python3.11/00415-cve-2023-27043-gh-102988-reject-malformed-addresses-in-email-parseaddr-111116.patch
Lumir Balhar fec299bb84 Security fix for CVE-2023-27043
Resolves: RHEL-7842
2024-01-12 23:42:50 +01:00

752 lines
28 KiB
Diff

From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
From: Victor Stinner <vstinner@python.org>
Date: Fri, 15 Dec 2023 16:10:40 +0100
Subject: [PATCH] 00415: [CVE-2023-27043] gh-102988: Reject malformed addresses
in email.parseaddr() (#111116)
Detect email address parsing errors and return empty tuple to
indicate the parsing error (old API). Add an optional 'strict'
parameter to getaddresses() and parseaddr() functions. Patch by
Thomas Dwyer.
Co-Authored-By: Thomas Dwyer <github@tomd.tel>
---
Doc/library/email.utils.rst | 19 +-
Lib/email/utils.py | 151 ++++++++++++-
Lib/test/test_email/test_email.py | 204 +++++++++++++++++-
...-10-20-15-28-08.gh-issue-102988.dStNO7.rst | 8 +
4 files changed, 361 insertions(+), 21 deletions(-)
create mode 100644 Misc/NEWS.d/next/Library/2023-10-20-15-28-08.gh-issue-102988.dStNO7.rst
diff --git a/Doc/library/email.utils.rst b/Doc/library/email.utils.rst
index 0e266b6a45..6723dc4f13 100644
--- a/Doc/library/email.utils.rst
+++ b/Doc/library/email.utils.rst
@@ -60,13 +60,18 @@ of the new API.
begins with angle brackets, they are stripped off.
-.. function:: parseaddr(address)
+.. function:: parseaddr(address, *, strict=True)
Parse address -- which should be the value of some address-containing field such
as :mailheader:`To` or :mailheader:`Cc` -- into its constituent *realname* and
*email address* parts. Returns a tuple of that information, unless the parse
fails, in which case a 2-tuple of ``('', '')`` is returned.
+ If *strict* is true, use a strict parser which rejects malformed inputs.
+
+ .. versionchanged:: 3.13
+ Add *strict* optional parameter and reject malformed inputs by default.
+
.. function:: formataddr(pair, charset='utf-8')
@@ -84,12 +89,15 @@ of the new API.
Added the *charset* option.
-.. function:: getaddresses(fieldvalues)
+.. function:: getaddresses(fieldvalues, *, strict=True)
This method returns a list of 2-tuples of the form returned by ``parseaddr()``.
*fieldvalues* is a sequence of header field values as might be returned by
- :meth:`Message.get_all <email.message.Message.get_all>`. Here's a simple
- example that gets all the recipients of a message::
+ :meth:`Message.get_all <email.message.Message.get_all>`.
+
+ If *strict* is true, use a strict parser which rejects malformed inputs.
+
+ Here's a simple example that gets all the recipients of a message::
from email.utils import getaddresses
@@ -99,6 +107,9 @@ of the new API.
resent_ccs = msg.get_all('resent-cc', [])
all_recipients = getaddresses(tos + ccs + resent_tos + resent_ccs)
+ .. versionchanged:: 3.13
+ Add *strict* optional parameter and reject malformed inputs by default.
+
.. function:: parsedate(date)
diff --git a/Lib/email/utils.py b/Lib/email/utils.py
index cfdfeb3f1a..9522341fab 100644
--- a/Lib/email/utils.py
+++ b/Lib/email/utils.py
@@ -48,6 +48,7 @@
specialsre = re.compile(r'[][\\()<>@,:;".]')
escapesre = re.compile(r'[\\"]')
+
def _has_surrogates(s):
"""Return True if s contains surrogate-escaped binary data."""
# This check is based on the fact that unless there are surrogates, utf8
@@ -106,12 +107,127 @@ def formataddr(pair, charset='utf-8'):
return address
+def _iter_escaped_chars(addr):
+ pos = 0
+ escape = False
+ for pos, ch in enumerate(addr):
+ if escape:
+ yield (pos, '\\' + ch)
+ escape = False
+ elif ch == '\\':
+ escape = True
+ else:
+ yield (pos, ch)
+ if escape:
+ yield (pos, '\\')
-def getaddresses(fieldvalues):
- """Return a list of (REALNAME, EMAIL) for each fieldvalue."""
