From d1484070030a97cf9808ab04c7fc9b11a0f147e2 Mon Sep 17 00:00:00 2001
From: Tomas R <tomas.roun8@gmail.com>
Date: Thu, 14 Nov 2024 23:17:42 +0100
Subject: [PATCH] gh-126807: pygettext: Do not attempt to extract messages from
 function definitions. (GH-126808)

Fixes a bug where pygettext would attempt
to extract a message from a code like this:

def _(x): pass

This is because pygettext only looks at one
token at a time and '_(x)' looks like a
function call.

However, since 'x' is not a string literal,
it would erroneously issue a warning.
(cherry picked from commit 9a456383bed52010b90bd491277ea855626a7bba)

Co-authored-by: Tomas R. <tomas.roun8@gmail.com>
---
 Lib/test/test_tools/test_i18n.py              | 33 ++++++++++++++++---
 ...-11-13-22-23-36.gh-issue-126807.vpaWuN.rst |  2 ++
 Tools/i18n/pygettext.py                       |  6 ++++
 3 files changed, 36 insertions(+), 5 deletions(-)
 create mode 100644 Misc/NEWS.d/next/Tools-Demos/2024-11-13-22-23-36.gh-issue-126807.vpaWuN.rst

diff --git a/Lib/test/test_tools/test_i18n.py b/Lib/test/test_tools/test_i18n.py
index 21dead8f943bb7..6f71f0976819f1 100644
--- a/Lib/test/test_tools/test_i18n.py
+++ b/Lib/test/test_tools/test_i18n.py
@@ -87,17 +87,23 @@ def assert_POT_equal(self, expected, actual):
         self.maxDiff = None
         self.assertEqual(normalize_POT_file(expected), normalize_POT_file(actual))
 
-    def extract_docstrings_from_str(self, module_content):
-        """ utility: return all msgids extracted from module_content """
-        filename = 'test_docstrings.py'
-        with temp_cwd(None) as cwd:
+    def extract_from_str(self, module_content, *, args=(), strict=True):
+        """Return all msgids extracted from module_content."""
+        filename = 'test.py'
+        with temp_cwd(None):
             with open(filename, 'w', encoding='utf-8') as fp:
                 fp.write(module_content)
-            assert_python_ok('-Xutf8', self.script, '-D', filename)
+            res = assert_python_ok('-Xutf8', self.script, *args, filename)
+            if strict:
+                self.assertEqual(res.err, b'')
             with open('messages.pot', encoding='utf-8') as fp:
                 data = fp.read()
         return self.get_msgids(data)
 
+    def extract_docstrings_from_str(self, module_content):
+        """Return all docstrings extracted from module_content."""
+        return self.extract_from_str(module_content, args=('--docstrings',), strict=False)
+
     def test_header(self):
         """Make sure the required fields are in the header, according to:
            http://www.gnu.org/software/gettext/manual/gettext.html#Header-Entry
@@ -344,6 +350,23 @@ def test_calls_in_fstring_with_partially_wrong_expression(self):
         self.assertNotIn('foo', msgids)
         self.assertIn('bar', msgids)
 
+    def test_function_and_class_names(self):
+        """Test that function and class names are not mistakenly extracted."""
+        msgids = self.extract_from_str(dedent('''\
+        def _(x):
+            pass
+
+        def _(x="foo"):
+            pass
+
+        async def _(x):
+            pass
+
+        class _(object):
+            pass
+        '''))
+        self.assertEqual(msgids, [''])
+
     def test_pygettext_output(self):
         """Test that the pygettext output exactly matches snapshots."""
         for input_file in DATA_DIR.glob('*.py'):
diff --git a/Misc/NEWS.d/next/Tools-Demos/2024-11-13-22-23-36.gh-issue-126807.vpaWuN.rst b/Misc/NEWS.d/next/Tools-Demos/2024-11-13-22-23-36.gh-issue-126807.vpaWuN.rst
new file mode 100644
index 00000000000000..310286ce8319ea
--- /dev/null
+++ b/Misc/NEWS.d/next/Tools-Demos/2024-11-13-22-23-36.gh-issue-126807.vpaWuN.rst
@@ -0,0 +1,2 @@
+Fix extraction warnings in :program:`pygettext.py` caused by mistaking
+function definitions for function calls.
diff --git a/Tools/i18n/pygettext.py b/Tools/i18n/pygettext.py
index 3a0b27ba420e7a..0d16e8f7da0071 100755
--- a/Tools/i18n/pygettext.py
+++ b/Tools/i18n/pygettext.py
@@ -341,6 +341,9 @@ def __waiting(self, ttype, tstring, lineno):
             if ttype == tokenize.NAME and tstring in ('class', 'def'):
                 self.__state = self.__suiteseen
                 return
+        if ttype == tokenize.NAME and tstring in ('class', 'def'):
+            self.__state = self.__ignorenext
+            return
         if ttype == tokenize.NAME and tstring in opts.keywords:
             self.__state = self.__keywordseen
             return
@@ -448,6 +451,9 @@ def __openseen(self, ttype, tstring, lineno):
                 }, file=sys.stderr)
             self.__state = self.__waiting
 
+    def __ignorenext(self, ttype, tstring, lineno):
+        self.__state = self.__waiting
+
     def __addentry(self, msg, lineno=None, isdocstring=0):
         if lineno is None:
             lineno = self.__lineno