Issue 9873: the URL parsing functions now accept ASCII encoded byte sequences in addition to character strings
diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
index e559142..e67c2b6 100644
--- a/Lib/test/test_urlparse.py
+++ b/Lib/test/test_urlparse.py
@@ -24,6 +24,17 @@
("&a=b", [('a', 'b')]),
("a=a+b&b=b+c", [('a', 'a b'), ('b', 'b c')]),
("a=1&a=2", [('a', '1'), ('a', '2')]),
+ (b"", []),
+ (b"&", []),
+ (b"&&", []),
+ (b"=", [(b'', b'')]),
+ (b"=a", [(b'', b'a')]),
+ (b"a", [(b'a', b'')]),
+ (b"a=", [(b'a', b'')]),
+ (b"a=", [(b'a', b'')]),
+ (b"&a=b", [(b'a', b'b')]),
+ (b"a=a+b&b=b+c", [(b'a', b'a b'), (b'b', b'b c')]),
+ (b"a=1&a=2", [(b'a', b'1'), (b'a', b'2')]),
]
class UrlParseTestCase(unittest.TestCase):
@@ -86,7 +97,7 @@
def test_roundtrips(self):
- testcases = [
+ str_cases = [
('file:///tmp/junk.txt',
('file', '', '/tmp/junk.txt', '', '', ''),
('file', '', '/tmp/junk.txt', '', '')),
@@ -110,16 +121,21 @@
('git+ssh', 'git@github.com','/user/project.git',
'','',''),
('git+ssh', 'git@github.com','/user/project.git',
- '', ''))
+ '', '')),
]
- for url, parsed, split in testcases:
+ def _encode(t):
+ return (t[0].encode('ascii'),
+ tuple(x.encode('ascii') for x in t[1]),
+ tuple(x.encode('ascii') for x in t[2]))
+ bytes_cases = [_encode(x) for x in str_cases]
+ for url, parsed, split in str_cases + bytes_cases:
self.checkRoundtrips(url, parsed, split)
def test_http_roundtrips(self):
# urllib.parse.urlsplit treats 'http:' as an optimized special case,
# so we test both 'http:' and 'https:' in all the following.
# Three cheers for white box knowledge!
- testcases = [
+ str_cases = [
('://www.python.org',
('www.python.org', '', '', '', ''),
('www.python.org', '', '', '')),
@@ -136,19 +152,34 @@
('a', '/b/c/d', 'p', 'q', 'f'),
('a', '/b/c/d;p', 'q', 'f')),
]
- for scheme in ('http', 'https'):
- for url, parsed, split in testcases:
- url = scheme + url
- parsed = (scheme,) + parsed
- split = (scheme,) + split
- self.checkRoundtrips(url, parsed, split)
+ def _encode(t):
+ return (t[0].encode('ascii'),
+ tuple(x.encode('ascii') for x in t[1]),
+ tuple(x.encode('ascii') for x in t[2]))
+ bytes_cases = [_encode(x) for x in str_cases]
+ str_schemes = ('http', 'https')
+ bytes_schemes = (b'http', b'https')
+ str_tests = str_schemes, str_cases
+ bytes_tests = bytes_schemes, bytes_cases
+ for schemes, test_cases in (str_tests, bytes_tests):
+ for scheme in schemes:
+ for url, parsed, split in test_cases:
+ url = scheme + url
+ parsed = (scheme,) + parsed
+ split = (scheme,) + split
+ self.checkRoundtrips(url, parsed, split)
def checkJoin(self, base, relurl, expected):
- self.assertEqual(urllib.parse.urljoin(base, relurl), expected,
- (base, relurl, expected))
+ str_components = (base, relurl, expected)
+ self.assertEqual(urllib.parse.urljoin(base, relurl), expected)
+ bytes_components = baseb, relurlb, expectedb = [
+ x.encode('ascii') for x in str_components]
+ self.assertEqual(urllib.parse.urljoin(baseb, relurlb), expectedb)
def test_unparse_parse(self):
- for u in ['Python', './Python','x-newscheme://foo.com/stuff','x://y','x:/y','x:/','/',]:
+ str_cases = ['Python', './Python','x-newscheme://foo.com/stuff','x://y','x:/y','x:/','/',]
+ bytes_cases = [x.encode('ascii') for x in str_cases]
+ for u in str_cases + bytes_cases:
