Issue #29319: Prevent RunMainFromImporter overwriting sys.path[0].

9 files changed, 152 insertions, 54 deletions

diff --git a/Lib/test/test_email/__init__.py b/Lib/test/test_email/__init__.py
index d4a03ee071..888751e9e6 100644
--- a/Lib/test/test_email/__init__.py
+++ b/Lib/test/test_email/__init__.py
@@ -1,5 +1,4 @@
 import os
-import sys
 import unittest
 import collections
 import email
diff --git a/Lib/test/test_email/test__header_value_parser.py b/Lib/test/test_email/test__header_value_parser.py
index f7ac0e3ded..26ece6911f 100644
--- a/Lib/test/test_email/test__header_value_parser.py
+++ b/Lib/test/test_email/test__header_value_parser.py
@@ -581,7 +581,7 @@ class TestParser(TestParserMixin, TestEmailBase):
 
     def test_get_comment_quoted_parens(self):
         self._test_get_x(parser.get_comment,
-            '(foo\) \(\)bar)', '(foo\) \(\)bar)', ' ', [], '', ['foo) ()bar'])
+            r'(foo\) \(\)bar)', r'(foo\) \(\)bar)', ' ', [], '', ['foo) ()bar'])
 
     def test_get_comment_non_printable(self):
         self._test_get_x(parser.get_comment,
@@ -625,7 +625,7 @@ class TestParser(TestParserMixin, TestEmailBase):
 
     def test_get_comment_qs_in_nested_comment(self):
         comment = self._test_get_x(parser.get_comment,
-            '(foo (b\)))', '(foo (b\)))', ' ', [], '', ['foo (b\))'])
+            r'(foo (b\)))', r'(foo (b\)))', ' ', [], '', [r'foo (b\))'])
         self.assertEqual(comment[2].content, 'b)')
 
     # get_cfws
diff --git a/Lib/test/test_email/test_asian_codecs.py b/Lib/test/test_email/test_asian_codecs.py
index f9cd7d9b4e..1e0caeeaed 100644
--- a/Lib/test/test_email/test_asian_codecs.py
+++ b/Lib/test/test_email/test_asian_codecs.py
@@ -3,7 +3,6 @@
 # email package unit tests for (optional) Asian codecs
 
 import unittest
-from test.support import run_unittest
 
 from test.test_email import TestEmailBase
 from email.charset import Charset
diff --git a/Lib/test/test_email/test_email.py b/Lib/test/test_email/test_email.py
index 9b86a2aee9..f97ccc6711 100644
--- a/Lib/test/test_email/test_email.py
+++ b/Lib/test/test_email/test_email.py
@@ -32,6 +32,7 @@ from email.mime.image import MIMEImage
 from email.mime.base import MIMEBase
 from email.mime.message import MIMEMessage
 from email.mime.multipart import MIMEMultipart
+from email.mime.nonmultipart import MIMENonMultipart
 from email import utils
 from email import errors
 from email import encoders
@@ -2078,7 +2079,13 @@ YXNkZg==
 --===============0012394164==--""")
         self.assertEqual(m.get_payload(0).get_payload(), 'YXNkZg==')
 
+    def test_mimebase_default_policy(self):
+        m = MIMEBase('multipart', 'mixed')
+        self.assertIs(m.policy, email.policy.compat32)
 
+    def test_mimebase_custom_policy(self):
+        m = MIMEBase('multipart', 'mixed', policy=email.policy.default)
+        self.assertIs(m.policy, email.policy.default)
 
 # Test some badly formatted messages
 class TestNonConformant(TestEmailBase):
@@ -2680,6 +2687,19 @@ message 2
         msg = MIMEMultipart()
         self.assertTrue(msg.is_multipart())
 
+    def test_multipart_default_policy(self):
+        msg = MIMEMultipart()
+        msg['To'] = 'a@b.com'
+        msg['To'] = 'c@d.com'
+        self.assertEqual(msg.get_all('to'), ['a@b.com', 'c@d.com'])
+
+    def test_multipart_custom_policy(self):
+        msg = MIMEMultipart(policy=email.policy.default)
+        msg['To'] = 'a@b.com'
+        with self.assertRaises(ValueError) as cm:
+            msg['To'] = 'c@d.com'
+        self.assertEqual(str(cm.exception),
+                         'There may be at most 1 To headers in a message')
 
 # A general test of parser->model->generator idempotency.  IOW, read a message
 # in, parse it into a message object tree, then without touching the tree,
@@ -3033,7 +3053,7 @@ class TestMiscellaneous(TestEmailBase):
 
     def test_escape_backslashes(self):
         self.assertEqual(
-            utils.formataddr(('Arthur \Backslash\ Foobar', 'person@dom.ain')),
+            utils.formataddr((r'Arthur \Backslash\ Foobar', 'person@dom.ain')),
             r'"Arthur \\Backslash\\ Foobar" <person@dom.ain>')
         a = r'Arthur \Backslash\ Foobar'
         b = 'person@dom.ain'
@@ -3340,6 +3360,27 @@ multipart/report
         g.flatten(msg, linesep='\r\n')
         self.assertEqual(s.getvalue(), msgtxt)
 
