Spaces:
Runtime error
Runtime error
File size: 32,313 Bytes
4a51346 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 |
import base64
import binascii
import json
import re
import uuid
import warnings
import zlib
from collections import deque
from types import TracebackType
from typing import (
TYPE_CHECKING,
Any,
AsyncIterator,
Deque,
Dict,
Iterator,
List,
Mapping,
Optional,
Sequence,
Tuple,
Type,
Union,
cast,
)
from urllib.parse import parse_qsl, unquote, urlencode
from multidict import CIMultiDict, CIMultiDictProxy, MultiMapping
from .hdrs import (
CONTENT_DISPOSITION,
CONTENT_ENCODING,
CONTENT_LENGTH,
CONTENT_TRANSFER_ENCODING,
CONTENT_TYPE,
)
from .helpers import CHAR, TOKEN, parse_mimetype, reify
from .http import HeadersParser
from .payload import (
JsonPayload,
LookupError,
Order,
Payload,
StringPayload,
get_payload,
payload_type,
)
from .streams import StreamReader
__all__ = (
"MultipartReader",
"MultipartWriter",
"BodyPartReader",
"BadContentDispositionHeader",
"BadContentDispositionParam",
"parse_content_disposition",
"content_disposition_filename",
)
if TYPE_CHECKING: # pragma: no cover
from .client_reqrep import ClientResponse
class BadContentDispositionHeader(RuntimeWarning):
pass
class BadContentDispositionParam(RuntimeWarning):
pass
def parse_content_disposition(
header: Optional[str],
) -> Tuple[Optional[str], Dict[str, str]]:
def is_token(string: str) -> bool:
return bool(string) and TOKEN >= set(string)
def is_quoted(string: str) -> bool:
return string[0] == string[-1] == '"'
def is_rfc5987(string: str) -> bool:
return is_token(string) and string.count("'") == 2
def is_extended_param(string: str) -> bool:
return string.endswith("*")
def is_continuous_param(string: str) -> bool:
pos = string.find("*") + 1
if not pos:
return False
substring = string[pos:-1] if string.endswith("*") else string[pos:]
return substring.isdigit()
def unescape(text: str, *, chars: str = "".join(map(re.escape, CHAR))) -> str:
return re.sub(f"\\\\([{chars}])", "\\1", text)
if not header:
return None, {}
disptype, *parts = header.split(";")
if not is_token(disptype):
warnings.warn(BadContentDispositionHeader(header))
return None, {}
params: Dict[str, str] = {}
while parts:
item = parts.pop(0)
if "=" not in item:
warnings.warn(BadContentDispositionHeader(header))
return None, {}
key, value = item.split("=", 1)
key = key.lower().strip()
value = value.lstrip()
if key in params:
warnings.warn(BadContentDispositionHeader(header))
return None, {}
if not is_token(key):
warnings.warn(BadContentDispositionParam(item))
continue
elif is_continuous_param(key):
if is_quoted(value):
value = unescape(value[1:-1])
elif not is_token(value):
warnings.warn(BadContentDispositionParam(item))
continue
elif is_extended_param(key):
if is_rfc5987(value):
encoding, _, value = value.split("'", 2)
encoding = encoding or "utf-8"
else:
warnings.warn(BadContentDispositionParam(item))
continue
try:
value = unquote(value, encoding, "strict")
except UnicodeDecodeError: # pragma: nocover
warnings.warn(BadContentDispositionParam(item))
continue
else:
failed = True
if is_quoted(value):
failed = False
value = unescape(value[1:-1].lstrip("\\/"))
elif is_token(value):
failed = False
elif parts:
# maybe just ; in filename, in any case this is just
# one case fix, for proper fix we need to redesign parser
_value = f"{value};{parts[0]}"
if is_quoted(_value):
parts.pop(0)
value = unescape(_value[1:-1].lstrip("\\/"))
failed = False
if failed:
warnings.warn(BadContentDispositionHeader(header))
return None, {}
params[key] = value
return disptype.lower(), params
def content_disposition_filename(
params: Mapping[str, str], name: str = "filename"
) -> Optional[str]:
name_suf = "%s*" % name
if not params:
return None
elif name_suf in params:
return params[name_suf]
elif name in params:
return params[name]
else:
parts = []
fnparams = sorted(
(key, value) for key, value in params.items() if key.startswith(name_suf)
)
for num, (key, value) in enumerate(fnparams):
_, tail = key.split("*", 1)
if tail.endswith("*"):
tail = tail[:-1]
if tail == str(num):
parts.append(value)
else:
break
if not parts:
return None
value = "".join(parts)
if "'" in value:
encoding, _, value = value.split("'", 2)
encoding = encoding or "utf-8"
return unquote(value, encoding, "strict")
return value
class MultipartResponseWrapper:
"""Wrapper around the MultipartReader.