self.assertEqual(urllib.parse.urlunsplit(urllib.parse.urlsplit(u)), u)
self.assertEqual(urllib.parse.urlunparse(urllib.parse.urlparse(u)), u)
@@ -328,7 +359,7 @@
self.checkJoin(SIMPLE_BASE, 'http:g?y/./x','http://a/b/c/g?y/./x')
def test_RFC2732(self):
- for url, hostname, port in [
+ str_cases = [
('http://Test.python.org:5432/foo/', 'test.python.org', 5432),
('http://12.34.56.78:5432/foo/', '12.34.56.78', 5432),
('http://[::1]:5432/foo/', '::1', 5432),
@@ -349,20 +380,26 @@
('http://[::12.34.56.78]/foo/', '::12.34.56.78', None),
('http://[::ffff:12.34.56.78]/foo/',
'::ffff:12.34.56.78', None),
- ]:
+ ]
+ def _encode(t):
+ return t[0].encode('ascii'), t[1].encode('ascii'), t[2]
+ bytes_cases = [_encode(x) for x in str_cases]
+ for url, hostname, port in str_cases + bytes_cases:
urlparsed = urllib.parse.urlparse(url)
self.assertEqual((urlparsed.hostname, urlparsed.port) , (hostname, port))
- for invalid_url in [
+ str_cases = [
'http://::12.34.56.78]/',
'http://[::1/foo/',
'ftp://[::1/foo/bad]/bad',
'http://[::1/foo/bad]/bad',
- 'http://[::ffff:12.34.56.78']:
+ 'http://[::ffff:12.34.56.78']
+ bytes_cases = [x.encode('ascii') for x in str_cases]
+ for invalid_url in str_cases + bytes_cases:
self.assertRaises(ValueError, urllib.parse.urlparse, invalid_url)
def test_urldefrag(self):
- for url, defrag, frag in [
+ str_cases = [
('http://python.org#frag', 'http://python.org', 'frag'),
('http://python.org', 'http://python.org', ''),
('http://python.org/#frag', 'http://python.org/', 'frag'),
@@ -373,8 +410,16 @@
('http://python.org/p?q', 'http://python.org/p?q', ''),
(RFC1808_BASE, 'http://a/b/c/d;p?q', 'f'),
(RFC2396_BASE, 'http://a/b/c/d;p?q', ''),
- ]:
- self.assertEqual(urllib.parse.urldefrag(url), (defrag, frag))
+ ]
+ def _encode(t):
+ return type(t)(x.encode('ascii') for x in t)
+ bytes_cases = [_encode(x) for x in str_cases]
+ for url, defrag, frag in str_cases + bytes_cases:
+ result = urllib.parse.urldefrag(url)
+ self.assertEqual(result.geturl(), url)
+ self.assertEqual(result, (defrag, frag))
+ self.assertEqual(result.url, defrag)
+ self.assertEqual(result.fragment, frag)
def test_urlsplit_attributes(self):
url = "HTTP://WWW.PYTHON.ORG/doc/#frag"
@@ -390,7 +435,8 @@
self.assertEqual(p.port, None)
# geturl() won't return exactly the original URL in this case
# since the scheme is always case-normalized
- #self.assertEqual(p.geturl(), url)
+ # We handle this by ignoring the first 4 characters of the URL
+ self.assertEqual(p.geturl()[4:], url[4:])
url = "http://User:Pass@www.python.org:080/doc/?query=yes#frag"
p = urllib.parse.urlsplit(url)
@@ -422,6 +468,45 @@
self.assertEqual(p.port, 80)
self.assertEqual(p.geturl(), url)
+ # And check them all again, only with bytes this time
+ url = b"HTTP://WWW.PYTHON.ORG/doc/#frag"
+ p = urllib.parse.urlsplit(url)
+ self.assertEqual(p.scheme, b"http")
+ self.assertEqual(p.netloc, b"WWW.PYTHON.ORG")
+ self.assertEqual(p.path, b"/doc/")
+ self.assertEqual(p.query, b"")
+ self.assertEqual(p.fragment, b"frag")
+ self.assertEqual(p.username, None)
+ self.assertEqual(p.password, None)
+ self.assertEqual(p.hostname, b"www.python.org")
+ self.assertEqual(p.port, None)
+ self.assertEqual(p.geturl()[4:], url[4:])
+
+ url = b"http://User:Pass@www.python.org:080/doc/?query=yes#frag"
+ p = urllib.parse.urlsplit(url)