+    def test_mime_classes_policy_argument(self):
+        with openfile('audiotest.au', 'rb') as fp:
+            audiodata = fp.read()
+        with openfile('PyBanner048.gif', 'rb') as fp:
+            bindata = fp.read()
+        classes = [
+            (MIMEApplication, ('',)),
+            (MIMEAudio, (audiodata,)),
+            (MIMEImage, (bindata,)),
+            (MIMEMessage, (Message(),)),
+            (MIMENonMultipart, ('multipart', 'mixed')),
+            (MIMEText, ('',)),
+        ]
+        for cls, constructor in classes:
+            with self.subTest(cls=cls.__name__, policy='compat32'):
+                m = cls(*constructor)
+                self.assertIs(m.policy, email.policy.compat32)
+            with self.subTest(cls=cls.__name__, policy='default'):
+                m = cls(*constructor, policy=email.policy.default)
+                self.assertIs(m.policy, email.policy.default)
+
 
 # Test the iterator/generators
 class TestIterators(TestEmailBase):
@@ -3448,7 +3489,6 @@ Do you like this message?
 class TestFeedParsers(TestEmailBase):
 
     def parse(self, chunks):
-        from email.feedparser import FeedParser
         feedparser = FeedParser()
         for chunk in chunks:
             feedparser.feed(chunk)
diff --git a/Lib/test/test_email/test_generator.py b/Lib/test/test_email/test_generator.py
index b1cbce26d5..7c8877fdcb 100644
--- a/Lib/test/test_email/test_generator.py
+++ b/Lib/test/test_email/test_generator.py
@@ -143,7 +143,7 @@ class TestGeneratorBase:
     def test_set_mangle_from_via_policy(self):
         source = textwrap.dedent("""\
             Subject: test that
-             from is mangeld in the body!
+             from is mangled in the body!
 
             From time to time I write a rhyme.
             """)
diff --git a/Lib/test/test_email/test_headerregistry.py b/Lib/test/test_email/test_headerregistry.py
index 55ecdea9aa..af836dc972 100644
--- a/Lib/test/test_email/test_headerregistry.py
+++ b/Lib/test/test_email/test_headerregistry.py
@@ -1,7 +1,6 @@
 import datetime
 import textwrap
 import unittest
-import types
 from email import errors
 from email import policy
 from email.message import Message
diff --git a/Lib/test/test_email/test_message.py b/Lib/test/test_email/test_message.py
index 434516226c..f3a57df9e9 100644
--- a/Lib/test/test_email/test_message.py
+++ b/Lib/test/test_email/test_message.py
@@ -764,6 +764,26 @@ class TestEmailMessage(TestEmailMessageBase, TestEmailBase):
         m.set_content(content_manager=cm)
         self.assertEqual(m['MIME-Version'], '1.0')
 
+    def test_as_string_uses_max_header_length_by_default(self):
+        m = self._str_msg('Subject: long line' + ' ab'*50 + '\n\n')
+        self.assertEqual(len(m.as_string().strip().splitlines()), 3)
+
+    def test_as_string_allows_maxheaderlen(self):
+        m = self._str_msg('Subject: long line' + ' ab'*50 + '\n\n')
+        self.assertEqual(len(m.as_string(maxheaderlen=0).strip().splitlines()),
+                         1)
+        self.assertEqual(len(m.as_string(maxheaderlen=34).strip().splitlines()),
+                         6)
+
+    def test_str_defaults_to_policy_max_line_length(self):
+        m = self._str_msg('Subject: long line' + ' ab'*50 + '\n\n')
+        self.assertEqual(len(str(m).strip().splitlines()), 3)
+
+    def test_str_defaults_to_utf8(self):
+        m = EmailMessage()
+        m['Subject'] = 'unicöde'
+        self.assertEqual(str(m), 'Subject: unicöde\n\n')
+
 
 class TestMIMEPart(TestEmailMessageBase, TestEmailBase):
     # Doing the full test run here may seem a bit redundant, since the two
diff --git a/Lib/test/test_email/test_parser.py b/Lib/test/test_email/test_parser.py
index 8ddc176389..06c86408ab 100644
--- a/Lib/test/test_email/test_parser.py
+++ b/Lib/test/test_email/test_parser.py
@@ -1,7 +1,7 @@
 import io
 import email
 import unittest
-from email.message import Message
+from email.message import Message, EmailMessage
 from email.policy import default
 from test.test_email import TestEmailBase
 
