From a3be5cfa92133fe79006f8b19b7606f4fbb64c57 Mon Sep 17 00:00:00 2001
From: Jeffery To <jeffery.to@gmail.com>
Date: Fri, 4 Oct 2019 23:54:46 +0800
Subject: [PATCH] python,python3: Fix CVE-2019-16056, CVE-2019-16935

These patches address issues:
CVE-2019-16056: email.utils.parseaddr mistakenly parse an email
CVE-2019-16935: A reflected XSS in python/Lib/DocXMLRPCServer.py (for
Python 2.7)

CVE-2019-16935 was fixed for python3 in #10109

Links to Python issues:
https://bugs.python.org/issue34155
https://bugs.python.org/issue38243

Signed-off-by: Jeffery To <jeffery.to@gmail.com>
---
 lang/python/python/Makefile                   |   2 +-
 ...-the-server-title-of-DocXMLRPCServer.patch | 159 ++++++++++++++++++
 ...nt-parse-domains-containing-GH-13079.patch |  80 +++++++++
 lang/python/python3/Makefile                  |   2 +-
 ...nt-parse-domains-containing-GH-13079.patch | 129 ++++++++++++++
 5 files changed, 370 insertions(+), 2 deletions(-)
 create mode 100644 lang/python/python/patches/027-bpo-38243-Escape-the-server-title-of-DocXMLRPCServer.patch
 create mode 100644 lang/python/python/patches/028-bpo-34155-Dont-parse-domains-containing-GH-13079.patch
 create mode 100644 lang/python/python3/patches/028-bpo-34155-Dont-parse-domains-containing-GH-13079.patch

diff --git a/lang/python/python/Makefile b/lang/python/python/Makefile
index a52e4a122..3a0ff994f 100644
--- a/lang/python/python/Makefile
+++ b/lang/python/python/Makefile
@@ -12,7 +12,7 @@ include ../python-version.mk
 
