def parse(self):
"""
Parse the POST data and break it into a FILES MultiValueDict and a POST
MultiValueDict.
Returns a tuple containing the POST and FILES dictionary, respectively.
"""
# We have to import QueryDict down here to avoid a circular import.
from london.http import QueryDict
encoding = self._encoding
handlers = self._upload_handlers
# HTTP spec says that Content-Length >= 0 is valid
# handling content-length == 0 before continuing
if self._content_length == 0:
return QueryDict(MultiValueDict(), encoding=self._encoding), MultiValueDict()
# See if the handler will want to take care of the parsing.
# This allows overriding everything if somebody wants it.
for handler in handlers:
result = handler.handle_raw_input(self._input_data,
self._meta,
self._content_length,
self._boundary,
encoding)
if result is not None:
return result[0], result[1]
# Create the data structures to be used later.
self._post = QueryDict('', mutable=True)
self._files = MultiValueDict()
# Instantiate the parser and stream:
stream = LazyStream(ChunkIter(self._input_data, self._chunk_size))
# Whether or not to signal a file-completion at the beginning of the loop.
old_field_name = None
counters = [0] * len(handlers)
try:
for item_type, meta_data, field_stream in Parser(stream, self._boundary):
if old_field_name:
# We run this at the beginning of the next loop
# since we cannot be sure a file is complete until
# we hit the next boundary/part of the multipart content.
self.handle_file_complete(old_field_name, counters)
old_field_name = None
try:
disposition = meta_data['content-disposition'][1]
field_name = disposition['name'].strip()
except (KeyError, IndexError, AttributeError):
continue
transfer_encoding = meta_data.get('content-transfer-encoding')
if transfer_encoding is not None:
transfer_encoding = transfer_encoding[0].strip()
field_name = force_unicode(field_name, encoding, errors='replace')
if item_type == FIELD:
# This is a post field, we can just set it in the post
if transfer_encoding == 'base64':
raw_data = field_stream.read()
try:
data = str(raw_data).decode('base64')
except:
data = raw_data
else:
data = field_stream.read()
self._post.appendlist(field_name,
force_unicode(data, encoding, errors='replace'))
elif item_type == FILE:
# This is a file, use the handler...
file_name = disposition.get('filename')
if not file_name:
continue
file_name = force_unicode(file_name, encoding, errors='replace')
file_name = self.IE_sanitize(unescape_entities(file_name))
content_type = meta_data.get('content-type', ('',))[0].strip()
try:
charset = meta_data.get('content-type', (0,{}))[1].get('charset', None)
except:
charset = None
try:
content_length = int(meta_data.get('content-length')[0])
except (IndexError, TypeError, ValueError):
content_length = None
counters = [0] * len(handlers)
try:
for handler in handlers:
try:
handler.new_file(field_name, file_name,
content_type, content_length,
charset)
except StopFutureHandlers:
break
for chunk in field_stream:
if transfer_encoding == 'base64':
# We only special-case base64 transfer encoding
try:
chunk = str(chunk).decode('base64')
except BaseException as e:
# Since this is only a chunk, any error is an unfixable error.
raise MultiPartParserError("Could not decode base64 data: %r" % e)
for i, handler in enumerate(handlers):
chunk_length = len(chunk)
chunk = handler.receive_data_chunk(chunk, counters[i])
counters[i] += chunk_length
if chunk is None:
# If the chunk received by the handler is None, then don't continue.
break
except SkipFile as e:
# Just use up the rest of this file...
exhaust(field_stream)
else:
# Handle file upload completions on next iteration.
old_field_name = field_name
else:
# If this is neither a FIELD or a FILE, just exhaust the stream.
exhaust(stream)
except StopUpload as e:
if not e.connection_reset:
exhaust(self._input_data)
else:
# Make sure that the request data is all fed
exhaust(self._input_data)
# Signal that the upload has completed.
for handler in handlers:
retval = handler.upload_complete()
if retval:
break
return self._post, self._files
class MultiPartParser(object):
"""
A rfc2388 multipart/form-data parser.
``MultiValueDict.parse()`` reads the input stream in ``chunk_size`` chunks
and returns a tuple of ``(MultiValueDict(POST), MultiValueDict(FILES))``.
"""
def __init__(self, META, input_data, upload_handlers, encoding=None):
"""
Initialize the MultiPartParser object.
:META:
The standard ``META`` dictionary in Django request objects.
:input_data:
The raw post data, as a file-like object.
:upload_handler:
An UploadHandler instance that performs operations on the uploaded
data.
:encoding:
The encoding with which to treat the incoming data.