@@ -39,38 +39,71 @@ class TestParserBase:
         # The unicode line splitter splits on unicode linebreaks, which are
         # more numerous than allowed by the email RFCs; make sure we are only
         # splitting on those two.
-        msg = self.parser(
-            "Next-Line: not\x85broken\r\n"
-            "Null: not\x00broken\r\n"
-            "Vertical-Tab: not\vbroken\r\n"
-            "Form-Feed: not\fbroken\r\n"
-            "File-Separator: not\x1Cbroken\r\n"
-            "Group-Separator: not\x1Dbroken\r\n"
-            "Record-Separator: not\x1Ebroken\r\n"
-            "Line-Separator: not\u2028broken\r\n"
-            "Paragraph-Separator: not\u2029broken\r\n"
-            "\r\n",
-            policy=default,
-        )
-        self.assertEqual(msg.items(), [
-            ("Next-Line", "not\x85broken"),
-            ("Null", "not\x00broken"),
-            ("Vertical-Tab", "not\vbroken"),
-            ("Form-Feed", "not\fbroken"),
-            ("File-Separator", "not\x1Cbroken"),
-            ("Group-Separator", "not\x1Dbroken"),
-            ("Record-Separator", "not\x1Ebroken"),
-            ("Line-Separator", "not\u2028broken"),
-            ("Paragraph-Separator", "not\u2029broken"),
-        ])
-        self.assertEqual(msg.get_payload(), "")
+        for parser in self.parsers:
+            with self.subTest(parser=parser.__name__):
+                msg = parser(
+                    "Next-Line: not\x85broken\r\n"
+                    "Null: not\x00broken\r\n"
+                    "Vertical-Tab: not\vbroken\r\n"
+                    "Form-Feed: not\fbroken\r\n"
+                    "File-Separator: not\x1Cbroken\r\n"
+                    "Group-Separator: not\x1Dbroken\r\n"
+                    "Record-Separator: not\x1Ebroken\r\n"
+                    "Line-Separator: not\u2028broken\r\n"
+                    "Paragraph-Separator: not\u2029broken\r\n"
+                    "\r\n",
+                    policy=default,
+                )
+                self.assertEqual(msg.items(), [
+                    ("Next-Line", "not\x85broken"),
+                    ("Null", "not\x00broken"),
+                    ("Vertical-Tab", "not\vbroken"),
+                    ("Form-Feed", "not\fbroken"),
+                    ("File-Separator", "not\x1Cbroken"),
+                    ("Group-Separator", "not\x1Dbroken"),
+                    ("Record-Separator", "not\x1Ebroken"),
+                    ("Line-Separator", "not\u2028broken"),
+                    ("Paragraph-Separator", "not\u2029broken"),
+                ])
+                self.assertEqual(msg.get_payload(), "")
+
+    class MyMessage(EmailMessage):
+        pass
+
+    def test_custom_message_factory_on_policy(self):
+        for parser in self.parsers:
+            with self.subTest(parser=parser.__name__):
+                MyPolicy = default.clone(message_factory=self.MyMessage)
+                msg = parser("To: foo\n\ntest", policy=MyPolicy)
+                self.assertIsInstance(msg, self.MyMessage)
+
+    def test_factory_arg_overrides_policy(self):
+        for parser in self.parsers:
+            with self.subTest(parser=parser.__name__):
+                MyPolicy = default.clone(message_factory=self.MyMessage)
+                msg = parser("To: foo\n\ntest", Message, policy=MyPolicy)
+                self.assertNotIsInstance(msg, self.MyMessage)
+                self.assertIsInstance(msg, Message)
+
+# Play some games to get nice output in subTest.  This code could be clearer
+# if staticmethod supported __name__.
+
+def message_from_file(s, *args, **kw):
+    f = io.StringIO(s)
+    return email.message_from_file(f, *args, **kw)
 
 class TestParser(TestParserBase, TestEmailBase):
-    parser = staticmethod(email.message_from_string)
+    parsers = (email.message_from_string, message_from_file)
+
+def message_from_bytes(s, *args, **kw):
+    return email.message_from_bytes(s.encode(), *args, **kw)
+
+def message_from_binary_file(s, *args, **kw):
+    f = io.BytesIO(s.encode())
+    return email.message_from_binary_file(f, *args, **kw)
 
 class TestBytesParser(TestParserBase, TestEmailBase):
-    def parser(self, s, *args, **kw):
-        return email.message_from_bytes(s.encode(), *args, **kw)
+    parsers = (message_from_bytes, message_from_binary_file)
 
