[3.14] gh-137078: Fix keyword typo recognition when executed over files (GH-137079) (#137826)

miss-islington · web-flow · commit 7b56d08219ee · 2025-08-15T18:22:17.000+01:00
diff --git a/Grammar/python.gram b/Grammar/python.gram
@@ -94,10 +94,12 @@ func_type[mod_ty]: '(' a=[type_expressions] ')' '->' b=expression NEWLINE* ENDMA
 # GENERAL STATEMENTS
 # ==================
 
-statements[asdl_stmt_seq*]: a=statement+ { _PyPegen_register_stmts(p, (asdl_stmt_seq*)_PyPegen_seq_flatten(p, a)) }
+statements[asdl_stmt_seq*]: a=statement+ { (asdl_stmt_seq*)_PyPegen_seq_flatten(p, a) }
 
 statement[asdl_stmt_seq*]:
-    | a=compound_stmt { (asdl_stmt_seq*)_PyPegen_singleton_seq(p, a) }
+    | a=compound_stmt { _PyPegen_register_stmts(p ,
+                           (asdl_stmt_seq*)_PyPegen_singleton_seq(p, a)
+                        ) }
     | a[asdl_stmt_seq*]=simple_stmts { a }
 
 single_compound_stmt[asdl_stmt_seq*]:
diff --git a/Lib/test/test_traceback.py b/Lib/test/test_traceback.py
@@ -19,7 +19,7 @@
                           requires_debug_ranges, has_no_debug_ranges,
                           requires_subprocess)
 from test.support.os_helper import TESTFN, unlink
-from test.support.script_helper import assert_python_ok, assert_python_failure
+from test.support.script_helper import assert_python_ok, assert_python_failure, make_script
 from test.support.import_helper import forget
 from test.support import force_not_colorized, force_not_colorized_test_class
 
@@ -1740,6 +1740,49 @@ def f():
         ]
         self.assertEqual(result_lines, expected)
 
+class TestKeywordTypoSuggestions(unittest.TestCase):
+    TYPO_CASES = [
+        ("with block ad something:\n  pass", "and"),
+        ("fur a in b:\n  pass", "for"),
+        ("for a in b:\n  pass\nelso:\n  pass", "else"),
+        ("whille True:\n  pass", "while"),
+        ("iff x > 5:\n  pass", "if"),
+        ("if x:\n  pass\nelseif y:\n  pass", "elif"),
+        ("tyo:\n  pass\nexcept y:\n  pass", "try"),
+        ("classe MyClass:\n  pass", "class"),
+        ("impor math", "import"),
+        ("form x import y", "from"),
+        ("defn calculate_sum(a, b):\n  return a + b", "def"),
+        ("def foo():\n  returm result", "return"),
+        ("lamda x: x ** 2", "lambda"),
+        ("def foo():\n  yeld i", "yield"),
+        ("def foo():\n  globel counter", "global"),
+        ("frum math import sqrt", "from"),
+        ("asynch def fetch_data():\n  pass", "async"),
+        ("async def foo():\n  awaid fetch_data()", "await"),
+        ('raisee ValueError("Error")', "raise"),
+        ("[x for x\nin range(3)\nof x]", "if"),
+        ("[123 fur x\nin range(3)\nif x]", "for"),
+        ("for x im n:\n  pass", "in"),
+    ]
+
+    def test_keyword_suggestions_from_file(self):
+        with tempfile.TemporaryDirectory() as script_dir:
+            for i, (code, expected_kw) in enumerate(self.TYPO_CASES):
+                with self.subTest(typo=expected_kw):
+                    source = textwrap.dedent(code).strip()
+                    script_name = make_script(script_dir, f"script_{i}", source)
+                    rc, stdout, stderr = assert_python_failure(script_name)
+                    stderr_text = stderr.decode('utf-8')
+                    self.assertIn(f"Did you mean '{expected_kw}'", stderr_text)
+
+    def test_keyword_suggestions_from_command_string(self):
+        for code, expected_kw in self.TYPO_CASES:
+            with self.subTest(typo=expected_kw):
+                source = textwrap.dedent(code).strip()
+                rc, stdout, stderr = assert_python_failure('-c', source)
+                stderr_text = stderr.decode('utf-8')
+                self.assertIn(f"Did you mean '{expected_kw}'", stderr_text)
 
 @requires_debug_ranges()
 @force_not_colorized_test_class
diff --git a/Lib/traceback.py b/Lib/traceback.py
@@ -1310,7 +1310,6 @@ def _find_keyword_typos(self):
             lines = source.splitlines()
 
         error_code = lines[line -1 if line > 0 else 0:end_line]
-        error_code[0] = error_code[0][offset:]
         error_code = textwrap.dedent('\n'.join(error_code))
 
         # Do not continue if the source is too large
@@ -1326,7 +1325,8 @@ def _find_keyword_typos(self):
             if token.type != tokenize.NAME:
                 continue
             # Only consider NAME tokens on the same line as the error
-            if from_filename and token.start[0]+line != end_line+1:
+            the_end = end_line if line == 0 else end_line + 1
+            if from_filename and token.start[0]+line != the_end:
                 continue
             wrong_name = token.string
             if wrong_name in keyword.kwlist:
diff --git a/Misc/NEWS.d/next/Core_and_Builtins/2025-08-15-15-45-26.gh-issue-137079.YEow69.rst b/Misc/NEWS.d/next/Core_and_Builtins/2025-08-15-15-45-26.gh-issue-137079.YEow69.rst
@@ -0,0 +1 @@
+Fix keyword typo recognition when parsing files. Patch by Pablo Galindo.
diff --git a/Parser/action_helpers.c b/Parser/action_helpers.c
@@ -1939,6 +1939,9 @@ _PyPegen_register_stmts(Parser *p, asdl_stmt_seq* stmts) {
         return stmts;
     }
     stmt_ty last_stmt = asdl_seq_GET(stmts, len - 1);
+    if (p->last_stmt_location.lineno > last_stmt->lineno) {
+        return stmts;
+    }
     p->last_stmt_location.lineno = last_stmt->lineno;
     p->last_stmt_location.col_offset = last_stmt->col_offset;
     p->last_stmt_location.end_lineno = last_stmt->end_lineno;
diff --git a/Parser/parser.c b/Parser/parser.c

Original file line number	Diff line number	Diff line change
`@@ -0,0 +1 @@`
	`1`	`+Fix keyword typo recognition when parsing files. Patch by Pablo Galindo.`