diff options
Diffstat (limited to 'urllib3/response.py')
| -rw-r--r-- | urllib3/response.py | 203 |
1 files changed, 168 insertions, 35 deletions
diff --git a/urllib3/response.py b/urllib3/response.py index e69de95..24140c4 100644 --- a/urllib3/response.py +++ b/urllib3/response.py @@ -1,15 +1,20 @@ +try: + import http.client as httplib +except ImportError: + import httplib import zlib import io from socket import timeout as SocketTimeout from ._collections import HTTPHeaderDict -from .exceptions import ProtocolError, DecodeError, ReadTimeoutError -from .packages.six import string_types as basestring, binary_type +from .exceptions import ( + ProtocolError, DecodeError, ReadTimeoutError, ResponseNotChunked +) +from .packages.six import string_types as basestring, binary_type, PY3 from .connection import HTTPException, BaseSSLError from .util.response import is_fp_closed - class DeflateDecoder(object): def __init__(self): @@ -21,6 +26,9 @@ class DeflateDecoder(object): return getattr(self._obj, name) def decompress(self, data): + if not data: + return data + if not self._first_try: return self._obj.decompress(data) @@ -36,9 +44,23 @@ class DeflateDecoder(object): self._data = None +class GzipDecoder(object): + + def __init__(self): + self._obj = zlib.decompressobj(16 + zlib.MAX_WBITS) + + def __getattr__(self, name): + return getattr(self._obj, name) + + def decompress(self, data): + if not data: + return data + return self._obj.decompress(data) + + def _get_decoder(mode): if mode == 'gzip': - return zlib.decompressobj(16 + zlib.MAX_WBITS) + return GzipDecoder() return DeflateDecoder() @@ -76,9 +98,10 @@ class HTTPResponse(io.IOBase): strict=0, preload_content=True, decode_content=True, original_response=None, pool=None, connection=None): - self.headers = HTTPHeaderDict() - if headers: - self.headers.update(headers) + if isinstance(headers, HTTPHeaderDict): + self.headers = headers + else: + self.headers = HTTPHeaderDict(headers) self.status = status self.version = version self.reason = reason @@ -100,7 +123,17 @@ class HTTPResponse(io.IOBase): if hasattr(body, 'read'): self._fp = body - if preload_content and not self._body: + # Are we using the chunked-style of transfer encoding? + self.chunked = False + self.chunk_left = None + tr_enc = self.headers.get('transfer-encoding', '').lower() + # Don't incur the penalty of creating a list and then discarding it + encodings = (enc.strip() for enc in tr_enc.split(",")) + if "chunked" in encodings: + self.chunked = True + + # We certainly don't want to preload content when the response is chunked. + if not self.chunked and preload_content and not self._body: self._body = self.read(decode_content=decode_content) def get_redirect_location(self): @@ -140,6 +173,35 @@ class HTTPResponse(io.IOBase): """ return self._fp_bytes_read + def _init_decoder(self): + """ + Set-up the _decoder attribute if necessar. + """ + # Note: content-encoding value should be case-insensitive, per RFC 7230 + # Section 3.2 + content_encoding = self.headers.get('content-encoding', '').lower() + if self._decoder is None and content_encoding in self.CONTENT_DECODERS: + self._decoder = _get_decoder(content_encoding) + + def _decode(self, data, decode_content, flush_decoder): + """ + Decode the data passed in and potentially flush the decoder. + """ + try: + if decode_content and self._decoder: + data = self._decoder.decompress(data) + except (IOError, zlib.error) as e: + content_encoding = self.headers.get('content-encoding', '').lower() + raise DecodeError( + "Received response with content-encoding: %s, but " + "failed to decode it." % content_encoding, e) + + if flush_decoder and decode_content and self._decoder: + buf = self._decoder.decompress(binary_type()) + data += buf + self._decoder.flush() + + return data + def read(self, amt=None, decode_content=None, cache_content=False): """ Similar to :meth:`httplib.HTTPResponse.read`, but with two additional @@ -161,12 +223,7 @@ class HTTPResponse(io.IOBase): after having ``.read()`` the file object. (Overridden if ``amt`` is set.) """ - # Note: content-encoding value should be case-insensitive, per RFC 7230 - # Section 3.2 - content_encoding = self.headers.get('content-encoding', '').lower() - if self._decoder is None: - if content_encoding in self.CONTENT_DECODERS: - self._decoder = _get_decoder(content_encoding) + self._init_decoder() if decode_content is None: decode_content = self.decode_content @@ -202,7 +259,7 @@ class HTTPResponse(io.IOBase): except BaseSSLError as e: # FIXME: Is there a better way to differentiate between SSLErrors? - if not 'read operation timed out' in str(e): # Defensive: + if 'read