+ self.assertEqual(p.scheme, b"http")
+ self.assertEqual(p.netloc, b"User:Pass@www.python.org:080")
+ self.assertEqual(p.path, b"/doc/")
+ self.assertEqual(p.query, b"query=yes")
+ self.assertEqual(p.fragment, b"frag")
+ self.assertEqual(p.username, b"User")
+ self.assertEqual(p.password, b"Pass")
+ self.assertEqual(p.hostname, b"www.python.org")
+ self.assertEqual(p.port, 80)
+ self.assertEqual(p.geturl(), url)
+
+ url = b"http://User@example.com:Pass@www.python.org:080/doc/?query=yes#frag"
+ p = urllib.parse.urlsplit(url)
+ self.assertEqual(p.scheme, b"http")
+ self.assertEqual(p.netloc, b"User@example.com:Pass@www.python.org:080")
+ self.assertEqual(p.path, b"/doc/")
+ self.assertEqual(p.query, b"query=yes")
+ self.assertEqual(p.fragment, b"frag")
+ self.assertEqual(p.username, b"User@example.com")
+ self.assertEqual(p.password, b"Pass")
+ self.assertEqual(p.hostname, b"www.python.org")
+ self.assertEqual(p.port, 80)
+ self.assertEqual(p.geturl(), url)
def test_attributes_bad_port(self):
"""Check handling of non-integer ports."""
@@ -433,6 +518,15 @@
self.assertEqual(p.netloc, "www.example.net:foo")
self.assertRaises(ValueError, lambda: p.port)
+ # Once again, repeat ourselves to test bytes
+ p = urllib.parse.urlsplit(b"http://www.example.net:foo")
+ self.assertEqual(p.netloc, b"www.example.net:foo")
+ self.assertRaises(ValueError, lambda: p.port)
+
+ p = urllib.parse.urlparse(b"http://www.example.net:foo")
+ self.assertEqual(p.netloc, b"www.example.net:foo")
+ self.assertRaises(ValueError, lambda: p.port)
+
def test_attributes_without_netloc(self):
# This example is straight from RFC 3261. It looks like it
# should allow the username, hostname, and port to be filled
@@ -456,10 +550,30 @@
self.assertEqual(p.port, None)
self.assertEqual(p.geturl(), uri)
+ # You guessed it, repeating the test with bytes input
+ uri = b"sip:alice@atlanta.com;maddr=239.255.255.1;ttl=15"
+ p = urllib.parse.urlsplit(uri)
+ self.assertEqual(p.netloc, b"")
+ self.assertEqual(p.username, None)
+ self.assertEqual(p.password, None)
+ self.assertEqual(p.hostname, None)
+ self.assertEqual(p.port, None)
+ self.assertEqual(p.geturl(), uri)
+
+ p = urllib.parse.urlparse(uri)
+ self.assertEqual(p.netloc, b"")
+ self.assertEqual(p.username, None)
+ self.assertEqual(p.password, None)
+ self.assertEqual(p.hostname, None)
+ self.assertEqual(p.port, None)
+ self.assertEqual(p.geturl(), uri)
+
def test_noslash(self):
# Issue 1637: http://foo.com?query is legal
self.assertEqual(urllib.parse.urlparse("http://example.com?blahblah=/foo"),
('http', 'example.com', '', '', 'blahblah=/foo', ''))
+ self.assertEqual(urllib.parse.urlparse(b"http://example.com?blahblah=/foo"),
+ (b'http', b'example.com', b'', b'', b'blahblah=/foo', b''))
def test_withoutscheme(self):
# Test urlparse without scheme
@@ -472,6 +586,13 @@
('','www.python.org:80','','','',''))
self.assertEqual(urllib.parse.urlparse("http://www.python.org:80"),
('http','www.python.org:80','','','',''))
+ # Repeat for bytes input
+ self.assertEqual(urllib.parse.urlparse(b"path"),
+ (b'',b'',b'path',b'',b'',b''))
+ self.assertEqual(urllib.parse.urlparse(b"//www.python.org:80"),
+ (b'',b'www.python.org:80',b'',b'',b'',b''))
+ self.assertEqual(urllib.parse.urlparse(b"http://www.python.org:80"),
+ (b'http',b'www.python.org:80',b'',b'',b'',b''))