It takes care about
underlying connection and close it when it needs in.
"""
def __init__(
self,
resp: "ClientResponse",
stream: "MultipartReader",
) -> None:
self.resp = resp
self.stream = stream
def __aiter__(self) -> "MultipartResponseWrapper":
return self
async def __anext__(
self,
) -> Union["MultipartReader", "BodyPartReader"]:
part = await self.next()
if part is None:
raise StopAsyncIteration
return part
def at_eof(self) -> bool:
"""Returns True when all response data had been read."""
return self.resp.content.at_eof()
async def next(
self,
) -> Optional[Union["MultipartReader", "BodyPartReader"]]:
"""Emits next multipart reader object."""
item = await self.stream.next()
if self.stream.at_eof():
await self.release()
return item
async def release(self) -> None:
"""Release the connection gracefully.
All remaining content is read to the void.
"""
await self.resp.release()
class BodyPartReader:
"""Multipart reader for single body part."""
chunk_size = 8192
def __init__(
self, boundary: bytes, headers: "CIMultiDictProxy[str]", content: StreamReader
) -> None:
self.headers = headers
self._boundary = boundary
self._content = content
self._at_eof = False
length = self.headers.get(CONTENT_LENGTH, None)
self._length = int(length) if length is not None else None
self._read_bytes = 0
# TODO: typeing.Deque is not supported by Python 3.5
self._unread: Deque[bytes] = deque()
self._prev_chunk: Optional[bytes] = None
self._content_eof = 0
self._cache: Dict[str, Any] = {}
def __aiter__(self) -> AsyncIterator["BodyPartReader"]:
return self # type: ignore[return-value]
async def __anext__(self) -> bytes:
part = await self.next()
if part is None:
raise StopAsyncIteration
return part
async def next(self) -> Optional[bytes]:
item = await self.read()
if not item:
return None
return item
async def read(self, *, decode: bool = False) -> bytes:
"""Reads body part data.
decode: Decodes data following by encoding
method from Content-Encoding header. If it missed
data remains untouched
"""
if self._at_eof:
return b""
data = bytearray()
while not self._at_eof:
data.extend(await self.read_chunk(self.chunk_size))
if decode:
return self.decode(data)
return data
async def read_chunk(self, size: int = chunk_size) -> bytes:
"""Reads body part content chunk of the specified size.
size: chunk size
"""
if self._at_eof:
return b""
if self._length:
chunk = await self._read_chunk_from_length(size)
else:
chunk = await self._read_chunk_from_stream(size)
self._read_bytes += len(chunk)
if self._read_bytes == self._length:
self._at_eof = True
if self._at_eof:
clrf = await self._content.readline()
assert (
b"\r\n" == clrf
), "reader did not read all the data or it is malformed"
return chunk
async def _read_chunk_from_length(self, size: int) -> bytes:
# Reads body part content chunk of the specified size.
# The body part must has Content-Length header with proper value.
assert self._length is not None, "Content-Length required for chunked read"
chunk_size = min(size, self._length - self._read_bytes)
chunk = await self._content.read(chunk_size)
return chunk
async def _read_chunk_from_stream(self, size: int) -> bytes:
# Reads content chunk of body part with unknown length.
# The Content-Length header for body part is not necessary.
assert (
size >= len(self._boundary) + 2
), "Chunk size must be greater or equal than boundary length + 2"
first_chunk = self._prev_chunk is None
if first_chunk:
self._prev_chunk = await self._content.read(size)
chunk = await self._content.read(size)
self._content_eof += int(self._content.at_eof())
assert self._content_eof < 3, "Reading after EOF"
assert self._prev_chunk is not None
window = self._prev_chunk + chunk
sub = b"\r\n" + self._boundary
if first_chunk:
idx = window.find(sub)
else:
idx = window.find(sub, max(0, len(self._prev_chunk) - len(sub)))
if idx >= 0:
# pushing boundary back to content
with warnings.catch_warnings():
warnings.filterwarnings("ignore", category=DeprecationWarning)
self._content.unread_data(window[idx:])
if size > idx:
self._prev_chunk = self._prev_chunk[:idx]
chunk = window[len(self._prev_chunk) : idx]
if not chunk:
self._at_eof = True
result = self._prev_chunk
self._prev_chunk = chunk
return result
async def readline(self) -> bytes:
"""Reads body part by line by line."""
if self._at_eof:
return b""
if self._unread:
line = self._unread.popleft()
else:
line = await self._content.readline()
if line.startswith(self._boundary):
# the very last boundary may not come with \r\n,
# so set single rules for everyone
sline = line.rstrip(b"\r\n")
boundary = self._boundary
last_boundary = self._boundary + b"--"
# ensure that we read exactly the boundary, not something alike
if sline == boundary or sline == last_boundary:
self._at_eof = True
self._unread.append(line)
return b""
else:
next_line = await self._content.readline()
if next_line.startswith(self._boundary):
line = line[:-2] # strip CRLF but only once
self._unread.append(next_line)
return line
async def release(self) -> None:
"""Like read(), but reads all the data to the void."""
if self._at_eof:
return
while not self._at_eof:
await self.read_chunk(self.chunk_size)
async def text(self, *, encoding: Optional[str] = None) -> str:
"""Like read(), but assumes that body part contains text data."""
data = await self.read(decode=True)
# see https://www.w3.org/TR/html5/forms.html#multipart/form-data-encoding-algorithm # NOQA
# and https://dvcs.w3.org/hg/xhr/raw-file/tip/Overview.html#dom-xmlhttprequest-send # NOQA
encoding = encoding or self.get_charset(default="utf-8")
return data.decode(encoding)
async def json(self, *, encoding: Optional[str] = None) -> Optional[Dict[str, Any]]:
"""Like read(), but assumes that body parts contains JSON data."""
data = await self.read(decode=True)
if not data:
return None
encoding = encoding or self.get_charset(default="utf-8")
return cast(Dict[str, Any], json.loads(data.decode(encoding)))
async def form(self, *, encoding: Optional[str] = None) -> List[Tuple[str, str]]:
"""Like read(), but assumes that body parts contain form urlencoded data."""
data = await self.read(decode=True)
if not data:
return []
if encoding is not None:
real_encoding = encoding
else:
real_encoding = self.get_charset(default="utf-8")
return parse_qsl(
data.rstrip().decode(real_encoding),
keep_blank_values=True,
encoding=real_encoding,
)
def at_eof(self) -> bool:
"""Returns True if the boundary was reached or False otherwise."""
return self._at_eof
def decode(self, data: bytes) -> bytes:
"""Decodes data.
Decoding is done according the specified Content-Encoding
or Content-Transfer-Encoding headers value.
