--- /dev/null
+From e37ef41289b77e0f0bb9a6aedb0360664c55bdd5 Mon Sep 17 00:00:00 2001
+From: Steve Dower <steve.dower@microsoft.com>
+Date: Thu, 7 Mar 2019 09:08:45 -0800
+Subject: [PATCH] bpo-36216: Add check for characters in netloc that normalize
+ to separators (GH-12201)
+
+Signed-off-by: Peter Korsgaard <peter@korsgaard.com>
+---
+ Doc/library/urlparse.rst | 20 ++++++++++++++++++
+ Lib/test/test_urlparse.py | 24 ++++++++++++++++++++++
+ Lib/urlparse.py | 17 +++++++++++++++
+ .../2019-03-06-09-38-40.bpo-36216.6q1m4a.rst | 3 +++
+ 4 files changed, 64 insertions(+)
+ create mode 100644 Misc/NEWS.d/next/Security/2019-03-06-09-38-40.bpo-36216.6q1m4a.rst
+
+diff --git a/Doc/library/urlparse.rst b/Doc/library/urlparse.rst
+index 22249da54f..0989c88c30 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 4e1ded73c2..73b0228ea8 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 +626,28 @@ 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)
++
++ for scheme in [u"http", u"https", u"ftp"]:
++ for c in denorm_chars:
++ url = u"{}://netloc{}false.netloc/path".format(scheme, c)
++ 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 f7c2b032b0..54eda08651 100644
+--- a/Lib/urlparse.py
++++ b/Lib/urlparse.py
+@@ -165,6 +165,21 @@ 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
++ netloc2 = unicodedata.normalize('NFKC', netloc)
++ if netloc == netloc2:
++ return
++ _, _, netloc = netloc.rpartition('@') # anything to the left of '@' is okay
++ for c in '/?#@:':
++ if c in netloc2:
++ raise ValueError("netloc '" + netloc2 + "' contains invalid " +
++ "characters under NFKC normalization")
++
+ def urlsplit(url, scheme='', allow_fragments=True):
+ """Parse a URL into 5 components:
+ <scheme>://<netloc>/<path>?<query>#<fragment>
+@@ -193,6 +208,7 @@ 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 +232,7 @@ 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
+diff --git a/Misc/NEWS.d/next/Security/2019-03-06-09-38-40.bpo-36216.6q1m4a.rst b/Misc/NEWS.d/next/Security/2019-03-06-09-38-40.bpo-36216.6q1m4a.rst
+new file mode 100644
+index 0000000000..1e1ad92c6f
+--- /dev/null
++++ b/Misc/NEWS.d/next/Security/2019-03-06-09-38-40.bpo-36216.6q1m4a.rst
+@@ -0,0 +1,3 @@
++Changes urlsplit() to raise ValueError when the URL contains characters that
++decompose under IDNA encoding (NFKC-normalization) into characters that
++affect how the URL is parsed.