- all = COMMASPACE.join(str(v) for v in fieldvalues)
- a = _AddressList(all)
- return a.addresslist
+
+def _strip_quoted_realnames(addr):
+ """Strip real names between quotes."""
+ if '"' not in addr:
+ # Fast path
+ return addr
+
+ start = 0
+ open_pos = None
+ result = []
+ for pos, ch in _iter_escaped_chars(addr):
+ if ch == '"':
+ if open_pos is None:
+ open_pos = pos
+ else:
+ if start != open_pos:
+ result.append(addr[start:open_pos])
+ start = pos + 1
+ open_pos = None
+
+ if start < len(addr):
+ result.append(addr[start:])
+
+ return ''.join(result)
+
+
+supports_strict_parsing = True
+
+def getaddresses(fieldvalues, *, strict=True):
+ """Return a list of (REALNAME, EMAIL) or ('','') for each fieldvalue.
+
+ When parsing fails for a fieldvalue, a 2-tuple of ('', '') is returned in
+ its place.
+
+ If strict is true, use a strict parser which rejects malformed inputs.
+ """
+
+ # If strict is true, if the resulting list of parsed addresses is greater
+ # than the number of fieldvalues in the input list, a parsing error has
+ # occurred and consequently a list containing a single empty 2-tuple [('',
+ # '')] is returned in its place. This is done to avoid invalid output.
+ #
+ # Malformed input: getaddresses(['alice@example.com <bob@example.com>'])
+ # Invalid output: [('', 'alice@example.com'), ('', 'bob@example.com')]
+ # Safe output: [('', '')]
+
+ if not strict:
+ all = COMMASPACE.join(str(v) for v in fieldvalues)
+ a = _AddressList(all)
+ return a.addresslist
+
+ fieldvalues = [str(v) for v in fieldvalues]
+ fieldvalues = _pre_parse_validation(fieldvalues)
+ addr = COMMASPACE.join(fieldvalues)
+ a = _AddressList(addr)
+ result = _post_parse_validation(a.addresslist)
+
+ # Treat output as invalid if the number of addresses is not equal to the
+ # expected number of addresses.
+ n = 0
+ for v in fieldvalues:
+ # When a comma is used in the Real Name part it is not a deliminator.
+ # So strip those out before counting the commas.
+ v = _strip_quoted_realnames(v)
+ # Expected number of addresses: 1 + number of commas
+ n += 1 + v.count(',')
+ if len(result) != n:
+ return [('', '')]
+
+ return result
+
+
+def _check_parenthesis(addr):
+ # Ignore parenthesis in quoted real names.
+ addr = _strip_quoted_realnames(addr)
+
+ opens = 0
+ for pos, ch in _iter_escaped_chars(addr):
+ if ch == '(':
+ opens += 1
+ elif ch == ')':
+ opens -= 1
+ if opens < 0:
+ return False
+ return (opens == 0)
+
+
+def _pre_parse_validation(email_header_fields):
+ accepted_values = []
+ for v in email_header_fields:
+ if not _check_parenthesis(v):
+ v = "('', '')"
+ accepted_values.append(v)
+
+ return accepted_values
+
+
+def _post_parse_validation(parsed_email_header_tuples):
+ accepted_values = []
+ # The parser would have parsed a correctly formatted domain-literal
+ # The existence of an [ after parsing indicates a parsing failure
+ for v in parsed_email_header_tuples:
+ if '[' in v[1]:
+ v = ('', '')
+ accepted_values.append(v)
+
+ return accepted_values
def _format_timetuple_and_zone(timetuple, zone):
@@ -205,16 +321,33 @@ def parsedate_to_datetime(data):
tzinfo=datetime.timezone(datetime.timedelta(seconds=tz)))
-def parseaddr(addr):
+def parseaddr(addr, *, strict=True):
"""
Parse addr into its constituent realname and email address parts.
Return a tuple of realname and email address, unless the parse fails, in
which case return a 2-tuple of ('', '').