"""
if CONTENT_TRANSFER_ENCODING in self.headers:
data = self._decode_content_transfer(data)
if CONTENT_ENCODING in self.headers:
return self._decode_content(data)
return data
def _decode_content(self, data: bytes) -> bytes:
encoding = self.headers.get(CONTENT_ENCODING, "").lower()
if encoding == "deflate":
return zlib.decompress(data, -zlib.MAX_WBITS)
elif encoding == "gzip":
return zlib.decompress(data, 16 + zlib.MAX_WBITS)
elif encoding == "identity":
return data
else:
raise RuntimeError(f"unknown content encoding: {encoding}")
def _decode_content_transfer(self, data: bytes) -> bytes:
encoding = self.headers.get(CONTENT_TRANSFER_ENCODING, "").lower()
if encoding == "base64":
return base64.b64decode(data)
elif encoding == "quoted-printable":
return binascii.a2b_qp(data)
elif encoding in ("binary", "8bit", "7bit"):
return data
else:
raise RuntimeError(
"unknown content transfer encoding: {}" "".format(encoding)
)
def get_charset(self, default: str) -> str:
"""Returns charset parameter from Content-Type header or default."""
ctype = self.headers.get(CONTENT_TYPE, "")
mimetype = parse_mimetype(ctype)
return mimetype.parameters.get("charset", default)
@reify
def name(self) -> Optional[str]:
"""Returns name specified in Content-Disposition header.
If the header is missing or malformed, returns None.
"""
_, params = parse_content_disposition(self.headers.get(CONTENT_DISPOSITION))
return content_disposition_filename(params, "name")
@reify
def filename(self) -> Optional[str]:
"""Returns filename specified in Content-Disposition header.
Returns None if the header is missing or malformed.
"""
_, params = parse_content_disposition(self.headers.get(CONTENT_DISPOSITION))
return content_disposition_filename(params, "filename")
@payload_type(BodyPartReader, order=Order.try_first)
class BodyPartReaderPayload(Payload):
def __init__(self, value: BodyPartReader, *args: Any, **kwargs: Any) -> None:
super().__init__(value, *args, **kwargs)
params: Dict[str, str] = {}
if value.name is not None:
params["name"] = value.name
if value.filename is not None:
params["filename"] = value.filename
if params:
self.set_content_disposition("attachment", True, **params)
async def write(self, writer: Any) -> None:
field = self._value
chunk = await field.read_chunk(size=2**16)
while chunk:
await writer.write(field.decode(chunk))
chunk = await field.read_chunk(size=2**16)
class MultipartReader:
"""Multipart body reader."""
#: Response wrapper, used when multipart readers constructs from response.
response_wrapper_cls = MultipartResponseWrapper
#: Multipart reader class, used to handle multipart/* body parts.
#: None points to type(self)
multipart_reader_cls = None
#: Body part reader class for non multipart/* content types.
part_reader_cls = BodyPartReader
def __init__(self, headers: Mapping[str, str], content: StreamReader) -> None:
self.headers = headers
self._boundary = ("--" + self._get_boundary()).encode()
self._content = content
self._last_part: Optional[Union["MultipartReader", BodyPartReader]] = None
self._at_eof = False
self._at_bof = True
self._unread: List[bytes] = []
def __aiter__(
self,
) -> AsyncIterator["BodyPartReader"]:
return self # type: ignore[return-value]
async def __anext__(
self,
) -> Optional[Union["MultipartReader", BodyPartReader]]:
part = await self.next()
if part is None:
raise StopAsyncIteration
return part
@classmethod
def from_response(
cls,
response: "ClientResponse",
) -> MultipartResponseWrapper:
"""Constructs reader instance from HTTP response.
:param response: :class:`~aiohttp.client.ClientResponse` instance
"""
obj = cls.response_wrapper_cls(
response, cls(response.headers, response.content)
)
return obj
def at_eof(self) -> bool:
"""Returns True if the final boundary was reached, false otherwise."""
return self._at_eof
async def next(
self,
) -> Optional[Union["MultipartReader", BodyPartReader]]:
"""Emits the next multipart body part."""
# So, if we're at BOF, we need to skip till the boundary.
if self._at_eof:
return None
await self._maybe_release_last_part()
if self._at_bof:
await self._read_until_first_boundary()
self._at_bof = False
else:
await self._read_boundary()
if self._at_eof: # we just read the last boundary, nothing to do there
return None
self._last_part = await self.fetch_next_part()
return self._last_part
async def release(self) -> None:
"""Reads all the body parts to the void till the final boundary."""
while not self._at_eof:
item = await self.next()
if item is None:
break
await item.release()
async def fetch_next_part(
self,
) -> Union["MultipartReader", BodyPartReader]:
"""Returns the next body part reader."""
headers = await self._read_headers()
return self._get_part_reader(headers)
def _get_part_reader(
self,
headers: "CIMultiDictProxy[str]",
) -> Union["MultipartReader", BodyPartReader]:
"""Dispatches the response by the `Content-Type` header.
Returns a suitable reader instance.
:param dict headers: Response headers
"""
ctype = headers.get(CONTENT_TYPE, "")
mimetype = parse_mimetype(ctype)
if mimetype.type == "multipart":
if self.multipart_reader_cls is None:
return type(self)(headers, self._content)
return self.multipart_reader_cls(headers, self._content)
else:
return self.part_reader_cls(self._boundary, headers, self._content)
def _get_boundary(self) -> str:
mimetype = parse_mimetype(self.headers[CONTENT_TYPE])
assert mimetype.type == "multipart", "multipart/* content type expected"
if "boundary" not in mimetype.parameters:
raise ValueError(
"boundary missed for Content-Type: %s" % self.headers[CONTENT_TYPE]
)
boundary = mimetype.parameters["boundary"]
if len(boundary) > 70:
raise ValueError("boundary %r is too long (70 chars max)" % boundary)
return boundary
async def _readline(self) -> bytes:
if self._unread:
return self._unread.pop()
return await self._content.readline()
async def _read_until_first_boundary(self) -> None:
while True:
chunk = await self._readline()
if chunk == b"":
raise ValueError(
"Could not find starting boundary %r" % (self._boundary)
)
chunk = chunk.rstrip()
if chunk == self._boundary:
return
elif chunk == self._boundary + b"--":
self._at_eof = True
return
async def _read_boundary(self) -> None:
chunk = (await self._readline()).rstrip()
if chunk == self._boundary:
pass
elif chunk == self._boundary + b"--":
self._at_eof = True
epilogue = await self._readline()
next_line = await self._readline()
# the epilogue is expected and then either the end of input or the
# parent multipart boundary, if the parent boundary is found then
# it should be marked as unread and handed to the parent for
# processing
if next_line[:2] == b"--":
self._unread.append(next_line)
# otherwise the request is likely missing an epilogue and both
# lines should be passed to the parent for processing
# (this handles the old behavior gracefully)
else:
self._unread.extend([next_line, epilogue])
else:
raise ValueError(f"Invalid boundary {chunk!r}, expected {self._boundary!r}")
async def _read_headers(self) -> "CIMultiDictProxy[str]":
lines = [b""]
while True:
chunk = await self._content.readline()
chunk = chunk.strip()
lines.append(chunk)
if not chunk:
break
parser = HeadersParser()
headers, raw_headers = parser.parse_headers(lines)
return headers
async def _maybe_release_last_part(self) -> None:
"""Ensures that the last read body part is read completely."""
if self._last_part is not None:
if not self._last_part.at_eof():
await self._last_part.release()
self._unread.extend(self._last_part._unread)
self._last_part = None
_Part = Tuple[Payload, str, str]
class MultipartWriter(Payload):
"""Multipart body writer."""
