def get_part_charset(self, headers):
# Figure out input charset for current part
content_type = headers.get('content-type')
if content_type:
mimetype, ct_params = parse_options_header(content_type)
return ct_params.get('charset', self.charset)
return self.charset
def parse_from_environ(self, environ):
"""Parses the information from the environment as form data.
:param environ: the WSGI environment to be used for parsing.
:return: A tuple in the form ``(stream, form, files)``.
"""
content_type = environ.get('CONTENT_TYPE', '')
mimetype, options = parse_options_header(content_type)
try:
content_length = int(environ['CONTENT_LENGTH'])
except (KeyError, ValueError):
content_length = 0
stream = environ['wsgi.input']
return self.parse(stream, mimetype, content_length, options)
def parse(self, file, boundary, content_length):
next_part = '--' + boundary
last_part = next_part + '--'
form = []
files = []
in_memory = 0
iterator = chain(make_line_iter(file, limit=content_length,
buffer_size=self.buffer_size),
_empty_string_iter)
terminator = self._find_terminator(iterator)
if terminator != next_part:
self.fail('Expected boundary at start of multipart data')
while terminator != last_part:
headers = parse_multipart_headers(iterator)
disposition = headers.get('content-disposition')
if disposition is None:
self.fail('Missing Content-Disposition header')
disposition, extra = parse_options_header(disposition)
transfer_encoding = self.get_part_encoding(headers)
name = extra.get('name')
filename = extra.get('filename')
part_charset = self.get_part_charset(headers)
# if no content type is given we stream into memory. A list is
# used as a temporary container.
if filename is None:
is_file = False
container = []
_write = container.append
guard_memory = self.max_form_memory_size is not None
# otherwise we parse the rest of the headers and ask the stream
# factory for something we can write in.
else:
is_file = True
guard_memory = False
filename, container = self.start_file_streaming(
filename, headers, content_length)
_write = container.write
buf = ''
for line in iterator:
if not line:
self.fail('unexpected end of stream')
if line[:2] == '--':
terminator = line.rstrip()
if terminator in (next_part, last_part):
break
if transfer_encoding is not None:
try:
line = line.decode(transfer_encoding)
except Exception:
self.fail('could not decode transfer encoded chunk')
# we have something in the buffer from the last iteration.
# this is usually a newline delimiter.
if buf:
_write(buf)
buf = ''
# If the line ends with windows CRLF we write everything except
# the last two bytes. In all other cases however we write
# everything except the last byte. If it was a newline, that's
# fine, otherwise it does not matter because we will write it
# the next iteration. this ensures we do not write the
# final newline into the stream. That way we do not have to
# truncate the stream. However we do have to make sure that
# if something else than a newline is in there we write it
# out.
if line[-2:] == '\r\n':
buf = '\r\n'
cutoff = -2
else:
buf = line[-1]
cutoff = -1
_write(line[:cutoff])
# if we write into memory and there is a memory size limit we
# count the number of bytes in memory and raise an exception if
# there is too much data in memory.
if guard_memory:
in_memory += len(line)
if in_memory > self.max_form_memory_size:
self.in_memory_threshold_reached(in_memory)
else: # pragma: no cover
raise ValueError('unexpected end of part')
# if we have a leftover in the buffer that is not a newline
# character we have to flush it, otherwise we will chop of
# certain values.
if buf not in ('', '\r', '\n', '\r\n'):
_write(buf)
if is_file:
container.seek(0)
files.append((name, FileStorage(container, filename, name,
headers=headers)))
else:
form.append((name, _decode_unicode(''.join(container),
part_charset, self.errors)))
return self.cls(form), self.cls(files)