 PKG_NAME:=python
 PKG_VERSION:=$(PYTHON_VERSION).$(PYTHON_VERSION_MICRO)
-PKG_RELEASE:=10
+PKG_RELEASE:=11
 
 PKG_SOURCE:=Python-$(PKG_VERSION).tar.xz
 PKG_SOURCE_URL:=https://www.python.org/ftp/python/$(PKG_VERSION)
diff --git a/lang/python/python/patches/027-bpo-38243-Escape-the-server-title-of-DocXMLRPCServer.patch b/lang/python/python/patches/027-bpo-38243-Escape-the-server-title-of-DocXMLRPCServer.patch
new file mode 100644
index 000000000..5b90eb9d8
--- /dev/null
+++ b/lang/python/python/patches/027-bpo-38243-Escape-the-server-title-of-DocXMLRPCServer.patch
@@ -0,0 +1,159 @@
+From b41cde823d026f2adc21ef14b1c2e92b1006de06 Mon Sep 17 00:00:00 2001
+From: Dong-hee Na <donghee.na92@gmail.com>
+Date: Sat, 28 Sep 2019 10:17:25 +0900
+Subject: [PATCH 1/3] [2.7] bpo-38243: Escape the server title of
+ DocXMLRPCServer when rendering
+
+---
+ Lib/DocXMLRPCServer.py                        | 10 +++++++++-
+ Lib/test/test_docxmlrpc.py                    | 20 +++++++++++++++++++
+ .../2019-09-25-13-21-09.bpo-38243.1pfz24.rst  |  3 +++
+ 3 files changed, 32 insertions(+), 1 deletion(-)
+ create mode 100644 Misc/NEWS.d/next/Security/2019-09-25-13-21-09.bpo-38243.1pfz24.rst
+
+diff --git a/Lib/DocXMLRPCServer.py b/Lib/DocXMLRPCServer.py
+index 4064ec2e48d4d..a0e407b6318ad 100644
+--- a/Lib/DocXMLRPCServer.py
++++ b/Lib/DocXMLRPCServer.py
+@@ -210,7 +210,15 @@ def generate_html_documentation(self):
+                                 methods
+                             )
+ 
+-        return documenter.page(self.server_title, documentation)
++        escape_table = {
++            "&": "&amp;",
++            '"': "&quot;",
++            "'": "&#x27;",
++            ">": "&gt;",
++            "<": "&lt;",
++        }
++        title = ''.join(escape_table.get(c, c) for c in self.server_title)
++        return documenter.page(title, documentation)
+ 
+ class DocXMLRPCRequestHandler(SimpleXMLRPCRequestHandler):
+     """XML-RPC and documentation request handler class.
+diff --git a/Lib/test/test_docxmlrpc.py b/Lib/test/test_docxmlrpc.py
+index 4dff4159e2466..c45b892b8b3e7 100644
+--- a/Lib/test/test_docxmlrpc.py
++++ b/Lib/test/test_docxmlrpc.py
+@@ -1,5 +1,6 @@
+ from DocXMLRPCServer import DocXMLRPCServer
+ import httplib
++import re
+ import sys
+ from test import test_support
+ threading = test_support.import_module('threading')
+@@ -176,6 +177,25 @@ def test_autolink_dotted_methods(self):
+         self.assertIn("""Try&nbsp;self.<strong>add</strong>,&nbsp;too.""",
+                       response.read())
+ 
++    def test_server_title_escape(self):
++        """Test that the server title and documentation
++        are escaped for HTML.
++        """
++        self.serv.set_server_title('test_title<script>')
++        self.serv.set_server_documentation('test_documentation<script>')
++        self.assertEqual('test_title<script>', self.serv.server_title)
++        self.assertEqual('test_documentation<script>',
++                self.serv.server_documentation)
++
++        generated = self.serv.generate_html_documentation()
++        title = re.search(r'<title>(.+?)</title>', generated).group()
++        documentation = re.search(r'<p><tt>(.+?)</tt></p>', generated).group()
++        self.assertEqual('<title>Python: test_title&lt;script&gt;</title>',
++                title)
++        self.assertEqual('<p><tt>test_documentation&lt;script&gt;</tt></p>',
++                documentation)
++
++
+ def test_main():
+     test_support.run_unittest(DocXMLRPCHTTPGETServer)