+
+ If strict is True, use a strict parser which rejects malformed inputs.
"""
- addrs = _AddressList(addr).addresslist
- if not addrs:
- return '', ''
+ if not strict:
+ addrs = _AddressList(addr).addresslist
+ if not addrs:
+ return ('', '')
+ return addrs[0]
+
+ if isinstance(addr, list):
+ addr = addr[0]
+
+ if not isinstance(addr, str):
+ return ('', '')
+
+ addr = _pre_parse_validation([addr])[0]
+ addrs = _post_parse_validation(_AddressList(addr).addresslist)
+
+ if not addrs or len(addrs) > 1:
+ return ('', '')
+
return addrs[0]
diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
index 677f2094b8..20b67792ea 100644
--- a/Lib/test/test_email/test_email.py
+++ b/Lib/test/test_email/test_email.py
@@ -17,6 +17,7 @@
import email
import email.policy
+import email.utils
from email.charset import Charset
from email.generator import Generator, DecodedGenerator, BytesGenerator
@@ -3321,15 +3322,154 @@ def test_getaddresses(self):
[('Al Person', 'aperson@dom.ain'),
('Bud Person', 'bperson@dom.ain')])
+ def test_getaddresses_comma_in_name(self):
+ """GH-106669 regression test."""
+ self.assertEqual(
+ utils.getaddresses(
+ [
+ '"Bud, Person" <bperson@dom.ain>',
+ 'aperson@dom.ain (Al Person)',
+ '"Mariusz Felisiak" <to@example.com>',
+ ]
+ ),
+ [
+ ('Bud, Person', 'bperson@dom.ain'),
+ ('Al Person', 'aperson@dom.ain'),
+ ('Mariusz Felisiak', 'to@example.com'),
+ ],
+ )
+
+ def test_parsing_errors(self):
+ """Test for parsing errors from CVE-2023-27043 and CVE-2019-16056"""
+ alice = 'alice@example.org'
+ bob = 'bob@example.com'
+ empty = ('', '')
+
+ # Test utils.getaddresses() and utils.parseaddr() on malformed email
+ # addresses: default behavior (strict=True) rejects malformed address,
+ # and strict=False which tolerates malformed address.
+ for invalid_separator, expected_non_strict in (
+ ('(', [(f'<{bob}>', alice)]),
+ (')', [('', alice), empty, ('', bob)]),
+ ('<', [('', alice), empty, ('', bob), empty]),
+ ('>', [('', alice), empty, ('', bob)]),
+ ('[', [('', f'{alice}[<{bob}>]')]),
+ (']', [('', alice), empty, ('', bob)]),
+ ('@', [empty, empty, ('', bob)]),
+ (';', [('', alice), empty, ('', bob)]),
+ (':', [('', alice), ('', bob)]),
+ ('.', [('', alice + '.'), ('', bob)]),
+ ('"', [('', alice), ('', f'<{bob}>')]),
+ ):
+ address = f'{alice}{invalid_separator}<{bob}>'
+ with self.subTest(address=address):
+ self.assertEqual(utils.getaddresses([address]),
+ [empty])
+ self.assertEqual(utils.getaddresses([address], strict=False),
+ expected_non_strict)
+
+ self.assertEqual(utils.parseaddr([address]),
+ empty)
+ self.assertEqual(utils.parseaddr([address], strict=False),
+ ('', address))
+
+ # Comma (',') is treated differently depending on strict parameter.
+ # Comma without quotes.
+ address = f'{alice},<{bob}>'
+ self.assertEqual(utils.getaddresses([address]),
+ [('', alice), ('', bob)])
+ self.assertEqual(utils.getaddresses([address], strict=False),
+ [('', alice), ('', bob)])
+ self.assertEqual(utils.parseaddr([address]),
+ empty)
+ self.assertEqual(utils.parseaddr([address], strict=False),
+ ('', address))
+
+ # Real name between quotes containing comma.
+ address = '"Alice, alice@example.org" <bob@example.com>'
+ expected_strict = ('Alice, alice@example.org', 'bob@example.com')
+ self.assertEqual(utils.getaddresses([address]), [expected_strict])
+ self.assertEqual(utils.getaddresses([address], strict=False), [expected_strict])
+ self.assertEqual(utils.parseaddr([address]), expected_strict)
+ self.assertEqual(utils.parseaddr([address], strict=False),
+ ('', address))
+
+ # Valid parenthesis in comments.
+ address = 'alice@example.org (Alice)'
+ expected_strict = ('Alice', 'alice@example.org')
+ self.assertEqual(utils.getaddresses([address]), [expected_strict])
+ self.assertEqual(utils.getaddresses([address], strict=False), [expected_strict])
+ self.assertEqual(utils.parseaddr([address]), expected_strict)
+ self.assertEqual(utils.parseaddr([address], strict=False),
+ ('', address))
+
+ # Invalid parenthesis in comments.
+ address = 'alice@example.org )Alice('
+ self.assertEqual(utils.getaddresses([address]), [empty])
+ self.assertEqual(utils.getaddresses([address], strict=False),
+ [('', 'alice@example.org'), ('', ''), ('', 'Alice')])
+ self.assertEqual(utils.parseaddr([address]), empty)
+ self.assertEqual(utils.parseaddr([address], strict=False),
+ ('', address))
+
+ # Two addresses with quotes separated by comma.
+ address = '"Jane Doe" <jane@example.net>, "John Doe" <john@example.net>'
+ self.assertEqual(utils.getaddresses([address]),
+ [('Jane Doe', 'jane@example.net'),
+ ('John Doe', 'john@example.net')])
+ self.assertEqual(utils.getaddresses([address], strict=False),
+ [('Jane Doe', 'jane@example.net'),
+ ('John Doe', 'john@example.net')])
+ self.assertEqual(utils.parseaddr([address]), empty)
+ self.assertEqual(utils.parseaddr([address], strict=False),
+ ('', address))
+
+ # Test email.utils.supports_strict_parsing attribute
+ self.assertEqual(email.utils.supports_strict_parsing, True)
+
def test_getaddresses_nasty(self):
- eq = self.assertEqual
- eq(utils.getaddresses(['foo: ;']), [('', '')])
- eq(utils.getaddresses(
- ['[]*-- =~$']),
- [('', ''), ('', ''), ('', '*--')])
- eq(utils.getaddresses(
- ['foo: ;', '"Jason R. Mastaler" <jason@dom.ain>']),
- [('', ''), ('Jason R. Mastaler', 'jason@dom.ain')])
+ for addresses, expected in (
+ (['"Sürname, Firstname" <to@example.com>'],
+ [('Sürname, Firstname', 'to@example.com')]),
+
+ (['foo: ;'],
+ [('', '')]),
+
+ (['foo: ;', '"Jason R. Mastaler" <jason@dom.ain>'],
+ [('', ''), ('Jason R. Mastaler', 'jason@dom.ain')]),
+
+ ([r'Pete(A nice \) chap) <pete(his account)@silly.test(his host)>'],
+ [('Pete (A nice ) chap his account his host)', 'pete@silly.test')]),
+
+ (['(Empty list)(start)Undisclosed recipients :(nobody(I know))'],
+ [('', '')]),
+
+ (['Mary <@machine.tld:mary@example.net>, , jdoe@test . example'],
+ [('Mary', 'mary@example.net'), ('', ''), ('', 'jdoe@test.example')]),
+
+ (['John Doe <jdoe@machine(comment). example>'],
+ [('John Doe (comment)', 'jdoe@machine.example')]),
+
+ (['"Mary Smith: Personal Account" <smith@home.example>'],
+ [('Mary Smith: Personal Account', 'smith@home.example')]),
+
+ (['Undisclosed recipients:;'],
+ [('', '')]),
+
+ ([r'<boss@nil.test>, "Giant; \"Big\" Box" <bob@example.net>'],
+ [('', 'boss@nil.test'), ('Giant; "Big" Box', 'bob@example.net')]),
+ ):
+ with self.subTest(addresses=addresses):
+ self.assertEqual(utils.getaddresses(addresses),
+ expected)
+ self.assertEqual(utils.getaddresses(addresses, strict=False),
+ expected)
+
+ addresses = ['[]*-- =~$']
+ self.assertEqual(utils.getaddresses(addresses),
+ [('', '')])
+ self.assertEqual(utils.getaddresses(addresses, strict=False),
+ [('', ''), ('', ''), ('', '*--')])
def test_getaddresses_embedded_comment(self):