"""
#
# Content-Type should containt multipart and the boundary information.
#
content_type = META.get('HTTP_CONTENT_TYPE', META.get('CONTENT_TYPE', ''))
if not content_type.startswith('multipart/'):
raise MultiPartParserError('Invalid Content-Type: %s' % content_type)
# Parse the header to get the boundary to split the parts.
ctypes, opts = parse_header(content_type)
boundary = opts.get('boundary')
if not boundary or not cgi.valid_boundary(boundary):
raise MultiPartParserError('Invalid boundary in multipart: %s' % boundary)
# Content-Length should contain the length of the body we are about
# to receive.
try:
content_length = int(META.get('HTTP_CONTENT_LENGTH', META.get('CONTENT_LENGTH',0)))
except (ValueError, TypeError):
content_length = 0
if content_length < 0:
# This means we shouldn't continue...raise an error.
raise MultiPartParserError("Invalid content length: %r" % content_length)
self._boundary = boundary
self._input_data = input_data
# For compatibility with low-level network APIs (with 32-bit integers),
# the chunk size should be < 2^31, but still divisible by 4.
possible_sizes = [x.chunk_size for x in upload_handlers if x.chunk_size]
self._chunk_size = min([2**31-4] + possible_sizes)
self._meta = META
self._encoding = encoding or settings.DEFAULT_CHARSET
self._content_length = content_length
self._upload_handlers = upload_handlers
def parse(self):
"""
Parse the POST data and break it into a FILES MultiValueDict and a POST
MultiValueDict.
Returns a tuple containing the POST and FILES dictionary, respectively.
"""
# We have to import QueryDict down here to avoid a circular import.
from london.http import QueryDict
encoding = self._encoding
handlers = self._upload_handlers
# HTTP spec says that Content-Length >= 0 is valid
# handling content-length == 0 before continuing
if self._content_length == 0:
return QueryDict(MultiValueDict(), encoding=self._encoding), MultiValueDict()
# See if the handler will want to take care of the parsing.
# This allows overriding everything if somebody wants it.
for handler in handlers:
result = handler.handle_raw_input(self._input_data,
self._meta,
self._content_length,
self._boundary,
encoding)
if result is not None:
return result[0], result[1]
# Create the data structures to be used later.
self._post = QueryDict('', mutable=True)
self._files = MultiValueDict()
# Instantiate the parser and stream:
stream = LazyStream(ChunkIter(self._input_data, self._chunk_size))
# Whether or not to signal a file-completion at the beginning of the loop.
old_field_name = None
counters = [0] * len(handlers)
try:
for item_type, meta_data, field_stream in Parser(stream, self._boundary):
if old_field_name:
# We run this at the beginning of the next loop
# since we cannot be sure a file is complete until
# we hit the next boundary/part of the multipart content.
self.handle_file_complete(old_field_name, counters)
old_field_name = None
try:
disposition = meta_data['content-disposition'][1]
field_name = disposition['name'].strip()
except (KeyError, IndexError, AttributeError):
continue
transfer_encoding = meta_data.get('content-transfer-encoding')
if transfer_encoding is not None:
transfer_encoding = transfer_encoding[0].strip()
field_name = force_unicode(field_name, encoding, errors='replace')
if item_type == FIELD:
# This is a post field, we can just set it in the post
if transfer_encoding == 'base64':
raw_data = field_stream.read()
try:
data = str(raw_data).decode('base64')
except:
data = raw_data
else:
data = field_stream.read()
self._post.appendlist(field_name,
force_unicode(data, encoding, errors='replace'))
elif item_type == FILE:
# This is a file, use the handler...
file_name = disposition.get('filename')
if not file_name:
continue
file_name = force_unicode(file_name, encoding, errors='replace')
file_name = self.IE_sanitize(unescape_entities(file_name))
content_type = meta_data.get('content-type', ('',))[0].strip()
try:
charset = meta_data.get('content-type', (0,{}))[1].get('charset', None)
except:
charset = None
try:
content_length = int(meta_data.get('content-length')[0])
except (IndexError, TypeError, ValueError):
content_length = None
counters = [0] * len(handlers)
try:
for handler in handlers:
try:
handler.new_file(field_name, file_name,
content_type, content_length,
charset)
except StopFutureHandlers:
break
for chunk in field_stream:
if transfer_encoding == 'base64':
# We only special-case base64 transfer encoding
try:
chunk = str(chunk).decode('base64')
except BaseException as e:
# Since this is only a chunk, any error is an unfixable error.
raise MultiPartParserError("Could not decode base64 data: %r" % e)
for i, handler in enumerate(handlers):
chunk_length = len(chunk)
chunk = handler.receive_data_chunk(chunk, counters[i])
counters[i] += chunk_length
if chunk is None:
# If the chunk received by the handler is None, then don't continue.
break
except SkipFile as e:
# Just use up the rest of this file...
exhaust(field_stream)
else:
# Handle file upload completions on next iteration.
old_field_name = field_name
else:
# If this is neither a FIELD or a FILE, just exhaust the stream.
exhaust(stream)
except StopUpload as e:
if not e.connection_reset:
exhaust(self._input_data)
else:
# Make sure that the request data is all fed
exhaust(self._input_data)
# Signal that the upload has completed.
for handler in handlers:
retval = handler.upload_complete()
if retval:
break
return self._post, self._files
def handle_file_complete(self, old_field_name, counters):
"""
Handle all the signalling that takes place when a file is complete.
"""
for i, handler in enumerate(self._upload_handlers):
file_obj = handler.file_complete(counters[i])
if file_obj:
# If it returns a file object, then set the files dict.
self._files.appendlist(force_unicode(old_field_name,
self._encoding,
errors='replace'),
file_obj)
break
def IE_sanitize(self, filename):
"""Cleanup filename from Internet Explorer full paths."""
return filename and filename[filename.rfind("\\")+1:].strip()