+ 
+diff --git a/Misc/NEWS.d/next/Security/2019-09-25-13-21-09.bpo-38243.1pfz24.rst b/Misc/NEWS.d/next/Security/2019-09-25-13-21-09.bpo-38243.1pfz24.rst
+new file mode 100644
+index 0000000000000..8f02baed9ebe5
+--- /dev/null
++++ b/Misc/NEWS.d/next/Security/2019-09-25-13-21-09.bpo-38243.1pfz24.rst
+@@ -0,0 +1,3 @@
++Escape the server title of :class:`DocXMLRPCServer.DocXMLRPCServer`
++when rendering the document page as HTML.
++(Contributed by Dong-hee Na in :issue:`38243`.)
+
+From 00251ae0244cfae1f5a77d15f3d0415c12b65ada Mon Sep 17 00:00:00 2001
+From: Dong-hee Na <donghee.na92@gmail.com>
+Date: Tue, 1 Oct 2019 09:31:33 +0900
+Subject: [PATCH 2/3] bpo-38243:Refect victor's review
+
+---
+ Lib/DocXMLRPCServer.py | 20 ++++++++++++--------
+ 1 file changed, 12 insertions(+), 8 deletions(-)
+
+diff --git a/Lib/DocXMLRPCServer.py b/Lib/DocXMLRPCServer.py
+index a0e407b6318ad..6ab41c31b403e 100644
+--- a/Lib/DocXMLRPCServer.py
++++ b/Lib/DocXMLRPCServer.py
+@@ -20,6 +20,17 @@
+             CGIXMLRPCRequestHandler,
+             resolve_dotted_attribute)
+ 
++
++def _html_escape_quote(s, quote=True):
++    s = s.replace("&", "&amp;") # Must be done first!
++    s = s.replace("<", "&lt;")
++    s = s.replace(">", "&gt;")
++    if quote:
++        s = s.replace('"', "&quot;")
++        s = s.replace('\'', "&#x27;")
++    return s
++
++
+ class ServerHTMLDoc(pydoc.HTMLDoc):
+     """Class used to generate pydoc HTML document for a server"""
+ 
+@@ -210,14 +221,7 @@ def generate_html_documentation(self):
+                                 methods
+                             )
+ 
+-        escape_table = {
+-            "&": "&amp;",
+-            '"': "&quot;",
+-            "'": "&#x27;",
+-            ">": "&gt;",
+-            "<": "&lt;",
+-        }
+-        title = ''.join(escape_table.get(c, c) for c in self.server_title)
++        title = _html_escape_quote(self.server_title)
+         return documenter.page(title, documentation)
+ 
+ class DocXMLRPCRequestHandler(SimpleXMLRPCRequestHandler):
+
+From 09b17d8230a24586e417d52c332058f541d47999 Mon Sep 17 00:00:00 2001
+From: Dong-hee Na <donghee.na92@gmail.com>
+Date: Tue, 1 Oct 2019 19:35:34 +0900
+Subject: [PATCH 3/3] bpo-38243: Update
+
+---
+ Lib/DocXMLRPCServer.py | 7 +++----
+ 1 file changed, 3 insertions(+), 4 deletions(-)
+
+diff --git a/Lib/DocXMLRPCServer.py b/Lib/DocXMLRPCServer.py
+index 6ab41c31b403e..90b037dd35d6b 100644
+--- a/Lib/DocXMLRPCServer.py
++++ b/Lib/DocXMLRPCServer.py
+@@ -21,13 +21,12 @@
+             resolve_dotted_attribute)
+ 
+ 
+-def _html_escape_quote(s, quote=True):
++def _html_escape_quote(s):
+     s = s.replace("&", "&amp;") # Must be done first!
+     s = s.replace("<", "&lt;")
+     s = s.replace(">", "&gt;")
+-    if quote:
+-        s = s.replace('"', "&quot;")
+-        s = s.replace('\'', "&#x27;")
++    s = s.replace('"', "&quot;")
++    s = s.replace('\'', "&#x27;")
+     return s
+ 
+ 
diff --git a/lang/python/python/patches/028-bpo-34155-Dont-parse-domains-containing-GH-13079.patch b/lang/python/python/patches/028-bpo-34155-Dont-parse-domains-containing-GH-13079.patch
new file mode 100644
index 000000000..0be3e4e95
--- /dev/null
+++ b/lang/python/python/patches/028-bpo-34155-Dont-parse-domains-containing-GH-13079.patch
@@ -0,0 +1,80 @@
+From c2828900ec85e1e2957016e1e078de3a9677a963 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Roberto=20C=2E=20S=C3=A1nchez?= <roberto@connexer.com>
+Date: Tue, 10 Sep 2019 21:48:34 -0400
