col(l, s) == ref_col) + + class _IndentGreater(Empty): + def __init__(self, ref_col: int): + super().__init__() + self.errmsg = "expected indent at column greater than {}".format(ref_col) + self.add_condition(lambda s, l, t: col(l, s) > ref_col) + + def __init__( + self, expr: ParserElement, *, recursive: bool = False, grouped: bool = True + ): + super().__init__(expr, savelist=True) + # if recursive: + # raise NotImplementedError("IndentedBlock with recursive is not implemented") + self._recursive = recursive + self._grouped = grouped + self.parent_anchor = 1 + + def parseImpl(self, instring, loc, doActions=True): + # advance parse position to non-whitespace by using an Empty() + # this should be the column to be used for all subsequent indented lines + anchor_loc = Empty().preParse(instring, loc) + + # see if self.expr matches at the current location - if not it will raise an exception + # and no further work is necessary + self.expr.try_parse(instring, anchor_loc, doActions) + + indent_col = col(anchor_loc, instring) + peer_detect_expr = self._Indent(indent_col) + + inner_expr = Empty() + peer_detect_expr + self.expr + if self._recursive: + sub_indent = self._IndentGreater(indent_col) + nested_block = IndentedBlock( + self.expr, recursive=self._recursive, grouped=self._grouped + ) + nested_block.set_debug(self.debug) + nested_block.parent_anchor = indent_col + inner_expr += Opt(sub_indent + nested_block) + + inner_expr.set_name(f"inner {hex(id(inner_expr))[-4:].upper()}@{indent_col}") + block = OneOrMore(inner_expr) + + trailing_undent = self._Indent(self.parent_anchor) | StringEnd() + + if self._grouped: + wrapper = Group + else: + wrapper = lambda expr: expr + return (wrapper(block) + Optional(trailing_undent)).parseImpl( + instring, anchor_loc, doActions + ) + + +class AtStringStart(ParseElementEnhance): + """Matches if expression matches at the beginning of the parse + string:: + + AtStringStart(Word(nums)).parse_string("123") + # prints ["123"] + + AtStringStart(Word(nums)).parse_string(" 123") + # raises ParseException + """ + + def __init__(self, expr: Union[ParserElement, str]): + super().__init__(expr) + self.callPreparse = False + + def parseImpl(self, instring, loc, doActions=True): + if loc != 0: + raise ParseException(instring, loc, "not found at string start") + return super().parseImpl(instring, loc, doActions) + + +class AtLineStart(ParseElementEnhance): + r"""Matches if an expression matches at the beginning of a line within + the parse string + + Example:: + + test = '''\ + AAA this line + AAA and this line + AAA but not this one + B AAA and definitely not this one + ''' + + for t in (AtLineStart('AAA') + restOfLine).search_string(test): + print(t) + + prints:: + + ['AAA', ' this line'] + ['AAA', ' and this line'] + + """ + + def __init__(self, expr: Union[ParserElement, str]): + super().__init__(expr) + self.callPreparse = False + + def parseImpl(self, instring, loc, doActions=True): + if col(loc, instring) != 1: + raise ParseException(instring, loc, "not found at line start") + return super().parseImpl(instring, loc, doActions) + + +class FollowedBy(ParseElementEnhance): + """Lookahead matching of the given parse expression. + ``FollowedBy`` does *not* advance the parsing position within + the input string, it only verifies that the specified parse + expression matches at the current position. ``FollowedBy`` + always returns a null token list. If any results names are defined + in the lookahead expression, those *will* be returned for access by + name. + + Example:: + + # use FollowedBy to match a label only if it is followed by a ':' + data_word = Word(alphas) + label = data_word + FollowedBy(':') + attr_expr = Group(label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) + + attr_expr[1, ...].parse_string("shape: SQUARE color: BLACK posn: upper left").pprint() + + prints:: + + [['shape', 'SQUARE'], ['color', 'BLACK'], ['posn', 'upper left']] + """ + + def __init__(self, expr: Union[ParserElement, str]): + super().__init__(expr) + self.mayReturnEmpty = True + + def parseImpl(self, instring, loc, doActions=True): + # by using self._expr.parse and deleting the contents of the returned ParseResults list + # we keep any named results that were defined in the FollowedBy expression + _, ret = self.expr._parse(instring, loc, doActions=doActions) + del ret[:] + + return loc, ret + + +class PrecededBy(ParseElementEnhance): + """Lookbehind matching of the given parse expression. + ``PrecededBy`` does not advance the parsing position within the + input string, it only verifies that the specified parse expression + matches prior to the current position. ``PrecededBy`` always + returns a null token list, but if a results name is defined on the + given expression, it is returned. + + Parameters: + + - expr - expression that must match prior to the current parse + location + - retreat - (default= ``None``) - (int) maximum number of characters + to lookbehind prior to the current parse location + + If the lookbehind expression is a string, :class:`Literal`, + :class:`Keyword`, or a :class:`Word` or :class:`CharsNotIn` + with a specified exact or maximum length, then the retreat + parameter is not required. Otherwise, retreat must be specified to + give a maximum number of characters to look back from + the current parse position for a lookbehind match. + + Example:: + + # VB-style variable names with type prefixes + int_var = PrecededBy("#") + pyparsing_common.identifier + str_var = PrecededBy("$") + pyparsing_common.identifier + + """ + + def __init__( + self, expr: Union[ParserElement, str], retreat: typing.Optional[int] = None + ): + super().__init__(expr) + self.expr = self.expr().leave_whitespace() + self.mayReturnEmpty = True + self.mayIndexError = False + self.exact = False + if isinstance(expr, str_type): + retreat = len(expr) + self.exact = True + elif isinstance(expr, (Literal, Keyword)): + retreat = expr.matchLen + self.exact = True + elif isinstance(expr, (Word, CharsNotIn)) and expr.maxLen != _MAX_INT: + retreat = expr.maxLen + self.exact = True + elif isinstance(expr, PositionToken): + retreat = 0 + self.exact = True + self.retreat = retreat + self.errmsg = "not preceded by " + str(expr) + self.skipWhitespace = False + self.parseAction.append(lambda s, l, t: t.__delitem__(slice(None, None))) + + def parseImpl(self, instring, loc=0, doActions=True): + if self.exact: + if loc < self.retreat: + raise ParseException(instring, loc, self.errmsg) + start = loc - self.retreat + _, ret = self.expr._parse(instring, start) + else: + # retreat specified a maximum lookbehind window, iterate + test_expr = self.expr + StringEnd() + instring_slice = instring[max(0, loc - self.retreat) : loc] + last_expr = ParseException(instring, loc, self.errmsg) + for offset in range(1, min(loc, self.retreat + 1) + 1): + try: + # print('trying', offset, instring_slice, repr(instring_slice[loc - offset:])) + _, ret = test_expr._parse( + instring_slice, len(instring_slice) - offset + ) + except ParseBaseException as pbe: + last_expr = pbe + else: + break + else: + raise last_expr + return loc, ret + + +class Located(ParseElementEnhance): + """ + Decorates a returned token with its starting and ending + locations in the input string. + + This helper adds the following results names: + + - ``locn_start`` - location where matched expression begins + - ``locn_end`` - location where matched expression ends + - ``value`` - the actual parsed results + + Be careful if the input text contains ``<TAB>`` characters, you + may want to call :class:`ParserElement.parse_with_tabs` + + Example:: + + wd = Word(alphas) + for match in Located(wd).search_string("ljsdf123lksdjjf123lkkjj1222"): + print(match) + + prints:: + + [0, ['ljsdf'], 5] + [8, ['lksdjjf'], 15] + [18, ['lkkjj'], 23] + + """ + + def parseImpl(self, instring, loc, doActions=True): + start = loc + loc, tokens = self.expr._parse(instring, start, doActions, callPreParse=False) + ret_tokens = ParseResults([start, tokens, loc]) + ret_tokens["locn_start"] = start + ret_tokens["value"] = tokens + ret_tokens["locn_end"] = loc + if self.resultsName: + # must return as a list, so that the name will be attached to the complete group + return loc, [ret_tokens] + else: + return loc, ret_tokens + + +class NotAny(ParseElementEnhance): + """ + Lookahead to disallow matching with the given parse expression. + ``NotAny`` does *not* advance the parsing position within the + input string, it only verifies that the specified parse expression + does *not* match at the current position. Also, ``NotAny`` does + *not* skip over leading whitespace. ``NotAny`` always returns + a null token list. May be constructed using the ``'~'`` operator. + + Example:: + + AND, OR, NOT = map(CaselessKeyword, "AND OR NOT".split()) + + # take care not to mistake keywords for identifiers + ident = ~(AND | OR | NOT) + Word(alphas) + boolean_term = Opt(NOT) + ident + + # very crude boolean expression - to support parenthesis groups and + # operation hierarchy, use infix_notation + boolean_expr = boolean_term + ((AND | OR) + boolean_term)[...] + + # integers that are followed by "." are actually floats + integer = Word(nums) + ~Char(".") + """ + + def __init__(self, expr: Union[ParserElement, str]): + super().__init__(expr) + # do NOT use self.leave_whitespace(), don't want to propagate to exprs + # self.leave_whitespace() + self.skipWhitespace = False + + self.mayReturnEmpty = True + self.errmsg = "Found unwanted token, " + str(self.expr) + + def parseImpl(self, instring, loc, doActions=True): + if self.expr.can_parse_next(instring, loc): + raise ParseException(instring, loc, self.errmsg, self) + return loc, [] + + def _generateDefaultName(self): + return "~{" + str(self.expr) + "}" + + +class _MultipleMatch(ParseElementEnhance): + def __init__( + self, + expr: ParserElement, + stop_on: typing.Optional[Union[ParserElement, str]] = None, + *, + stopOn: typing.Optional[Union[ParserElement, str]] = None, + ): + super().__init__(expr) + stopOn = stopOn or stop_on + self.saveAsList = True + ender = stopOn + if isinstance(ender, str_type): + ender = self._literalStringClass(ender) + self.stopOn(ender) + + def stopOn(self, ender) -> ParserElement: + if isinstance(ender, str_type): + ender = self._literalStringClass(ender) + self.not_ender = ~ender if ender is not None else None + return self + + def parseImpl(self, instring, loc, doActions=True): + self_expr_parse = self.expr._parse + self_skip_ignorables = self._skipIgnorables + check_ender = self.not_ender is not None + if check_ender: + try_not_ender = self.not_ender.tryParse + + # must be at least one (but first see if we are the stopOn sentinel; + # if so, fail) + if check_ender: + try_not_ender(instring, loc) + loc, tokens = self_expr_parse(instring, loc, doActions) + try: + hasIgnoreExprs = not not self.ignoreExprs + while 1: + if check_ender: + try_not_ender(instring, loc) + if hasIgnoreExprs: + preloc = self_skip_ignorables(instring, loc) + else: + preloc = loc + loc, tmptokens = self_expr_parse(instring, preloc, doActions) + if tmptokens or tmptokens.haskeys(): + tokens += tmptokens + except (ParseException, IndexError): + pass + + return loc, tokens + + def _setResultsName(self, name, listAllMatches=False): + if ( + __diag__.warn_ungrouped_named_tokens_in_collection + and Diagnostics.warn_ungrouped_named_tokens_in_collection + not in self.suppress_warnings_ + ): + for e in [self.expr] + self.expr.recurse(): + if ( + isinstance(e, ParserElement) + and e.resultsName + and Diagnostics.warn_ungrouped_named_tokens_in_collection + not in e.suppress_warnings_ + ): + warnings.warn( + "{}: setting results name {!r} on {} expression " + "collides with {!r} on contained expression".format( + "warn_ungrouped_named_tokens_in_collection", + name, + type(self).__name__, + e.resultsName, + ), + stacklevel=3, + ) + + return super()._setResultsName(name, listAllMatches) + + +class OneOrMore(_MultipleMatch): + """ + Repetition of one or more of the given expression. + + Parameters: + - expr - expression that must match one or more times + - stop_on - (default= ``None``) - expression for a terminating sentinel + (only required if the sentinel would ordinarily match the repetition + expression) + + Example:: + + data_word = Word(alphas) + label = data_word + FollowedBy(':') + attr_expr = Group(label + Suppress(':') + OneOrMore(data_word).set_parse_action(' '.join)) + + text = "shape: SQUARE posn: upper left color: BLACK" + attr_expr[1, ...].parse_string(text).pprint() # Fail! read 'color' as data instead of next label -> [['shape', 'SQUARE color']] + + # use stop_on attribute for OneOrMore to avoid reading label string as part of the data + attr_expr = Group(label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) + OneOrMore(attr_expr).parse_string(text).pprint() # Better -> [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'BLACK']] + + # could also be written as + (attr_expr * (1,)).parse_string(text).pprint() + """ + + def _generateDefaultName(self): + return "{" + str(self.expr) + "}..." + + +class ZeroOrMore(_MultipleMatch): + """ + Optional repetition of zero or more of the given expression. + + Parameters: + - ``expr`` - expression that must match zero or more times + - ``stop_on`` - expression for a terminating sentinel + (only required if the sentinel would ordinarily match the repetition + expression) - (default= ``None``) + + Example: similar to :class:`OneOrMore` + """ + + def __init__( + self, + expr: ParserElement, + stop_on: typing.Optional[Union[ParserElement, str]] = None, + *, + stopOn: typing.Optional[Union[ParserElement, str]] = None, + ): + super().__init__(expr, stopOn=stopOn or stop_on) + self.mayReturnEmpty = True + + def parseImpl(self, instring, loc, doActions=True): + try: + return super().parseImpl(instring, loc, doActions) + except (ParseException, IndexError): + return loc, ParseResults([], name=self.resultsName) + + def _generateDefaultName(self): + return "[" + str(self.expr) + "]..." + + +class _NullToken: + def __bool__(self): + return False + + def __str__(self): + return "" + + +class Opt(ParseElementEnhance): + """ + Optional matching of the given expression. + + Parameters: + - ``expr`` - expression that must match zero or more times + - ``default`` (optional) - value to be returned if the optional expression is not found. + + Example:: + + # US postal code can be a 5-digit zip, plus optional 4-digit qualifier + zip = Combine(Word(nums, exact=5) + Opt('-' + Word(nums, exact=4))) + zip.run_tests(''' + # traditional ZIP code + 12345 + + # ZIP+4 form + 12101-0001 + + # invalid ZIP + 98765- + ''') + + prints:: + + # traditional ZIP code + 12345 + ['12345'] + + # ZIP+4 form + 12101-0001 + ['12101-0001'] + + # invalid ZIP + 98765- + ^ + FAIL: Expected end of text (at char 5), (line:1, col:6) + """ + + __optionalNotMatched = _NullToken() + + def __init__( + self, expr: Union[ParserElement, str], default: Any = __optionalNotMatched + ): + super().__init__(expr, savelist=False) + self.saveAsList = self.expr.saveAsList + self.defaultValue = default + self.mayReturnEmpty = True + + def parseImpl(self, instring, loc, doActions=True): + self_expr = self.expr + try: + loc, tokens = self_expr._parse(instring, loc, doActions, callPreParse=False) + except (ParseException, IndexError): + default_value = self.defaultValue + if default_value is not self.__optionalNotMatched: + if self_expr.resultsName: + tokens = ParseResults([default_value]) + tokens[self_expr.resultsName] = default_value + else: + tokens = [default_value] + else: + tokens = [] + return loc, tokens + + def _generateDefaultName(self): + inner = str(self.expr) + # strip off redundant inner {}'s + while len(inner) > 1 and inner[0 :: len(inner) - 1] == "{}": + inner = inner[1:-1] + return "[" + inner + "]" + + +Optional = Opt + + +class SkipTo(ParseElementEnhance): + """ + Token for skipping over all undefined text until the matched + expression is found. + + Parameters: + - ``expr`` - target expression marking the end of the data to be skipped + - ``include`` - if ``True``, the target expression is also parsed + (the skipped text and target expression are returned as a 2-element + list) (default= ``False``). + - ``ignore`` - (default= ``None``) used to define grammars (typically quoted strings and + comments) that might contain false matches to the target expression + - ``fail_on`` - (default= ``None``) define expressions that are not allowed to be + included in the skipped test; if found before the target expression is found, + the :class:`SkipTo` is not a match + + Example:: + + report = ''' + Outstanding Issues Report - 1 Jan 2000 + + # | Severity | Description | Days Open + -----+----------+-------------------------------------------+----------- + 101 | Critical | Intermittent system crash | 6 + 94 | Cosmetic | Spelling error on Login ('log|n') | 14 + 79 | Minor | System slow when running too many reports | 47 + ''' + integer = Word(nums) + SEP = Suppress('|') + # use SkipTo to simply match everything up until the next SEP + # - ignore quoted strings, so that a '|' character inside a quoted string does not match + # - parse action will call token.strip() for each matched token, i.e., the description body + string_data = SkipTo(SEP, ignore=quoted_string) + string_data.set_parse_action(token_map(str.strip)) + ticket_expr = (integer("issue_num") + SEP + + string_data("sev") + SEP + + string_data("desc") + SEP + + integer("days_open")) + + for tkt in ticket_expr.search_string(report): + print tkt.dump() + + prints:: + + ['101', 'Critical', 'Intermittent system crash', '6'] + - days_open: '6' + - desc: 'Intermittent system crash' + - issue_num: '101' + - sev: 'Critical' + ['94', 'Cosmetic', "Spelling error on Login ('log|n')", '14'] + - days_open: '14' + - desc: "Spelling error on Login ('log|n')" + - issue_num: '94' + - sev: 'Cosmetic' + ['79', 'Minor', 'System slow when running too many reports', '47'] + - days_open: '47' + - desc: 'System slow when running too many reports' + - issue_num: '79' + - sev: 'Minor' + """ + + def __init__( + self, + other: Union[ParserElement, str], + include: bool = False, + ignore: bool = None, + fail_on: typing.Optional[Union[ParserElement, str]] = None, + *, + failOn: Union[ParserElement, str] = None, + ): + super().__init__(other) + failOn = failOn or fail_on + self.ignoreExpr = ignore + self.mayReturnEmpty = True + self.mayIndexError = False + self.includeMatch = include + self.saveAsList = False + if isinstance(failOn, str_type): + self.failOn = self._literalStringClass(failOn) + else: + self.failOn = failOn + self.errmsg = "No match found for " + str(self.expr) + + def parseImpl(self, instring, loc, doActions=True): + startloc = loc + instrlen = len(instring) + self_expr_parse = self.expr._parse + self_failOn_canParseNext = ( + self.failOn.canParseNext if self.failOn is not None else None + ) + self_ignoreExpr_tryParse = ( + self.ignoreExpr.tryParse if self.ignoreExpr is not None else None + ) + + tmploc = loc + while tmploc <= instrlen: + if self_failOn_canParseNext is not None: + # break if failOn expression matches + if self_failOn_canParseNext(instring, tmploc): + break + + if self_ignoreExpr_tryParse is not None: + # advance past ignore expressions + while 1: + try: + tmploc = self_ignoreExpr_tryParse(instring, tmploc) + except ParseBaseException: + break + + try: + self_expr_parse(instring, tmploc, doActions=False, callPreParse=False) + except (ParseException, IndexError): + # no match, advance loc in string + tmploc += 1 + else: + # matched skipto expr, done + break + + else: + # ran off the end of the input string without matching skipto expr, fail + raise ParseException(instring, loc, self.errmsg, self) + + # build up return values + loc = tmploc + skiptext = instring[startloc:loc] + skipresult = ParseResults(skiptext) + + if self.includeMatch: + loc, mat = self_expr_parse(instring, loc, doActions, callPreParse=False) + skipresult += mat + + return loc, skipresult + + +class Forward(ParseElementEnhance): + """ + Forward declaration of an expression to be defined later - + used for recursive grammars, such as algebraic infix notation. + When the expression is known, it is assigned to the ``Forward`` + variable using the ``'<<'`` operator. + + Note: take care when assigning to ``Forward`` not to overlook + precedence of operators. + + Specifically, ``'|'`` has a lower precedence than ``'<<'``, so that:: + + fwd_expr << a | b | c + + will actually be evaluated as:: + + (fwd_expr << a) | b | c + + thereby leaving b and c out as parseable alternatives. It is recommended that you + explicitly group the values inserted into the ``Forward``:: + + fwd_expr << (a | b | c) + + Converting to use the ``'<<='`` operator instead will avoid this problem. + + See :class:`ParseResults.pprint` for an example of a recursive + parser created using ``Forward``. + """ + + def __init__(self, other: typing.Optional[Union[ParserElement, str]] = None): + self.caller_frame = traceback.extract_stack(limit=2)[0] + super().