diff --git a/Doc/library/urllib.parse.rst b/Doc/library/urllib.parse.rst index 40098d0..1b3d4e3 100644 --- a/Doc/library/urllib.parse.rst +++ b/Doc/library/urllib.parse.rst @@ -118,6 +118,11 @@ or on combining URL components into a URL string. See section :ref:`urlparse-result-object` for more information on the result object. + Characters in the :attr:`netloc` attribute that decompose under NFKC + normalization (as used by the IDNA encoding) into any of ``/``, ``?``, + ``#``, ``@``, or ``:`` will raise a :exc:`ValueError`. If the URL is + decomposed before parsing, no error will be raised. + .. versionchanged:: 3.2 Added IPv6 URL parsing capabilities. @@ -126,6 +131,10 @@ or on combining URL components into a URL string. false), in accordance with :rfc:`3986`. Previously, a whitelist of schemes that support fragments existed. + .. versionchanged:: 3.5.7 + Characters that affect netloc parsing under NFKC normalization will + now raise :exc:`ValueError`. + .. function:: parse_qs(qs, keep_blank_values=False, strict_parsing=False, encoding='utf-8', errors='replace') @@ -231,6 +240,15 @@ or on combining URL components into a URL string. See section :ref:`urlparse-result-object` for more information on the result object. + Characters in the :attr:`netloc` attribute that decompose under NFKC + normalization (as used by the IDNA encoding) into any of ``/``, ``?``, + ``#``, ``@``, or ``:`` will raise a :exc:`ValueError`. If the URL is + decomposed before parsing, no error will be raised. + + .. versionchanged:: 3.5.7 + Characters that affect netloc parsing under NFKC normalization will + now raise :exc:`ValueError`. + .. function:: urlunsplit(parts) diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py index 0552f90..06c29da 100644 --- a/Lib/test/test_urlparse.py +++ b/Lib/test/test_urlparse.py @@ -1,3 +1,5 @@ +import sys +import unicodedata import unittest import urllib.parse @@ -910,6 +912,33 @@ class UrlParseTestCase(unittest.TestCase): expected.append(name) self.assertCountEqual(urllib.parse.__all__, expected) + def test_urlsplit_normalization(self): + # Certain characters should never occur in the netloc, + # including under normalization. + # Ensure that ALL of them are detected and cause an error + illegal_chars = '/:#?@' + hex_chars = {'{:04X}'.format(ord(c)) for c in illegal_chars} + denorm_chars = [ + c for c in map(chr, range(128, sys.maxunicode)) + if (hex_chars & set(unicodedata.decomposition(c).split())) + and c not in illegal_chars + ] + # Sanity check that we found at least one such character + self.assertIn('\u2100', denorm_chars) + self.assertIn('\uFF03', denorm_chars) + + # bpo-36742: Verify port separators are ignored when they + # existed prior to decomposition + urllib.parse.urlsplit('http://\u30d5\u309a:80') + with self.assertRaises(ValueError): + urllib.parse.urlsplit('http://\u30d5\u309a\ufe1380') + + for scheme in ["http", "https", "ftp"]: + for c in denorm_chars: + url = "{}://netloc{}false.netloc/path".format(scheme, c) + with self.subTest(url=url, char='{:04X}'.format(ord(c))): + with self.assertRaises(ValueError): + urllib.parse.urlsplit(url) class Utility_Tests(unittest.TestCase): """Testcase to test the various utility functions in the urllib.""" diff --git a/Lib/urllib/parse.py b/Lib/urllib/parse.py index 01c9e58..c449b3c 100644 --- a/Lib/urllib/parse.py +++ b/Lib/urllib/parse.py @@ -318,6 +318,24 @@ def _splitnetloc(url, start=0): delim = min(delim, wdelim) # use earliest delim position return url[start:delim], url[delim:] # return (domain, rest) +def _checknetloc(netloc): + if not netloc or not any(ord(c) > 127 for c in netloc): + return + # looking for characters like \u2100 that expand to 'a/c' + # IDNA uses NFKC equivalence, so normalize for this check + import unicodedata + n = netloc.rpartition('@')[2] # ignore anything to the left of '@' + n = n.replace(':', '') # ignore characters already included + n = n.replace('#', '') # but not the surrounding text + n = n.replace('?', '') + netloc2 = unicodedata.normalize('NFKC', n) + if n == netloc2: + return + for c in '/?#@:': + if c in netloc2: + raise ValueError("netloc '" + netloc + "' contains invalid " + + "characters under NFKC normalization") + def urlsplit(url, scheme='', allow_fragments=True): """Parse a URL into 5 components: :///?# @@ -347,6 +365,7 @@ def urlsplit(url, scheme='', allow_fragments=True): url, fragment = url.split('#', 1) if '?' in url: url, query = url.split('?', 1) + _checknetloc(netloc) v = SplitResult(scheme, netloc, url, query, fragment) _parse_cache[key] = v return _coerce_result(v) @@ -370,6 +389,7 @@ def urlsplit(url, scheme='', allow_fragments=True): url, fragment = url.split('#', 1) if '?' in url: url, query = url.split('?', 1) + _checknetloc(netloc) v = SplitResult(scheme, netloc, url, query, fragment) _parse_cache[key] = v return _coerce_result(v)