143 lines
5.5 KiB
Diff
143 lines
5.5 KiB
Diff
diff --git a/Doc/library/urlparse.rst b/Doc/library/urlparse.rst
|
|
index 22249da..0989c88 100644
|
|
--- a/Doc/library/urlparse.rst
|
|
+++ b/Doc/library/urlparse.rst
|
|
@@ -119,12 +119,22 @@ The :mod:`urlparse` module defines the following functions:
|
|
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, or is not a Unicode string, no error will be
|
|
+ raised.
|
|
+
|
|
.. versionchanged:: 2.5
|
|
Added attributes to return value.
|
|
|
|
.. versionchanged:: 2.7
|
|
Added IPv6 URL parsing capabilities.
|
|
|
|
+ .. versionchanged:: 2.7.17
|
|
+ Characters that affect netloc parsing under NFKC normalization will
|
|
+ now raise :exc:`ValueError`.
|
|
+
|
|
|
|
.. function:: parse_qs(qs[, keep_blank_values[, strict_parsing[, max_num_fields]]])
|
|
|
|
@@ -232,11 +242,21 @@ The :mod:`urlparse` module defines the following functions:
|
|
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, or is not a Unicode string, no error will be
|
|
+ raised.
|
|
+
|
|
.. versionadded:: 2.2
|
|
|
|
.. versionchanged:: 2.5
|
|
Added attributes to return value.
|
|
|
|
+ .. versionchanged:: 2.7.17
|
|
+ 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 4e1ded7..857ed96 100644
|
|
--- a/Lib/test/test_urlparse.py
|
|
+++ b/Lib/test/test_urlparse.py
|
|
@@ -1,4 +1,6 @@
|
|
from test import test_support
|
|
+import sys
|
|
+import unicodedata
|
|
import unittest
|
|
import urlparse
|
|
|
|
@@ -624,6 +626,36 @@ class UrlParseTestCase(unittest.TestCase):
|
|
self.assertEqual(urlparse.urlparse("http://www.python.org:80"),
|
|
('http','www.python.org:80','','','',''))
|
|
|
|
+ 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 = u'/:#?@'
|
|
+ hex_chars = {'{:04X}'.format(ord(c)) for c in illegal_chars}
|
|
+ denorm_chars = [
|
|
+ c for c in map(unichr, 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(u'\u2100', denorm_chars)
|
|
+ self.assertIn(u'\uFF03', denorm_chars)
|
|
+
|
|
+ # bpo-36742: Verify port separators are ignored when they
|
|
+ # existed prior to decomposition
|
|
+ urlparse.urlsplit(u'http://\u30d5\u309a:80')
|
|
+ with self.assertRaises(ValueError):
|
|
+ urlparse.urlsplit(u'http://\u30d5\u309a\ufe1380')
|
|
+
|
|
+ for scheme in [u"http", u"https", u"ftp"]:
|
|
+ for netloc in [u"netloc{}false.netloc", u"n{}user@netloc"]:
|
|
+ for c in denorm_chars:
|
|
+ url = u"{}://{}/path".format(scheme, netloc.format(c))
|
|
+ if test_support.verbose:
|
|
+ print "Checking %r" % url
|
|
+ with self.assertRaises(ValueError):
|
|
+ urlparse.urlsplit(url)
|
|
+
|
|
def test_main():
|
|
test_support.run_unittest(UrlParseTestCase)
|
|
|
|
diff --git a/Lib/urlparse.py b/Lib/urlparse.py
|
|
index f7c2b03..6834f3c 100644
|
|
--- a/Lib/urlparse.py
|
|
+++ b/Lib/urlparse.py
|
|
@@ -165,6 +165,24 @@ 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 isinstance(netloc, unicode):
|
|
+ return
|
|
+ # looking for characters like \u2100 that expand to 'a/c'
|
|
+ # IDNA uses NFKC equivalence, so normalize for this check
|
|
+ import unicodedata
|
|
+ n = netloc.replace(u'@', u'') # ignore characters already included
|
|
+ n = n.replace(u':', u'') # but not the surrounding text
|
|
+ n = n.replace(u'#', u'')
|
|
+ n = n.replace(u'?', u'')
|
|
+ netloc2 = unicodedata.normalize('NFKC', n)
|
|
+ if n == netloc2:
|
|
+ return
|
|
+ for c in '/?#@:':
|
|
+ if c in netloc2:
|
|
+ raise ValueError(u"netloc '" + netloc + u"' contains invalid " +
|
|
+ u"characters under NFKC normalization")
|
|
+
|
|
def urlsplit(url, scheme='', allow_fragments=True):
|
|
"""Parse a URL into 5 components:
|
|
<scheme>://<netloc>/<path>?<query>#<fragment>
|
|
@@ -193,6 +211,7 @@ 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 v
|
|
@@ -216,6 +235,7 @@ 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 v
|