+Subject: [PATCH] [2.7] bpo-34155: Dont parse domains containing @ (GH-13079)
+
+https://bugs.python.org/issue34155
+(cherry picked from commit 8cb65d1381b027f0b09ee36bfed7f35bb4dec9a9)
+
+Excludes changes to Lib/email/_header_value_parser.py, which did not
+exist in 2.7.
+
+Co-authored-by: jpic <jpic@users.noreply.github.com>
+---
+ Lib/email/_parseaddr.py                            | 11 ++++++++++-
+ Lib/email/test/test_email.py                       | 14 ++++++++++++++
+ .../2019-05-04-13-33-37.bpo-34155.MJll68.rst       |  1 +
+ 3 files changed, 25 insertions(+), 1 deletion(-)
+ create mode 100644 Misc/NEWS.d/next/Security/2019-05-04-13-33-37.bpo-34155.MJll68.rst
+
+diff --git a/Lib/email/_parseaddr.py b/Lib/email/_parseaddr.py
+index 690db2c22d34d..dc49d2e45a5eb 100644
+--- a/Lib/email/_parseaddr.py
++++ b/Lib/email/_parseaddr.py
+@@ -336,7 +336,12 @@ def getaddrspec(self):
+         aslist.append('@')
+         self.pos += 1
+         self.gotonext()
+-        return EMPTYSTRING.join(aslist) + self.getdomain()
++        domain = self.getdomain()
++        if not domain:
++            # Invalid domain, return an empty address instead of returning a
++            # local part to denote failed parsing.
++            return EMPTYSTRING
++        return EMPTYSTRING.join(aslist) + domain
+ 
+     def getdomain(self):
+         """Get the complete domain name from an address."""
+@@ -351,6 +356,10 @@ def getdomain(self):
+             elif self.field[self.pos] == '.':
+                 self.pos += 1
+                 sdlist.append('.')
++            elif self.field[self.pos] == '@':
++                # bpo-34155: Don't parse domains with two `@` like
++                # `a@malicious.org@important.com`.
++                return EMPTYSTRING
+             elif self.field[self.pos] in self.atomends:
+                 break
+             else:
+diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py
+index 4b4dee3d34644..2efe44ac5a73f 100644
+--- a/Lib/email/test/test_email.py
++++ b/Lib/email/test/test_email.py
+@@ -2306,6 +2306,20 @@ def test_parseaddr_empty(self):
+         self.assertEqual(Utils.parseaddr('<>'), ('', ''))
+         self.assertEqual(Utils.formataddr(Utils.parseaddr('<>')), '')
+ 
++    def test_parseaddr_multiple_domains(self):
++        self.assertEqual(
++            Utils.parseaddr('a@b@c'),
++            ('', '')
++        )
++        self.assertEqual(
++            Utils.parseaddr('a@b.c@c'),
++            ('', '')
++        )
++        self.assertEqual(
++            Utils.parseaddr('a@172.17.0.1@c'),
++            ('', '')
++        )
++
+     def test_noquote_dump(self):
+         self.assertEqual(
+             Utils.formataddr(('A Silly Person', 'person@dom.ain')),
+diff --git a/Misc/NEWS.d/next/Security/2019-05-04-13-33-37.bpo-34155.MJll68.rst b/Misc/NEWS.d/next/Security/2019-05-04-13-33-37.bpo-34155.MJll68.rst
+new file mode 100644
+index 0000000000000..50292e29ed1d2
+--- /dev/null
++++ b/Misc/NEWS.d/next/Security/2019-05-04-13-33-37.bpo-34155.MJll68.rst
+@@ -0,0 +1 @@
++Fix parsing of invalid email addresses with more than one ``@`` (e.g. a@b@c.com.) to not return the part before 2nd ``@`` as valid email address. Patch by maxking & jpic.
diff --git a/lang/python/python3/Makefile b/lang/python/python3/Makefile
index 5d809f79a..10842f12c 100644
--- a/lang/python/python3/Makefile
+++ b/lang/python/python3/Makefile
@@ -14,7 +14,7 @@ PYTHON_VERSION:=$(PYTHON3_VERSION)
 PYTHON_VERSION_MICRO:=$(PYTHON3_VERSION_MICRO)
 
