main/python2: fix a few CVEs

- CVE-2018-14647
- CVE-2019-9636
- CVE-2019-9948

4 files changed, 300 insertions, 2 deletions

diff --git a/main/python2/APKBUILD b/main/python2/APKBUILD
index 79bbe4fe34..986fbf52ed 100644
--- a/main/python2/APKBUILD
+++ b/main/python2/APKBUILD
@@ -17,10 +17,18 @@ makedepends="expat-dev libressl-dev zlib-dev ncurses-dev bzip2-dev
 	gdbm-dev sqlite-dev libffi-dev readline-dev linux-headers paxmark"
 source="http://www.python.org/ftp/python/$pkgver/Python-$pkgver.tar.xz
 	musl-find_library.patch
-	unchecked-ioctl.patch"
+	unchecked-ioctl.patch
+	CVE-2018-14647.patch
+	CVE-2019-9636.patch
+	CVE-2019-9948.patch
+	"
 builddir="$srcdir/Python-$pkgver"
 
 # secfixes:
+#   2.7.15-r2:
+#     - CVE-2019-9636
+#     - CVE-2019-9948
+#     - CVE-2018-14647
 #   2.7.15-r0:
 #     - CVE-2018-1060
 #     - CVE-2018-1061
@@ -126,4 +134,7 @@ gdbm() {
 