__init__(other, savelist=False) + self.lshift_line = None + + def __lshift__(self, other): + if hasattr(self, "caller_frame"): + del self.caller_frame + if isinstance(other, str_type): + other = self._literalStringClass(other) + self.expr = other + self.mayIndexError = self.expr.mayIndexError + self.mayReturnEmpty = self.expr.mayReturnEmpty + self.set_whitespace_chars( + self.expr.whiteChars, copy_defaults=self.expr.copyDefaultWhiteChars + ) + self.skipWhitespace = self.expr.skipWhitespace + self.saveAsList = self.expr.saveAsList + self.ignoreExprs.extend(self.expr.ignoreExprs) + self.lshift_line = traceback.extract_stack(limit=2)[-2] + return self + + def __ilshift__(self, other): + return self << other + + def __or__(self, other): + caller_line = traceback.extract_stack(limit=2)[-2] + if ( + __diag__.warn_on_match_first_with_lshift_operator + and caller_line == self.lshift_line + and Diagnostics.warn_on_match_first_with_lshift_operator + not in self.suppress_warnings_ + ): + warnings.warn( + "using '<<' operator with '|' is probably an error, use '<<='", + stacklevel=2, + ) + ret = super().__or__(other) + return ret + + def __del__(self): + # see if we are getting dropped because of '=' reassignment of var instead of '<<=' or '<<' + if ( + self.expr is None + and __diag__.warn_on_assignment_to_Forward + and Diagnostics.warn_on_assignment_to_Forward not in self.suppress_warnings_ + ): + warnings.warn_explicit( + "Forward defined here but no expression attached later using '<<=' or '<<'", + UserWarning, + filename=self.caller_frame.filename, + lineno=self.caller_frame.lineno, + ) + + def parseImpl(self, instring, loc, doActions=True): + if ( + self.expr is None + and __diag__.warn_on_parse_using_empty_Forward + and Diagnostics.warn_on_parse_using_empty_Forward + not in self.suppress_warnings_ + ): + # walk stack until parse_string, scan_string, search_string, or transform_string is found + parse_fns = [ + "parse_string", + "scan_string", + "search_string", + "transform_string", + ] + tb = traceback.extract_stack(limit=200) + for i, frm in enumerate(reversed(tb), start=1): + if frm.name in parse_fns: + stacklevel = i + 1 + break + else: + stacklevel = 2 + warnings.warn( + "Forward expression was never assigned a value, will not parse any input", + stacklevel=stacklevel, + ) + if not ParserElement._left_recursion_enabled: + return super().parseImpl(instring, loc, doActions) + # ## Bounded Recursion algorithm ## + # Recursion only needs to be processed at ``Forward`` elements, since they are + # the only ones that can actually refer to themselves. The general idea is + # to handle recursion stepwise: We start at no recursion, then recurse once, + # recurse twice, ..., until more recursion offers no benefit (we hit the bound). + # + # The "trick" here is that each ``Forward`` gets evaluated in two contexts + # - to *match* a specific recursion level, and + # - to *search* the bounded recursion level + # and the two run concurrently. The *search* must *match* each recursion level + # to find the best possible match. This is handled by a memo table, which + # provides the previous match to the next level match attempt. + # + # See also "Left Recursion in Parsing Expression Grammars", Medeiros et al. + # + # There is a complication since we not only *parse* but also *transform* via + # actions: We do not want to run the actions too often while expanding. Thus, + # we expand using `doActions=False` and only run `doActions=True` if the next + # recursion level is acceptable. + with ParserElement.recursion_lock: + memo = ParserElement.recursion_memos + try: + # we are parsing at a specific recursion expansion - use it as-is + prev_loc, prev_result = memo[loc, self, doActions] + if isinstance(prev_result, Exception): + raise prev_result + return prev_loc, prev_result.copy() + except KeyError: + act_key = (loc, self, True) + peek_key = (loc, self, False) + # we are searching for the best recursion expansion - keep on improving + # both `doActions` cases must be tracked separately here! + prev_loc, prev_peek = memo[peek_key] = ( + loc - 1, + ParseException( + instring, loc, "Forward recursion without base case", self + ), + ) + if doActions: + memo[act_key] = memo[peek_key] + while True: + try: + new_loc, new_peek = super().parseImpl(instring, loc, False) + except ParseException: + # we failed before getting any match – do not hide the error + if isinstance(prev_peek, Exception): + raise + new_loc, new_peek = prev_loc, prev_peek + # the match did not get better: we are done + if new_loc <= prev_loc: + if doActions: + # replace the match for doActions=False as well, + # in case the action did backtrack + prev_loc, prev_result = memo[peek_key] = memo[act_key] + del memo[peek_key], memo[act_key] + return prev_loc, prev_result.copy() + del memo[peek_key] + return prev_loc, prev_peek.copy() + # the match did get better: see if we can improve further + else: + if doActions: + try: + memo[act_key] = super().parseImpl(instring, loc, True) + except ParseException as e: + memo[peek_key] = memo[act_key] = (new_loc, e) + raise + prev_loc, prev_peek = memo[peek_key] = new_loc, new_peek + + def leave_whitespace(self, recursive: bool = True) -> ParserElement: + self.skipWhitespace = False + return self + + def ignore_whitespace(self, recursive: bool = True) -> ParserElement: + self.skipWhitespace = True + return self + + def streamline(self) -> ParserElement: + if not self.streamlined: + self.streamlined = True + if self.expr is not None: + self.expr.streamline() + return self + + def validate(self, validateTrace=None) -> None: + if validateTrace is None: + validateTrace = [] + + if self not in validateTrace: + tmp = validateTrace[:] + [self] + if self.expr is not None: + self.expr.validate(tmp) + self._checkRecursion([]) + + def _generateDefaultName(self): + # Avoid infinite recursion by setting a temporary _defaultName + self._defaultName = ": ..." + + # Use the string representation of main expression. + retString = "..." + try: + if self.expr is not None: + retString = str(self.expr)[:1000] + else: + retString = "None" + finally: + return self.__class__.__name__ + ": " + retString + + def copy(self) -> ParserElement: + if self.expr is not None: + return super().copy() + else: + ret = Forward() + ret <<= self + return ret + + def _setResultsName(self, name, list_all_matches=False): + if ( + __diag__.warn_name_set_on_empty_Forward + and Diagnostics.warn_name_set_on_empty_Forward + not in self.suppress_warnings_ + ): + if self.expr is None: + warnings.warn( + "{}: setting results name {!r} on {} expression " + "that has no contained expression".format( + "warn_name_set_on_empty_Forward", name, type(self).__name__ + ), + stacklevel=3, + ) + + return super()._setResultsName(name, list_all_matches) + + ignoreWhitespace = ignore_whitespace + leaveWhitespace = leave_whitespace + + +class TokenConverter(ParseElementEnhance): + """ + Abstract subclass of :class:`ParseExpression`, for converting parsed results. + """ + + def __init__(self, expr: Union[ParserElement, str], savelist=False): + super().__init__(expr) # , savelist) + self.saveAsList = False + + +class Combine(TokenConverter): + """Converter to concatenate all matching tokens to a single string. + By default, the matching patterns must also be contiguous in the + input string; this can be disabled by specifying + ``'adjacent=False'`` in the constructor. + + Example:: + + real = Word(nums) + '.' + Word(nums) + print(real.parse_string('3.1416')) # -> ['3', '.', '1416'] + # will also erroneously match the following + print(real.parse_string('3. 1416')) # -> ['3', '.', '1416'] + + real = Combine(Word(nums) + '.' + Word(nums)) + print(real.parse_string('3.1416')) # -> ['3.1416'] + # no match when there are internal spaces + print(real.parse_string('3. 1416')) # -> Exception: Expected W:(0123...) + """ + + def __init__( + self, + expr: ParserElement, + join_string: str = "", + adjacent: bool = True, + *, + joinString: typing.Optional[str] = None, + ): + super().__init__(expr) + joinString = joinString if joinString is not None else join_string + # suppress whitespace-stripping in contained parse expressions, but re-enable it on the Combine itself + if adjacent: + self.leave_whitespace() + self.adjacent = adjacent + self.skipWhitespace = True + self.joinString = joinString + self.callPreparse = True + + def ignore(self, other) -> ParserElement: + if self.adjacent: + ParserElement.ignore(self, other) + else: + super().ignore(other) + return self + + def postParse(self, instring, loc, tokenlist): + retToks = tokenlist.copy() + del retToks[:] + retToks += ParseResults( + ["".join(tokenlist._asStringList(self.joinString))], modal=self.modalResults + ) + + if self.resultsName and retToks.haskeys(): + return [retToks] + else: + return retToks + + +class Group(TokenConverter): + """Converter to return the matched tokens as a list - useful for + returning tokens of :class:`ZeroOrMore` and :class:`OneOrMore` expressions. + + The optional ``aslist`` argument when set to True will return the + parsed tokens as a Python list instead of a pyparsing ParseResults. + + Example:: + + ident = Word(alphas) + num = Word(nums) + term = ident | num + func = ident + Opt(delimited_list(term)) + print(func.parse_string("fn a, b, 100")) + # -> ['fn', 'a', 'b', '100'] + + func = ident + Group(Opt(delimited_list(term))) + print(func.parse_string("fn a, b, 100")) + # -> ['fn', ['a', 'b', '100']] + """ + + def __init__(self, expr: ParserElement, aslist: bool = False): + super().__init__(expr) + self.saveAsList = True + self._asPythonList = aslist + + def postParse(self, instring, loc, tokenlist): + if self._asPythonList: + return ParseResults.List( + tokenlist.asList() + if isinstance(tokenlist, ParseResults) + else list(tokenlist) + ) + else: + return [tokenlist] + + +class Dict(TokenConverter): + """Converter to return a repetitive expression as a list, but also + as a dictionary. Each element can also be referenced using the first + token in the expression as its key. Useful for tabular report + scraping when the first column can be used as a item key. + + The optional ``asdict`` argument when set to True will return the + parsed tokens as a Python dict instead of a pyparsing ParseResults. + + Example:: + + data_word = Word(alphas) + label = data_word + FollowedBy(':') + + text = "shape: SQUARE posn: upper left color: light blue texture: burlap" + attr_expr = (label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) + + # print attributes as plain groups + print(attr_expr[1, ...].parse_string(text).dump()) + + # instead of OneOrMore(expr), parse using Dict(Group(expr)[1, ...]) - Dict will auto-assign names + result = Dict(Group(attr_expr)[1, ...]).parse_string(text) + print(result.dump()) + + # access named fields as dict entries, or output as dict + print(result['shape']) + print(result.as_dict()) + + prints:: + + ['shape', 'SQUARE', 'posn', 'upper left', 'color', 'light blue', 'texture', 'burlap'] + [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'light blue'], ['texture', 'burlap']] + - color: 'light blue' + - posn: 'upper left' + - shape: 'SQUARE' + - texture: 'burlap' + SQUARE + {'color': 'light blue', 'posn': 'upper left', 'texture': 'burlap', 'shape': 'SQUARE'} + + See more examples at :class:`ParseResults` of accessing fields by results name. + """ + + def __init__(self, expr: ParserElement, asdict: bool = False): + super().__init__(expr) + self.saveAsList = True + self._asPythonDict = asdict + + def postParse(self, instring, loc, tokenlist): + for i, tok in enumerate(tokenlist): + if len(tok) == 0: + continue + + ikey = tok[0] + if isinstance(ikey, int): + ikey = str(ikey).strip() + + if len(tok) == 1: + tokenlist[ikey] = _ParseResultsWithOffset("", i) + + elif len(tok) == 2 and not isinstance(tok[1], ParseResults): + tokenlist[ikey] = _ParseResultsWithOffset(tok[1], i) + + else: + try: + dictvalue = tok.copy() # ParseResults(i) + except Exception: + exc = TypeError( + "could not extract dict values from parsed results" + " - Dict expression must contain Grouped expressions" + ) + raise exc from None + + del dictvalue[0] + + if len(dictvalue) != 1 or ( + isinstance(dictvalue, ParseResults) and dictvalue.haskeys() + ): + tokenlist[ikey] = _ParseResultsWithOffset(dictvalue, i) + else: + tokenlist[ikey] = _ParseResultsWithOffset(dictvalue[0], i) + + if self._asPythonDict: + return [tokenlist.as_dict()] if self.resultsName else tokenlist.as_dict() + else: + return [tokenlist] if self.resultsName else tokenlist + + +class Suppress(TokenConverter): + """Converter for ignoring the results of a parsed expression. + + Example:: + + source = "a, b, c,d" + wd = Word(alphas) + wd_list1 = wd + (',' + wd)[...] + print(wd_list1.parse_string(source)) + + # often, delimiters that are useful during parsing are just in the + # way afterward - use Suppress to keep them out of the parsed output + wd_list2 = wd + (Suppress(',') + wd)[...] + print(wd_list2.parse_string(source)) + + # Skipped text (using '...') can be suppressed as well + source = "lead in START relevant text END trailing text" + start_marker = Keyword("START") + end_marker = Keyword("END") + find_body = Suppress(...) + start_marker + ... + end_marker + print(find_body.parse_string(source) + + prints:: + + ['a', ',', 'b', ',', 'c', ',', 'd'] + ['a', 'b', 'c', 'd'] + ['START', 'relevant text ', 'END'] + + (See also :class:`delimited_list`.) + """ + + def __init__(self, expr: Union[ParserElement, str], savelist: bool = False): + if expr is ...: + expr = _PendingSkip(NoMatch()) + super().__init__(expr) + + def __add__(self, other) -> "ParserElement": + if isinstance(self.expr, _PendingSkip): + return Suppress(SkipTo(other)) + other + else: + return super().__add__(other) + + def __sub__(self, other) -> "ParserElement": + if isinstance(self.expr, _PendingSkip): + return Suppress(SkipTo(other)) - other + else: + return super().__sub__(other) + + def postParse(self, instring, loc, tokenlist): + return [] + + def suppress(self) -> ParserElement: + return self + + +def trace_parse_action(f: ParseAction) -> ParseAction: + """Decorator for debugging parse actions. + + When the parse action is called, this decorator will print + ``">> entering method-name(line:<current_source_line>, <parse_location>, <matched_tokens>)"``. + When the parse action completes, the decorator will print + ``"<<"`` followed by the returned value, or any exception that the parse action raised. + + Example:: + + wd = Word(alphas) + + @trace_parse_action + def remove_duplicate_chars(tokens): + return ''.join(sorted(set(''.join(tokens)))) + + wds = wd[1, ...].set_parse_action(remove_duplicate_chars) + print(wds.parse_string("slkdjs sld sldd sdlf sdljf")) + + prints:: + + >>entering remove_duplicate_chars(line: 'slkdjs sld sldd sdlf sdljf', 0, (['slkdjs', 'sld', 'sldd', 'sdlf', 'sdljf'], {})) + <<leaving remove_duplicate_chars (ret: 'dfjkls') + ['dfjkls'] + """ + f = _trim_arity(f) + + def z(*paArgs): + thisFunc = f.__name__ + s, l, t = paArgs[-3:] + if len(paArgs) > 3: + thisFunc = paArgs[0].__class__.__name__ + "." + thisFunc + sys.stderr.write( + ">>entering {}(line: {!r}, {}, {!r})\n".format(thisFunc, line(l, s), l, t) + ) + try: + ret = f(*paArgs) + except Exception as exc: + sys.stderr.write("<<leaving {} (exception: {})\n".format(thisFunc, exc)) + raise + sys.stderr.write("<<leaving {} (ret: {!r})\n".format(thisFunc, ret)) + return ret + + z.__name__ = f.__name__ + return z + + +# convenience constants for positional expressions +empty = Empty().set_name("empty") +line_start = LineStart().set_name("line_start") +line_end = LineEnd().set_name("line_end") +string_start = StringStart().set_name("string_start") +string_end = StringEnd().set_name("string_end") + +_escapedPunc = Word(_bslash, r"\[]-*.$+^?()~ ", exact=2).set_parse_action( + lambda s, l, t: t[0][1] +) +_escapedHexChar = Regex(r"\\0?[xX][0-9a-fA-F]+").set_parse_action( + lambda s, l, t: chr(int(t[0].lstrip(r"\0x"), 16)) +) +_escapedOctChar = Regex(r"\\0[0-7]+").set_parse_action( + lambda s, l, t: chr(int(t[0][1:], 8)) +) +_singleChar = ( + _escapedPunc | _escapedHexChar | _escapedOctChar | CharsNotIn(r"\]", exact=1) +) +_charRange = Group(_singleChar + Suppress("-") + _singleChar) +_reBracketExpr = ( + Literal("[") + + Opt("^").set_results_name("negate") + + Group(OneOrMore(_charRange | _singleChar)).set_results_name("body") + + "]" +) + + +def srange(s: str) -> str: + r"""Helper to easily define string ranges for use in :class:`Word` + construction. Borrows syntax from regexp ``'[]'`` string range + definitions:: + + srange("[0-9]") -> "0123456789" + srange("[a-z]") -> "abcdefghijklmnopqrstuvwxyz" + srange("[a-z$_]") -> "abcdefghijklmnopqrstuvwxyz$_" + + The input string must be enclosed in []'s, and the returned string + is the expanded character set joined into a single string. The + values enclosed in the []'s may be: + + - a single character + - an escaped character with a leading backslash (such as ``\-`` + or ``\]``) + - an escaped hex character with a leading ``'\x'`` + (``\x21``, which is a ``'!'`` character) (``\0x##`` + is also supported for backwards compatibility) + - an escaped octal character with a leading ``'\0'`` + (``\041``, which is a ``'!'`` character) + - a range of any of the above, separated by a dash (``'a-z'``, + etc.) + - any combination of the above (``'aeiouy'``, + ``'a-zA-Z0-9_$'``, etc.) + """ + _expanded = ( + lambda p: p + if not isinstance(p, ParseResults) + else "".join(chr(c) for c in range(ord(p[0]), ord(p[1]) + 1)) + ) + try: + return "".join(_expanded(part) for part in _reBracketExpr.parse_string(s).body) + except Exception: + return "" + + +def token_map(func, *args) -> ParseAction: + """Helper to define a parse action by mapping a function to all + elements of a :class:`ParseResults` list. If any additional args are passed, + they are forwarded to the given function as additional arguments + after the token, as in + ``hex_integer = Word(hexnums).set_parse_action(token_map(int, 16))``, + which will convert the parsed data to an integer using base 16. + + Example (compare the last to example in :class:`ParserElement.transform_string`:: + + hex_ints = Word(hexnums)[1, ...].set_parse_action(token_map(int, 16)) + hex_ints.run_tests(''' + 00 11 22 aa FF 0a 0d 1a + ''') + + upperword = Word(alphas).set_parse_action(token_map(str.upper)) + upperword[1, ...].run_tests(''' + my kingdom for a horse + ''') + + wd = Word(alphas).set_parse_action(token_map(str.title)) + wd[1, ...].set_parse_action(' '.join).run_tests(''' + now is the winter of our discontent made glorious summer by this sun of york + ''') + + prints:: + + 00 11 22 aa FF 0a 0d 1a + [0, 17, 34, 170, 255, 10, 13, 26] + + my kingdom for a horse + ['MY', 'KINGDOM', 'FOR', 'A', 'HORSE'] + + now is the winter of our discontent made glorious summer by this sun of york + ['Now Is The Winter Of Our Discontent Made Glorious Summer By This Sun Of York'] + """ + + def pa(s, l, t): + return [func(tokn, *args) for tokn in t] + + func_name = getattr(func, "__name__", getattr(func, "__class__").