def test_portseparator(self):
# Issue 754016 makes changes for port separator ':' from scheme separator
@@ -481,6 +602,13 @@
self.assertEqual(urllib.parse.urlparse("https:"),('https','','','','',''))
self.assertEqual(urllib.parse.urlparse("http://www.python.org:80"),
('http','www.python.org:80','','','',''))
+ # As usual, need to check bytes input as well
+ self.assertEqual(urllib.parse.urlparse(b"path:80"),
+ (b'',b'',b'path:80',b'',b'',b''))
+ self.assertEqual(urllib.parse.urlparse(b"http:"),(b'http',b'',b'',b'',b'',b''))
+ self.assertEqual(urllib.parse.urlparse(b"https:"),(b'https',b'',b'',b'',b'',b''))
+ self.assertEqual(urllib.parse.urlparse(b"http://www.python.org:80"),
+ (b'http',b'www.python.org:80',b'',b'',b'',b''))
def test_usingsys(self):
# Issue 3314: sys module is used in the error
@@ -492,6 +620,71 @@
('s3', 'foo.com', '/stuff', '', '', ''))
self.assertEqual(urllib.parse.urlparse("x-newscheme://foo.com/stuff"),
('x-newscheme', 'foo.com', '/stuff', '', '', ''))
+ # And for bytes...
+ self.assertEqual(urllib.parse.urlparse(b"s3://foo.com/stuff"),
+ (b's3', b'foo.com', b'/stuff', b'', b'', b''))
+ self.assertEqual(urllib.parse.urlparse(b"x-newscheme://foo.com/stuff"),
+ (b'x-newscheme', b'foo.com', b'/stuff', b'', b'', b''))
+
+ def test_mixed_types_rejected(self):
+ # Several functions that process either strings or ASCII encoded bytes
+ # accept multiple arguments. Check they reject mixed type input
+ with self.assertRaisesRegexp(TypeError, "Cannot mix str"):
+ urllib.parse.urlparse("www.python.org", b"http")
+ with self.assertRaisesRegexp(TypeError, "Cannot mix str"):
+ urllib.parse.urlparse(b"www.python.org", "http")
+ with self.assertRaisesRegexp(TypeError, "Cannot mix str"):
+ urllib.parse.urlsplit("www.python.org", b"http")
+ with self.assertRaisesRegexp(TypeError, "Cannot mix str"):
+ urllib.parse.urlsplit(b"www.python.org", "http")
+ with self.assertRaisesRegexp(TypeError, "Cannot mix str"):
+ urllib.parse.urlunparse(( b"http", "www.python.org","","","",""))
+ with self.assertRaisesRegexp(TypeError, "Cannot mix str"):
+ urllib.parse.urlunparse(("http", b"www.python.org","","","",""))
+ with self.assertRaisesRegexp(TypeError, "Cannot mix str"):
+ urllib.parse.urlunsplit((b"http", "www.python.org","","",""))
+ with self.assertRaisesRegexp(TypeError, "Cannot mix str"):
+ urllib.parse.urlunsplit(("http", b"www.python.org","","",""))
+ with self.assertRaisesRegexp(TypeError, "Cannot mix str"):
+ urllib.parse.urljoin("http://python.org", b"http://python.org")
+ with self.assertRaisesRegexp(TypeError, "Cannot mix str"):
+ urllib.parse.urljoin(b"http://python.org", "http://python.org")
+
+ def _check_result_type(self, str_type):
+ num_args = len(str_type._fields)
+ bytes_type = str_type._encoded_counterpart
+ self.assertIs(bytes_type._decoded_counterpart, str_type)
+ str_args = ('',) * num_args
+ bytes_args = (b'',) * num_args
+ str_result = str_type(*str_args)
+ bytes_result = bytes_type(*bytes_args)
+ encoding = 'ascii'
+ errors = 'strict'
+ self.assertEqual(str_result, str_args)
+ self.assertEqual(bytes_result.decode(), str_args)
+ self.assertEqual(bytes_result.decode(), str_result)
+ self.assertEqual(bytes_result.decode(encoding), str_args)
+ self.assertEqual(bytes_result.decode(encoding), str_result)
+ self.assertEqual(bytes_result.decode(encoding, errors), str_args)
+ self.assertEqual(bytes_result.decode(encoding, errors), str_result)
+ self.assertEqual(bytes_result, bytes_args)
+ self.assertEqual(str_result.encode(), bytes_args)
+ self.assertEqual(str_result.encode(), bytes_result)
+ self.assertEqual(str_result.encode(encoding), bytes_args)
+ self.assertEqual(str_result.encode(encoding), bytes_result)
+ self.assertEqual(str_result.encode(encoding, errors), bytes_args)
+ self.assertEqual(str_result.encode(encoding, errors), bytes_result)
+
+ def test_result_pairs(self):
+ # Check encoding and decoding between result pairs
+ result_types = [
+ urllib.parse.DefragResult,
+ urllib.parse.SplitResult,
+ urllib.parse.ParseResult,
+ ]
+ for result_type in result_types:
+ self._check_result_type(result_type)
+
def test_main():
support.run_unittest(UrlParseTestCase)
diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py
index 78f3084..ab5b356 100644
--- a/Lib/urllib/parse.py
+++ b/Lib/urllib/parse.py
@@ -60,6 +60,7 @@
'0123456789'
'+-.')
+# XXX: Consider replacing with functools.lru_cache
MAX_CACHE_SIZE = 20
_parse_cache = {}
@@ -69,66 +70,210 @@
_safe_quoters.clear()
-class ResultMixin(object):
- """Shared methods for the parsed result objects."""
+# Helpers for bytes handling
+# For 3.2, we deliberately require applications that
+# handle improperly quoted URLs to do their own
+# decoding and encoding. If valid use cases are
+# presented, we may relax this by using latin-1
+# decoding internally for 3.3
+_implicit_encoding = 'ascii'
+_implicit_errors = 'strict'
+
+def _noop(obj):
+ return obj
+
+def _encode_result(obj, encoding=_implicit_encoding,
+ errors=_implicit_errors):
+ return obj.encode(encoding, errors)
+
+def _decode_args(args, encoding=_implicit_encoding,
+ errors=_implicit_errors):
+ return tuple(x.decode(encoding, errors) if x else '' for x in args)
+
+def _coerce_args(*args):
+ # Invokes decode if necessary to create str args
+ # and returns the coerced inputs along with
+ # an appropriate result coercion function
+ # - noop for str inputs
+ # - encoding function otherwise
+ str_input = isinstance(args[0], str)
+ for arg in args[1:]:
+ # We special-case the empty string to support the
+ # "scheme=''" default argument to some functions
+ if arg and isinstance(arg, str) != str_input:
+ raise TypeError("Cannot mix str and non-str arguments")
+ if str_input:
+ return args + (_noop,)
+ return _decode_args(args) + (_encode_result,)
+
+# Result objects are more helpful than simple tuples
+class _ResultMixinStr(object):
+ """Standard approach to encoding parsed results from str to bytes"""
+ __slots__ = ()
+
+ def encode(self, encoding='ascii', errors='strict'):
+ return self._encoded_counterpart(*(x.encode(encoding, errors) for x in self))
+
+
+class _ResultMixinBytes(object):
+ """Standard approach to decoding parsed results from bytes to str"""
+ __slots__ = ()
+
+ def decode(self, encoding='ascii', errors='strict'):
+ return self._decoded_counterpart(*(x.decode(encoding, errors) for x in self))
+
+
+class _NetlocResultMixinBase(object):
+ """Shared methods for the parsed result objects containing a netloc element"""
+ __slots__ = ()
@property
def username(self):
- netloc = self.netloc
- if "@" in netloc:
- userinfo = netloc.rsplit("@", 1)[0]
- if ":" in userinfo:
- userinfo = userinfo.split(":", 1)[0]
- return userinfo
- return None
+ return self._userinfo[0]
@property
def password(self):
- netloc = self.netloc
- if "@" in netloc:
- userinfo = netloc.rsplit("@", 1)[0]
- if ":" in userinfo:
- return userinfo.split(":", 1)[1]
- return None
+ return self._userinfo[1]
@property
def hostname(self):
- netloc = self.netloc.split('@')[-1]
- if '[' in netloc and ']' in netloc:
- return netloc.split(']')[0][1:].lower()
- elif ':' in netloc:
- return netloc.split(':')[0].lower()
- elif netloc == '':
- return None
- else:
- return netloc.lower()
+ hostname = self._hostinfo[0]
+ if not hostname:
+ hostname = None
+ elif hostname is not None:
+ hostname = hostname.lower()
+ return hostname
@property
def port(self):
- netloc = self.netloc.split('@')[-1].split(']')[-1]
- if ':' in netloc:
- port = netloc.split(':')[1]
- return int(port, 10)
+ port = self._hostinfo[1]
+ if port is not None:
+ port = int(port, 10)
+ return port
+
+
+class _NetlocResultMixinStr(_NetlocResultMixinBase, _ResultMixinStr):
+ __slots__ = ()
+
+ @property
+ def _userinfo(self):
+ netloc = self.netloc
+ userinfo, have_info, hostinfo = netloc.rpartition('@')
+ if have_info:
+ username, have_password, password = userinfo.partition(':')
+ if not have_password:
+ password = None
else:
- return None
+ username = password = None
+ return username, password
+
+ @property
+ def _hostinfo(self):
+ netloc = self.netloc
+ _, _, hostinfo = netloc.rpartition('@')
+ _, have_open_br, bracketed = hostinfo.partition('[')
+ if have_open_br:
+ hostname, _, port = bracketed.partition(']')
+ _, have_port, port = port.partition(':')
+ else:
+ hostname, have_port, port = hostinfo.partition(':')
+ if not have_port:
+ port = None
+ return hostname, port
+
+
+class _NetlocResultMixinBytes(_NetlocResultMixinBase, _ResultMixinBytes):
+ __slots__ = ()
+
+ @property
+ def _userinfo(self):
+ netloc = self.netloc
+ userinfo, have_info, hostinfo = netloc.rpartition(b'@')
+ if have_info:
+ username, have_password, password = userinfo.partition(b':')
+ if not have_password:
+ password = None
+ else:
+ username = password = None
+ return username, password
+
+ @property
+ def _hostinfo(self):
+ netloc = self.netloc
+ _, _, hostinfo = netloc.rpartition(b'@')
+ _, have_open_br, bracketed = hostinfo.partition(b'[')
+ if have_open_br:
+ hostname, _, port = bracketed.partition(b']')
+ _, have_port, port = port.partition(b':')
+ else:
+ hostname, have_port, port = hostinfo.partition(b':')
+ if not have_port:
+ port = None
+ return hostname, port
+
from collections import namedtuple
-class SplitResult(namedtuple('SplitResult', 'scheme netloc path query fragment'), ResultMixin):
+_DefragResultBase = namedtuple('DefragResult', 'url fragment')
+_SplitResultBase = namedtuple('SplitResult', 'scheme netloc path query fragment')
+_ParseResultBase = namedtuple('ParseResult', 'scheme netloc path params query fragment')
+# For backwards compatibility, alias _NetlocResultMixinStr
+# ResultBase is no longer part of the documented API, but it is
+# retained since deprecating it isn't worth the hassle
+ResultBase = _NetlocResultMixinStr
+
+# Structured result objects for string data
+class DefragResult(_DefragResultBase, _ResultMixinStr):