operation timed out' not in str(e): # Defensive: # This shouldn't happen but just in case we're missing an edge # case, let's avoid swallowing SSL errors. raise @@ -215,17 +272,7 @@ class HTTPResponse(io.IOBase): self._fp_bytes_read += len(data) - try: - if decode_content and self._decoder: - data = self._decoder.decompress(data) - except (IOError, zlib.error) as e: - raise DecodeError( - "Received response with content-encoding: %s, but " - "failed to decode it." % content_encoding, e) - - if flush_decoder and decode_content and self._decoder: - buf = self._decoder.decompress(binary_type()) - data += buf + self._decoder.flush() + data = self._decode(data, decode_content, flush_decoder) if cache_content: self._body = data @@ -252,11 +299,15 @@ class HTTPResponse(io.IOBase): If True, will attempt to decode the body based on the 'content-encoding' header. """ - while not is_fp_closed(self._fp): - data = self.read(amt=amt, decode_content=decode_content) + if self.chunked: + for line in self.read_chunked(amt, decode_content=decode_content): + yield line + else: + while not is_fp_closed(self._fp): + data = self.read(amt=amt, decode_content=decode_content) - if data: - yield data + if data: + yield data @classmethod def from_httplib(ResponseCls, r, **response_kw): @@ -267,14 +318,16 @@ class HTTPResponse(io.IOBase): Remaining parameters are passed to the HTTPResponse constructor, along with ``original_response=r``. """ - - headers = HTTPHeaderDict() - for k, v in r.getheaders(): - headers.add(k, v) + headers = r.msg + if not isinstance(headers, HTTPHeaderDict): + if PY3: # Python 3 + headers = HTTPHeaderDict(headers.items()) + else: # Python 2 + headers = HTTPHeaderDict.from_httplib(headers) # HTTPResponse objects in Python 3 don't have a .strict attribute strict = getattr(r, 'strict', 0) - return ResponseCls(body=r, + resp = ResponseCls(body=r, headers=headers, status=r.status, version=r.version, @@ -282,6 +335,7 @@ class HTTPResponse(io.IOBase): strict=strict, original_response=r, **response_kw) + return resp # Backwards-compatibility methods for httplib.HTTPResponse def getheaders(self): @@ -331,3 +385,82 @@ class HTTPResponse(io.IOBase): else: b[:len(temp)] = temp return len(temp) + + def _update_chunk_length(self): + # First, we'll figure out length of a chunk and then + # we'll try to read it from socket. + if self.chunk_left is not None: + return + line = self._fp.fp.readline() + line = line.split(b';', 1)[0] + try: + self.chunk_left = int(line, 16) + except ValueError: + # Invalid chunked protocol response, abort. + self.close() + raise httplib.IncompleteRead(line) + + def _handle_chunk(self, amt): + returned_chunk = None + if amt is None: + chunk = self._fp._safe_read(self.chunk_left) + returned_chunk = chunk + self._fp._safe_read(2) # Toss the CRLF at the end of the chunk. + self.chunk_left = None + elif amt < self.chunk_left: + value = self._fp._safe_read(amt) + self.chunk_left = self.chunk_left - amt + returned_chunk = value + elif amt == self.chunk_left: + value = self._fp._safe_read(amt) + self._fp._safe_read(2) # Toss the CRLF at the end of the chunk. + self.chunk_left = None + returned_chunk = value + else: # amt > self.chunk_left + returned_chunk = self._fp._safe_read(self.chunk_left) + self._fp._safe_read(2) # Toss the CRLF at the end of the chunk. + self.chunk_left = None + return returned_chunk + + def read_chunked(self, amt=None, decode_content=None): + """ + Similar to :meth:`HTTPResponse.read`, but with an additional + parameter: ``decode_content``. + + :param decode_content: + If True, will attempt to decode the body based on the + 'content-encoding' header. + """ + self._init_decoder() + # FIXME: Rewrite this method and make it a class with a better structured logic. + if not self.chunked: + raise ResponseNotChunked("Response is not chunked. " + "Header 'transfer-encoding: chunked' is missing.") + + if self._original_response and self._original_response._method.upper() == 'HEAD': + # Don't bother reading the body of a HEAD request. + # FIXME: Can we do this somehow without accessing private httplib _method? + self._original_response.close() + return + + while True: + self._update_chunk_length() + if self.chunk_left == 0: + break + chunk = self._handle_chunk(amt) + yield self._decode(chunk, decode_content=decode_content, + flush_decoder=True) + + # Chunk content ends with \r\n: discard it. + while True: + line = self._fp.fp.readline() + if not line: + # Some sites may not end with '\r\n'. + break + if line == b'\r\n': + break + + # We read everything; close the "file". + if self._original_response: + self._original_response.close() + self.release_conn() |