__name__) + pa.__name__ = func_name + + return pa + + +def autoname_elements() -> None: + """ + Utility to simplify mass-naming of parser elements, for + generating railroad diagram with named subdiagrams. + """ + for name, var in sys._getframe().f_back.f_locals.items(): + if isinstance(var, ParserElement) and not var.customName: + var.set_name(name) + + +dbl_quoted_string = Combine( + Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*') + '"' +).set_name("string enclosed in double quotes") + +sgl_quoted_string = Combine( + Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*") + "'" +).set_name("string enclosed in single quotes") + +quoted_string = Combine( + Regex(r'"(?:[^"\n\r\\]|(?:"")|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*') + '"' + | Regex(r"'(?:[^'\n\r\\]|(?:'')|(?:\\(?:[^x]|x[0-9a-fA-F]+)))*") + "'" +).set_name("quotedString using single or double quotes") + +unicode_string = Combine("u" + quoted_string.copy()).set_name("unicode string literal") + + +alphas8bit = srange(r"[\0xc0-\0xd6\0xd8-\0xf6\0xf8-\0xff]") +punc8bit = srange(r"[\0xa1-\0xbf\0xd7\0xf7]") + +# build list of built-in expressions, for future reference if a global default value +# gets updated +_builtin_exprs: List[ParserElement] = [ + v for v in vars().values() if isinstance(v, ParserElement) +] + +# backward compatibility names +tokenMap = token_map +conditionAsParseAction = condition_as_parse_action +nullDebugAction = null_debug_action +sglQuotedString = sgl_quoted_string +dblQuotedString = dbl_quoted_string +quotedString = quoted_string +unicodeString = unicode_string +lineStart = line_start +lineEnd = line_end +stringStart = string_start +stringEnd = string_end +traceParseAction = trace_parse_action diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/diagram/__init__.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/diagram/__init__.py new file mode 100644 index 0000000..8986447 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/diagram/__init__.py @@ -0,0 +1,642 @@ +import railroad +import pyparsing +import typing +from typing import ( + List, + NamedTuple, + Generic, + TypeVar, + Dict, + Callable, + Set, + Iterable, +) +from jinja2 import Template +from io import StringIO +import inspect + + +jinja2_template_source = """\ +<!DOCTYPE html> +<html> +<head> + {% if not head %} + <style type="text/css"> + .railroad-heading { + font-family: monospace; + } + </style> + {% else %} + {{ head | safe }} + {% endif %} +</head> +<body> +{{ body | safe }} +{% for diagram in diagrams %} + <div class="railroad-group"> + <h1 class="railroad-heading">{{ diagram.title }}</h1> + <div class="railroad-description">{{ diagram.text }}</div> + <div class="railroad-svg"> + {{ diagram.svg }} + </div> + </div> +{% endfor %} +</body> +</html> +""" + +template = Template(jinja2_template_source) + +# Note: ideally this would be a dataclass, but we're supporting Python 3.5+ so we can't do this yet +NamedDiagram = NamedTuple( + "NamedDiagram", + [("name", str), ("diagram", typing.Optional[railroad.DiagramItem]), ("index", int)], +) +""" +A simple structure for associating a name with a railroad diagram +""" + +T = TypeVar("T") + + +class EachItem(railroad.Group): + """ + Custom railroad item to compose a: + - Group containing a + - OneOrMore containing a + - Choice of the elements in the Each + with the group label indicating that all must be matched + """ + + all_label = "[ALL]" + + def __init__(self, *items): + choice_item = railroad.Choice(len(items) - 1, *items) + one_or_more_item = railroad.OneOrMore(item=choice_item) + super().__init__(one_or_more_item, label=self.all_label) + + +class AnnotatedItem(railroad.Group): + """ + Simple subclass of Group that creates an annotation label + """ + + def __init__(self, label: str, item): + super().__init__(item=item, label="[{}]".format(label) if label else label) + + +class EditablePartial(Generic[T]): + """ + Acts like a functools.partial, but can be edited. In other words, it represents a type that hasn't yet been + constructed. + """ + + # We need this here because the railroad constructors actually transform the data, so can't be called until the + # entire tree is assembled + + def __init__(self, func: Callable[..., T], args: list, kwargs: dict): + self.func = func + self.args = args + self.kwargs = kwargs + + @classmethod + def from_call(cls, func: Callable[..., T], *args, **kwargs) -> "EditablePartial[T]": + """ + If you call this function in the same way that you would call the constructor, it will store the arguments + as you expect. For example EditablePartial.from_call(Fraction, 1, 3)() == Fraction(1, 3) + """ + return EditablePartial(func=func, args=list(args), kwargs=kwargs) + + @property + def name(self): + return self.kwargs["name"] + + def __call__(self) -> T: + """ + Evaluate the partial and return the result + """ + args = self.args.copy() + kwargs = self.kwargs.copy() + + # This is a helpful hack to allow you to specify varargs parameters (e.g. *args) as keyword args (e.g. + # args=['list', 'of', 'things']) + arg_spec = inspect.getfullargspec(self.func) + if arg_spec.varargs in self.kwargs: + args += kwargs.pop(arg_spec.varargs) + + return self.func(*args, **kwargs) + + +def railroad_to_html(diagrams: List[NamedDiagram], **kwargs) -> str: + """ + Given a list of NamedDiagram, produce a single HTML string that visualises those diagrams + :params kwargs: kwargs to be passed in to the template + """ + data = [] + for diagram in diagrams: + if diagram.diagram is None: + continue + io = StringIO() + diagram.diagram.writeSvg(io.write) + title = diagram.name + if diagram.index == 0: + title += " (root)" + data.append({"title": title, "text": "", "svg": io.getvalue()}) + + return template.render(diagrams=data, **kwargs) + + +def resolve_partial(partial: "EditablePartial[T]") -> T: + """ + Recursively resolves a collection of Partials into whatever type they are + """ + if isinstance(partial, EditablePartial): + partial.args = resolve_partial(partial.args) + partial.kwargs = resolve_partial(partial.kwargs) + return partial() + elif isinstance(partial, list): + return [resolve_partial(x) for x in partial] + elif isinstance(partial, dict): + return {key: resolve_partial(x) for key, x in partial.items()} + else: + return partial + + +def to_railroad( + element: pyparsing.ParserElement, + diagram_kwargs: typing.Optional[dict] = None, + vertical: int = 3, + show_results_names: bool = False, + show_groups: bool = False, +) -> List[NamedDiagram]: + """ + Convert a pyparsing element tree into a list of diagrams. This is the recommended entrypoint to diagram + creation if you want to access the Railroad tree before it is converted to HTML + :param element: base element of the parser being diagrammed + :param diagram_kwargs: kwargs to pass to the Diagram() constructor + :param vertical: (optional) - int - limit at which number of alternatives should be + shown vertically instead of horizontally + :param show_results_names - bool to indicate whether results name annotations should be + included in the diagram + :param show_groups - bool to indicate whether groups should be highlighted with an unlabeled + surrounding box + """ + # Convert the whole tree underneath the root + lookup = ConverterState(diagram_kwargs=diagram_kwargs or {}) + _to_diagram_element( + element, + lookup=lookup, + parent=None, + vertical=vertical, + show_results_names=show_results_names, + show_groups=show_groups, + ) + + root_id = id(element) + # Convert the root if it hasn't been already + if root_id in lookup: + if not element.customName: + lookup[root_id].name = "" + lookup[root_id].mark_for_extraction(root_id, lookup, force=True) + + # Now that we're finished, we can convert from intermediate structures into Railroad elements + diags = list(lookup.diagrams.values()) + if len(diags) > 1: + # collapse out duplicate diags with the same name + seen = set() + deduped_diags = [] + for d in diags: + # don't extract SkipTo elements, they are uninformative as subdiagrams + if d.name == "...": + continue + if d.name is not None and d.name not in seen: + seen.add(d.name) + deduped_diags.append(d) + resolved = [resolve_partial(partial) for partial in deduped_diags] + else: + # special case - if just one diagram, always display it, even if + # it has no name + resolved = [resolve_partial(partial) for partial in diags] + return sorted(resolved, key=lambda diag: diag.index) + + +def _should_vertical( + specification: int, exprs: Iterable[pyparsing.ParserElement] +) -> bool: + """ + Returns true if we should return a vertical list of elements + """ + if specification is None: + return False + else: + return len(_visible_exprs(exprs)) >= specification + + +class ElementState: + """ + State recorded for an individual pyparsing Element + """ + + # Note: this should be a dataclass, but we have to support Python 3.5 + def __init__( + self, + element: pyparsing.ParserElement, + converted: EditablePartial, + parent: EditablePartial, + number: int, + name: str = None, + parent_index: typing.Optional[int] = None, + ): + #: The pyparsing element that this represents + self.element: pyparsing.ParserElement = element + #: The name of the element + self.name: typing.Optional[str] = name + #: The output Railroad element in an unconverted state + self.converted: EditablePartial = converted + #: The parent Railroad element, which we store so that we can extract this if it's duplicated + self.parent: EditablePartial = parent + #: The order in which we found this element, used for sorting diagrams if this is extracted into a diagram + self.number: int = number + #: The index of this inside its parent + self.parent_index: typing.Optional[int] = parent_index + #: If true, we should extract this out into a subdiagram + self.extract: bool = False + #: If true, all of this element's children have been filled out + self.complete: bool = False + + def mark_for_extraction( + self, el_id: int, state: "ConverterState", name: str = None, force: bool = False + ): + """ + Called when this instance has been seen twice, and thus should eventually be extracted into a sub-diagram + :param el_id: id of the element + :param state: element/diagram state tracker + :param name: name to use for this element's text + :param force: If true, force extraction now, regardless of the state of this. Only useful for extracting the + root element when we know we're finished + """ + self.extract = True + + # Set the name + if not self.name: + if name: + # Allow forcing a custom name + self.name = name + elif self.element.customName: + self.name = self.element.customName + else: + self.name = "" + + # Just because this is marked for extraction doesn't mean we can do it yet. We may have to wait for children + # to be added + # Also, if this is just a string literal etc, don't bother extracting it + if force or (self.complete and _worth_extracting(self.element)): + state.extract_into_diagram(el_id) + + +class ConverterState: + """ + Stores some state that persists between recursions into the element tree + """ + + def __init__(self, diagram_kwargs: typing.Optional[dict] = None): + #: A dictionary mapping ParserElements to state relating to them + self._element_diagram_states: Dict[int, ElementState] = {} + #: A dictionary mapping ParserElement IDs to subdiagrams generated from them + self.diagrams: Dict[int, EditablePartial[NamedDiagram]] = {} + #: The index of the next unnamed element + self.unnamed_index: int = 1 + #: The index of the next element. This is used for sorting + self.index: int = 0 + #: Shared kwargs that are used to customize the construction of diagrams + self.diagram_kwargs: dict = diagram_kwargs or {} + self.extracted_diagram_names: Set[str] = set() + + def __setitem__(self, key: int, value: ElementState): + self._element_diagram_states[key] = value + + def __getitem__(self, key: int) -> ElementState: + return self._element_diagram_states[key] + + def __delitem__(self, key: int): + del self._element_diagram_states[key] + + def __contains__(self, key: int): + return key in self._element_diagram_states + + def generate_unnamed(self) -> int: + """ + Generate a number used in the name of an otherwise unnamed diagram + """ + self.unnamed_index += 1 + return self.unnamed_index + + def generate_index(self) -> int: + """ + Generate a number used to index a diagram + """ + self.index += 1 + return self.index + + def extract_into_diagram(self, el_id: int): + """ + Used when we encounter the same token twice in the same tree. When this + happens, we replace all instances of that token with a terminal, and + create a new subdiagram for the token + """ + position = self[el_id] + + # Replace the original definition of this element with a regular block + if position.parent: + ret = EditablePartial.from_call(railroad.NonTerminal, text=position.name) + if "item" in position.parent.kwargs: + position.parent.kwargs["item"] = ret + elif "items" in position.parent.kwargs: + position.parent.kwargs["items"][position.parent_index] = ret + + # If the element we're extracting is a group, skip to its content but keep the title + if position.converted.func == railroad.Group: + content = position.converted.kwargs["item"] + else: + content = position.converted + + self.diagrams[el_id] = EditablePartial.from_call( + NamedDiagram, + name=position.name, + diagram=EditablePartial.from_call( + railroad.Diagram, content, **self.diagram_kwargs + ), + index=position.number, + ) + + del self[el_id] + + +def _worth_extracting(element: pyparsing.ParserElement) -> bool: + """ + Returns true if this element is worth having its own sub-diagram. Simply, if any of its children + themselves have children, then its complex enough to extract + """ + children = element.recurse() + return any(child.recurse() for child in children) + + +def _apply_diagram_item_enhancements(fn): + """ + decorator to ensure enhancements to a diagram item (such as results name annotations) + get applied on return from _to_diagram_element (we do this since there are several + returns in _to_diagram_element) + """ + + def _inner( + element: pyparsing.ParserElement, + parent: typing.Optional[EditablePartial], + lookup: ConverterState = None, + vertical: int = None, + index: int = 0, + name_hint: str = None, + show_results_names: bool = False, + show_groups: bool = False, + ) -> typing.Optional[EditablePartial]: + + ret = fn( + element, + parent, + lookup, + vertical, + index, + name_hint, + show_results_names, + show_groups, + ) + + # apply annotation for results name, if present + if show_results_names and ret is not None: + element_results_name = element.resultsName + if element_results_name: + # add "*" to indicate if this is a "list all results" name + element_results_name += "" if element.modalResults else "*" + ret = EditablePartial.from_call( + railroad.Group, item=ret, label=element_results_name + ) + + return ret + + return _inner + + +def _visible_exprs(exprs: Iterable[pyparsing.ParserElement]): + non_diagramming_exprs = ( + pyparsing.ParseElementEnhance, + pyparsing.PositionToken, + pyparsing.And._ErrorStop, + ) + return [ + e + for e in exprs + if not (e.customName or e.resultsName or isinstance(e, non_diagramming_exprs)) + ] + + +@_apply_diagram_item_enhancements +def _to_diagram_element( + element: pyparsing.ParserElement, + parent: typing.Optional[EditablePartial], + lookup: ConverterState = None, + vertical: int = None, + index: int = 0, + name_hint: str = None, + show_results_names: bool = False, + show_groups: bool = False, +) -> typing.Optional[EditablePartial]: + """ + Recursively converts a PyParsing Element to a railroad Element + :param lookup: The shared converter state that keeps track of useful things + :param index: The index of this element within the parent + :param parent: The parent of this element in the output tree + :param vertical: Controls at what point we make a list of elements vertical. If this is an integer (the default), + it sets the threshold of the number of items before we go vertical. If True, always go vertical, if False, never + do so + :param name_hint: If provided, this will override the generated name + :param show_results_names: bool flag indicating whether to add annotations for results names + :returns: The converted version of the input element, but as a Partial that hasn't yet been constructed + :param show_groups: bool flag indicating whether to show groups using bounding box + """ + exprs = element.recurse() + name = name_hint or element.customName or element.__class__.__name__ + + # Python's id() is used to provide a unique identifier for elements + el_id = id(element) + + element_results_name = element.resultsName + + # Here we basically bypass processing certain wrapper elements if they contribute nothing to the diagram + if not element.customName: + if isinstance( + element, + ( + # pyparsing.TokenConverter, + # pyparsing.Forward, + pyparsing.Located, + ), + ): + # However, if this element has a useful custom name, and its child does not, we can pass it on to the child + if exprs: + if not exprs[0].customName: + propagated_name = name + else: + propagated_name = None + + return _to_diagram_element( + element.expr, + parent=parent, + lookup=lookup, + vertical=vertical, + index=index, + name_hint=propagated_name, + show_results_names=show_results_names, + show_groups=show_groups, + ) + + # If the element isn't worth extracting, we always treat it as the first time we say it + if _worth_extracting(element): + if el_id in lookup: + # If we've seen this element exactly once before, we are only just now finding out that it's a duplicate, + # so we have to extract it into a new diagram. + looked_up = lookup[el_id] + looked_up.mark_for_extraction(el_id, lookup, name=name_hint) + ret = EditablePartial.from_call(railroad.NonTerminal, text=looked_up.name) + return ret + + elif el_id in lookup.diagrams: + # If we have seen the element at least twice before, and have already extracted it into a subdiagram, we + # just put in a marker element that refers to the sub-diagram + ret = EditablePartial.from_call( + railroad.NonTerminal, text=lookup.diagrams[el_id].kwargs["name"] + ) + return ret + + # Recursively convert child elements + # Here we find the most relevant Railroad element for matching pyparsing Element + # We use ``items=[]`` here to hold the place for where the child elements will go once created + if isinstance(element, pyparsing.And): + # detect And's created with ``expr*N`` notation - for these use a OneOrMore with a repeat + # (all will have the same name, and resultsName) + if not exprs: + return None + if len(set((e.name, e.resultsName) for e in exprs)) == 1: + ret = EditablePartial.from_call( + railroad.OneOrMore, item="", repeat=str(len(exprs)) + ) + elif _should_vertical(vertical, exprs): + ret = EditablePartial.from_call(railroad.Stack, items=[]) + else: + ret = EditablePartial.from_call(railroad.Sequence, items=[]) + elif isinstance(element, (pyparsing.Or, pyparsing.MatchFirst)): + if not exprs: + return None + if _should_vertical(vertical, exprs): + ret = EditablePartial.from_call(railroad.Choice, 0, items=[]) + else: + ret = EditablePartial.from_call(railroad.HorizontalChoice, items=[]) + elif isinstance(element, pyparsing.Each): + if not exprs: + return None + ret = EditablePartial.from_call(EachItem, items=[]) + elif isinstance(element, pyparsing.NotAny): + ret = EditablePartial.from_call(AnnotatedItem, label="NOT", item="") + elif isinstance(element, pyparsing.FollowedBy): + ret = EditablePartial.from_call(AnnotatedItem, label="LOOKAHEAD", item="") + elif isinstance(element, pyparsing.PrecededBy): + ret = EditablePartial.from_call(AnnotatedItem, label="LOOKBEHIND", item="") + elif isinstance(element, pyparsing.Group): + if show_groups: + ret = EditablePartial.from_call(AnnotatedItem, label="", item="") + else: + ret = EditablePartial.from_call(railroad.Group, label="", item="") + elif isinstance(element, pyparsing.TokenConverter): + ret = EditablePartial.from_call( + AnnotatedItem, label=type(element).