"""Test proper handling of a nested comment"""
@@ -3520,6 +3660,54 @@ def test_mime_classes_policy_argument(self):
m = cls(*constructor, policy=email.policy.default)
self.assertIs(m.policy, email.policy.default)
+ def test_iter_escaped_chars(self):
+ self.assertEqual(list(utils._iter_escaped_chars(r'a\\b\"c\\"d')),
+ [(0, 'a'),
+ (2, '\\\\'),
+ (3, 'b'),
+ (5, '\\"'),
+ (6, 'c'),
+ (8, '\\\\'),
+ (9, '"'),
+ (10, 'd')])
+ self.assertEqual(list(utils._iter_escaped_chars('a\\')),
+ [(0, 'a'), (1, '\\')])
+
+ def test_strip_quoted_realnames(self):
+ def check(addr, expected):
+ self.assertEqual(utils._strip_quoted_realnames(addr), expected)
+
+ check('"Jane Doe" <jane@example.net>, "John Doe" <john@example.net>',
+ ' <jane@example.net>, <john@example.net>')
+ check(r'"Jane \"Doe\"." <jane@example.net>',
+ ' <jane@example.net>')
+
+ # special cases
+ check(r'before"name"after', 'beforeafter')
+ check(r'before"name"', 'before')
+ check(r'b"name"', 'b') # single char
+ check(r'"name"after', 'after')
+ check(r'"name"a', 'a') # single char
+ check(r'"name"', '')
+
+ # no change
+ for addr in (
+ 'Jane Doe <jane@example.net>, John Doe <john@example.net>',
+ 'lone " quote',
+ ):
+ self.assertEqual(utils._strip_quoted_realnames(addr), addr)
+
+
+ def test_check_parenthesis(self):
+ addr = 'alice@example.net'
+ self.assertTrue(utils._check_parenthesis(f'{addr} (Alice)'))
+ self.assertFalse(utils._check_parenthesis(f'{addr} )Alice('))
+ self.assertFalse(utils._check_parenthesis(f'{addr} (Alice))'))
+ self.assertFalse(utils._check_parenthesis(f'{addr} ((Alice)'))
+
+ # Ignore real name between quotes
+ self.assertTrue(utils._check_parenthesis(f'")Alice((" {addr}'))
+
# Test the iterator/generators
class TestIterators(TestEmailBase):
diff --git a/Misc/NEWS.d/next/Library/2023-10-20-15-28-08.gh-issue-102988.dStNO7.rst b/Misc/NEWS.d/next/Library/2023-10-20-15-28-08.gh-issue-102988.dStNO7.rst
new file mode 100644
index 0000000000..3d0e9e4078
--- /dev/null
+++ b/Misc/NEWS.d/next/Library/2023-10-20-15-28-08.gh-issue-102988.dStNO7.rst
@@ -0,0 +1,8 @@
+:func:`email.utils.getaddresses` and :func:`email.utils.parseaddr` now
+return ``('', '')`` 2-tuples in more situations where invalid email
+addresses are encountered instead of potentially inaccurate values. Add
+optional *strict* parameter to these two functions: use ``strict=False`` to
+get the old behavior, accept malformed inputs.
+``getattr(email.utils, 'supports_strict_parsing', False)`` can be use to check
+if the *strict* paramater is available. Patch by Thomas Dwyer and Victor
+Stinner to improve the CVE-2023-27043 fix.
From 84627ff5841b6715edc47a643225195a0718de99 Mon Sep 17 00:00:00 2001
From: Lumir Balhar <lbalhar@redhat.com>
Date: Wed, 10 Jan 2024 08:53:53 +0100
Subject: [PATCH] Make it possible to disable strict parsing in email module
---
Doc/library/email.utils.rst | 26 +++++++++++
Lib/email/utils.py | 54 ++++++++++++++++++++++-
Lib/test/test_email/test_email.py | 72 ++++++++++++++++++++++++++++++-
3 files changed, 149 insertions(+), 3 deletions(-)
diff --git a/Doc/library/email.utils.rst b/Doc/library/email.utils.rst
index 6723dc4..c89602d 100644
--- a/Doc/library/email.utils.rst
+++ b/Doc/library/email.utils.rst
@@ -69,6 +69,19 @@ of the new API.
