def handle_response(url, code, msg, data):
"""Interpret the code & headers and wrap the provided data in a RangeFile.
This is a factory method which returns an appropriate RangeFile based on
the code & headers it's given.
:param url: The url being processed. Mostly for error reporting
:param code: The integer HTTP response code
:param msg: An HTTPMessage containing the headers for the response
:param data: A file-like object that can be read() to get the
requested data
:return: A file-like object that can seek()+read() the
ranges indicated by the headers.
"""
rfile = RangeFile(url, data)
if code == 200:
# A whole file
size = msg.getheader('content-length', None)
if size is None:
size = -1
else:
size = int(size)
rfile.set_range(0, size)
elif code == 206:
content_type = msg.getheader('content-type', None)
if content_type is None:
# When there is no content-type header we treat the response as
# being of type 'application/octet-stream' as per RFC2616 section
# 7.2.1.
# Therefore it is obviously not multipart
content_type = 'application/octet-stream'
is_multipart = False
else:
is_multipart = (msg.getmaintype() == 'multipart'
and msg.getsubtype() == 'byteranges')
if is_multipart:
# Full fledged multipart response
rfile.set_boundary(msg.getparam('boundary'))
else:
# A response to a range request, but not multipart
content_range = msg.getheader('content-range', None)
if content_range is None:
raise errors.InvalidHttpResponse(
url,
'Missing the Content-Range header in a 206 range response')
rfile.set_range_from_header(content_range)
else:
raise errors.InvalidHttpResponse(url,
'Unknown response code %s' % code)
return rfile
def _raise_curl_http_error(self, curl, info=None, body=None):
"""Common curl->bzrlib error translation.
Some methods may choose to override this for particular cases.
The URL and code are automatically included as appropriate.
:param info: Extra information to include in the message.
:param body: File-like object from which the body of the page can be
read.
"""
code = curl.getinfo(pycurl.HTTP_CODE)
url = curl.getinfo(pycurl.EFFECTIVE_URL)
if body is not None:
response_body = body.read()
plaintext_body = unhtml_roughly(response_body)
else:
response_body = None
plaintext_body = ''
if code == 403:
raise errors.TransportError(
'Server refuses to fulfill the request (403 Forbidden)'
' for %s: %s' % (url, plaintext_body))
else:
if info is None:
msg = ''
else:
msg = ': ' + info
raise errors.InvalidHttpResponse(
url, 'Unable to handle http code %d%s: %s'
% (code, msg, plaintext_body))
def send_http_smart_request(self, bytes):
try:
# Get back the http_transport hold by the weak reference
t = self._http_transport_ref()
code, body_filelike = t._post(bytes)
if code != 200:
raise errors.InvalidHttpResponse(
t._remote_path('.bzr/smart'),
'Expected 200 response code, got %r' % (code, ))
except (errors.InvalidHttpResponse, errors.ConnectionReset), e:
raise errors.SmartProtocolError(str(e))
def read_range_definition(self):
"""Read a new range definition in a multi parts message.
Parse the headers including the empty line following them so that we
are ready to read the data itself.
"""
self._headers = httplib.HTTPMessage(self._file, seekable=0)
# Extract the range definition
content_range = self._headers.getheader('content-range', None)
if content_range is None:
raise errors.InvalidHttpResponse(
self._path,
'Content-Range header missing in a multi-part response')
self.set_range_from_header(content_range)
def _raise_curl_http_error(self, curl, info=None):
code = curl.getinfo(pycurl.HTTP_CODE)
url = curl.getinfo(pycurl.EFFECTIVE_URL)
# Some error codes can be handled the same way for all
# requests
if code == 403:
raise errors.TransportError(
'Server refuses to fulfill the request (403 Forbidden)'
' for %s' % url)
else:
if info is None:
msg = ''
else:
msg = ': ' + info
raise errors.InvalidHttpResponse(
url, 'Unable to handle http code %d%s' % (code, msg))
def read_boundary(self):
"""Read the boundary headers defining a new range"""
boundary_line = '\r\n'
while boundary_line == '\r\n':
# RFC2616 19.2 Additional CRLFs may precede the first boundary
# string entity.
# To be on the safe side we allow it before any boundary line
boundary_line = self._file.readline()
if boundary_line != '--' + self._boundary + '\r\n':
# rfc822.unquote() incorrectly unquotes strings enclosed in <>
# IIS 6 and 7 incorrectly wrap boundary strings in <>
# together they make a beautiful bug, which we will be gracious
# about here
if (self._unquote_boundary(boundary_line) !=
'--' + self._boundary + '\r\n'):
raise errors.InvalidHttpResponse(
self._path, "Expected a boundary (%s) line, got '%s'" %
(self._boundary, boundary_line))