 sha512sums="27ea43eb45fc68f3d2469d5f07636e10801dee11635a430ec8ec922ed790bb426b072da94df885e4dfa1ea8b7a24f2f56dd92f9b0f51e162330f161216bd6de6  Python-2.7.15.tar.xz
 ab8eaa2858d5109049b1f9f553198d40e0ef8d78211ad6455f7b491af525bffb16738fed60fc84e960c4889568d25753b9e4a1494834fea48291b33f07000ec2  musl-find_library.patch
-5a8e013a4132d71c4360771f130d27b37275ae59330cf9a75378dc8a11236017f540eb224f2a148984e82ca3fb6b29129375b1080ba05b81044faa717520ab82  unchecked-ioctl.patch"
+5a8e013a4132d71c4360771f130d27b37275ae59330cf9a75378dc8a11236017f540eb224f2a148984e82ca3fb6b29129375b1080ba05b81044faa717520ab82  unchecked-ioctl.patch
+6ea4cde4483250bd3ecbf46214935c80ecd79958d09d7fab4f5ba0b80d73ff0a1433f7b6fbd9a5c42d4f2a3dda877cde6a3264a5c832c1e8f4ee3eb2405a624e  CVE-2018-14647.patch
+54086e7b4d3597969b945b1460fe578ff3a13289703d58d79b8f00f644eccc4acc11fc6128b7b114f022a6f6cedc91e02eead6373bac0d36e22eb580a1becb53  CVE-2019-9636.patch
+2f9523bd3e39c4831110821d93aef1562ca80708f1b553428eb5c228cdf2192feb13d7aef41097a5df4b4243da8b8f7247f691c0ab73967b0bf2bf6a1a0d487f  CVE-2019-9948.patch"
diff --git a/main/python2/CVE-2018-14647.patch b/main/python2/CVE-2018-14647.patch
new file mode 100644
index 0000000000..ff27dba745
--- /dev/null
+++ b/main/python2/CVE-2018-14647.patch
@@ -0,0 +1,82 @@
+From 18b20bad75b4ff0486940fba4ec680e96e70f3a2 Mon Sep 17 00:00:00 2001
+From: Christian Heimes <christian@python.org>
+Date: Tue, 18 Sep 2018 15:13:09 +0200
+Subject: [PATCH] [2.7] bpo-34623: Use XML_SetHashSalt in _elementtree
+ (GH-9146) (GH-9394)
+
+The C accelerated _elementtree module now initializes hash randomization
+salt from _Py_HashSecret instead of libexpat's default CPRNG.
+
+Signed-off-by: Christian Heimes <christian@python.org>
+
+https://bugs.python.org/issue34623.
+(cherry picked from commit cb5778f00ce48631c7140f33ba242496aaf7102b)
+
+Co-authored-by: Christian Heimes <christian@python.org>
+
+
+
+https://bugs.python.org/issue34623
+---
+ Include/pyexpat.h                                            | 4 +++-
+ .../next/Security/2018-09-10-16-05-39.bpo-34623.Ua9jMv.rst   | 2 ++
+ Modules/_elementtree.c                                       | 5 +++++
+ Modules/pyexpat.c                                            | 5 +++++
+ 4 files changed, 15 insertions(+), 1 deletion(-)
+ create mode 100644 Misc/NEWS.d/next/Security/2018-09-10-16-05-39.bpo-34623.Ua9jMv.rst
+
+diff --git a/Include/pyexpat.h b/Include/pyexpat.h
+index 5340ef5fa386..3fc5fa54da63 100644
+--- a/Include/pyexpat.h
++++ b/Include/pyexpat.h
+@@ -3,7 +3,7 @@
+ 
+ /* note: you must import expat.h before importing this module! */
+ 
+-#define PyExpat_CAPI_MAGIC  "pyexpat.expat_CAPI 1.0"
++#define PyExpat_CAPI_MAGIC  "pyexpat.expat_CAPI 1.1"
+ #define PyExpat_CAPSULE_NAME "pyexpat.expat_CAPI"
+ 
+ struct PyExpat_CAPI 
+@@ -43,6 +43,8 @@ struct PyExpat_CAPI
+         XML_Parser parser, XML_UnknownEncodingHandler handler,
+         void *encodingHandlerData);
+     void (*SetUserData)(XML_Parser parser, void *userData);
++    /* might be none for expat < 2.1.0 */
++    int (*SetHashSalt)(XML_Parser parser, unsigned long hash_salt);
+     /* always add new stuff to the end! */
+ };
+ 
+diff --git a/Modules/_elementtree.c b/Modules/_elementtree.c
+index f7f992dd3a95..b38e0ab329c7 100644
+--- a/Modules/_elementtree.c
++++ b/Modules/_elementtree.c
+@@ -2574,6 +2574,11 @@ xmlparser(PyObject* self_, PyObject* args, PyObject* kw)
+         PyErr_NoMemory();
+         return NULL;
+     }
++    /* expat < 2.1.0 has no XML_SetHashSalt() */
++    if (EXPAT(SetHashSalt) != NULL) {
++        EXPAT(SetHashSalt)(self->parser,
++                           (unsigned long)_Py_HashSecret.prefix);
++    }
+ 
+     ALLOC(sizeof(XMLParserObject), "create expatparser");
+ 
+diff --git a/Modules/pyexpat.c b/Modules/pyexpat.c
+index 2b4d31293c64..1f8c0d70a559 100644
+--- a/Modules/pyexpat.c
++++ b/Modules/pyexpat.c
+@@ -2042,6 +2042,11 @@ MODULE_INITFUNC(void)
+     capi.SetProcessingInstructionHandler = XML_SetProcessingInstructionHandler;
+     capi.SetUnknownEncodingHandler = XML_SetUnknownEncodingHandler;
+     capi.SetUserData = XML_SetUserData;
++#if XML_COMBINED_VERSION >= 20100
++    capi.SetHashSalt = XML_SetHashSalt;
++#else
++    capi.SetHashSalt = NULL;
++#endif
+ 
+     /* export using capsule */
+     capi_object = PyCapsule_New(&capi, PyExpat_CAPSULE_NAME, NULL);
+
diff --git a/main/python2/CVE-2019-9636.patch b/main/python2/CVE-2019-9636.patch
new file mode 100644
index 0000000000..17a98a4196
--- /dev/null
+++ b/main/python2/CVE-2019-9636.patch
@@ -0,0 +1,155 @@
+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)
+
+---
+ 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 22249da54fbb..0989c88c3022 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 4e1ded73c266..73b0228ea8e3 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 @@ def test_portseparator(self):
+         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 f7c2b032b097..54eda08651ab 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 000000000000..1e1ad92c6feb
+--- /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
diff --git a/main/python2/CVE-2019-9948.patch b/main/python2/CVE-2019-9948.patch
new file mode 100644
index 0000000000..e5d38bd0ac
--- /dev/null
+++ b/main/python2/CVE-2019-9948.patch
@@ -0,0 +1,50 @@
+From 8f99cc799e4393bf1112b9395b2342f81b3f45ef Mon Sep 17 00:00:00 2001
+From: push0ebp <push0ebp@shl-MacBook-Pro.local>
+Date: Thu, 14 Feb 2019 02:05:46 +0900
+Subject: [PATCH] bpo-35907: Avoid file reading as disallowing the unnecessary
+ URL scheme in urllib
+
+---
+ Lib/test/test_urllib.py | 12 ++++++++++++
+ Lib/urllib.py           |  5 ++++-
+ 2 files changed, 16 insertions(+), 1 deletion(-)
+
+diff --git a/Lib/test/test_urllib.py b/Lib/test/test_urllib.py
+index 1ce9201c0693..e5f210e62a18 100644
+--- a/Lib/test/test_urllib.py
++++ b/Lib/test/test_urllib.py
+@@ -1023,6 +1023,18 @@ def open_spam(self, url):
+             "spam://c:|windows%/:=&?~#+!$,;'@()*[]|/path/"),
+             "//c:|windows%/:=&?~#+!$,;'@()*[]|/path/")
+ 
++    def test_local_file_open(self):
++        class DummyURLopener(urllib.URLopener):
++            def open_local_file(self, url):
++                return url
++        self.assertEqual(DummyURLopener().open(
++            'local-file://example'), '//example')
++        self.assertEqual(DummyURLopener().open(
++            'local_file://example'), '//example')
++        self.assertRaises(IOError, urllib.urlopen,
++            'local-file://example')
++        self.assertRaises(IOError, urllib.urlopen,
++            'local_file://example')
+ 
+ # Just commented them out.
+ # Can't really tell why keep failing in windows and sparc.
+diff --git a/Lib/urllib.py b/Lib/urllib.py
+index d85504a5cb7e..a24e9a5c68fb 100644
+--- a/Lib/urllib.py
++++ b/Lib/urllib.py
+@@ -203,7 +203,10 @@ def open(self, fullurl, data=None):
+         name = 'open_' + urltype
+         self.type = urltype
+         name = name.replace('-', '_')
+-        if not hasattr(self, name):
++        
++        # bpo-35907: # disallow the file reading with the type not allowed
++        if not hasattr(self, name) or \
++            (self == _urlopener and name == 'open_local_file'):
+             if proxy:
+                 return self.open_unknown_proxy(proxy, fullurl, data)
+             else: