def uri_to_iri(uri, charset='utf-8', errors='replace'):
r"""Converts a URI in a given charset to a IRI.
Examples for URI versus IRI
>>> uri_to_iri('http://xn--n3h.net/')
u'http://\u2603.net/'
>>> uri_to_iri('http://%C3%BCser:p%C3%[email protected]/p%C3%A5th')
u'http://\xfcser:p\xe4ssword@\u2603.net/p\xe5th'
Query strings are left unchanged:
>>> uri_to_iri('/?foo=24&x=%26%2f')
u'/?foo=24&x=%26%2f'
.. versionadded:: 0.6
:param uri: the URI to convert
:param charset: the charset of the URI
:param errors: the error handling on decode
"""
uri = url_fix(str(uri), charset)
scheme, auth, hostname, port, path, query, fragment = _uri_split(uri)
scheme = _decode_unicode(scheme, 'ascii', errors)
try:
hostname = hostname.decode('idna')
except UnicodeError:
# dammit, that codec raised an error. Because it does not support
# any error handling we have to fake it.... badly
if errors not in ('ignore', 'replace'):
raise
hostname = hostname.decode('ascii', errors)
if auth:
if ':' in auth:
auth, password = auth.split(':', 1)
else:
password = None
auth = _decode_unicode(_unquote(auth), charset, errors)
if password:
auth += u':' + _decode_unicode(_unquote(password),
charset, errors)
hostname = auth + u'@' + hostname
if port:
# port should be numeric, but you never know...
hostname += u':' + port.decode(charset, errors)
path = _decode_unicode(_unquote(path, '/;?'), charset, errors)
query = _decode_unicode(_unquote(query, ';/?:@&=+,$'),
charset, errors)
return urlparse.urlunsplit([scheme, hostname, path, query, fragment])
def uri_to_iri(uri, charset='utf-8', errors='replace'):
r"""Converts a URI in a given charset to a IRI.
Examples for URI versus IRI
>>> uri_to_iri('http://xn--n3h.net/')
u'http://\u2603.net/'
>>> uri_to_iri('http://%C3%BCser:p%C3%[email protected]/p%C3%A5th')
u'http://\xfcser:p\xe4ssword@\u2603.net/p\xe5th'
Query strings are left unchanged:
>>> uri_to_iri('/?foo=24&x=%26%2f')
u'/?foo=24&x=%26%2f'
.. versionadded:: 0.6
:param uri: the URI to convert
:param charset: the charset of the URI
:param errors: the error handling on decode
"""
uri = url_fix(str(uri), charset)
scheme, auth, hostname, port, path, query, fragment = _uri_split(uri)
scheme = _decode_unicode(scheme, 'ascii', errors)
try:
hostname = hostname.decode('idna')
except UnicodeError:
# dammit, that codec raised an error. Because it does not support
# any error handling we have to fake it.... badly
if errors not in ('ignore', 'replace'):
raise
hostname = hostname.decode('ascii', errors)
if auth:
if ':' in auth:
auth, password = auth.split(':', 1)
else:
password = None
auth = _decode_unicode(_unquote(auth), charset, errors)
if password:
auth += u':' + _decode_unicode(_unquote(password), charset, errors)
hostname = auth + u'@' + hostname
if port:
# port should be numeric, but you never know...
hostname += u':' + port.decode(charset, errors)
path = _decode_unicode(_unquote(path, '/;?'), charset, errors)
query = _decode_unicode(_unquote(query, ';/?:@&=+,$'), charset, errors)
return urlparse.urlunsplit([scheme, hostname, path, query, fragment])
def from_file(cls,
file,
charset='utf-8',
errors='strict',
unicode_mode=True):
"""Load a template from a file.
.. versionchanged:: 0.5
The encoding parameter was renamed to charset.
:param file: a filename or file object to load the template from.
:param charset: the charset of the template to load.
:param errors: the error behavior of the charset decoding.
:param unicode_mode: set to `False` to disable unicode mode.
:return: a template
"""
close = False
f = file
if isinstance(file, basestring):
f = open(file, 'r')
close = True
try:
data = _decode_unicode(f.read(), charset, errors)
finally:
if close:
f.close()
return cls(data, getattr(f, 'name', '<template>'), charset, errors,
unicode_mode)
def from_file(cls, file, charset='utf-8', errors='strict',
unicode_mode=True):
"""Load a template from a file.
.. versionchanged:: 0.5
The encoding parameter was renamed to charset.
:param file: a filename or file object to load the template from.
:param charset: the charset of the template to load.
:param errors: the error behavior of the charset decoding.
:param unicode_mode: set to `False` to disable unicode mode.
:return: a template
"""
close = False
f = file
if isinstance(file, basestring):
f = open(file, 'r')
close = True
try:
data = _decode_unicode(f.read(), charset, errors)
finally:
if close:
f.close()
return cls(data, getattr(f, 'name', '<template>'), charset,
errors, unicode_mode)
def start_file_streaming(self, filename, headers, total_content_length):
filename = _decode_unicode(filename, self.charset, self.errors)
filename = self._fix_ie_filename(filename)
content_type = headers.get('content_type')
try:
content_length = int(headers['content-length'])
except (KeyError, ValueError):
content_length = 0
container = self.stream_factory(total_content_length, content_type,
filename, content_length)
return filename, container
def __init__(self, source, filename='<template>', charset='utf-8',
errors='strict', unicode_mode=True):
if isinstance(source, str):
source = _decode_unicode(source, charset, errors)
if isinstance(filename, unicode):
filename = filename.encode('utf-8')
node = Parser(tokenize(u'\n'.join(source.splitlines()),
filename), filename).parse()
self.code = TemplateCodeGenerator(node, filename).getCode()
self.filename = filename
self.charset = charset
self.errors = errors
self.unicode_mode = unicode_mode
def url_unquote(s, charset='utf-8', errors='replace'):
"""URL decode a single string with a given decoding.