def __init__(self, subtype: str = "mixed", boundary: Optional[str] = None) -> None:
boundary = boundary if boundary is not None else uuid.uuid4().hex
# The underlying Payload API demands a str (utf-8), not bytes,
# so we need to ensure we don't lose anything during conversion.
# As a result, require the boundary to be ASCII only.
# In both situations.
try:
self._boundary = boundary.encode("ascii")
except UnicodeEncodeError:
raise ValueError("boundary should contain ASCII only chars") from None
ctype = f"multipart/{subtype}; boundary={self._boundary_value}"
super().__init__(None, content_type=ctype)
self._parts: List[_Part] = []
def __enter__(self) -> "MultipartWriter":
return self
def __exit__(
self,
exc_type: Optional[Type[BaseException]],
exc_val: Optional[BaseException],
exc_tb: Optional[TracebackType],
) -> None:
pass
def __iter__(self) -> Iterator[_Part]:
return iter(self._parts)
def __len__(self) -> int:
return len(self._parts)
def __bool__(self) -> bool:
return True
_valid_tchar_regex = re.compile(rb"\A[!#$%&'*+\-.^_`|~\w]+\Z")
_invalid_qdtext_char_regex = re.compile(rb"[\x00-\x08\x0A-\x1F\x7F]")
@property
def _boundary_value(self) -> str:
"""Wrap boundary parameter value in quotes, if necessary.
Reads self.boundary and returns a unicode sting.
"""
# Refer to RFCs 7231, 7230, 5234.
#
# parameter = token "=" ( token / quoted-string )
# token = 1*tchar
# quoted-string = DQUOTE *( qdtext / quoted-pair ) DQUOTE
# qdtext = HTAB / SP / %x21 / %x23-5B / %x5D-7E / obs-text
# obs-text = %x80-FF
# quoted-pair = "\" ( HTAB / SP / VCHAR / obs-text )
# tchar = "!" / "#" / "$" / "%" / "&" / "'" / "*"
# / "+" / "-" / "." / "^" / "_" / "`" / "|" / "~"
# / DIGIT / ALPHA
# ; any VCHAR, except delimiters
# VCHAR = %x21-7E
value = self._boundary
if re.match(self._valid_tchar_regex, value):
return value.decode("ascii") # cannot fail
if re.search(self._invalid_qdtext_char_regex, value):
raise ValueError("boundary value contains invalid characters")
# escape %x5C and %x22
quoted_value_content = value.replace(b"\\", b"\\\\")
quoted_value_content = quoted_value_content.replace(b'"', b'\\"')
return '"' + quoted_value_content.decode("ascii") + '"'
@property
def boundary(self) -> str:
return self._boundary.decode("ascii")
def append(self, obj: Any, headers: Optional[MultiMapping[str]] = None) -> Payload:
if headers is None:
headers = CIMultiDict()
if isinstance(obj, Payload):
obj.headers.update(headers)
return self.append_payload(obj)
else:
try:
payload = get_payload(obj, headers=headers)
except LookupError:
raise TypeError("Cannot create payload from %r" % obj)
else:
return self.append_payload(payload)
def append_payload(self, payload: Payload) -> Payload:
"""Adds a new body part to multipart writer."""
# compression
encoding: Optional[str] = payload.headers.get(
CONTENT_ENCODING,
"",
).lower()
if encoding and encoding not in ("deflate", "gzip", "identity"):
raise RuntimeError(f"unknown content encoding: {encoding}")
if encoding == "identity":
encoding = None
# te encoding
te_encoding: Optional[str] = payload.headers.get(
CONTENT_TRANSFER_ENCODING,
"",
).lower()
if te_encoding not in ("", "base64", "quoted-printable", "binary"):
raise RuntimeError(
"unknown content transfer encoding: {}" "".format(te_encoding)
)
if te_encoding == "binary":
te_encoding = None
# size
size = payload.size
if size is not None and not (encoding or te_encoding):
payload.headers[CONTENT_LENGTH] = str(size)
self._parts.append((payload, encoding, te_encoding)) # type: ignore[arg-type]
return payload
def append_json(
self, obj: Any, headers: Optional[MultiMapping[str]] = None
) -> Payload:
"""Helper to append JSON part."""
