bpo-40334: Avoid collisions between parser variables and grammar variables (GH-19987)

This is for the C generator:
- Disallow rule and variable names starting with `_`
- Rename most local variable names generated by the parser to start with `_`

Exceptions:
- Renaming `p` to `_p` will be a separate PR
- There are still some names that might clash, e.g.
  - anything starting with `Py`
  - C reserved words (`if` etc.)
  - Macros like `EXTRA` and `CHECK`

1 files changed, 27 insertions, 0 deletions

diff --git a/Lib/test/test_peg_generator/test_pegen.py b/Lib/test/test_peg_generator/test_pegen.py
index 0a2a6d4..30e1b67 100644
--- a/Lib/test/test_peg_generator/test_pegen.py
+++ b/Lib/test/test_peg_generator/test_pegen.py
@@ -540,6 +540,33 @@ class TestPegen(unittest.TestCase):
         with self.assertRaises(GrammarError):
             parser_class = make_parser(grammar)
 
+    def test_invalid_rule_name(self) -> None:
+        grammar = """
+        start: _a b
+        _a: 'a'
+        b: 'b'
+        """
+        with self.assertRaisesRegex(GrammarError, "cannot start with underscore: '_a'"):
+            parser_class = make_parser(grammar)
+
+    def test_invalid_variable_name(self) -> None:
+        grammar = """
+        start: a b
+        a: _x='a'
+        b: 'b'
+        """
+        with self.assertRaisesRegex(GrammarError, "cannot start with underscore: '_x'"):
+            parser_class = make_parser(grammar)
+
+    def test_invalid_variable_name_in_temporal_rule(self) -> None:
+        grammar = """
+        start: a b
+        a: (_x='a' | 'b') | 'c'
+        b: 'b'
+        """
+        with self.assertRaisesRegex(GrammarError, "cannot start with underscore: '_x'"):
+            parser_class = make_parser(grammar)
+
 
 class TestGrammarVisitor:
     class Visitor(GrammarVisitor):