+\ No newline at end of file
+--
+2.11.0
+
--- /dev/null
+From 507bd8cde60ced74d13a1ffa883bb9b0e73c38be Mon Sep 17 00:00:00 2001
+From: Steve Dower <steve.dower@microsoft.com>
+Date: Tue, 12 Mar 2019 13:51:58 -0700
+Subject: [PATCH] [3.7] bpo-36216: Only print test messages when verbose
+ (GH-12291)
+
+Signed-off-by: Peter Korsgaard <peter@korsgaard.com>
+---
+ Lib/test/test_urlparse.py | 3 ++-
+ 1 file changed, 2 insertions(+), 1 deletion(-)
+
+diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
+index 73b0228ea8..1830d0b286 100644
+--- a/Lib/test/test_urlparse.py
++++ b/Lib/test/test_urlparse.py
+@@ -644,7 +644,8 @@ class UrlParseTestCase(unittest.TestCase):
+ for scheme in [u"http", u"https", u"ftp"]:
+ for c in denorm_chars:
+ url = u"{}://netloc{}false.netloc/path".format(scheme, c)
+- print "Checking %r" % url
++ if test_support.verbose:
++ print "Checking %r" % url
+ with self.assertRaises(ValueError):
+ urlparse.urlsplit(url)
+
+--
+2.11.0
+
--- /dev/null
+From 98a4dcefbbc3bce5ab07e7c0830a183157250259 Mon Sep 17 00:00:00 2001
+From: Steve Dower <steve.dower@python.org>
+Date: Wed, 1 May 2019 15:00:27 +0000
+Subject: [PATCH] bpo-36742: Fixes handling of pre-normalization characters in
+ urlsplit() (GH-13017)
+
+Signed-off-by: Peter Korsgaard <peter@korsgaard.com>
+---
+ Lib/test/test_urlparse.py | 6 ++++++
+ Lib/urlparse.py | 11 +++++++----
+ .../next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst | 1 +
+ 3 files changed, 14 insertions(+), 4 deletions(-)
+ create mode 100644 Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst
+
+diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
+index 1830d0b286..6fd1071bf7 100644
+--- a/Lib/test/test_urlparse.py
++++ b/Lib/test/test_urlparse.py
+@@ -641,6 +641,12 @@ class UrlParseTestCase(unittest.TestCase):
+ 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 c in denorm_chars:
+ url = u"{}://netloc{}false.netloc/path".format(scheme, c)
+diff --git a/Lib/urlparse.py b/Lib/urlparse.py
+index 54eda08651..f08e0fe584 100644
+--- a/Lib/urlparse.py
++++ b/Lib/urlparse.py
+@@ -171,13 +171,16 @@ def _checknetloc(netloc):
+ # looking for characters like \u2100 that expand to 'a/c'
+ # IDNA uses NFKC equivalence, so normalize for this check
+ import unicodedata
+- netloc2 = unicodedata.normalize('NFKC', netloc)
+- if netloc == netloc2:
++ 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
+- _, _, netloc = netloc.rpartition('@') # anything to the left of '@' is okay
+ for c in '/?#@:':
+ if c in netloc2:
+- raise ValueError("netloc '" + netloc2 + "' contains invalid " +
++ raise ValueError("netloc '" + netloc + "' contains invalid " +
+ "characters under NFKC normalization")
+
+ def urlsplit(url, scheme='', allow_fragments=True):
+diff --git a/Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst b/Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst
+new file mode 100644
+index 0000000000..d729ed2f3c
+--- /dev/null
++++ b/Misc/NEWS.d/next/Security/2019-04-29-15-34-59.bpo-36742.QCUY0i.rst
+@@ -0,0 +1 @@
++Fixes mishandling of pre-normalization characters in urlsplit().
+--
+2.11.0
+
--- /dev/null
+From f61599b050c621386a3fc6bc480359e2d3bb93de Mon Sep 17 00:00:00 2001
+From: Steve Dower <steve.dower@python.org>
+Date: Tue, 4 Jun 2019 09:40:16 -0700
+Subject: [PATCH] bpo-36742: Corrects fix to handle decomposition in usernames
+ (GH-13812)
+
+Signed-off-by: Peter Korsgaard <peter@korsgaard.com>
+---
+ Lib/test/test_urlparse.py | 13 +++++++------
+ Lib/urlparse.py | 12 ++++++------
+ 2 files changed, 13 insertions(+), 12 deletions(-)
+
+diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
+index 6fd1071bf7..857ed96d92 100644
+--- a/Lib/test/test_urlparse.py
++++ b/Lib/test/test_urlparse.py
+@@ -648,12 +648,13 @@ class UrlParseTestCase(unittest.TestCase):
+ urlparse.urlsplit(u'http://\u30d5\u309a\ufe1380')
+
+ for scheme in [u"http", u"https", u"ftp"]:
+- for c in denorm_chars:
+- url = u"{}://netloc{}false.netloc/path".format(scheme, c)
+- if test_support.verbose:
+- print "Checking %r" % url
+- with self.assertRaises(ValueError):
+- urlparse.urlsplit(url)
++ 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 f08e0fe584..6834f3c179 100644
+--- a/Lib/urlparse.py
++++ b/Lib/urlparse.py
+@@ -171,17 +171,17 @@ def _checknetloc(netloc):
+ # 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('?', '')
++ 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("netloc '" + netloc + "' contains invalid " +
+- "characters under NFKC normalization")
++ 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:
+--
+2.11.0
+
--- /dev/null
+From 2b578479b96aa3deeeb8bac313a02b5cf3cb1aff Mon Sep 17 00:00:00 2001
+From: Victor Stinner <vstinner@redhat.com>
+Date: Tue, 11 Jun 2019 12:45:35 +0200
+Subject: [PATCH] [2.7] bpo-36742: Fix urlparse.urlsplit() error message for
+ Unicode URL (GH-13937)
+
+If urlparse.urlsplit() detects an invalid netloc according to NFKC
+normalization, the error message type is now str rather than unicode,
+and use repr() to format the URL, to prevent <exception str() failed>
+when display the error message.