if headers is None:
headers = CIMultiDict()
return self.append_payload(JsonPayload(obj, headers=headers))
def append_form(
self,
obj: Union[Sequence[Tuple[str, str]], Mapping[str, str]],
headers: Optional[MultiMapping[str]] = None,
) -> Payload:
"""Helper to append form urlencoded part."""
assert isinstance(obj, (Sequence, Mapping))
if headers is None:
headers = CIMultiDict()
if isinstance(obj, Mapping):
obj = list(obj.items())
data = urlencode(obj, doseq=True)
return self.append_payload(
StringPayload(
data, headers=headers, content_type="application/x-www-form-urlencoded"
)
)
@property
def size(self) -> Optional[int]:
"""Size of the payload."""
total = 0
for part, encoding, te_encoding in self._parts:
if encoding or te_encoding or part.size is None:
return None
total += int(
2
+ len(self._boundary)
+ 2
+ part.size # b'--'+self._boundary+b'\r\n'
+ len(part._binary_headers)
+ 2 # b'\r\n'
)
total += 2 + len(self._boundary) + 4 # b'--'+self._boundary+b'--\r\n'
return total
async def write(self, writer: Any, close_boundary: bool = True) -> None:
"""Write body."""
for part, encoding, te_encoding in self._parts:
await writer.write(b"--" + self._boundary + b"\r\n")
await writer.write(part._binary_headers)
if encoding or te_encoding:
w = MultipartPayloadWriter(writer)
if encoding:
w.enable_compression(encoding)
if te_encoding:
w.enable_encoding(te_encoding)
await part.write(w) # type: ignore[arg-type]
await w.write_eof()
else:
await part.write(writer)
await writer.write(b"\r\n")
if close_boundary:
await writer.write(b"--" + self._boundary + b"--\r\n")
class MultipartPayloadWriter:
def __init__(self, writer: Any) -> None:
self._writer = writer
self._encoding: Optional[str] = None
self._compress: Any = None
self._encoding_buffer: Optional[bytearray] = None
def enable_encoding(self, encoding: str) -> None:
if encoding == "base64":
self._encoding = encoding
self._encoding_buffer = bytearray()
elif encoding == "quoted-printable":
self._encoding = "quoted-printable"
def enable_compression(
self, encoding: str = "deflate", strategy: int = zlib.Z_DEFAULT_STRATEGY
) -> None:
zlib_mode = 16 + zlib.MAX_WBITS if encoding == "gzip" else -zlib.MAX_WBITS
self._compress = zlib.compressobj(wbits=zlib_mode, strategy=strategy)
async def write_eof(self) -> None:
if self._compress is not None:
chunk = self._compress.flush()
if chunk:
self._compress = None
await self.write(chunk)
if self._encoding == "base64":
if self._encoding_buffer:
await self._writer.write(base64.b64encode(self._encoding_buffer))
async def write(self, chunk: bytes) -> None:
if self._compress is not None:
if chunk:
chunk = self._compress.compress(chunk)
if not chunk:
return
if self._encoding == "base64":
buf = self._encoding_buffer
assert buf is not None
buf.extend(chunk)
if buf:
div, mod = divmod(len(buf), 3)
enc_chunk, self._encoding_buffer = (buf[: div * 3], buf[div * 3 :])
if enc_chunk:
b64chunk = base64.b64encode(enc_chunk)
await self._writer.write(b64chunk)
elif self._encoding == "quoted-printable":
await self._writer.write(binascii.b2a_qp(chunk))
else:
await self._writer.write(chunk)
|