__name__.lower(), item="" + ) + elif isinstance(element, pyparsing.Opt): + ret = EditablePartial.from_call(railroad.Optional, item="") + elif isinstance(element, pyparsing.OneOrMore): + ret = EditablePartial.from_call(railroad.OneOrMore, item="") + elif isinstance(element, pyparsing.ZeroOrMore): + ret = EditablePartial.from_call(railroad.ZeroOrMore, item="") + elif isinstance(element, pyparsing.Group): + ret = EditablePartial.from_call( + railroad.Group, item=None, label=element_results_name + ) + elif isinstance(element, pyparsing.Empty) and not element.customName: + # Skip unnamed "Empty" elements + ret = None + elif len(exprs) > 1: + ret = EditablePartial.from_call(railroad.Sequence, items=[]) + elif len(exprs) > 0 and not element_results_name: + ret = EditablePartial.from_call(railroad.Group, item="", label=name) + else: + terminal = EditablePartial.from_call(railroad.Terminal, element.defaultName) + ret = terminal + + if ret is None: + return + + # Indicate this element's position in the tree so we can extract it if necessary + lookup[el_id] = ElementState( + element=element, + converted=ret, + parent=parent, + parent_index=index, + number=lookup.generate_index(), + ) + if element.customName: + lookup[el_id].mark_for_extraction(el_id, lookup, element.customName) + + i = 0 + for expr in exprs: + # Add a placeholder index in case we have to extract the child before we even add it to the parent + if "items" in ret.kwargs: + ret.kwargs["items"].insert(i, None) + + item = _to_diagram_element( + expr, + parent=ret, + lookup=lookup, + vertical=vertical, + index=i, + show_results_names=show_results_names, + show_groups=show_groups, + ) + + # Some elements don't need to be shown in the diagram + if item is not None: + if "item" in ret.kwargs: + ret.kwargs["item"] = item + elif "items" in ret.kwargs: + # If we've already extracted the child, don't touch this index, since it's occupied by a nonterminal + ret.kwargs["items"][i] = item + i += 1 + elif "items" in ret.kwargs: + # If we're supposed to skip this element, remove it from the parent + del ret.kwargs["items"][i] + + # If all this items children are none, skip this item + if ret and ( + ("items" in ret.kwargs and len(ret.kwargs["items"]) == 0) + or ("item" in ret.kwargs and ret.kwargs["item"] is None) + ): + ret = EditablePartial.from_call(railroad.Terminal, name) + + # Mark this element as "complete", ie it has all of its children + if el_id in lookup: + lookup[el_id].complete = True + + if el_id in lookup and lookup[el_id].extract and lookup[el_id].complete: + lookup.extract_into_diagram(el_id) + if ret is not None: + ret = EditablePartial.from_call( + railroad.NonTerminal, text=lookup.diagrams[el_id].kwargs["name"] + ) + + return ret diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/diagram/__pycache__/__init__.cpython-311.pyc b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/diagram/__pycache__/__init__.cpython-311.pyc Binary files differnew file mode 100644 index 0000000..f26565d --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/diagram/__pycache__/__init__.cpython-311.pyc diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/exceptions.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/exceptions.py new file mode 100644 index 0000000..a38447b --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/exceptions.py @@ -0,0 +1,267 @@ +# exceptions.py + +import re +import sys +import typing + +from .util import col, line, lineno, _collapse_string_to_ranges +from .unicode import pyparsing_unicode as ppu + + +class ExceptionWordUnicode(ppu.Latin1, ppu.LatinA, ppu.LatinB, ppu.Greek, ppu.Cyrillic): + pass + + +_extract_alphanums = _collapse_string_to_ranges(ExceptionWordUnicode.alphanums) +_exception_word_extractor = re.compile("([" + _extract_alphanums + "]{1,16})|.") + + +class ParseBaseException(Exception): + """base exception class for all parsing runtime exceptions""" + + # Performance tuning: we construct a *lot* of these, so keep this + # constructor as small and fast as possible + def __init__( + self, + pstr: str, + loc: int = 0, + msg: typing.Optional[str] = None, + elem=None, + ): + self.loc = loc + if msg is None: + self.msg = pstr + self.pstr = "" + else: + self.msg = msg + self.pstr = pstr + self.parser_element = self.parserElement = elem + self.args = (pstr, loc, msg) + + @staticmethod + def explain_exception(exc, depth=16): + """ + Method to take an exception and translate the Python internal traceback into a list + of the pyparsing expressions that caused the exception to be raised. + + Parameters: + + - exc - exception raised during parsing (need not be a ParseException, in support + of Python exceptions that might be raised in a parse action) + - depth (default=16) - number of levels back in the stack trace to list expression + and function names; if None, the full stack trace names will be listed; if 0, only + the failing input line, marker, and exception string will be shown + + Returns a multi-line string listing the ParserElements and/or function names in the + exception's stack trace. + """ + import inspect + from .core import ParserElement + + if depth is None: + depth = sys.getrecursionlimit() + ret = [] + if isinstance(exc, ParseBaseException): + ret.append(exc.line) + ret.append(" " * (exc.column - 1) + "^") + ret.append("{}: {}".format(type(exc).__name__, exc)) + + if depth > 0: + callers = inspect.getinnerframes(exc.__traceback__, context=depth) + seen = set() + for i, ff in enumerate(callers[-depth:]): + frm = ff[0] + + f_self = frm.f_locals.get("self", None) + if isinstance(f_self, ParserElement): + if frm.f_code.co_name not in ("parseImpl", "_parseNoCache"): + continue + if id(f_self) in seen: + continue + seen.add(id(f_self)) + + self_type = type(f_self) + ret.append( + "{}.{} - {}".format( + self_type.__module__, self_type.__name__, f_self + ) + ) + + elif f_self is not None: + self_type = type(f_self) + ret.append("{}.{}".format(self_type.__module__, self_type.__name__)) + + else: + code = frm.f_code + if code.co_name in ("wrapper", "<module>"): + continue + + ret.append("{}".format(code.co_name)) + + depth -= 1 + if not depth: + break + + return "\n".join(ret) + + @classmethod + def _from_exception(cls, pe): + """ + internal factory method to simplify creating one type of ParseException + from another - avoids having __init__ signature conflicts among subclasses + """ + return cls(pe.pstr, pe.loc, pe.msg, pe.parserElement) + + @property + def line(self) -> str: + """ + Return the line of text where the exception occurred. + """ + return line(self.loc, self.pstr) + + @property + def lineno(self) -> int: + """ + Return the 1-based line number of text where the exception occurred. + """ + return lineno(self.loc, self.pstr) + + @property + def col(self) -> int: + """ + Return the 1-based column on the line of text where the exception occurred. + """ + return col(self.loc, self.pstr) + + @property + def column(self) -> int: + """ + Return the 1-based column on the line of text where the exception occurred. + """ + return col(self.loc, self.pstr) + + def __str__(self) -> str: + if self.pstr: + if self.loc >= len(self.pstr): + foundstr = ", found end of text" + else: + # pull out next word at error location + found_match = _exception_word_extractor.match(self.pstr, self.loc) + if found_match is not None: + found = found_match.group(0) + else: + found = self.pstr[self.loc : self.loc + 1] + foundstr = (", found %r" % found).replace(r"\\", "\\") + else: + foundstr = "" + return "{}{} (at char {}), (line:{}, col:{})".format( + self.msg, foundstr, self.loc, self.lineno, self.column + ) + + def __repr__(self): + return str(self) + + def mark_input_line(self, marker_string: str = None, *, markerString=">!<") -> str: + """ + Extracts the exception line from the input string, and marks + the location of the exception with a special symbol. + """ + markerString = marker_string if marker_string is not None else markerString + line_str = self.line + line_column = self.column - 1 + if markerString: + line_str = "".join( + (line_str[:line_column], markerString, line_str[line_column:]) + ) + return line_str.strip() + + def explain(self, depth=16) -> str: + """ + Method to translate the Python internal traceback into a list + of the pyparsing expressions that caused the exception to be raised. + + Parameters: + + - depth (default=16) - number of levels back in the stack trace to list expression + and function names; if None, the full stack trace names will be listed; if 0, only + the failing input line, marker, and exception string will be shown + + Returns a multi-line string listing the ParserElements and/or function names in the + exception's stack trace. + + Example:: + + expr = pp.Word(pp.nums) * 3 + try: + expr.parse_string("123 456 A789") + except pp.ParseException as pe: + print(pe.explain(depth=0)) + + prints:: + + 123 456 A789 + ^ + ParseException: Expected W:(0-9), found 'A' (at char 8), (line:1, col:9) + + Note: the diagnostic output will include string representations of the expressions + that failed to parse. These representations will be more helpful if you use `set_name` to + give identifiable names to your expressions. Otherwise they will use the default string + forms, which may be cryptic to read. + + Note: pyparsing's default truncation of exception tracebacks may also truncate the + stack of expressions that are displayed in the ``explain`` output. To get the full listing + of parser expressions, you may have to set ``ParserElement.verbose_stacktrace = True`` + """ + return self.explain_exception(self, depth) + + markInputline = mark_input_line + + +class ParseException(ParseBaseException): + """ + Exception thrown when a parse expression doesn't match the input string + + Example:: + + try: + Word(nums).set_name("integer").parse_string("ABC") + except ParseException as pe: + print(pe) + print("column: {}".format(pe.column)) + + prints:: + + Expected integer (at char 0), (line:1, col:1) + column: 1 + + """ + + +class ParseFatalException(ParseBaseException): + """ + User-throwable exception thrown when inconsistent parse content + is found; stops all parsing immediately + """ + + +class ParseSyntaxException(ParseFatalException): + """ + Just like :class:`ParseFatalException`, but thrown internally + when an :class:`ErrorStop<And._ErrorStop>` ('-' operator) indicates + that parsing is to stop immediately because an unbacktrackable + syntax error has been found. + """ + + +class RecursiveGrammarException(Exception): + """ + Exception thrown by :class:`ParserElement.validate` if the + grammar could be left-recursive; parser may need to enable + left recursion using :class:`ParserElement.enable_left_recursion<ParserElement.enable_left_recursion>` + """ + + def __init__(self, parseElementList): + self.parseElementTrace = parseElementList + + def __str__(self) -> str: + return "RecursiveGrammarException: {}".format(self.parseElementTrace) diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/helpers.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/helpers.py new file mode 100644 index 0000000..9588b3b --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/helpers.py @@ -0,0 +1,1088 @@ +# helpers.py +import html.entities +import re +import typing + +from . import __diag__ +from .core import * +from .util import _bslash, _flatten, _escape_regex_range_chars + + +# +# global helpers +# +def delimited_list( + expr: Union[str, ParserElement], + delim: Union[str, ParserElement] = ",", + combine: bool = False, + min: typing.Optional[int] = None, + max: typing.Optional[int] = None, + *, + allow_trailing_delim: bool = False, +) -> ParserElement: + """Helper to define a delimited list of expressions - the delimiter + defaults to ','. By default, the list elements and delimiters can + have intervening whitespace, and comments, but this can be + overridden by passing ``combine=True`` in the constructor. If + ``combine`` is set to ``True``, the matching tokens are + returned as a single token string, with the delimiters included; + otherwise, the matching tokens are returned as a list of tokens, + with the delimiters suppressed. + + If ``allow_trailing_delim`` is set to True, then the list may end with + a delimiter. + + Example:: + + delimited_list(Word(alphas)).parse_string("aa,bb,cc") # -> ['aa', 'bb', 'cc'] + delimited_list(Word(hexnums), delim=':', combine=True).parse_string("AA:BB:CC:DD:EE") # -> ['AA:BB:CC:DD:EE'] + """ + if isinstance(expr, str_type): + expr = ParserElement._literalStringClass(expr) + + dlName = "{expr} [{delim} {expr}]...{end}".format( + expr=str(expr.copy().streamline()), + delim=str(delim), + end=" [{}]".format(str(delim)) if allow_trailing_delim else "", + ) + + if not combine: + delim = Suppress(delim) + + if min is not None: + if min < 1: + raise ValueError("min must be greater than 0") + min -= 1 + if max is not None: + if min is not None and max <= min: + raise ValueError("max must be greater than, or equal to min") + max -= 1 + delimited_list_expr = expr + (delim + expr)[min, max] + + if allow_trailing_delim: + delimited_list_expr += Opt(delim) + + if combine: + return Combine(delimited_list_expr).set_name(dlName) + else: + return delimited_list_expr.set_name(dlName) + + +def counted_array( + expr: ParserElement, + int_expr: typing.Optional[ParserElement] = None, + *, + intExpr: typing.Optional[ParserElement] = None, +) -> ParserElement: + """Helper to define a counted list of expressions. + + This helper defines a pattern of the form:: + + integer expr expr expr... + + where the leading integer tells how many expr expressions follow. + The matched tokens returns the array of expr tokens as a list - the + leading count token is suppressed. + + If ``int_expr`` is specified, it should be a pyparsing expression + that produces an integer value. + + Example:: + + counted_array(Word(alphas)).parse_string('2 ab cd ef') # -> ['ab', 'cd'] + + # in this parser, the leading integer value is given in binary, + # '10' indicating that 2 values are in the array + binary_constant = Word('01').set_parse_action(lambda t: int(t[0], 2)) + counted_array(Word(alphas), int_expr=binary_constant).parse_string('10 ab cd ef') # -> ['ab', 'cd'] + + # if other fields must be parsed after the count but before the + # list items, give the fields results names and they will + # be preserved in the returned ParseResults: + count_with_metadata = integer + Word(alphas)("type") + typed_array = counted_array(Word(alphanums), int_expr=count_with_metadata)("items") + result = typed_array.parse_string("3 bool True True False") + print(result.dump()) + + # prints + # ['True', 'True', 'False'] + # - items: ['True', 'True', 'False'] + # - type: 'bool' + """ + intExpr = intExpr or int_expr + array_expr = Forward() + + def count_field_parse_action(s, l, t): + nonlocal array_expr + n = t[0] + array_expr <<= (expr * n) if n else Empty() + # clear list contents, but keep any named results + del t[:] + + if intExpr is None: + intExpr = Word(nums).set_parse_action(lambda t: int(t[0])) + else: + intExpr = intExpr.copy() + intExpr.set_name("arrayLen") + intExpr.add_parse_action(count_field_parse_action, call_during_try=True) + return (intExpr + array_expr).set_name("(len) " + str(expr) + "...") + + +def match_previous_literal(expr: ParserElement) -> ParserElement: + """Helper to define an expression that is indirectly defined from + the tokens matched in a previous expression, that is, it looks for + a 'repeat' of a previous expression. For example:: + + first = Word(nums) + second = match_previous_literal(first) + match_expr = first + ":" + second + + will match ``"1:1"``, but not ``"1:2"``. Because this + matches a previous literal, will also match the leading + ``"1:1"`` in ``"1:10"``. If this is not desired, use + :class:`match_previous_expr`. Do *not* use with packrat parsing + enabled. + """ + rep = Forward() + + def copy_token_to_repeater(s, l, t): + if t: + if len(t) == 1: + rep << t[0] + else: + # flatten t tokens + tflat = _flatten(t.as_list()) + rep << And(Literal(tt) for tt in tflat) + else: + rep << Empty() + + expr.add_parse_action(copy_token_to_repeater, callDuringTry=True) + rep.set_name("(prev) " + str(expr)) + return rep + + +def match_previous_expr(expr: ParserElement) -> ParserElement: + """Helper to define an expression that is indirectly defined from + the tokens matched in a previous expression, that is, it looks for + a 'repeat' of a previous expression. For example:: + + first = Word(nums) + second = match_previous_expr(first) + match_expr = first + ":" + second + + will match ``"1:1"``, but not ``"1:2"``. Because this + matches by expressions, will *not* match the leading ``"1:1"`` + in ``"1:10"``; the expressions are evaluated first, and then + compared, so ``"1"`` is compared with ``"10"``. Do *not* use + with packrat parsing enabled. + """ + rep = Forward() + e2 = expr.copy() + rep <<= e2 + + def copy_token_to_repeater(s, l, t): + matchTokens = _flatten(t.as_list()) + + def must_match_these_tokens(s, l, t): + theseTokens = _flatten(t.as_list()) + if theseTokens != matchTokens: + raise ParseException( + s, l, "Expected {}, found{}".format(matchTokens, theseTokens) + ) + + rep.set_parse_action(must_match_these_tokens, callDuringTry=True) + + expr.add_parse_action(copy_token_to_repeater, callDuringTry=True) + rep.set_name("(prev) " + str(expr)) + return rep + + +def one_of( + strs: Union[typing.Iterable[str], str], + caseless: bool = False, + use_regex: bool = True, + as_keyword: bool = False, + *, + useRegex: bool = True, + asKeyword: bool = False, +) -> ParserElement: + """Helper to quickly define a set of alternative :class:`Literal` s, + and makes sure to do longest-first testing when there is a conflict, + regardless of the input order, but returns + a :class:`MatchFirst` for best performance. + + Parameters: + + - ``strs`` - a string of space-delimited literals, or a collection of + string literals + - ``caseless`` - treat all literals as caseless - (default= ``False``) + - ``use_regex`` - as an optimization, will + generate a :class:`Regex` object; otherwise, will generate + a :class:`MatchFirst` object (if ``caseless=True`` or ``asKeyword=True``, or if + creating a :class:`Regex` raises an exception) - (default= ``True``) + - ``as_keyword`` - enforce :class:`Keyword`-style matching on the + generated expressions - (default= ``False``) + - ``asKeyword`` and ``useRegex`` are retained for pre-PEP8 compatibility, + but will be removed in a future release + + Example:: + + comp_oper = one_of("< = > <= >= !