If *strict* is true, use a strict parser which rejects malformed inputs.
+ The default setting for *strict* is set to ``True``, but you can override
+ it by setting the environment variable ``PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING``
+ to non-empty string.
+
+ Additionally, you can permanently set the default value for *strict* to
+ ``False`` by creating the configuration file ``/etc/python/email.cfg``
+ with the following content:
+
+ .. code-block:: ini
+
+ [email_addr_parsing]
+ PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING = true
+
.. versionchanged:: 3.13
Add *strict* optional parameter and reject malformed inputs by default.
@@ -97,6 +110,19 @@ of the new API.
If *strict* is true, use a strict parser which rejects malformed inputs.
+ The default setting for *strict* is set to ``True``, but you can override
+ it by setting the environment variable ``PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING``
+ to non-empty string.
+
+ Additionally, you can permanently set the default value for *strict* to
+ ``False`` by creating the configuration file ``/etc/python/email.cfg``
+ with the following content:
+
+ .. code-block:: ini
+
+ [email_addr_parsing]
+ PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING = true
+
Here's a simple example that gets all the recipients of a message::
from email.utils import getaddresses
diff --git a/Lib/email/utils.py b/Lib/email/utils.py
index 9522341..2e30e09 100644
--- a/Lib/email/utils.py
+++ b/Lib/email/utils.py
@@ -48,6 +48,46 @@ TICK = "'"
specialsre = re.compile(r'[][\\()<>@,:;".]')
escapesre = re.compile(r'[\\"]')
+_EMAIL_CONFIG_FILE = "/etc/python/email.cfg"
+_cached_strict_addr_parsing = None
+
+
+def _use_strict_email_parsing():
+ """"Cache implementation for _cached_strict_addr_parsing"""
+ global _cached_strict_addr_parsing
+ if _cached_strict_addr_parsing is None:
+ _cached_strict_addr_parsing = _use_strict_email_parsing_impl()
+ return _cached_strict_addr_parsing
+
+
+def _use_strict_email_parsing_impl():
+ """Returns True if strict email parsing is not disabled by
+ config file or env variable.
+ """
+ disabled = bool(os.environ.get("PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING"))
+ if disabled:
+ return False
+
+ try:
+ file = open(_EMAIL_CONFIG_FILE)
+ except FileNotFoundError:
+ pass
+ else:
+ with file:
+ import configparser
+ config = configparser.ConfigParser(
+ interpolation=None,
+ comment_prefixes=('#', ),
+
+ )
+ config.read_file(file)
+ disabled = config.getboolean('email_addr_parsing', "PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING", fallback=None)
+
+ if disabled:
+ return False
+
+ return True
+
def _has_surrogates(s):
"""Return True if s contains surrogate-escaped binary data."""
@@ -149,7 +189,7 @@ def _strip_quoted_realnames(addr):
supports_strict_parsing = True
-def getaddresses(fieldvalues, *, strict=True):
+def getaddresses(fieldvalues, *, strict=None):
"""Return a list of (REALNAME, EMAIL) or ('','') for each fieldvalue.
When parsing fails for a fieldvalue, a 2-tuple of ('', '') is returned in
@@ -158,6 +198,11 @@ def getaddresses(fieldvalues, *, strict=True):
If strict is true, use a strict parser which rejects malformed inputs.
"""
+ # If default is used, it's True unless disabled
+ # by env variable or config file.
+ if strict == None:
+ strict = _use_strict_email_parsing()
+
# If strict is true, if the resulting list of parsed addresses is greater
# than the number of fieldvalues in the input list, a parsing error has
# occurred and consequently a list containing a single empty 2-tuple [('',
@@ -321,7 +366,7 @@ def parsedate_to_datetime(data):
tzinfo=datetime.timezone(datetime.timedelta(seconds=tz)))
-def parseaddr(addr, *, strict=True):
+def parseaddr(addr, *, strict=None):
"""
Parse addr into its constituent realname and email address parts.