 
 if __name__ == '__main__':
diff --git a/Lib/test/test_email/test_policy.py b/Lib/test/test_email/test_policy.py
index 70ac4db8b0..8fecb8a5fc 100644
--- a/Lib/test/test_email/test_policy.py
+++ b/Lib/test/test_email/test_policy.py
@@ -5,6 +5,7 @@ import unittest
 import email.policy
 import email.parser
 import email.generator
+import email.message
 from email import headerregistry
 
 def make_defaults(base_defaults, differences):
@@ -23,6 +24,7 @@ class PolicyAPITests(unittest.TestCase):
         'cte_type':                 '8bit',
         'raise_on_defect':          False,
         'mangle_from_':             True,
+        'message_factory':          None,
         }
     # These default values are the ones set on email.policy.default.
     # If any of these defaults change, the docs must be updated.
@@ -34,6 +36,7 @@ class PolicyAPITests(unittest.TestCase):
         'refold_source':            'long',
         'content_manager':          email.policy.EmailPolicy.content_manager,
         'mangle_from_':             False,
+        'message_factory':          email.message.EmailMessage,
         })
 
     # For each policy under test, we give here what we expect the defaults to
@@ -62,20 +65,22 @@ class PolicyAPITests(unittest.TestCase):
     def test_defaults(self):
         for policy, expected in self.policies.items():
             for attr, value in expected.items():
-                self.assertEqual(getattr(policy, attr), value,
-                                ("change {} docs/docstrings if defaults have "
-                                "changed").format(policy))
+                with self.subTest(policy=policy, attr=attr):
+                    self.assertEqual(getattr(policy, attr), value,
+                                    ("change {} docs/docstrings if defaults have "
+                                    "changed").format(policy))
 
     def test_all_attributes_covered(self):
         for policy, expected in self.policies.items():
             for attr in dir(policy):
-                if (attr.startswith('_') or
-                        isinstance(getattr(email.policy.EmailPolicy, attr),
-                              types.FunctionType)):
-                    continue
-                else:
-                    self.assertIn(attr, expected,
-                                  "{} is not fully tested".format(attr))
+                with self.subTest(policy=policy, attr=attr):
+                    if (attr.startswith('_') or
+                            isinstance(getattr(email.policy.EmailPolicy, attr),
+                                  types.FunctionType)):
+                        continue
+                    else:
+                        self.assertIn(attr, expected,
+                                      "{} is not fully tested".format(attr))
 
     def test_abc(self):
         with self.assertRaises(TypeError) as cm:
@@ -237,6 +242,9 @@ class PolicyAPITests(unittest.TestCase):
     # wins), but that the order still works (right overrides left).
 
 
+class TestException(Exception):
+    pass
+
 class TestPolicyPropagation(unittest.TestCase):
 
     # The abstract methods are used by the parser but not by the wrapper
@@ -244,40 +252,40 @@ class TestPolicyPropagation(unittest.TestCase):
     # policy was actually propagated all the way to feedparser.
     class MyPolicy(email.policy.Policy):
         def badmethod(self, *args, **kw):
-            raise Exception("test")
+            raise TestException("test")
         fold = fold_binary = header_fetch_parser = badmethod
         header_source_parse = header_store_parse = badmethod
 
     def test_message_from_string(self):
-        with self.assertRaisesRegex(Exception, "^test$"):
+        with self.assertRaisesRegex(TestException, "^test$"):
             email.message_from_string("Subject: test\n\n",
                                       policy=self.MyPolicy)
 
     def test_message_from_bytes(self):
-        with self.assertRaisesRegex(Exception, "^test$"):
+        with self.assertRaisesRegex(TestException, "^test$"):
             email.message_from_bytes(b"Subject: test\n\n",
                                      policy=self.MyPolicy)
 
     def test_message_from_file(self):
         f = io.StringIO('Subject: test\n\n')
-        with self.assertRaisesRegex(Exception, "^test$"):
+        with self.assertRaisesRegex(TestException, "^test$"):
             email.message_from_file(f, policy=self.MyPolicy)
 
     def test_message_from_binary_file(self):
         f = io.BytesIO(b'Subject: test\n\n')
-        with self.assertRaisesRegex(Exception, "^test$"):
+        with self.assertRaisesRegex(TestException, "^test$"):
             email.message_from_binary_file(f, policy=self.MyPolicy)
 
     # These are redundant, but we need them for black-box completeness.
 
     def test_parser(self):
         p = email.parser.Parser(policy=self.MyPolicy)
-        with self.assertRaisesRegex(Exception, "^test$"):
+        with self.assertRaisesRegex(TestException, "^test$"):
             p.parsestr('Subject: test\n\n')
 
     def test_bytes_parser(self):
         p = email.parser.BytesParser(policy=self.MyPolicy)
-        with self.assertRaisesRegex(Exception, "^test$"):
+        with self.assertRaisesRegex(TestException, "^test$"):
             p.parsebytes(b'Subject: test\n\n')
 
     # Now that we've established that all the parse methods get the