=") + var = Word(alphas) + number = Word(nums) + term = var | number + comparison_expr = term + comp_oper + term + print(comparison_expr.search_string("B = 12 AA=23 B<=AA AA>12")) + + prints:: + + [['B', '=', '12'], ['AA', '=', '23'], ['B', '<=', 'AA'], ['AA', '>', '12']] + """ + asKeyword = asKeyword or as_keyword + useRegex = useRegex and use_regex + + if ( + isinstance(caseless, str_type) + and __diag__.warn_on_multiple_string_args_to_oneof + ): + warnings.warn( + "More than one string argument passed to one_of, pass" + " choices as a list or space-delimited string", + stacklevel=2, + ) + + if caseless: + isequal = lambda a, b: a.upper() == b.upper() + masks = lambda a, b: b.upper().startswith(a.upper()) + parseElementClass = CaselessKeyword if asKeyword else CaselessLiteral + else: + isequal = lambda a, b: a == b + masks = lambda a, b: b.startswith(a) + parseElementClass = Keyword if asKeyword else Literal + + symbols: List[str] = [] + if isinstance(strs, str_type): + symbols = strs.split() + elif isinstance(strs, Iterable): + symbols = list(strs) + else: + raise TypeError("Invalid argument to one_of, expected string or iterable") + if not symbols: + return NoMatch() + + # reorder given symbols to take care to avoid masking longer choices with shorter ones + # (but only if the given symbols are not just single characters) + if any(len(sym) > 1 for sym in symbols): + i = 0 + while i < len(symbols) - 1: + cur = symbols[i] + for j, other in enumerate(symbols[i + 1 :]): + if isequal(other, cur): + del symbols[i + j + 1] + break + elif masks(cur, other): + del symbols[i + j + 1] + symbols.insert(i, other) + break + else: + i += 1 + + if useRegex: + re_flags: int = re.IGNORECASE if caseless else 0 + + try: + if all(len(sym) == 1 for sym in symbols): + # symbols are just single characters, create range regex pattern + patt = "[{}]".format( + "".join(_escape_regex_range_chars(sym) for sym in symbols) + ) + else: + patt = "|".join(re.escape(sym) for sym in symbols) + + # wrap with \b word break markers if defining as keywords + if asKeyword: + patt = r"\b(?:{})\b".format(patt) + + ret = Regex(patt, flags=re_flags).set_name(" | ".join(symbols)) + + if caseless: + # add parse action to return symbols as specified, not in random + # casing as found in input string + symbol_map = {sym.lower(): sym for sym in symbols} + ret.add_parse_action(lambda s, l, t: symbol_map[t[0].lower()]) + + return ret + + except re.error: + warnings.warn( + "Exception creating Regex for one_of, building MatchFirst", stacklevel=2 + ) + + # last resort, just use MatchFirst + return MatchFirst(parseElementClass(sym) for sym in symbols).set_name( + " | ".join(symbols) + ) + + +def dict_of(key: ParserElement, value: ParserElement) -> ParserElement: + """Helper to easily and clearly define a dictionary by specifying + the respective patterns for the key and value. Takes care of + defining the :class:`Dict`, :class:`ZeroOrMore`, and + :class:`Group` tokens in the proper order. The key pattern + can include delimiting markers or punctuation, as long as they are + suppressed, thereby leaving the significant key text. The value + pattern can include named results, so that the :class:`Dict` results + can include named token fields. + + Example:: + + text = "shape: SQUARE posn: upper left color: light blue texture: burlap" + attr_expr = (label + Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join)) + print(attr_expr[1, ...].parse_string(text).dump()) + + attr_label = label + attr_value = Suppress(':') + OneOrMore(data_word, stop_on=label).set_parse_action(' '.join) + + # similar to Dict, but simpler call format + result = dict_of(attr_label, attr_value).parse_string(text) + print(result.dump()) + print(result['shape']) + print(result.shape) # object attribute access works too + print(result.as_dict()) + + prints:: + + [['shape', 'SQUARE'], ['posn', 'upper left'], ['color', 'light blue'], ['texture', 'burlap']] + - color: 'light blue' + - posn: 'upper left' + - shape: 'SQUARE' + - texture: 'burlap' + SQUARE + SQUARE + {'color': 'light blue', 'shape': 'SQUARE', 'posn': 'upper left', 'texture': 'burlap'} + """ + return Dict(OneOrMore(Group(key + value))) + + +def original_text_for( + expr: ParserElement, as_string: bool = True, *, asString: bool = True +) -> ParserElement: + """Helper to return the original, untokenized text for a given + expression. Useful to restore the parsed fields of an HTML start + tag into the raw tag text itself, or to revert separate tokens with + intervening whitespace back to the original matching input text. By + default, returns astring containing the original parsed text. + + If the optional ``as_string`` argument is passed as + ``False``, then the return value is + a :class:`ParseResults` containing any results names that + were originally matched, and a single token containing the original + matched text from the input string. So if the expression passed to + :class:`original_text_for` contains expressions with defined + results names, you must set ``as_string`` to ``False`` if you + want to preserve those results name values. + + The ``asString`` pre-PEP8 argument is retained for compatibility, + but will be removed in a future release. + + Example:: + + src = "this is test <b> bold <i>text</i> </b> normal text " + for tag in ("b", "i"): + opener, closer = make_html_tags(tag) + patt = original_text_for(opener + SkipTo(closer) + closer) + print(patt.search_string(src)[0]) + + prints:: + + ['<b> bold <i>text</i> </b>'] + ['<i>text</i>'] + """ + asString = asString and as_string + + locMarker = Empty().set_parse_action(lambda s, loc, t: loc) + endlocMarker = locMarker.copy() + endlocMarker.callPreparse = False + matchExpr = locMarker("_original_start") + expr + endlocMarker("_original_end") + if asString: + extractText = lambda s, l, t: s[t._original_start : t._original_end] + else: + + def extractText(s, l, t): + t[:] = [s[t.pop("_original_start") : t.pop("_original_end")]] + + matchExpr.set_parse_action(extractText) + matchExpr.ignoreExprs = expr.ignoreExprs + matchExpr.suppress_warning(Diagnostics.warn_ungrouped_named_tokens_in_collection) + return matchExpr + + +def ungroup(expr: ParserElement) -> ParserElement: + """Helper to undo pyparsing's default grouping of And expressions, + even if all but one are non-empty. + """ + return TokenConverter(expr).add_parse_action(lambda t: t[0]) + + +def locatedExpr(expr: ParserElement) -> ParserElement: + """ + (DEPRECATED - future code should use the Located class) + Helper to decorate a returned token with its starting and ending + locations in the input string. + + This helper adds the following results names: + + - ``locn_start`` - location where matched expression begins + - ``locn_end`` - location where matched expression ends + - ``value`` - the actual parsed results + + Be careful if the input text contains ``<TAB>`` characters, you + may want to call :class:`ParserElement.parseWithTabs` + + Example:: + + wd = Word(alphas) + for match in locatedExpr(wd).searchString("ljsdf123lksdjjf123lkkjj1222"): + print(match) + + prints:: + + [[0, 'ljsdf', 5]] + [[8, 'lksdjjf', 15]] + [[18, 'lkkjj', 23]] + """ + locator = Empty().set_parse_action(lambda ss, ll, tt: ll) + return Group( + locator("locn_start") + + expr("value") + + locator.copy().leaveWhitespace()("locn_end") + ) + + +def nested_expr( + opener: Union[str, ParserElement] = "(", + closer: Union[str, ParserElement] = ")", + content: typing.Optional[ParserElement] = None, + ignore_expr: ParserElement = quoted_string(), + *, + ignoreExpr: ParserElement = quoted_string(), +) -> ParserElement: + """Helper method for defining nested lists enclosed in opening and + closing delimiters (``"("`` and ``")"`` are the default). + + Parameters: + - ``opener`` - opening character for a nested list + (default= ``"("``); can also be a pyparsing expression + - ``closer`` - closing character for a nested list + (default= ``")"``); can also be a pyparsing expression + - ``content`` - expression for items within the nested lists + (default= ``None``) + - ``ignore_expr`` - expression for ignoring opening and closing delimiters + (default= :class:`quoted_string`) + - ``ignoreExpr`` - this pre-PEP8 argument is retained for compatibility + but will be removed in a future release + + If an expression is not provided for the content argument, the + nested expression will capture all whitespace-delimited content + between delimiters as a list of separate values. + + Use the ``ignore_expr`` argument to define expressions that may + contain opening or closing characters that should not be treated as + opening or closing characters for nesting, such as quoted_string or + a comment expression. Specify multiple expressions using an + :class:`Or` or :class:`MatchFirst`. The default is + :class:`quoted_string`, but if no expressions are to be ignored, then + pass ``None`` for this argument. + + Example:: + + data_type = one_of("void int short long char float double") + decl_data_type = Combine(data_type + Opt(Word('*'))) + ident = Word(alphas+'_', alphanums+'_') + number = pyparsing_common.number + arg = Group(decl_data_type + ident) + LPAR, RPAR = map(Suppress, "()") + + code_body = nested_expr('{', '}', ignore_expr=(quoted_string | c_style_comment)) + + c_function = (decl_data_type("type") + + ident("name") + + LPAR + Opt(delimited_list(arg), [])("args") + RPAR + + code_body("body")) + c_function.ignore(c_style_comment) + + source_code = ''' + int is_odd(int x) { + return (x%2); + } + + int dec_to_hex(char hchar) { + if (hchar >= '0' && hchar <= '9') { + return (ord(hchar)-ord('0')); + } else { + return (10+ord(hchar)-ord('A')); + } + } + ''' + for func in c_function.search_string(source_code): + print("%(name)s (%(type)s) args: %(args)s" % func) + + + prints:: + + is_odd (int) args: [['int', 'x']] + dec_to_hex (int) args: [['char', 'hchar']] + """ + if ignoreExpr != ignore_expr: + ignoreExpr = ignore_expr if ignoreExpr == quoted_string() else ignoreExpr + if opener == closer: + raise ValueError("opening and closing strings cannot be the same") + if content is None: + if isinstance(opener, str_type) and isinstance(closer, str_type): + if len(opener) == 1 and len(closer) == 1: + if ignoreExpr is not None: + content = Combine( + OneOrMore( + ~ignoreExpr + + CharsNotIn( + opener + closer + ParserElement.DEFAULT_WHITE_CHARS, + exact=1, + ) + ) + ).set_parse_action(lambda t: t[0].strip()) + else: + content = empty.copy() + CharsNotIn( + opener + closer + ParserElement.DEFAULT_WHITE_CHARS + ).set_parse_action(lambda t: t[0].strip()) + else: + if ignoreExpr is not None: + content = Combine( + OneOrMore( + ~ignoreExpr + + ~Literal(opener) + + ~Literal(closer) + + CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS, exact=1) + ) + ).set_parse_action(lambda t: t[0].strip()) + else: + content = Combine( + OneOrMore( + ~Literal(opener) + + ~Literal(closer) + + CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS, exact=1) + ) + ).set_parse_action(lambda t: t[0].strip()) + else: + raise ValueError( + "opening and closing arguments must be strings if no content expression is given" + ) + ret = Forward() + if ignoreExpr is not None: + ret <<= Group( + Suppress(opener) + ZeroOrMore(ignoreExpr | ret | content) + Suppress(closer) + ) + else: + ret <<= Group(Suppress(opener) + ZeroOrMore(ret | content) + Suppress(closer)) + ret.set_name("nested %s%s expression" % (opener, closer)) + return ret + + +def _makeTags(tagStr, xml, suppress_LT=Suppress("<"), suppress_GT=Suppress(">")): + """Internal helper to construct opening and closing tag expressions, given a tag name""" + if isinstance(tagStr, str_type): + resname = tagStr + tagStr = Keyword(tagStr, caseless=not xml) + else: + resname = tagStr.name + + tagAttrName = Word(alphas, alphanums + "_-:") + if xml: + tagAttrValue = dbl_quoted_string.copy().set_parse_action(remove_quotes) + openTag = ( + suppress_LT + + tagStr("tag") + + Dict(ZeroOrMore(Group(tagAttrName + Suppress("=") + tagAttrValue))) + + Opt("/", default=[False])("empty").set_parse_action( + lambda s, l, t: t[0] == "/" + ) + + suppress_GT + ) + else: + tagAttrValue = quoted_string.copy().set_parse_action(remove_quotes) | Word( + printables, exclude_chars=">" + ) + openTag = ( + suppress_LT + + tagStr("tag") + + Dict( + ZeroOrMore( + Group( + tagAttrName.set_parse_action(lambda t: t[0].lower()) + + Opt(Suppress("=") + tagAttrValue) + ) + ) + ) + + Opt("/", default=[False])("empty").set_parse_action( + lambda s, l, t: t[0] == "/" + ) + + suppress_GT + ) + closeTag = Combine(Literal("</") + tagStr + ">", adjacent=False) + + openTag.set_name("<%s>" % resname) + # add start<tagname> results name in parse action now that ungrouped names are not reported at two levels + openTag.add_parse_action( + lambda t: t.__setitem__( + "start" + "".join(resname.replace(":", " ").title().split()), t.copy() + ) + ) + closeTag = closeTag( + "end" + "".join(resname.replace(":", " ").title().split()) + ).set_name("</%s>" % resname) + openTag.tag = resname + closeTag.tag = resname + openTag.tag_body = SkipTo(closeTag()) + return openTag, closeTag + + +def make_html_tags( + tag_str: Union[str, ParserElement] +) -> Tuple[ParserElement, ParserElement]: + """Helper to construct opening and closing tag expressions for HTML, + given a tag name. Matches tags in either upper or lower case, + attributes with namespaces and with quoted or unquoted values. + + Example:: + + text = '<td>More info at the <a href="https://github.com/pyparsing/pyparsing/wiki">pyparsing</a> wiki page</td>' + # make_html_tags returns pyparsing expressions for the opening and + # closing tags as a 2-tuple + a, a_end = make_html_tags("A") + link_expr = a + SkipTo(a_end)("link_text") + a_end + + for link in link_expr.search_string(text): + # attributes in the <A> tag (like "href" shown here) are + # also accessible as named results + print(link.link_text, '->', link.href) + + prints:: + + pyparsing -> https://github.com/pyparsing/pyparsing/wiki + """ + return _makeTags(tag_str, False) + + +def make_xml_tags( + tag_str: Union[str, ParserElement] +) -> Tuple[ParserElement, ParserElement]: + """Helper to construct opening and closing tag expressions for XML, + given a tag name. Matches tags only in the given upper/lower case. + + Example: similar to :class:`make_html_tags` + """ + return _makeTags(tag_str, True) + + +any_open_tag: ParserElement +any_close_tag: ParserElement +any_open_tag, any_close_tag = make_html_tags( + Word(alphas, alphanums + "_:").set_name("any tag") +) + +_htmlEntityMap = {k.rstrip(";"): v for k, v in html.entities.html5.items()} +common_html_entity = Regex("&(?P<entity>" + "|".join(_htmlEntityMap) + ");").set_name( + "common HTML entity" +) + + +def replace_html_entity(t): + """Helper parser action to replace common HTML entities with their special characters""" + return _htmlEntityMap.get(t.entity) + + +class OpAssoc(Enum): + LEFT = 1 + RIGHT = 2 + + +InfixNotationOperatorArgType = Union[ + ParserElement, str, Tuple[Union[ParserElement, str], Union[ParserElement, str]] +] +InfixNotationOperatorSpec = Union[ + Tuple[ + InfixNotationOperatorArgType, + int, + OpAssoc, + typing.Optional[ParseAction], + ], + Tuple[ + InfixNotationOperatorArgType, + int, + OpAssoc, + ], +] + + +def infix_notation( + base_expr: ParserElement, + op_list: List[InfixNotationOperatorSpec], + lpar: Union[str, ParserElement] = Suppress("("), + rpar: Union[str, ParserElement] = Suppress(")"), +) -> ParserElement: + """Helper method for constructing grammars of expressions made up of + operators working in a precedence hierarchy. Operators may be unary + or binary, left- or right-associative. Parse actions can also be + attached to operator expressions. The generated parser will also + recognize the use of parentheses to override operator precedences + (see example below). + + Note: if you define a deep operator list, you may see performance + issues when using infix_notation. See + :class:`ParserElement.enable_packrat` for a mechanism to potentially + improve your parser performance. + + Parameters: + - ``base_expr`` - expression representing the most basic operand to + be used in the expression + - ``op_list`` - list of tuples, one for each operator precedence level + in the expression grammar; each tuple is of the form ``(op_expr, + num_operands, right_left_assoc, (optional)parse_action)``, where: + + - ``op_expr`` is the pyparsing expression for the operator; may also + be a string, which will be converted to a Literal; if ``num_operands`` + is 3, ``op_expr`` is a tuple of two expressions, for the two + operators separating the 3 terms + - ``num_operands`` is the number of terms for this operator (must be 1, + 2, or 3) + - ``right_left_assoc`` is the indicator whether the operator is right + or left associative, using the pyparsing-defined constants + ``OpAssoc.RIGHT`` and ``OpAssoc.LEFT``. + - ``parse_action`` is the parse action to be associated with + expressions matching this operator expression (the parse action + tuple member may be omitted); if the parse action is passed + a tuple or list of functions, this is equivalent to calling + ``set_parse_action(*fn)`` + (:class:`ParserElement.set_parse_action`) + - ``lpar`` - expression for matching left-parentheses; if passed as a + str, then will be parsed as Suppress(lpar). If lpar is passed as + an expression (such as ``Literal('(')``), then it will be kept in + the parsed results, and grouped with them. (default= ``Suppress('(')``) + - ``rpar`` - expression for matching right-parentheses; if passed as a + str, then will be parsed as Suppress(rpar). If rpar is passed as + an expression (such as ``Literal(')')``), then it will be kept in + the parsed results, and grouped with them. (default= ``Suppress(')')``) + + Example:: + + # simple example of four-function arithmetic with ints and + # variable names + integer = pyparsing_common.signed_integer + varname = pyparsing_common.identifier + + arith_expr = infix_notation(integer | varname, + [ + ('-', 1, OpAssoc.RIGHT), + (one_of('* /'), 2, OpAssoc.LEFT), + (one_of('+ -'), 2, OpAssoc.LEFT), + ]) + + arith_expr.run_tests(''' + 5+3*6 + (5+3)*6 + -2--11 + ''', full_dump=False) + + prints:: + + 5+3*6 + [[5, '+', [3, '*', 6]]] + + (5+3)*6 + [[[5, '+', 3], '*', 6]] + + -2--11 + [[['-', 2], '-', ['-', 11]]] + """ + # captive version of FollowedBy that does not do parse actions or capture results names + class _FB(FollowedBy): + def parseImpl(self, instring, loc, doActions=True): + self.expr.try_parse(instring, loc) + return loc, [] + + _FB.__name__ = "FollowedBy>" + + ret = Forward() + if isinstance(lpar, str): + lpar = Suppress(lpar) + if isinstance(rpar, str): + rpar = Suppress(rpar) + + # if lpar and rpar are not suppressed, wrap in group + if not (isinstance(rpar, Suppress) and isinstance(rpar, Suppress)): + lastExpr = base_expr | Group(lpar + ret + rpar) + else: + lastExpr = base_expr | (lpar + ret + rpar) + + for i, operDef in enumerate(op_list): + opExpr, arity, rightLeftAssoc, pa = (operDef + (None,))[:4] + if isinstance(opExpr, str_type): + opExpr = ParserElement._literalStringClass(opExpr) + if arity == 3: + if not isinstance(opExpr, (tuple, list)) or len(opExpr) != 2: + raise ValueError( + "if numterms=3, opExpr must be a tuple or list of two expressions" + ) + opExpr1, opExpr2 = opExpr + term_name = "{}{} term".format(opExpr1, opExpr2) + else: + term_name = "{} term".format(opExpr) + + if not 1 <= arity <= 3: + raise ValueError("operator must be unary (1), binary (2), or ternary (3)") + + if rightLeftAssoc not in (OpAssoc.LEFT, OpAssoc.RIGHT): + raise ValueError("operator must indicate right or left associativity") + + thisExpr: Forward = Forward().set_name(term_name) + if rightLeftAssoc is OpAssoc.LEFT: + if arity == 1: + matchExpr = _FB(lastExpr + opExpr) + Group(lastExpr + opExpr[1, ...]) + elif arity == 2: + if opExpr is not None: + matchExpr = _FB(lastExpr + opExpr + lastExpr) + Group( + lastExpr + (opExpr + lastExpr)[1, ...] + ) + else: + matchExpr = _FB(lastExpr + lastExpr) + Group(lastExpr[2, ...]) + elif arity == 3: + matchExpr = _FB( + lastExpr + opExpr1 + lastExpr + opExpr2 + lastExpr + ) + Group(lastExpr + OneOrMore(opExpr1 + lastExpr + opExpr2 + lastExpr)) + elif rightLeftAssoc is OpAssoc.RIGHT: + if arity == 1: + # try to avoid LR with this extra test + if not isinstance(opExpr, Opt): + opExpr = Opt(opExpr) + matchExpr = _FB(opExpr.expr + thisExpr) + Group(opExpr + thisExpr) + elif arity == 2: + if opExpr is not None: + matchExpr = _FB(lastExpr + opExpr + thisExpr) + Group( + lastExpr + (opExpr + thisExpr)[1, ...] + ) + else: + matchExpr = _FB(lastExpr + thisExpr) + Group( + lastExpr + thisExpr[1, ...] + ) + elif arity == 3: + matchExpr = _FB( + lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr + ) + Group(lastExpr + opExpr1 + thisExpr + opExpr2 + thisExpr) + if pa: + if isinstance(pa, (tuple, list)): + matchExpr.set_parse_action(*pa) + else: + matchExpr.set_parse_action(pa) + thisExpr <<= (matchExpr | lastExpr).setName(term_name) + lastExpr = thisExpr + ret <<= lastExpr + return ret + + +def indentedBlock(blockStatementExpr, indentStack, indent=True, backup_stacks=[]): + """ + (DEPRECATED - use IndentedBlock class instead) + Helper method for defining space-delimited indentation blocks, + such as those used to define block statements in Python source code. + + Parameters: + + - ``blockStatementExpr`` - expression defining syntax of statement that + is repeated within the indented block + - ``indentStack`` - list created by caller to manage indentation stack + (multiple ``statementWithIndentedBlock`` expressions within a single + grammar should share a common ``indentStack``) + - ``indent`` - boolean indicating whether block must be indented beyond + the current level; set to ``False`` for block of left-most statements + (default= ``True``) + + A valid block must contain at least one ``blockStatement``. + + (Note that indentedBlock uses internal parse actions which make it + incompatible with packrat parsing.) + + Example:: + + data = ''' + def A(z): + A1 + B = 100 + G = A2 + A2 + A3 + B + def BB(a,b,c): + BB1 + def BBA(): + bba1 + bba2 + bba3 + C + D + def spam(x,y): + def eggs(z): + pass + ''' + + + indentStack = [1] + stmt = Forward() + + identifier = Word(alphas, alphanums) + funcDecl = ("def" + identifier + Group("(" + Opt(delimitedList(identifier)) + ")") + ":") + func_body = indentedBlock(stmt, indentStack) + funcDef = Group(funcDecl + func_body) + + rvalue = Forward() + funcCall = Group(identifier + "(" + Opt(delimitedList(rvalue)) + ")") + rvalue << (funcCall | identifier | Word(nums)) + assignment = Group(identifier + "=" + rvalue) + stmt << (funcDef | assignment | identifier) + + module_body = stmt[1, ...] + + parseTree = module_body.parseString(data) + parseTree.pprint() + + prints:: + + [['def', + 'A', + ['(', 'z', ')'], + ':', + [['A1'], [['B', '=', '100']], [['G', '=', 'A2']], ['A2'], ['A3']]], + 'B', + ['def', + 'BB', + ['(', 'a', 'b', 'c', ')'], + ':', + [['BB1'], [['def', 'BBA', ['(', ')'], ':', [['bba1'], ['bba2'], ['bba3']]]]]], + 'C', + 'D', + ['def', + 'spam', + ['(', 'x', 'y', ')'], + ':', + [[['def', 'eggs', ['(', 'z', ')'], ':', [['pass']]]]]]] + """ + backup_stacks.append(indentStack[:]) + + def reset_stack(): + indentStack[:] = backup_stacks[-1] + + def checkPeerIndent(s, l, t): + if l >= len(s): + return + curCol = col(l, s) + if curCol != indentStack[-1]: + if curCol > indentStack[-1]: + raise ParseException(s, l, "illegal nesting") + raise ParseException(s, l, "not a peer entry") + + def checkSubIndent(s, l, t): + curCol = col(l, s) + if curCol > indentStack[-1]: + indentStack.append(curCol) + else: + raise ParseException(s, l, "not a subentry") + + def checkUnindent(s, l, t): + if l >= len(s): + return + curCol = col(l, s) + if not (indentStack and curCol in indentStack): + raise ParseException(s, l, "not an unindent") + if curCol < indentStack[-1]: + indentStack.pop() + + NL = OneOrMore(LineEnd().set_whitespace_chars("\t ").suppress()) + INDENT = (Empty() + Empty().set_parse_action(checkSubIndent)).set_name("INDENT") + PEER = Empty().set_parse_action(checkPeerIndent).set_name("") + UNDENT = Empty().set_parse_action(checkUnindent).set_name("UNINDENT") + if indent: + smExpr = Group( + Opt(NL) + + INDENT + + OneOrMore(PEER + Group(blockStatementExpr) + Opt(NL)) + + UNDENT + ) + else: + smExpr = Group( + Opt(NL) + + OneOrMore(PEER + Group(blockStatementExpr) + Opt(NL)) + + Opt(UNDENT) + ) + + # add a parse action to remove backup_stack from list of backups + smExpr.add_parse_action( + lambda: backup_stacks.pop(-1) and None if backup_stacks else None + ) + smExpr.set_fail_action(lambda a, b, c, d: reset_stack()) + blockStatementExpr.ignore(_bslash + LineEnd()) + return smExpr.set_name("indented block") + + +# it's easy to get these comment structures wrong - they're very common, so may as well make them available +c_style_comment = Combine(Regex(r"/\*(?:[^*]|\*(?!/))*") + "*/").set_name( + "C style comment" +) +"Comment of the form ``/* ... */``" + +html_comment = Regex(r"<!--[\s\S]*?-->").set_name("HTML comment") +"Comment of the form ``<!-- ... -->``" + +rest_of_line = Regex(r".*").leave_whitespace().set_name("rest of line") +dbl_slash_comment = Regex(r"//(?:\\\n|[^\n])*").set_name("// comment") +"Comment of the form ``// ... (to end of line)``" + +cpp_style_comment = Combine( + Regex(r"/\*(?:[^*]|\*(?!/))*") + "*/" | dbl_slash_comment +).set_name("C++ style comment") +"Comment of either form :class:`c_style_comment` or :class:`dbl_slash_comment`" + +java_style_comment = cpp_style_comment +"Same as :class:`cpp_style_comment`" + +python_style_comment = Regex(r"#.*").set_name("Python style comment") +"Comment of the form ``# ... (to end of line)``" + + +# build list of built-in expressions, for future reference if a global default value +# gets updated +_builtin_exprs: List[ParserElement] = [ + v for v in vars().values() if isinstance(v, ParserElement) +] + + +# pre-PEP8 compatible names +delimitedList = delimited_list +countedArray = counted_array +matchPreviousLiteral = match_previous_literal +matchPreviousExpr = match_previous_expr +oneOf = one_of +dictOf = dict_of +originalTextFor = original_text_for +nestedExpr = nested_expr +makeHTMLTags = make_html_tags +makeXMLTags = make_xml_tags +anyOpenTag, anyCloseTag = any_open_tag, any_close_tag +commonHTMLEntity = common_html_entity +replaceHTMLEntity = replace_html_entity +opAssoc = OpAssoc +infixNotation = infix_notation +cStyleComment = c_style_comment +htmlComment = html_comment +restOfLine = rest_of_line +dblSlashComment = dbl_slash_comment +cppStyleComment = cpp_style_comment +javaStyleComment = java_style_comment +pythonStyleComment = python_style_comment diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/results.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/results.py new file mode 100644 index 0000000..00c9421 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/results.py @@ -0,0 +1,760 @@ +# results.py +from collections.abc import MutableMapping, Mapping, MutableSequence, Iterator +import pprint +from weakref import ref as wkref +from typing import Tuple, Any + +str_type: Tuple[type, ...] = (str, bytes) +_generator_type = type((_ for _ in ())) + + +class _ParseResultsWithOffset: + __slots__ = ["tup"] + + def __init__(self, p1, p2): + self.tup = (p1, p2) + + def __getitem__(self, i): + return self.tup[i] + + def __getstate__(self): + return self.tup + + def __setstate__(self, *args): + self.tup = args[0] + + +class ParseResults: + """Structured parse results, to provide multiple means of access to + the parsed data: + + - as a list (``len(results)``) + - by list index (``results[0], results[1]``, etc.) + - by attribute (``results.<results_name>`` - see :class:`ParserElement.set_results_name`) + + Example:: + + integer = Word(nums) + date_str = (integer.set_results_name("year") + '/' + + integer.set_results_name("month") + '/' + + integer.set_results_name("day")) + # equivalent form: + # date_str = (integer("year") + '/' + # + integer("month") + '/' + # + integer("day")) + + # parse_string returns a ParseResults object + result = date_str.parse_string("1999/12/31") + + def test(s, fn=repr): + print("{} -> {}".format(s, fn(eval(s)))) + test("list(result)") + test("result[0]") + test("result['month']") + test("result.day") + test("'month' in result") + test("'minutes' in result") + test("result.dump()", str) + + prints:: + + list(result) -> ['1999', '/', '12', '/', '31'] + result[0] -> '1999' + result['month'] -> '12' + result.day -> '31' + 'month' in result -> True + 'minutes' in result -> False + result.dump() -> ['1999', '/', '12', '/', '31'] + - day: '31' + - month: '12' + - year: '1999' + """ + + _null_values: Tuple[Any, ...] = (None, [], "", ()) + + __slots__ = [ + "_name", + "_parent", + "_all_names", + "_modal", + "_toklist", + "_tokdict", + "__weakref__", + ] + + class List(list): + """ + Simple wrapper class to distinguish parsed list results that should be preserved + as actual Python lists, instead of being converted to :class:`ParseResults`: + + LBRACK, RBRACK = map(pp.Suppress, "[]") + element = pp.Forward() + item = ppc.integer + element_list = LBRACK + pp.delimited_list(element) + RBRACK + + # add parse actions to convert from ParseResults to actual Python collection types + def as_python_list(t): + return pp.ParseResults.List(t.as_list()) + element_list.add_parse_action(as_python_list) + + element <<= item | element_list + + element.run_tests(''' + 100 + [2,3,4] + [[2, 1],3,4] + [(2, 1),3,4] + (2,3,4) + ''', post_parse=lambda s, r: (r[0], type(r[0]))) + + prints: + + 100 + (100, <class 'int'>) + + [2,3,4] + ([2, 3, 4], <class 'list'>) + + [[2, 1],3,4] + ([[2, 1], 3, 4], <class 'list'>) + + (Used internally by :class:`Group` when `aslist=True`.) + """ + + def __new__(cls, contained=None): + if contained is None: + contained = [] + + if not isinstance(contained, list): + raise TypeError( + "{} may only be constructed with a list," + " not {}".format(cls.__name__, type(contained).__name__) + ) + + return list.__new__(cls) + + def __new__(cls, toklist=None, name=None, **kwargs): + if isinstance(toklist, ParseResults): + return toklist + self = object.__new__(cls) + self._name = None + self._parent = None + self._all_names = set() + + if toklist is None: + self._toklist = [] + elif isinstance(toklist, (list, _generator_type)): + self._toklist = ( + [toklist[:]] + if isinstance(toklist, ParseResults.List) + else list(toklist) + ) + else: + self._toklist = [toklist] + self._tokdict = dict() + return self + + # Performance tuning: we construct a *lot* of these, so keep this + # constructor as small and fast as possible + def __init__( + self, toklist=None, name=None, asList=True, modal=True, isinstance=isinstance + ): + self._modal = modal + if name is not None and name != "": + if isinstance(name, int): + name = str(name) + if not modal: + self._all_names = {name} + self._name = name + if toklist not in self._null_values: + if isinstance(toklist, (str_type, type)): + toklist = [toklist] + if asList: + if isinstance(toklist, ParseResults): + self[name] = _ParseResultsWithOffset( + ParseResults(toklist._toklist), 0 + ) + else: + self[name] = _ParseResultsWithOffset( + ParseResults(toklist[0]), 0 + ) + self[name]._name = name + else: + try: + self[name] = toklist[0] + except (KeyError, TypeError, IndexError): + if toklist is not self: + self[name] = toklist + else: + self._name = name + + def __getitem__(self, i): + if isinstance(i, (int, slice)): + return self._toklist[i] + else: + if i not in self._all_names: + return self._tokdict[i][-1][0] + else: + return ParseResults([v[0] for v in self._tokdict[i]]) + + def __setitem__(self, k, v, isinstance=isinstance): + if isinstance(v, _ParseResultsWithOffset): + self._tokdict[k] = self._tokdict.get(k, list()) + [v] + sub = v[0] + elif isinstance(k, (int, slice)): + self._toklist[k] = v + sub = v + else: + self._tokdict[k] = self._tokdict.get(k, list()) + [ + _ParseResultsWithOffset(v, 0) + ] + sub = v + if isinstance(sub, ParseResults): + sub._parent = wkref(self) + + def __delitem__(self, i): + if isinstance(i, (int, slice)): + mylen = len(self._toklist) + del self._toklist[i] + + # convert int to slice + if isinstance(i, int): + if i < 0: + i += mylen + i = slice(i, i + 1) + # get removed indices + removed = list(range(*i.indices(mylen))) + removed.reverse() + # fixup indices in token dictionary + for name, occurrences in self._tokdict.items(): + for j in removed: + for k, (value, position) in enumerate(occurrences): + occurrences[k] = _ParseResultsWithOffset( + value, position - (position > j) + ) + else: + del self._tokdict[i] + + def __contains__(self, k) -> bool: + return k in self._tokdict + + def __len__(self) -> int: + return len(self._toklist) + + def __bool__(self) -> bool: + return not not (self._toklist or self._tokdict) + + def __iter__(self) -> Iterator: + return iter(self._toklist) + + def __reversed__(self) -> Iterator: + return iter(self._toklist[::-1]) + + def keys(self): + return iter(self._tokdict) + + def values(self): + return (self[k] for k in self.keys()) + + def items(self): + return ((k, self[k]) for k in self.keys()) + + def haskeys(self) -> bool: + """ + Since ``keys()`` returns an iterator, this method is helpful in bypassing + code that looks for the existence of any defined results names.""" + return bool(self._tokdict) + + def pop(self, *args, **kwargs): + """ + Removes and returns item at specified index (default= ``last``). + Supports both ``list`` and ``dict`` semantics for ``pop()``. If + passed no argument or an integer argument, it will use ``list`` + semantics and pop tokens from the list of parsed tokens. If passed + a non-integer argument (most likely a string), it will use ``dict`` + semantics and pop the corresponding value from any defined results + names. A second default return value argument is supported, just as in + ``dict.pop()``. + + Example:: + + numlist = Word(nums)[...] + print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321'] + + def remove_first(tokens): + tokens.pop(0) + numlist.add_parse_action(remove_first) + print(numlist.parse_string("0 123 321")) # -> ['123', '321'] + + label = Word(alphas) + patt = label("LABEL") + Word(nums)[1, ...] + print(patt.parse_string("AAB 123 321").dump()) + + # Use pop() in a parse action to remove named result (note that corresponding value is not + # removed from list form of results) + def remove_LABEL(tokens): + tokens.pop("LABEL") + return tokens + patt.add_parse_action(remove_LABEL) + print(patt.parse_string("AAB 123 321").dump()) + + prints:: + + ['AAB', '123', '321'] + - LABEL: 'AAB' + + ['AAB', '123', '321'] + """ + if not args: + args = [-1] + for k, v in kwargs.items(): + if k == "default": + args = (args[0], v) + else: + raise TypeError( + "pop() got an unexpected keyword argument {!r}".format(k) + ) + if isinstance(args[0], int) or len(args) == 1 or args[0] in self: + index = args[0] + ret = self[index] + del self[index] + return ret + else: + defaultvalue = args[1] + return defaultvalue + + def get(self, key, default_value=None): + """ + Returns named result matching the given key, or if there is no + such name, then returns the given ``default_value`` or ``None`` if no + ``default_value`` is specified. + + Similar to ``dict.get()``. + + Example:: + + integer = Word(nums) + date_str = integer("year") + '/' + integer("month") + '/' + integer("day") + + result = date_str.parse_string("1999/12/31") + print(result.get("year")) # -> '1999' + print(result.get("hour", "not specified")) # -> 'not specified' + print(result.get("hour")) # -> None + """ + if key in self: + return self[key] + else: + return default_value + + def insert(self, index, ins_string): + """ + Inserts new element at location index in the list of parsed tokens. + + Similar to ``list.insert()``. + + Example:: + + numlist = Word(nums)[...] + print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321'] + + # use a parse action to insert the parse location in the front of the parsed results + def insert_locn(locn, tokens): + tokens.insert(0, locn) + numlist.add_parse_action(insert_locn) + print(numlist.parse_string("0 123 321")) # -> [0, '0', '123', '321'] + """ + self._toklist.insert(index, ins_string) + # fixup indices in token dictionary + for name, occurrences in self._tokdict.items(): + for k, (value, position) in enumerate(occurrences): + occurrences[k] = _ParseResultsWithOffset( + value, position + (position > index) + ) + + def append(self, item): + """ + Add single element to end of ``ParseResults`` list of elements. + + Example:: + + numlist = Word(nums)[...] + print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321'] + + # use a parse action to compute the sum of the parsed integers, and add it to the end + def append_sum(tokens): + tokens.append(sum(map(int, tokens))) + numlist.add_parse_action(append_sum) + print(numlist.parse_string("0 123 321")) # -> ['0', '123', '321', 444] + """ + self._toklist.append(item) + + def extend(self, itemseq): + """ + Add sequence of elements to end of ``ParseResults`` list of elements. + + Example:: + + patt = Word(alphas)[1, ...] + + # use a parse action to append the reverse of the matched strings, to make a palindrome + def make_palindrome(tokens): + tokens.extend(reversed([t[::-1] for t in tokens])) + return ''.join(tokens) + patt.add_parse_action(make_palindrome) + print(patt.parse_string("lskdj sdlkjf lksd")) # -> 'lskdjsdlkjflksddsklfjkldsjdksl' + """ + if isinstance(itemseq, ParseResults): + self.__iadd__(itemseq) + else: + self._toklist.extend(itemseq) + + def clear(self): + """ + Clear all elements and results names. + """ + del self._toklist[:] + self._tokdict.clear() + + def __getattr__(self, name): + try: + return self[name] + except KeyError: + if name.startswith("__"): + raise AttributeError(name) + return "" + + def __add__(self, other) -> "ParseResults": + ret = self.copy() + ret += other + return ret + + def __iadd__(self, other) -> "ParseResults": + if other._tokdict: + offset = len(self._toklist) + addoffset = lambda a: offset if a < 0 else a + offset + otheritems = other._tokdict.items() + otherdictitems = [ + (k, _ParseResultsWithOffset(v[0], addoffset(v[1]))) + for k, vlist in otheritems + for v in vlist + ] + for k, v in otherdictitems: + self[k] = v + if isinstance(v[0], ParseResults): + v[0]._parent = wkref(self) + + self._toklist += other._toklist + self._all_names |= other._all_names + return self + + def __radd__(self, other) -> "ParseResults": + if isinstance(other, int) and other == 0: + # useful for merging many ParseResults using sum() builtin + return self.copy() + else: + # this may raise a TypeError - so be it + return other + self + + def __repr__(self) -> str: + return "{}({!r}, {})".format(type(self).__name__, self._toklist, self.as_dict()) + + def __str__(self) -> str: + return ( + "[" + + ", ".join( + [ + str(i) if isinstance(i, ParseResults) else repr(i) + for i in self._toklist + ] + ) + + "]" + ) + + def _asStringList(self, sep=""): + out = [] + for item in self._toklist: + if out and sep: + out.append(sep) + if isinstance(item, ParseResults): + out += item._asStringList() + else: + out.append(str(item)) + return out + + def as_list(self) -> list: + """ + Returns the parse results as a nested list of matching tokens, all converted to strings. + + Example:: + + patt = Word(alphas)[1, ...] + result = patt.parse_string("sldkj lsdkj sldkj") + # even though the result prints in string-like form, it is actually a pyparsing ParseResults + print(type(result), result) # -> <class 'pyparsing.ParseResults'> ['sldkj', 'lsdkj', 'sldkj'] + + # Use as_list() to create an actual list + result_list = result.as_list() + print(type(result_list), result_list) # -> <class 'list'> ['sldkj', 'lsdkj', 'sldkj'] + """ + return [ + res.as_list() if isinstance(res, ParseResults) else res + for res in self._toklist + ] + + def as_dict(self) -> dict: + """ + Returns the named parse results as a nested dictionary. + + Example:: + + integer = Word(nums) + date_str = integer("year") + '/' + integer("month") + '/' + integer("day") + + result = date_str.parse_string('12/31/1999') + print(type(result), repr(result)) # -> <class 'pyparsing.ParseResults'> (['12', '/', '31', '/', '1999'], {'day': [('1999', 4)], 'year': [('12', 0)], 'month': [('31', 2)]}) + + result_dict = result.as_dict() + print(type(result_dict), repr(result_dict)) # -> <class 'dict'> {'day': '1999', 'year': '12', 'month': '31'} + + # even though a ParseResults supports dict-like access, sometime you just need to have a dict + import json + print(json.dumps(result)) # -> Exception: TypeError: ... is not JSON serializable + print(json.dumps(result.as_dict())) # -> {"month": "31", "day": "1999", "year": "12"} + """ + + def to_item(obj): + if isinstance(obj, ParseResults): + return obj.as_dict() if obj.haskeys() else [to_item(v) for v in obj] + else: + return obj + + return dict((k, to_item(v)) for k, v in self.items()) + + def copy(self) -> "ParseResults": + """ + Returns a new copy of a :class:`ParseResults` object. + """ + ret = ParseResults(self._toklist) + ret._tokdict = self._tokdict.copy() + ret._parent = self._parent + ret._all_names |= self._all_names + ret._name = self._name + return ret + + def get_name(self): + r""" + Returns the results name for this token expression. Useful when several + different expressions might match at a particular location. + + Example:: + + integer = Word(nums) + ssn_expr = Regex(r"\d\d\d-\d\d-\d\d\d\d") + house_number_expr = Suppress('#') + Word(nums, alphanums) + user_data = (Group(house_number_expr)("house_number") + | Group(ssn_expr)("ssn") + | Group(integer)("age")) + user_info = user_data[1, ...] + + result = user_info.parse_string("22 111-22-3333 #221B") + for item in result: + print(item.get_name(), ':', item[0]) + + prints:: + + age : 22 + ssn : 111-22-3333 + house_number : 221B + """ + if self._name: + return self._name + elif self._parent: + par = self._parent() + + def find_in_parent(sub): + return next( + ( + k + for k, vlist in par._tokdict.items() + for v, loc in vlist + if sub is v + ), + None, + ) + + return find_in_parent(self) if par else None + elif ( + len(self) == 1 + and len(self._tokdict) == 1 + and next(iter(self._tokdict.values()))[0][1] in (0, -1) + ): + return next(iter(self._tokdict.keys())) + else: + return None + + def dump(self, indent="", full=True, include_list=True, _depth=0) -> str: + """ + Diagnostic method for listing out the contents of + a :class:`ParseResults`. Accepts an optional ``indent`` argument so + that this string can be embedded in a nested display of other data. + + Example:: + + integer = Word(nums) + date_str = integer("year") + '/' + integer("month") + '/' + integer("day") + + result = date_str.parse_string('1999/12/31') + print(result.dump()) + + prints:: + + ['1999', '/', '12', '/', '31'] + - day: '31' + - month: '12' + - year: '1999' + """ + out = [] + NL = "\n" + out.append(indent + str(self.as_list()) if include_list else "") + + if full: + if self.haskeys(): + items = sorted((str(k), v) for k, v in self.items()) + for k, v in items: + if out: + out.append(NL) + out.append("{}{}- {}: ".format(indent, (" " * _depth), k)) + if isinstance(v, ParseResults): + if v: + out.append( + v.dump( + indent=indent, + full=full, + include_list=include_list, + _depth=_depth + 1, + ) + ) + else: + out.append(str(v)) + else: + out.append(repr(v)) + if any(isinstance(vv, ParseResults) for vv in self): + v = self + for i, vv in enumerate(v): + if isinstance(vv, ParseResults): + out.append( + "\n{}{}[{}]:\n{}{}{}".format( + indent, + (" " * (_depth)), + i, + indent, + (" " * (_depth + 1)), + vv.dump( + indent=indent, + full=full, + include_list=include_list, + _depth=_depth + 1, + ), + ) + ) + else: + out.append( + "\n%s%s[%d]:\n%s%s%s" + % ( + indent, + (" " * (_depth)), + i, + indent, + (" " * (_depth + 1)), + str(vv), + ) + ) + + return "".join(out) + + def pprint(self, *args, **kwargs): + """ + Pretty-printer for parsed results as a list, using the + `pprint <https://docs.python.org/3/library/pprint.html>`_ module. + Accepts additional positional or keyword args as defined for + `pprint.pprint <https://docs.python.org/3/library/pprint.html#pprint.pprint>`_ . + + Example:: + + ident = Word(alphas, alphanums) + num = Word(nums) + func = Forward() + term = ident | num | Group('(' + func + ')') + func <<= ident + Group(Optional(delimited_list(term))) + result = func.parse_string("fna a,b,(fnb c,d,200),100") + result.pprint(width=40) + + prints:: + + ['fna', + ['a', + 'b', + ['(', 'fnb', ['c', 'd', '200'], ')'], + '100']] + """ + pprint.pprint(self.as_list(), *args, **kwargs) + + # add support for pickle protocol + def __getstate__(self): + return ( + self._toklist, + ( + self._tokdict.copy(), + self._parent is not None and self._parent() or None, + self._all_names, + self._name, + ), + ) + + def __setstate__(self, state): + self._toklist, (self._tokdict, par, inAccumNames, self._name) = state + self._all_names = set(inAccumNames) + if par is not None: + self._parent = wkref(par) + else: + self._parent = None + + def __getnewargs__(self): + return self._toklist, self._name + + def __dir__(self): + return dir(type(self)) + list(self.keys()) + + @classmethod + def from_dict(cls, other, name=None) -> "ParseResults": + """ + Helper classmethod to construct a ``ParseResults`` from a ``dict``, preserving the + name-value relations as results names. If an optional ``name`` argument is + given, a nested ``ParseResults`` will be returned. + """ + + def is_iterable(obj): + try: + iter(obj) + except Exception: + return False + else: + return not isinstance(obj, str_type) + + ret = cls([]) + for k, v in other.items(): + if isinstance(v, Mapping): + ret += cls.from_dict(v, name=k) + else: + ret += cls([v], name=k, asList=is_iterable(v)) + if name is not None: + ret = cls([ret], name=name) + return ret + + asList = as_list + asDict = as_dict + getName = get_name + + +MutableMapping.register(ParseResults) +MutableSequence.register(ParseResults) diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/testing.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/testing.py new file mode 100644 index 0000000..84a0ef1 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/testing.py @@ -0,0 +1,331 @@ +# testing.py + +from contextlib import contextmanager +import typing + +from .core import ( + ParserElement, + ParseException, + Keyword, + __diag__, + __compat__, +) + + +class pyparsing_test: + """ + namespace class for classes useful in writing unit tests + """ + + class reset_pyparsing_context: + """ + Context manager to be used when writing unit tests that modify pyparsing config values: + - packrat parsing + - bounded recursion parsing + - default whitespace characters. + - default keyword characters + - literal string auto-conversion class + - __diag__ settings + + Example:: + + with reset_pyparsing_context(): + # test that literals used to construct a grammar are automatically suppressed + ParserElement.inlineLiteralsUsing(Suppress) + + term = Word(alphas) | Word(nums) + group = Group('(' + term[...] + ')') + + # assert that the '()' characters are not included in the parsed tokens + self.assertParseAndCheckList(group, "(abc 123 def)", ['abc', '123', 'def']) + + # after exiting context manager, literals are converted to Literal expressions again + """ + + def __init__(self): + self._save_context = {} + + def save(self): + self._save_context["default_whitespace"] = ParserElement.DEFAULT_WHITE_CHARS + self._save_context["default_keyword_chars"] = Keyword.DEFAULT_KEYWORD_CHARS + + self._save_context[ + "literal_string_class" + ] = ParserElement._literalStringClass + + self._save_context["verbose_stacktrace"] = ParserElement.verbose_stacktrace + + self._save_context["packrat_enabled"] = ParserElement._packratEnabled + if ParserElement._packratEnabled: + self._save_context[ + "packrat_cache_size" + ] = ParserElement.packrat_cache.size + else: + self._save_context["packrat_cache_size"] = None + self._save_context["packrat_parse"] = ParserElement._parse + self._save_context[ + "recursion_enabled" + ] = ParserElement._left_recursion_enabled + + self._save_context["__diag__"] = { + name: getattr(__diag__, name) for name in __diag__._all_names + } + + self._save_context["__compat__"] = { + "collect_all_And_tokens": __compat__.collect_all_And_tokens + } + + return self + + def restore(self): + # reset pyparsing global state + if ( + ParserElement.DEFAULT_WHITE_CHARS + != self._save_context["default_whitespace"] + ): + ParserElement.set_default_whitespace_chars( + self._save_context["default_whitespace"] + ) + + ParserElement.verbose_stacktrace = self._save_context["verbose_stacktrace"] + + Keyword.DEFAULT_KEYWORD_CHARS = self._save_context["default_keyword_chars"] + ParserElement.inlineLiteralsUsing( + self._save_context["literal_string_class"] + ) + + for name, value in self._save_context["__diag__"].items(): + (__diag__.enable if value else __diag__.disable)(name) + + ParserElement._packratEnabled = False + if self._save_context["packrat_enabled"]: + ParserElement.enable_packrat(self._save_context["packrat_cache_size"]) + else: + ParserElement._parse = self._save_context["packrat_parse"] + ParserElement._left_recursion_enabled = self._save_context[ + "recursion_enabled" + ] + + __compat__.collect_all_And_tokens = self._save_context["__compat__"] + + return self + + def copy(self): + ret = type(self)() + ret._save_context.update(self._save_context) + return ret + + def __enter__(self): + return self.save() + + def __exit__(self, *args): + self.restore() + + class TestParseResultsAsserts: + """ + A mixin class to add parse results assertion methods to normal unittest.TestCase classes. + """ + + def assertParseResultsEquals( + self, result, expected_list=None, expected_dict=None, msg=None + ): + """ + Unit test assertion to compare a :class:`ParseResults` object with an optional ``expected_list``, + and compare any defined results names with an optional ``expected_dict``. + """ + if expected_list is not None: + self.assertEqual(expected_list, result.as_list(), msg=msg) + if expected_dict is not None: + self.assertEqual(expected_dict, result.as_dict(), msg=msg) + + def assertParseAndCheckList( + self, expr, test_string, expected_list, msg=None, verbose=True + ): + """ + Convenience wrapper assert to test a parser element and input string, and assert that + the resulting ``ParseResults.asList()`` is equal to the ``expected_list``. + """ + result = expr.parse_string(test_string, parse_all=True) + if verbose: + print(result.dump()) + else: + print(result.as_list()) + self.assertParseResultsEquals(result, expected_list=expected_list, msg=msg) + + def assertParseAndCheckDict( + self, expr, test_string, expected_dict, msg=None, verbose=True + ): + """ + Convenience wrapper assert to test a parser element and input string, and assert that + the resulting ``ParseResults.asDict()`` is equal to the ``expected_dict``. + """ + result = expr.parse_string(test_string, parseAll=True) + if verbose: + print(result.dump()) + else: + print(result.as_list()) + self.assertParseResultsEquals(result, expected_dict=expected_dict, msg=msg) + + def assertRunTestResults( + self, run_tests_report, expected_parse_results=None, msg=None + ): + """ + Unit test assertion to evaluate output of ``ParserElement.runTests()``. If a list of + list-dict tuples is given as the ``expected_parse_results`` argument, then these are zipped + with the report tuples returned by ``runTests`` and evaluated using ``assertParseResultsEquals``. + Finally, asserts that the overall ``runTests()`` success value is ``True``. + + :param run_tests_report: tuple(bool, [tuple(str, ParseResults or Exception)]) returned from runTests + :param expected_parse_results (optional): [tuple(str, list, dict, Exception)] + """ + run_test_success, run_test_results = run_tests_report + + if expected_parse_results is not None: + merged = [ + (*rpt, expected) + for rpt, expected in zip(run_test_results, expected_parse_results) + ] + for test_string, result, expected in merged: + # expected should be a tuple containing a list and/or a dict or an exception, + # and optional failure message string + # an empty tuple will skip any result validation + fail_msg = next( + (exp for exp in expected if isinstance(exp, str)), None + ) + expected_exception = next( + ( + exp + for exp in expected + if isinstance(exp, type) and issubclass(exp, Exception) + ), + None, + ) + if expected_exception is not None: + with self.assertRaises( + expected_exception=expected_exception, msg=fail_msg or msg + ): + if isinstance(result, Exception): + raise result + else: + expected_list = next( + (exp for exp in expected if isinstance(exp, list)), None + ) + expected_dict = next( + (exp for exp in expected if isinstance(exp, dict)), None + ) + if (expected_list, expected_dict) != (None, None): + self.assertParseResultsEquals( + result, + expected_list=expected_list, + expected_dict=expected_dict, + msg=fail_msg or msg, + ) + else: + # warning here maybe? + print("no validation for {!r}".format(test_string)) + + # do this last, in case some specific test results can be reported instead + self.assertTrue( + run_test_success, msg=msg if msg is not None else "failed runTests" + ) + + @contextmanager + def assertRaisesParseException(self, exc_type=ParseException, msg=None): + with self.assertRaises(exc_type, msg=msg): + yield + + @staticmethod + def with_line_numbers( + s: str, + start_line: typing.Optional[int] = None, + end_line: typing.Optional[int] = None, + expand_tabs: bool = True, + eol_mark: str = "|", + mark_spaces: typing.Optional[str] = None, + mark_control: typing.Optional[str] = None, + ) -> str: + """ + Helpful method for debugging a parser - prints a string with line and column numbers. + (Line and column numbers are 1-based.) + + :param s: tuple(bool, str - string to be printed with line and column numbers + :param start_line: int - (optional) starting line number in s to print (default=1) + :param end_line: int - (optional) ending line number in s to print (default=len(s)) + :param expand_tabs: bool - (optional) expand tabs to spaces, to match the pyparsing default + :param eol_mark: str - (optional) string to mark the end of lines, helps visualize trailing spaces (default="|") + :param mark_spaces: str - (optional) special character to display in place of spaces + :param mark_control: str - (optional) convert non-printing control characters to a placeholding + character; valid values: + - "unicode" - replaces control chars with Unicode symbols, such as "␍" and "␊" + - any single character string - replace control characters with given string + - None (default) - string is displayed as-is + + :return: str - input string with leading line numbers and column number headers + """ + if expand_tabs: + s = s.expandtabs() + if mark_control is not None: + if mark_control == "unicode": + tbl = str.maketrans( + {c: u for c, u in zip(range(0, 33), range(0x2400, 0x2433))} + | {127: 0x2421} + ) + eol_mark = "" + else: + tbl = str.maketrans( + {c: mark_control for c in list(range(0, 32)) + [127]} + ) + s = s.translate(tbl) + if mark_spaces is not None and mark_spaces != " ": + if mark_spaces == "unicode": + tbl = str.maketrans({9: 0x2409, 32: 0x2423}) + s = s.translate(tbl) + else: + s = s.replace(" ", mark_spaces) + if start_line is None: + start_line = 1 + if end_line is None: + end_line = len(s) + end_line = min(end_line, len(s)) + start_line = min(max(1, start_line), end_line) + + if mark_control != "unicode": + s_lines = s.splitlines()[start_line - 1 : end_line] + else: + s_lines = [line + "␊" for line in s.split("␊")[start_line - 1 : end_line]] + if not s_lines: + return "" + + lineno_width = len(str(end_line)) + max_line_len = max(len(line) for line in s_lines) + lead = " " * (lineno_width + 1) + if max_line_len >= 99: + header0 = ( + lead + + "".join( + "{}{}".format(" " * 99, (i + 1) % 100) + for i in range(max(max_line_len // 100, 1)) + ) + + "\n" + ) + else: + header0 = "" + header1 = ( + header0 + + lead + + "".join( + " {}".format((i + 1) % 10) + for i in range(-(-max_line_len // 10)) + ) + + "\n" + ) + header2 = lead + "1234567890" * (-(-max_line_len // 10)) + "\n" + return ( + header1 + + header2 + + "\n".join( + "{:{}d}:{}{}".format(i, lineno_width, line, eol_mark) + for i, line in enumerate(s_lines, start=start_line) + ) + + "\n" + ) diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/unicode.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/unicode.py new file mode 100644 index 0000000..0652620 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/unicode.py @@ -0,0 +1,352 @@ +# unicode.py + +import sys +from itertools import filterfalse +from typing import List, Tuple, Union + + +class _lazyclassproperty: + def __init__(self, fn): + self.fn = fn + self.__doc__ = fn.__doc__ + self.__name__ = fn.__name__ + + def __get__(self, obj, cls): + if cls is None: + cls = type(obj) + if not hasattr(cls, "_intern") or any( + cls._intern is getattr(superclass, "_intern", []) + for superclass in cls.__mro__[1:] + ): + cls._intern = {} + attrname = self.fn.__name__ + if attrname not in cls._intern: + cls._intern[attrname] = self.fn(cls) + return cls._intern[attrname] + + +UnicodeRangeList = List[Union[Tuple[int, int], Tuple[int]]] + + +class unicode_set: + """ + A set of Unicode characters, for language-specific strings for + ``alphas``, ``nums``, ``alphanums``, and ``printables``. + A unicode_set is defined by a list of ranges in the Unicode character + set, in a class attribute ``_ranges``. Ranges can be specified using + 2-tuples or a 1-tuple, such as:: + + _ranges = [ + (0x0020, 0x007e), + (0x00a0, 0x00ff), + (0x0100,), + ] + + Ranges are left- and right-inclusive. A 1-tuple of (x,) is treated as (x, x). + + A unicode set can also be defined using multiple inheritance of other unicode sets:: + + class CJK(Chinese, Japanese, Korean): + pass + """ + + _ranges: UnicodeRangeList = [] + + @_lazyclassproperty + def _chars_for_ranges(cls): + ret = [] + for cc in cls.