1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
|
from __future__ import annotations
import io
import os
import typing
from pathlib import Path
from ._types import (
AsyncByteStream,
FileContent,
FileTypes,
RequestData,
RequestFiles,
SyncByteStream,
)
from ._utils import (
format_form_param,
guess_content_type,
peek_filelike_length,
primitive_value_to_str,
to_bytes,
)
def get_multipart_boundary_from_content_type(
content_type: bytes | None,
) -> bytes | None:
if not content_type or not content_type.startswith(b"multipart/form-data"):
return None
# parse boundary according to
# https://www.rfc-editor.org/rfc/rfc2046#section-5.1.1
if b";" in content_type:
for section in content_type.split(b";"):
if section.strip().lower().startswith(b"boundary="):
return section.strip()[len(b"boundary=") :].strip(b'"')
return None
class DataField:
"""
A single form field item, within a multipart form field.
"""
def __init__(self, name: str, value: str | bytes | int | float | None) -> None:
if not isinstance(name, str):
raise TypeError(
f"Invalid type for name. Expected str, got {type(name)}: {name!r}"
)
if value is not None and not isinstance(value, (str, bytes, int, float)):
raise TypeError(
"Invalid type for value. Expected primitive type,"
f" got {type(value)}: {value!r}"
)
self.name = name
self.value: str | bytes = (
value if isinstance(value, bytes) else primitive_value_to_str(value)
)
def render_headers(self) -> bytes:
if not hasattr(self, "_headers"):
name = format_form_param("name", self.name)
self._headers = b"".join(
[b"Content-Disposition: form-data; ", name, b"\r\n\r\n"]
)
return self._headers
def render_data(self) -> bytes:
if not hasattr(self, "_data"):
self._data = to_bytes(self.value)
return self._data
def get_length(self) -> int:
headers = self.render_headers()
data = self.render_data()
return len(headers) + len(data)
def render(self) -> typing.Iterator[bytes]:
yield self.render_headers()
yield self.render_data()
class FileField:
"""
A single file field item, within a multipart form field.
"""
CHUNK_SIZE = 64 * 1024
def __init__(self, name: str, value: FileTypes) -> None:
self.name = name
fileobj: FileContent
headers: dict[str, str] = {}
content_type: str | None = None
# This large tuple based API largely mirror's requests' API
# It would be good to think of better APIs for this that we could
# include in httpx 2.0 since variable length tuples(especially of 4 elements)
# are quite unwieldly
if isinstance(value, tuple):
if len(value) == 2:
# neither the 3rd parameter (content_type) nor the 4th (headers)
# was included
filename, fileobj = value
elif len(value) == 3:
filename, fileobj, content_type = value
else:
# all 4 parameters included
filename, fileobj, content_type, headers = value # type: ignore
else:
filename = Path(str(getattr(value, "name", "upload"))).name
fileobj = value
if content_type is None:
content_type = guess_content_type(filename)
has_content_type_header = any("content-type" in key.lower() for key in headers)
if content_type is not None and not has_content_type_header:
# note that unlike requests, we ignore the content_type provided in the 3rd
# tuple element if it is also included in the headers requests does
# the opposite (it overwrites the headerwith the 3rd tuple element)
headers["Content-Type"] = content_type
if isinstance(fileobj, io.StringIO):
raise TypeError(
"Multipart file uploads require 'io.BytesIO', not 'io.StringIO'."
)
if isinstance(fileobj, io.TextIOBase):
raise TypeError(
"Multipart file uploads must be opened in binary mode, not text mode."
)
self.filename = filename
self.file = fileobj
self.headers = headers
def get_length(self) -> int | None:
headers = self.render_headers()
if isinstance(self.file, (str, bytes)):
return len(headers) + len(to_bytes(self.file))
file_length = peek_filelike_length(self.file)
# If we can't determine the filesize without reading it into memory,
# then return `None` here, to indicate an unknown file length.
if file_length is None:
return None
return len(headers) + file_length
def render_headers(self) -> bytes:
if not hasattr(self, "_headers"):
parts = [
b"Content-Disposition: form-data; ",
format_form_param("name", self.name),
]
if self.filename:
filename = format_form_param("filename", self.filename)
parts.extend([b"; ", filename])
for header_name, header_value in self.headers.items():
key, val = f"\r\n{header_name}: ".encode(), header_value.encode()
parts.extend([key, val])
parts.append(b"\r\n\r\n")
self._headers = b"".join(parts)
return self._headers
def render_data(self) -> typing.Iterator[bytes]:
if isinstance(self.file, (str, bytes)):
yield to_bytes(self.file)
return
if hasattr(self.file, "seek"):
try:
self.file.seek(0)
except io.UnsupportedOperation:
pass
chunk = self.file.read(self.CHUNK_SIZE)
while chunk:
yield to_bytes(chunk)
chunk = self.file.read(self.CHUNK_SIZE)
def render(self) -> typing.Iterator[bytes]:
yield self.render_headers()
yield from self.render_data()
class MultipartStream(SyncByteStream, AsyncByteStream):
"""
Request content as streaming multipart encoded form data.
"""
def __init__(
self,
data: RequestData,
files: RequestFiles,
boundary: bytes | None = None,
) -> None:
if boundary is None:
boundary = os.urandom(16).hex().encode("ascii")
self.boundary = boundary
self.content_type = "multipart/form-data; boundary=%s" % boundary.decode(
"ascii"
)
self.fields = list(self._iter_fields(data, files))
def _iter_fields(
self, data: RequestData, files: RequestFiles
) -> typing.Iterator[FileField | DataField]:
for name, value in data.items():
if isinstance(value, (tuple, list)):
for item in value:
yield DataField(name=name, value=item)
else:
yield DataField(name=name, value=value)
file_items = files.items() if isinstance(files, typing.Mapping) else files
for name, value in file_items:
yield FileField(name=name, value=value)
def iter_chunks(self) -> typing.Iterator[bytes]:
for field in self.fields:
yield b"--%s\r\n" % self.boundary
yield from field.render()
yield b"\r\n"
yield b"--%s--\r\n" % self.boundary
def get_content_length(self) -> int | None:
"""
Return the length of the multipart encoded content, or `None` if
any of the files have a length that cannot be determined upfront.
"""
boundary_length = len(self.boundary)
length = 0
for field in self.fields:
field_length = field.get_length()
if field_length is None:
return None
length += 2 + boundary_length + 2 # b"--{boundary}\r\n"
length += field_length
length += 2 # b"\r\n"
length += 2 + boundary_length + 4 # b"--{boundary}--\r\n"
return length
# Content stream interface.
def get_headers(self) -> dict[str, str]:
content_length = self.get_content_length()
content_type = self.content_type
if content_length is None:
return {"Transfer-Encoding": "chunked", "Content-Type": content_type}
return {"Content-Length": str(content_length), "Content-Type": content_type}
def __iter__(self) -> typing.Iterator[bytes]:
for chunk in self.iter_chunks():
yield chunk
async def __aiter__(self) -> typing.AsyncIterator[bytes]:
for chunk in self.iter_chunks():
yield chunk
|