@@ -330,6 +375,11 @@ def parseaddr(addr, *, strict=True):
If strict is True, use a strict parser which rejects malformed inputs.
"""
+ # If default is used, it's True unless disabled
+ # by env variable or config file.
+ if strict == None:
+ strict = _use_strict_email_parsing()
+
if not strict:
addrs = _AddressList(addr).addresslist
if not addrs:
diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
index a1a7859..f4e8c7f 100644
--- a/Lib/test/test_email/test_email.py
+++ b/Lib/test/test_email/test_email.py
@@ -8,6 +8,9 @@ import base64
import unittest
import textwrap
import warnings
+import contextlib
+import tempfile
+import os
from io import StringIO, BytesIO
from itertools import chain
@@ -40,7 +43,7 @@ from email import iterators
from email import quoprimime
from email import utils
-from test.support import threading_helper
-from test.support.os_helper import unlink
+from test.support import threading_helper, swap_attr
+from test.support.os_helper import unlink, EnvironmentVarGuard
from test.test_email import openfile, TestEmailBase
@@ -3426,6 +3429,73 @@ Foo
# Test email.utils.supports_strict_parsing attribute
self.assertEqual(email.utils.supports_strict_parsing, True)
+ def test_parsing_errors_strict_set_via_env_var(self):
+ address = 'alice@example.org )Alice('
+ empty = ('', '')
+
+ # Reset cached default value to make the function
+ # reload the config file provided below.
+ utils._cached_strict_addr_parsing = None
+
+ # Strict disabled via env variable, old behavior expected
+ with EnvironmentVarGuard() as environ:
+ environ["PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING"] = "1"
+
+ self.assertEqual(utils.getaddresses([address]),
+ [('', 'alice@example.org'), ('', ''), ('', 'Alice')])
+ self.assertEqual(utils.parseaddr([address]), ('', address))
+
+ # Clear cache again
+ utils._cached_strict_addr_parsing = None
+
+ # Default strict=True, empty result expected
+ self.assertEqual(utils.getaddresses([address]), [empty])
+ self.assertEqual(utils.parseaddr([address]), empty)
+
+ # Clear cache again
+ utils._cached_strict_addr_parsing = None
+
+ # Empty string in env variable = strict parsing enabled (default)
+ with EnvironmentVarGuard() as environ:
+ environ["PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING"] = ""
+
+ # Default strict=True, empty result expected
+ self.assertEqual(utils.getaddresses([address]), [empty])
+ self.assertEqual(utils.parseaddr([address]), empty)
+
+ @contextlib.contextmanager
+ def _email_strict_parsing_conf(self):
+ """Context for the given email strict parsing configured in config file"""
+ with tempfile.TemporaryDirectory() as tmpdirname:
+ filename = os.path.join(tmpdirname, 'conf.cfg')
+ with swap_attr(utils, "_EMAIL_CONFIG_FILE", filename):
+ with open(filename, 'w') as file:
+ file.write('[email_addr_parsing]\n')
+ file.write('PYTHON_EMAIL_DISABLE_STRICT_ADDR_PARSING = true')
+ utils._EMAIL_CONFIG_FILE = filename
+ yield
+
+ def test_parsing_errors_strict_disabled_via_config_file(self):
+ address = 'alice@example.org )Alice('
+ empty = ('', '')
+
+ # Reset cached default value to make the function
+ # reload the config file provided below.
+ utils._cached_strict_addr_parsing = None
+
+ # Strict disabled via config file, old results expected
+ with self._email_strict_parsing_conf():
+ self.assertEqual(utils.getaddresses([address]),
+ [('', 'alice@example.org'), ('', ''), ('', 'Alice')])
+ self.assertEqual(utils.parseaddr([address]), ('', address))
+
+ # Clear cache again
+ utils._cached_strict_addr_parsing = None
+
+ # Default strict=True, empty result expected
+ self.assertEqual(utils.getaddresses([address]), [empty])
+ self.assertEqual(utils.parseaddr([address]), empty)
+
def test_getaddresses_nasty(self):
for addresses, expected in (
(['"Sürname, Firstname" <to@example.com>'],
--
2.43.0