__mro__: + if cc is unicode_set: + break + for rr in getattr(cc, "_ranges", ()): + ret.extend(range(rr[0], rr[-1] + 1)) + return [chr(c) for c in sorted(set(ret))] + + @_lazyclassproperty + def printables(cls): + "all non-whitespace characters in this range" + return "".join(filterfalse(str.isspace, cls._chars_for_ranges)) + + @_lazyclassproperty + def alphas(cls): + "all alphabetic characters in this range" + return "".join(filter(str.isalpha, cls._chars_for_ranges)) + + @_lazyclassproperty + def nums(cls): + "all numeric digit characters in this range" + return "".join(filter(str.isdigit, cls._chars_for_ranges)) + + @_lazyclassproperty + def alphanums(cls): + "all alphanumeric characters in this range" + return cls.alphas + cls.nums + + @_lazyclassproperty + def identchars(cls): + "all characters in this range that are valid identifier characters, plus underscore '_'" + return "".join( + sorted( + set( + "".join(filter(str.isidentifier, cls._chars_for_ranges)) + + "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyzªµº" + + "ÀÁÂÃÄÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖØÙÚÛÜÝÞßàáâãäåæçèéêëìíîïðñòóôõöøùúûüýþÿ" + + "_" + ) + ) + ) + + @_lazyclassproperty + def identbodychars(cls): + """ + all characters in this range that are valid identifier body characters, + plus the digits 0-9 + """ + return "".join( + sorted( + set( + cls.identchars + + "0123456789" + + "".join( + [c for c in cls._chars_for_ranges if ("_" + c).isidentifier()] + ) + ) + ) + ) + + +class pyparsing_unicode(unicode_set): + """ + A namespace class for defining common language unicode_sets. + """ + + # fmt: off + + # define ranges in language character sets + _ranges: UnicodeRangeList = [ + (0x0020, sys.maxunicode), + ] + + class BasicMultilingualPlane(unicode_set): + "Unicode set for the Basic Multilingual Plane" + _ranges: UnicodeRangeList = [ + (0x0020, 0xFFFF), + ] + + class Latin1(unicode_set): + "Unicode set for Latin-1 Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x0020, 0x007E), + (0x00A0, 0x00FF), + ] + + class LatinA(unicode_set): + "Unicode set for Latin-A Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x0100, 0x017F), + ] + + class LatinB(unicode_set): + "Unicode set for Latin-B Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x0180, 0x024F), + ] + + class Greek(unicode_set): + "Unicode set for Greek Unicode Character Ranges" + _ranges: UnicodeRangeList = [ + (0x0342, 0x0345), + (0x0370, 0x0377), + (0x037A, 0x037F), + (0x0384, 0x038A), + (0x038C,), + (0x038E, 0x03A1), + (0x03A3, 0x03E1), + (0x03F0, 0x03FF), + (0x1D26, 0x1D2A), + (0x1D5E,), + (0x1D60,), + (0x1D66, 0x1D6A), + (0x1F00, 0x1F15), + (0x1F18, 0x1F1D), + (0x1F20, 0x1F45), + (0x1F48, 0x1F4D), + (0x1F50, 0x1F57), + (0x1F59,), + (0x1F5B,), + (0x1F5D,), + (0x1F5F, 0x1F7D), + (0x1F80, 0x1FB4), + (0x1FB6, 0x1FC4), + (0x1FC6, 0x1FD3), + (0x1FD6, 0x1FDB), + (0x1FDD, 0x1FEF), + (0x1FF2, 0x1FF4), + (0x1FF6, 0x1FFE), + (0x2129,), + (0x2719, 0x271A), + (0xAB65,), + (0x10140, 0x1018D), + (0x101A0,), + (0x1D200, 0x1D245), + (0x1F7A1, 0x1F7A7), + ] + + class Cyrillic(unicode_set): + "Unicode set for Cyrillic Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x0400, 0x052F), + (0x1C80, 0x1C88), + (0x1D2B,), + (0x1D78,), + (0x2DE0, 0x2DFF), + (0xA640, 0xA672), + (0xA674, 0xA69F), + (0xFE2E, 0xFE2F), + ] + + class Chinese(unicode_set): + "Unicode set for Chinese Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x2E80, 0x2E99), + (0x2E9B, 0x2EF3), + (0x31C0, 0x31E3), + (0x3400, 0x4DB5), + (0x4E00, 0x9FEF), + (0xA700, 0xA707), + (0xF900, 0xFA6D), + (0xFA70, 0xFAD9), + (0x16FE2, 0x16FE3), + (0x1F210, 0x1F212), + (0x1F214, 0x1F23B), + (0x1F240, 0x1F248), + (0x20000, 0x2A6D6), + (0x2A700, 0x2B734), + (0x2B740, 0x2B81D), + (0x2B820, 0x2CEA1), + (0x2CEB0, 0x2EBE0), + (0x2F800, 0x2FA1D), + ] + + class Japanese(unicode_set): + "Unicode set for Japanese Unicode Character Range, combining Kanji, Hiragana, and Katakana ranges" + _ranges: UnicodeRangeList = [] + + class Kanji(unicode_set): + "Unicode set for Kanji Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x4E00, 0x9FBF), + (0x3000, 0x303F), + ] + + class Hiragana(unicode_set): + "Unicode set for Hiragana Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x3041, 0x3096), + (0x3099, 0x30A0), + (0x30FC,), + (0xFF70,), + (0x1B001,), + (0x1B150, 0x1B152), + (0x1F200,), + ] + + class Katakana(unicode_set): + "Unicode set for Katakana Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x3099, 0x309C), + (0x30A0, 0x30FF), + (0x31F0, 0x31FF), + (0x32D0, 0x32FE), + (0xFF65, 0xFF9F), + (0x1B000,), + (0x1B164, 0x1B167), + (0x1F201, 0x1F202), + (0x1F213,), + ] + + class Hangul(unicode_set): + "Unicode set for Hangul (Korean) Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x1100, 0x11FF), + (0x302E, 0x302F), + (0x3131, 0x318E), + (0x3200, 0x321C), + (0x3260, 0x327B), + (0x327E,), + (0xA960, 0xA97C), + (0xAC00, 0xD7A3), + (0xD7B0, 0xD7C6), + (0xD7CB, 0xD7FB), + (0xFFA0, 0xFFBE), + (0xFFC2, 0xFFC7), + (0xFFCA, 0xFFCF), + (0xFFD2, 0xFFD7), + (0xFFDA, 0xFFDC), + ] + + Korean = Hangul + + class CJK(Chinese, Japanese, Hangul): + "Unicode set for combined Chinese, Japanese, and Korean (CJK) Unicode Character Range" + + class Thai(unicode_set): + "Unicode set for Thai Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x0E01, 0x0E3A), + (0x0E3F, 0x0E5B) + ] + + class Arabic(unicode_set): + "Unicode set for Arabic Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x0600, 0x061B), + (0x061E, 0x06FF), + (0x0700, 0x077F), + ] + + class Hebrew(unicode_set): + "Unicode set for Hebrew Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x0591, 0x05C7), + (0x05D0, 0x05EA), + (0x05EF, 0x05F4), + (0xFB1D, 0xFB36), + (0xFB38, 0xFB3C), + (0xFB3E,), + (0xFB40, 0xFB41), + (0xFB43, 0xFB44), + (0xFB46, 0xFB4F), + ] + + class Devanagari(unicode_set): + "Unicode set for Devanagari Unicode Character Range" + _ranges: UnicodeRangeList = [ + (0x0900, 0x097F), + (0xA8E0, 0xA8FF) + ] + + # fmt: on + + +pyparsing_unicode.Japanese._ranges = ( + pyparsing_unicode.Japanese.Kanji._ranges + + pyparsing_unicode.Japanese.Hiragana._ranges + + pyparsing_unicode.Japanese.Katakana._ranges +) + +pyparsing_unicode.BMP = pyparsing_unicode.BasicMultilingualPlane + +# add language identifiers using language Unicode +pyparsing_unicode.العربية = pyparsing_unicode.Arabic +pyparsing_unicode.中文 = pyparsing_unicode.Chinese +pyparsing_unicode.кириллица = pyparsing_unicode.Cyrillic +pyparsing_unicode.Ελληνικά = pyparsing_unicode.Greek +pyparsing_unicode.עִברִית = pyparsing_unicode.Hebrew +pyparsing_unicode.日本語 = pyparsing_unicode.Japanese +pyparsing_unicode.Japanese.漢字 = pyparsing_unicode.Japanese.Kanji +pyparsing_unicode.Japanese.カタカナ = pyparsing_unicode.Japanese.Katakana +pyparsing_unicode.Japanese.ひらがな = pyparsing_unicode.Japanese.Hiragana +pyparsing_unicode.한국어 = pyparsing_unicode.Korean +pyparsing_unicode.ไทย = pyparsing_unicode.Thai +pyparsing_unicode.देवनागरी = pyparsing_unicode.Devanagari diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/util.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/util.py new file mode 100644 index 0000000..34ce092 --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/pyparsing/util.py @@ -0,0 +1,235 @@ +# util.py +import warnings +import types +import collections +import itertools +from functools import lru_cache +from typing import List, Union, Iterable + +_bslash = chr(92) + + +class __config_flags: + """Internal class for defining compatibility and debugging flags""" + + _all_names: List[str] = [] + _fixed_names: List[str] = [] + _type_desc = "configuration" + + @classmethod + def _set(cls, dname, value): + if dname in cls._fixed_names: + warnings.warn( + "{}.{} {} is {} and cannot be overridden".format( + cls.__name__, + dname, + cls._type_desc, + str(getattr(cls, dname)).upper(), + ) + ) + return + if dname in cls._all_names: + setattr(cls, dname, value) + else: + raise ValueError("no such {} {!r}".format(cls._type_desc, dname)) + + enable = classmethod(lambda cls, name: cls._set(name, True)) + disable = classmethod(lambda cls, name: cls._set(name, False)) + + +@lru_cache(maxsize=128) +def col(loc: int, strg: str) -> int: + """ + Returns current column within a string, counting newlines as line separators. + The first column is number 1. + + Note: the default parsing behavior is to expand tabs in the input string + before starting the parsing process. See + :class:`ParserElement.parseString` for more + information on parsing strings containing ``<TAB>`` s, and suggested + methods to maintain a consistent view of the parsed string, the parse + location, and line and column positions within the parsed string. + """ + s = strg + return 1 if 0 < loc < len(s) and s[loc - 1] == "\n" else loc - s.rfind("\n", 0, loc) + + +@lru_cache(maxsize=128) +def lineno(loc: int, strg: str) -> int: + """Returns current line number within a string, counting newlines as line separators. + The first line is number 1. + + Note - the default parsing behavior is to expand tabs in the input string + before starting the parsing process. See :class:`ParserElement.parseString` + for more information on parsing strings containing ``<TAB>`` s, and + suggested methods to maintain a consistent view of the parsed string, the + parse location, and line and column positions within the parsed string. + """ + return strg.count("\n", 0, loc) + 1 + + +@lru_cache(maxsize=128) +def line(loc: int, strg: str) -> str: + """ + Returns the line of text containing loc within a string, counting newlines as line separators. + """ + last_cr = strg.rfind("\n", 0, loc) + next_cr = strg.find("\n", loc) + return strg[last_cr + 1 : next_cr] if next_cr >= 0 else strg[last_cr + 1 :] + + +class _UnboundedCache: + def __init__(self): + cache = {} + cache_get = cache.get + self.not_in_cache = not_in_cache = object() + + def get(_, key): + return cache_get(key, not_in_cache) + + def set_(_, key, value): + cache[key] = value + + def clear(_): + cache.clear() + + self.size = None + self.get = types.MethodType(get, self) + self.set = types.MethodType(set_, self) + self.clear = types.MethodType(clear, self) + + +class _FifoCache: + def __init__(self, size): + self.not_in_cache = not_in_cache = object() + cache = collections.OrderedDict() + cache_get = cache.get + + def get(_, key): + return cache_get(key, not_in_cache) + + def set_(_, key, value): + cache[key] = value + while len(cache) > size: + cache.popitem(last=False) + + def clear(_): + cache.clear() + + self.size = size + self.get = types.MethodType(get, self) + self.set = types.MethodType(set_, self) + self.clear = types.MethodType(clear, self) + + +class LRUMemo: + """ + A memoizing mapping that retains `capacity` deleted items + + The memo tracks retained items by their access order; once `capacity` items + are retained, the least recently used item is discarded. + """ + + def __init__(self, capacity): + self._capacity = capacity + self._active = {} + self._memory = collections.OrderedDict() + + def __getitem__(self, key): + try: + return self._active[key] + except KeyError: + self._memory.move_to_end(key) + return self._memory[key] + + def __setitem__(self, key, value): + self._memory.pop(key, None) + self._active[key] = value + + def __delitem__(self, key): + try: + value = self._active.pop(key) + except KeyError: + pass + else: + while len(self._memory) >= self._capacity: + self._memory.popitem(last=False) + self._memory[key] = value + + def clear(self): + self._active.clear() + self._memory.clear() + + +class UnboundedMemo(dict): + """ + A memoizing mapping that retains all deleted items + """ + + def __delitem__(self, key): + pass + + +def _escape_regex_range_chars(s: str) -> str: + # escape these chars: ^-[] + for c in r"\^-[]": + s = s.replace(c, _bslash + c) + s = s.replace("\n", r"\n") + s = s.replace("\t", r"\t") + return str(s) + + +def _collapse_string_to_ranges( + s: Union[str, Iterable[str]], re_escape: bool = True +) -> str: + def is_consecutive(c): + c_int = ord(c) + is_consecutive.prev, prev = c_int, is_consecutive.prev + if c_int - prev > 1: + is_consecutive.value = next(is_consecutive.counter) + return is_consecutive.value + + is_consecutive.prev = 0 + is_consecutive.counter = itertools.count() + is_consecutive.value = -1 + + def escape_re_range_char(c): + return "\\" + c if c in r"\^-][" else c + + def no_escape_re_range_char(c): + return c + + if not re_escape: + escape_re_range_char = no_escape_re_range_char + + ret = [] + s = "".join(sorted(set(s))) + if len(s) > 3: + for _, chars in itertools.groupby(s, key=is_consecutive): + first = last = next(chars) + last = collections.deque( + itertools.chain(iter([last]), chars), maxlen=1 + ).pop() + if first == last: + ret.append(escape_re_range_char(first)) + else: + sep = "" if ord(last) == ord(first) + 1 else "-" + ret.append( + "{}{}{}".format( + escape_re_range_char(first), sep, escape_re_range_char(last) + ) + ) + else: + ret = [escape_re_range_char(c) for c in s] + + return "".join(ret) + + +def _flatten(ll: list) -> list: + ret = [] + for i in ll: + if isinstance(i, list): + ret.extend(_flatten(i)) + else: + ret.append(i) + return ret diff --git a/venv/lib/python3.11/site-packages/pkg_resources/_vendor/zipp.py b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/zipp.py new file mode 100644 index 0000000..26b723c --- /dev/null +++ b/venv/lib/python3.11/site-packages/pkg_resources/_vendor/zipp.py @@ -0,0 +1,329 @@ +import io +import posixpath +import zipfile +import itertools +import contextlib +import sys +import pathlib + +if sys.version_info < (3, 7): + from collections import OrderedDict +else: + OrderedDict = dict + + +__all__ = ['Path'] + + +def _parents(path): + """ + Given a path with elements separated by + posixpath.sep, generate all parents of that path. + + >>> list(_parents('b/d')) + ['b'] + >>> list(_parents('/b/d/')) + ['/b'] + >>> list(_parents('b/d/f/')) + ['b/d', 'b'] + >>> list(_parents('b')) + [] + >>> list(_parents('')) + [] + """ + return itertools.islice(_ancestry(path), 1, None) + + +def _ancestry(path): + """ + Given a path with elements separated by + posixpath.sep, generate all elements of that path + + >>> list(_ancestry('b/d')) + ['b/d', 'b'] + >>> list(_ancestry('/b/d/')) + ['/b/d', '/b'] + >>> list(_ancestry('b/d/f/')) + ['b/d/f', 'b/d', 'b'] + >>> list(_ancestry('b')) + ['b'] + >>> list(_ancestry('')) + [] + """ + path = path.rstrip(posixpath.sep) + while path and path != posixpath.sep: + yield path + path, tail = posixpath.split(path) + + +_dedupe = OrderedDict.fromkeys +"""Deduplicate an iterable in original order""" + + +def _difference(minuend, subtrahend): + """ + Return items in minuend not in subtrahend, retaining order + with O(1) lookup. + """ + return itertools.filterfalse(set(subtrahend).__contains__, minuend) + + +class CompleteDirs(zipfile.ZipFile): + """ + A ZipFile subclass that ensures that implied directories + are always included in the namelist. + """ + + @staticmethod + def _implied_dirs(names): + parents = itertools.chain.from_iterable(map(_parents, names)) + as_dirs = (p + posixpath.sep for p in parents) + return _dedupe(_difference(as_dirs, names)) + + def namelist(self): + names = super(CompleteDirs, self).namelist() + return names + list(self._implied_dirs(names)) + + def _name_set(self): + return set(self.namelist()) + + def resolve_dir(self, name): + """ + If the name represents a directory, return that name + as a directory (with the trailing slash). + """ + names = self._name_set() + dirname = name + '/' + dir_match = name not in names and dirname in names + return dirname if dir_match else name + + @classmethod + def make(cls, source): + """ + Given a source (filename or zipfile), return an + appropriate CompleteDirs subclass. + """ + if isinstance(source, CompleteDirs): + return source + + if not isinstance(source, zipfile.ZipFile): + return cls(_pathlib_compat(source)) + + # Only allow for FastLookup when supplied zipfile is read-only + if 'r' not in source.mode: + cls = CompleteDirs + + source.__class__ = cls + return source + + +class FastLookup(CompleteDirs): + """ + ZipFile subclass to ensure implicit + dirs exist and are resolved rapidly. + """ + + def namelist(self): + with contextlib.suppress(AttributeError): + return self.__names + self.__names = super(FastLookup, self).namelist() + return self.__names + + def _name_set(self): + with contextlib.suppress(AttributeError): + return self.__lookup + self.__lookup = super(FastLookup, self)._name_set() + return self.__lookup + + +def _pathlib_compat(path): + """ + For path-like objects, convert to a filename for compatibility + on Python 3.6.1 and earlier. + """ + try: + return path.__fspath__() + except AttributeError: + return str(path) + + +class Path: + """ + A pathlib-compatible interface for zip files. + + Consider a zip file with this structure:: + + . + ├── a.txt + └── b + ├── c.txt + └── d + └── e.txt + + >>> data = io.BytesIO() + >>> zf = zipfile.ZipFile(data, 'w') + >>> zf.writestr('a.txt', 'content of a') + >>> zf.writestr('b/c.txt', 'content of c') + >>> zf.writestr('b/d/e.txt', 'content of e') + >>> zf.filename = 'mem/abcde.zip' + + Path accepts the zipfile object itself or a filename + + >>> root = Path(zf) + + From there, several path operations are available. + + Directory iteration (including the zip file itself): + + >>> a, b = root.iterdir() + >>> a + Path('mem/abcde.zip', 'a.txt') + >>> b + Path('mem/abcde.zip', 'b/') + + name property: + + >>> b.name + 'b' + + join with divide operator: + + >>> c = b / 'c.txt' + >>> c + Path('mem/abcde.zip', 'b/c.txt') + >>> c.name + 'c.txt' + + Read text: + + >>> c.read_text() + 'content of c' + + existence: + + >>> c.exists() + True + >>> (b / 'missing.txt').exists() + False + + Coercion to string: + + >>> import os + >>> str(c).replace(os.sep, posixpath.sep) + 'mem/abcde.zip/b/c.txt' + + At the root, ``name``, ``filename``, and ``parent`` + resolve to the zipfile. Note these attributes are not + valid and will raise a ``ValueError`` if the zipfile + has no filename. + + >>> root.name + 'abcde.zip' + >>> str(root.filename).replace(os.sep, posixpath.sep) + 'mem/abcde.zip' + >>> str(root.parent) + 'mem' + """ + + __repr = "{self.__class__.__name__}({self.root.filename!r}, {self.at!r})" + + def __init__(self, root, at=""): + """ + Construct a Path from a ZipFile or filename. + + Note: When the source is an existing ZipFile object, + its type (__class__) will be mutated to a + specialized type. If the caller wishes to retain the + original type, the caller should either create a + separate ZipFile object or pass a filename. + """ + self.root = FastLookup.make(root) + self.at = at + + def open(self, mode='r', *args, pwd=None, **kwargs): + """ + Open this entry as text or binary following the semantics + of ``pathlib.Path.open()`` by passing arguments through + to io.TextIOWrapper(). + """ + if self.is_dir(): + raise IsADirectoryError(self) + zip_mode = mode[0] + if not self.exists() and zip_mode == 'r': + raise FileNotFoundError(self) + stream = self.root.open(self.at, zip_mode, pwd=pwd) + if 'b' in mode: + if args or kwargs: + raise ValueError("encoding args invalid for binary operation") + return stream + return io.TextIOWrapper(stream, *args, **kwargs) + + @property + def name(self): + return pathlib.Path(self.at).name or self.filename.name + + @property + def suffix(self): + return pathlib.Path(self.at).suffix or self.filename.suffix + + @property + def suffixes(self): + return pathlib.Path(self.at).suffixes or self.filename.suffixes + + @property + def stem(self): + return pathlib.Path(self.at).stem or self.filename.stem + + @property + def filename(self): + return pathlib.Path(self.root.filename).joinpath(self.at) + + def read_text(self, *args, **kwargs): + with self.open('r', *args, **kwargs) as strm: + return strm.read() + + def read_bytes(self): + with self.open('rb') as strm: + return strm.read() + + def _is_child(self, path): + return posixpath.dirname(path.at.rstrip("/")) == self.at.rstrip("/") + + def _next(self, at): + return self.__class__(self.root, at) + + def is_dir(self): + return not self.at or self.at.endswith("/") + + def is_file(self): + return self.exists() and not self.is_dir() + + def exists(self): + return self.at in self.root._name_set() + + def iterdir(self): + if not self.is_dir(): + raise ValueError("Can't listdir a file") + subs = map(self._next, self.root.namelist()) + return filter(self._is_child, subs) + + def __str__(self): + return posixpath.join(self.root.filename, self.at) + + def __repr__(self): + return self.__repr.format(self=self) + + def joinpath(self, *other): + next = posixpath.join(self.at, *map(_pathlib_compat, other)) + return self._next(self.root.resolve_dir(next)) + + __truediv__ = joinpath + + @property + def parent(self): + if not self.at: + return self.filename.parent + parent_at = posixpath.dirname(self.at.rstrip('/')) + if parent_at: + parent_at += '/' + return self._next(parent_at) |