 PKG_NAME:=python3
-PKG_RELEASE:=4
+PKG_RELEASE:=5
 PKG_VERSION:=$(PYTHON_VERSION).$(PYTHON_VERSION_MICRO)
 
 PKG_SOURCE:=Python-$(PKG_VERSION).tar.xz
diff --git a/lang/python/python3/patches/028-bpo-34155-Dont-parse-domains-containing-GH-13079.patch b/lang/python/python3/patches/028-bpo-34155-Dont-parse-domains-containing-GH-13079.patch
new file mode 100644
index 000000000..917c74f2b
--- /dev/null
+++ b/lang/python/python3/patches/028-bpo-34155-Dont-parse-domains-containing-GH-13079.patch
@@ -0,0 +1,129 @@
+From 77bb21f6e06aabc81d672dbdd6f8834c40544351 Mon Sep 17 00:00:00 2001
+From: jpic <jpic@users.noreply.github.com>
+Date: Wed, 17 Jul 2019 23:54:25 +0200
+Subject: [PATCH] bpo-34155: Dont parse domains containing @ (GH-13079)
+
+Before:
+
+        >>> email.message_from_string('From: a@malicious.org@important.com', policy=email.policy.default)['from'].addresses
+        (Address(display_name='', username='a', domain='malicious.org'),)
+
+        >>> parseaddr('a@malicious.org@important.com')
+        ('', 'a@malicious.org')
+
+    After:
+
+        >>> email.message_from_string('From: a@malicious.org@important.com', policy=email.policy.default)['from'].addresses
+        (Address(display_name='', username='', domain=''),)
+
+        >>> parseaddr('a@malicious.org@important.com')
+        ('', 'a@')
+
+https://bugs.python.org/issue34155
+(cherry picked from commit 8cb65d1381b027f0b09ee36bfed7f35bb4dec9a9)
+
+Co-authored-by: jpic <jpic@users.noreply.github.com>
+---
+ Lib/email/_header_value_parser.py                  |  2 ++
+ Lib/email/_parseaddr.py                            | 11 ++++++++++-
+ Lib/test/test_email/test__header_value_parser.py   | 10 ++++++++++
+ Lib/test/test_email/test_email.py                  | 14 ++++++++++++++
+ .../2019-05-04-13-33-37.bpo-34155.MJll68.rst       |  1 +
+ 5 files changed, 37 insertions(+), 1 deletion(-)
+ create mode 100644 Misc/NEWS.d/next/Security/2019-05-04-13-33-37.bpo-34155.MJll68.rst
+
+diff --git a/Lib/email/_header_value_parser.py b/Lib/email/_header_value_parser.py
+index 801ae728dd136..c09f4f121ffb6 100644
+--- a/Lib/email/_header_value_parser.py
++++ b/Lib/email/_header_value_parser.py
+@@ -1585,6 +1585,8 @@ def get_domain(value):
+         token, value = get_dot_atom(value)
+     except errors.HeaderParseError:
+         token, value = get_atom(value)
++    if value and value[0] == '@':
++        raise errors.HeaderParseError('Invalid Domain')
+     if leader is not None:
+         token[:0] = [leader]
+     domain.append(token)
+diff --git a/Lib/email/_parseaddr.py b/Lib/email/_parseaddr.py
+index cdfa3729adc79..41ff6f8c000d5 100644
+--- a/Lib/email/_parseaddr.py
++++ b/Lib/email/_parseaddr.py
+@@ -379,7 +379,12 @@ def getaddrspec(self):
+         aslist.append('@')
+         self.pos += 1
+         self.gotonext()
+-        return EMPTYSTRING.join(aslist) + self.getdomain()
++        domain = self.getdomain()
++        if not domain:
++            # Invalid domain, return an empty address instead of returning a
++            # local part to denote failed parsing.
++            return EMPTYSTRING
++        return EMPTYSTRING.join(aslist) + domain
+ 
+     def getdomain(self):
+         """Get the complete domain name from an address."""
+@@ -394,6 +399,10 @@ def getdomain(self):
+             elif self.field[self.pos] == '.':
+                 self.pos += 1
+                 sdlist.append('.')
++            elif self.field[self.pos] == '@':
++                # bpo-34155: Don't parse domains with two `@` like
++                # `a@malicious.org@important.com`.
++                return EMPTYSTRING
+             elif self.field[self.pos] in self.atomends:
+                 break
+             else:
+diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py
+index 9e862feab10c9..0f19f8bcc2e0f 100644
+--- a/Lib/test/test_email/test__header_value_parser.py
++++ b/Lib/test/test_email/test__header_value_parser.py
+@@ -1448,6 +1448,16 @@ def test_get_addr_spec_dot_atom(self):
+         self.assertEqual(addr_spec.domain, 'example.com')
+         self.assertEqual(addr_spec.addr_spec, 'star.a.star@example.com')
+ 
++    def test_get_addr_spec_multiple_domains(self):
++        with self.assertRaises(errors.HeaderParseError):
++            parser.get_addr_spec('star@a.star@example.com')
++
++        with self.assertRaises(errors.HeaderParseError):
++            parser.get_addr_spec('star@a@example.com')
++
++        with self.assertRaises(errors.HeaderParseError):
++            parser.get_addr_spec('star@172.17.0.1@example.com')
++
+     # get_obs_route
+ 
+     def test_get_obs_route_simple(self):
+diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
+index c29cc56203b1f..aa775881c5521 100644
+--- a/Lib/test/test_email/test_email.py
++++ b/Lib/test/test_email/test_email.py
+@@ -3041,6 +3041,20 @@ def test_parseaddr_empty(self):
+         self.assertEqual(utils.parseaddr('<>'), ('', ''))
+         self.assertEqual(utils.formataddr(utils.parseaddr('<>')), '')
+ 
++    def test_parseaddr_multiple_domains(self):
++        self.assertEqual(
++            utils.parseaddr('a@b@c'),
++            ('', '')
++        )
++        self.assertEqual(
++            utils.parseaddr('a@b.c@c'),
++            ('', '')
++        )
++        self.assertEqual(
++            utils.parseaddr('a@172.17.0.1@c'),
++            ('', '')
++        )
++
+     def test_noquote_dump(self):
+         self.assertEqual(
+             utils.formataddr(('A Silly Person', 'person@dom.ain')),
+diff --git a/Misc/NEWS.d/next/Security/2019-05-04-13-33-37.bpo-34155.MJll68.rst b/Misc/NEWS.d/next/Security/2019-05-04-13-33-37.bpo-34155.MJll68.rst
+new file mode 100644
+index 0000000000000..50292e29ed1d2
+--- /dev/null
++++ b/Misc/NEWS.d/next/Security/2019-05-04-13-33-37.bpo-34155.MJll68.rst
+@@ -0,0 +1 @@
++Fix parsing of invalid email addresses with more than one ``@`` (e.g. a@b@c.com.) to not return the part before 2nd ``@`` as valid email address. Patch by maxking & jpic.