Per default encoding errors are ignored. If you want a different behavior
you can set `errors` to ``'replace'`` or ``'strict'``. In strict mode a
`HTTPUnicodeError` is raised.
:param s: the string to unquote.
:param charset: the charset to be used.
:param errors: the error handling for the charset decoding.
"""
if isinstance(s, unicode):
s = s.encode(charset)
return _decode_unicode(_unquote(s), charset, errors)
def url_unquote(s, charset='utf-8', errors='replace'):
"""URL decode a single string with a given decoding.
Per default encoding errors are ignored. If you want a different behavior
you can set `errors` to ``'replace'`` or ``'strict'``. In strict mode a
`HTTPUnicodeError` is raised.
:param s: the string to unquote.
:param charset: the charset to be used.
:param errors: the error handling for the charset decoding.
"""
if isinstance(s, unicode):
s = s.encode(charset)
return _decode_unicode(_unquote(s), charset, errors)
def _url_decode_impl(pair_iter, charset, decode_keys, include_empty, errors):
for pair in pair_iter:
if not pair:
continue
if '=' in pair:
key, value = pair.split('=', 1)
else:
if not include_empty:
continue
key = pair
value = ''
key = _unquote_plus(key)
if decode_keys:
key = _decode_unicode(key, charset, errors)
yield key, url_unquote_plus(value, charset, errors)
def _url_decode_impl(pair_iter, charset, decode_keys, include_empty,
errors):
for pair in pair_iter:
if not pair:
continue
if '=' in pair:
key, value = pair.split('=', 1)
else:
if not include_empty:
continue
key = pair
value = ''
key = _unquote_plus(key)
if decode_keys:
key = _decode_unicode(key, charset, errors)
yield key, url_unquote_plus(value, charset, errors)
def __init__(self,
source,
filename='<template>',
charset='utf-8',
errors='strict',
unicode_mode=True):
if isinstance(source, str):
source = _decode_unicode(source, charset, errors)
if isinstance(filename, unicode):
filename = filename.encode('utf-8')
node = Parser(tokenize(u'\n'.join(source.splitlines()), filename),
filename).parse()
self.code = TemplateCodeGenerator(node, filename).getCode()
self.filename = filename
self.charset = charset
self.errors = errors
self.unicode_mode = unicode_mode
def parse_cookie(header, charset='utf-8', errors='replace',
cls=None):
"""Parse a cookie. Either from a string or WSGI environ.
Per default encoding errors are ignored. If you want a different behavior
you can set `errors` to ``'replace'`` or ``'strict'``. In strict mode a
:exc:`HTTPUnicodeError` is raised.
.. versionchanged:: 0.5
This function now returns a :class:`TypeConversionDict` instead of a
regular dict. The `cls` parameter was added.
:param header: the header to be used to parse the cookie. Alternatively
this can be a WSGI environment.
:param charset: the charset for the cookie values.
:param errors: the error behavior for the charset decoding.
:param cls: an optional dict class to use. If this is not specified
or `None` the default :class:`TypeConversionDict` is
used.
"""
if isinstance(header, dict):
header = header.get('HTTP_COOKIE', '')
if cls is None:
cls = TypeConversionDict
cookie = _ExtendedCookie()
cookie.load(header)
result = {}
# decode to unicode and skip broken items. Our extended morsel
# and extended cookie will catch CookieErrors and convert them to
# `None` items which we have to skip here.
for key, value in cookie.iteritems():
if value.value is not None:
result[key] = _decode_unicode(unquote_header_value(value.value),
charset, errors)
return cls(result)
def parse_cookie(header, charset='utf-8', errors='replace', cls=None):
"""Parse a cookie. Either from a string or WSGI environ.
Per default encoding errors are ignored. If you want a different behavior
you can set `errors` to ``'replace'`` or ``'strict'``. In strict mode a
:exc:`HTTPUnicodeError` is raised.
.. versionchanged:: 0.5
This function now returns a :class:`TypeConversionDict` instead of a
regular dict. The `cls` parameter was added.
:param header: the header to be used to parse the cookie. Alternatively
this can be a WSGI environment.
:param charset: the charset for the cookie values.
:param errors: the error behavior for the charset decoding.
:param cls: an optional dict class to use. If this is not specified
or `None` the default :class:`TypeConversionDict` is
used.
"""
if isinstance(header, dict):
header = header.get('HTTP_COOKIE', '')
if cls is None:
cls = TypeConversionDict
cookie = _ExtendedCookie()
cookie.load(header)
result = {}
# decode to unicode and skip broken items. Our extended morsel
# and extended cookie will catch CookieErrors and convert them to
# `None` items which we have to skip here.
for key, value in cookie.iteritems():
if value.value is not None:
result[key] = _decode_unicode(unquote_header_value(value.value),
charset, errors)
return cls(result)
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)
def to_unicode(self, value):
if isinstance(value, str):
return _decode_unicode(value, self.charset, self.errors)
return unicode(value)
def to_unicode(self, value):
if isinstance(value, str):
return _decode_unicode(value, self.charset, self.errors)
return unicode(value)