+
+Signed-off-by: Peter Korsgaard <peter@korsgaard.com>
+---
+ Lib/test/test_urlparse.py | 9 +++++++++
+ Lib/urlparse.py | 5 +++--
+ .../NEWS.d/next/Library/2019-06-10-12-02-45.bpo-36742.UEdHXJ.rst | 3 +++
+ 3 files changed, 15 insertions(+), 2 deletions(-)
+ create mode 100644 Misc/NEWS.d/next/Library/2019-06-10-12-02-45.bpo-36742.UEdHXJ.rst
+
+diff --git a/Lib/test/test_urlparse.py b/Lib/test/test_urlparse.py
+index 857ed96d92..86c4a0595c 100644
+--- a/Lib/test/test_urlparse.py
++++ b/Lib/test/test_urlparse.py
+@@ -656,6 +656,15 @@ class UrlParseTestCase(unittest.TestCase):
+ with self.assertRaises(ValueError):
+ urlparse.urlsplit(url)
+
++ # check error message: invalid netloc must be formated with repr()
++ # to get an ASCII error message
++ with self.assertRaises(ValueError) as cm:
++ urlparse.urlsplit(u'http://example.com\uFF03@bing.com')
++ self.assertEqual(str(cm.exception),
++ "netloc u'example.com\\uff03@bing.com' contains invalid characters "
++ "under NFKC normalization")
++ self.assertIsInstance(cm.exception.args[0], str)
++
+ def test_main():
+ test_support.run_unittest(UrlParseTestCase)
+
+diff --git a/Lib/urlparse.py b/Lib/urlparse.py
+index 6834f3c179..798b467b60 100644
+--- a/Lib/urlparse.py
++++ b/Lib/urlparse.py
+@@ -180,8 +180,9 @@ def _checknetloc(netloc):
+ return
+ for c in '/?#@:':
+ if c in netloc2:
+- raise ValueError(u"netloc '" + netloc + u"' contains invalid " +
+- u"characters under NFKC normalization")
++ raise ValueError("netloc %r contains invalid characters "
++ "under NFKC normalization"
++ % netloc)
+
+ def urlsplit(url, scheme='', allow_fragments=True):
+ """Parse a URL into 5 components:
+diff --git a/Misc/NEWS.d/next/Library/2019-06-10-12-02-45.bpo-36742.UEdHXJ.rst b/Misc/NEWS.d/next/Library/2019-06-10-12-02-45.bpo-36742.UEdHXJ.rst
+new file mode 100644
+index 0000000000..3ba774056f
+--- /dev/null
++++ b/Misc/NEWS.d/next/Library/2019-06-10-12-02-45.bpo-36742.UEdHXJ.rst
+@@ -0,0 +1,3 @@
++:func:`urlparse.urlsplit` error message for invalid ``netloc`` according to
++NFKC normalization is now a :class:`str` string, rather than a
++:class:`unicode` string, to prevent error when displaying the error.
+--
+2.11.0
+
projects / buildroot.git / commitdiff