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 ':' in hostname:
hostname = '[' + hostname + ']'
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 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)