__slots__ = ()
+ def geturl(self):
+ if self.fragment:
+ return self.url + '#' + self.fragment
+ else:
+ return self.url
+class SplitResult(_SplitResultBase, _NetlocResultMixinStr):
+ __slots__ = ()
def geturl(self):
return urlunsplit(self)
-
-class ParseResult(namedtuple('ParseResult', 'scheme netloc path params query fragment'), ResultMixin):
-
+class ParseResult(_ParseResultBase, _NetlocResultMixinStr):
__slots__ = ()
-
def geturl(self):
return urlunparse(self)
+# Structured result objects for bytes data
+class DefragResultBytes(_DefragResultBase, _ResultMixinBytes):
+ __slots__ = ()
+ def geturl(self):
+ if self.fragment:
+ return self.url + b'#' + self.fragment
+ else:
+ return self.url
+
+class SplitResultBytes(_SplitResultBase, _NetlocResultMixinBytes):
+ __slots__ = ()
+ def geturl(self):
+ return urlunsplit(self)
+
+class ParseResultBytes(_ParseResultBase, _NetlocResultMixinBytes):
+ __slots__ = ()
+ def geturl(self):
+ return urlunparse(self)
+
+# Set up the encode/decode result pairs
+def _fix_result_transcoding():
+ _result_pairs = (
+ (DefragResult, DefragResultBytes),
+ (SplitResult, SplitResultBytes),
+ (ParseResult, ParseResultBytes),
+ )
+ for _decoded, _encoded in _result_pairs:
+ _decoded._encoded_counterpart = _encoded
+ _encoded._decoded_counterpart = _decoded
+
+_fix_result_transcoding()
+del _fix_result_transcoding
def urlparse(url, scheme='', allow_fragments=True):
"""Parse a URL into 6 components:
@@ -136,13 +281,15 @@
Return a 6-tuple: (scheme, netloc, path, params, query, fragment).
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes."""
+ url, scheme, _coerce_result = _coerce_args(url, scheme)
tuple = urlsplit(url, scheme, allow_fragments)
scheme, netloc, url, query, fragment = tuple
if scheme in uses_params and ';' in url:
url, params = _splitparams(url)
else:
params = ''
- return ParseResult(scheme, netloc, url, params, query, fragment)
+ result = ParseResult(scheme, netloc, url, params, query, fragment)
+ return _coerce_result(result)
def _splitparams(url):
if '/' in url:
@@ -167,11 +314,12 @@
Return a 5-tuple: (scheme, netloc, path, query, fragment).
Note that we don't break the components up in smaller bits
(e.g. netloc is a single string) and we don't expand % escapes."""
+ url, scheme, _coerce_result = _coerce_args(url, scheme)
allow_fragments = bool(allow_fragments)
key = url, scheme, allow_fragments, type(url), type(scheme)
cached = _parse_cache.get(key, None)
if cached:
- return cached
+ return _coerce_result(cached)
if len(_parse_cache) >= MAX_CACHE_SIZE: # avoid runaway growth
clear_cache()
netloc = query = fragment = ''
@@ -191,7 +339,7 @@
url, query = url.split('?', 1)
v = SplitResult(scheme, netloc, url, query, fragment)
_parse_cache[key] = v
- return v
+ return _coerce_result(v)
if url.endswith(':') or not url[i+1].isdigit():
for c in url[:i]:
if c not in scheme_chars:
@@ -209,17 +357,18 @@
url, query = url.split('?', 1)
v = SplitResult(scheme, netloc, url, query, fragment)
_parse_cache[key] = v
- return v
+ return _coerce_result(v)
def urlunparse(components):
"""Put a parsed URL back together again. This may result in a
slightly different, but equivalent URL, if the URL that was parsed
originally had redundant delimiters, e.g. a ? with an empty query
(the draft states that these are equivalent)."""
- scheme, netloc, url, params, query, fragment = components
+ scheme, netloc, url, params, query, fragment, _coerce_result = (
+ _coerce_args(*components))
if params:
url = "%s;%s" % (url, params)
- return urlunsplit((scheme, netloc, url, query, fragment))
+ return _coerce_result(urlunsplit((scheme, netloc, url, query, fragment)))
def urlunsplit(components):
"""Combine the elements of a tuple as returned by urlsplit() into a
@@ -227,7 +376,8 @@
This may result in a slightly different, but equivalent URL, if the URL that
was parsed originally had unnecessary delimiters (for example, a ? with an
empty query; the RFC states that these are equivalent)."""
- scheme, netloc, url, query, fragment = components
+ scheme, netloc, url, query, fragment, _coerce_result = (
+ _coerce_args(*components))
if netloc or (scheme and scheme in uses_netloc and url[:2] != '//'):
if url and url[:1] != '/': url = '/' + url
url = '//' + (netloc or '') + url
@@ -237,7 +387,7 @@
url = url + '?' + query
if fragment:
url = url + '#' + fragment
- return url
+ return _coerce_result(url)
def urljoin(base, url, allow_fragments=True):
"""Join a base URL and a possibly relative URL to form an absolute
@@ -246,32 +396,33 @@
return url
if not url:
return base
+ base, url, _coerce_result = _coerce_args(base, url)
bscheme, bnetloc, bpath, bparams, bquery, bfragment = \
urlparse(base, '', allow_fragments)
scheme, netloc, path, params, query, fragment = \
urlparse(url, bscheme, allow_fragments)
if scheme != bscheme or scheme not in uses_relative:
- return url
+ return _coerce_result(url)
if scheme in uses_netloc:
if netloc:
- return urlunparse((scheme, netloc, path,
- params, query, fragment))
+ return _coerce_result(urlunparse((scheme, netloc, path,
+ params, query, fragment)))
netloc = bnetloc
if path[:1] == '/':
- return urlunparse((scheme, netloc, path,
- params, query, fragment))
+ return _coerce_result(urlunparse((scheme, netloc, path,
+ params, query, fragment)))
if not path:
path = bpath
if not params:
params = bparams
else:
path = path[:-1]
- return urlunparse((scheme, netloc, path,
- params, query, fragment))
+ return _coerce_result(urlunparse((scheme, netloc, path,
+ params, query, fragment)))
if not query:
query = bquery
- return urlunparse((scheme, netloc, path,
- params, query, fragment))
+ return _coerce_result(urlunparse((scheme, netloc, path,
+ params, query, fragment)))
segments = bpath.split('/')[:-1] + path.split('/')
# XXX The stuff below is bogus in various ways...
if segments[-1] == '.':
@@ -293,8 +444,8 @@
segments[-1] = ''
elif len(segments) >= 2 and segments[-1] == '..':
segments[-2:] = ['']
- return urlunparse((scheme, netloc, '/'.join(segments),
- params, query, fragment))
+ return _coerce_result(urlunparse((scheme, netloc, '/'.join(segments),
+ params, query, fragment)))
def urldefrag(url):
"""Removes any existing fragment from URL.
@@ -303,12 +454,14 @@
the URL contained no fragments, the second element is the
empty string.
"""
+ url, _coerce_result = _coerce_args(url)
if '#' in url:
s, n, p, a, q, frag = urlparse(url)
defrag = urlunparse((s, n, p, a, q, ''))
- return defrag, frag
else:
- return url, ''
+ frag = ''
+ defrag = url
+ return _coerce_result(DefragResult(defrag, frag))
def unquote_to_bytes(string):
"""unquote_to_bytes('abc%20def') -> b'abc def'."""
@@ -420,6 +573,7 @@
Returns a list, as G-d intended.
"""
+ qs, _coerce_result = _coerce_args(qs)
pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
r = []
for name_value in pairs:
@@ -435,10 +589,9 @@
else:
continue
if len(nv[1]) or keep_blank_values:
- name = unquote(nv[0].replace('+', ' '))
- value = unquote(nv[1].replace('+', ' '))
+ name = _coerce_result(unquote(nv[0].replace('+', ' ')))
+ value = _coerce_result(unquote(nv[1].replace('+', ' ')))
r.append((name, value))
-
return r
def unquote_plus(string, encoding='utf-8', errors='replace'):