gh-93671: Avoid exponential backtracking in deeply nested sequence patterns in match...

Co-authored-by: Łukasz Langa <lukasz@langa.pl>

diff --git a/Grammar/python.gram b/Grammar/python.gram
index 15c40b6bbbacdcb4334e85b914b6fddca96bd8a3..67b7a553b93be4735cb8731544a9b43e3ec618d6 100644 (file)
--- a/Grammar/python.gram
+++ b/Grammar/python.gram
@@ -471,7 +471,7 @@ or_pattern[pattern_ty]:
     | patterns[asdl_pattern_seq*]='|'.closed_pattern+ {
         asdl_seq_LEN(patterns) == 1 ? asdl_seq_GET(patterns, 0) : _PyAST_MatchOr(patterns, EXTRA) }
 
-closed_pattern[pattern_ty]:
+closed_pattern[pattern_ty] (memo):
     | literal_pattern
     | capture_pattern
     | wildcard_pattern
@@ -558,7 +558,7 @@ maybe_star_pattern[pattern_ty]:
     | star_pattern
     | pattern
 
-star_pattern[pattern_ty]:
+star_pattern[pattern_ty] (memo):
     | '*' target=pattern_capture_target {
         _PyAST_MatchStar(target->v.Name.id, EXTRA) }
     | '*' wildcard_pattern {
@@ -1312,4 +1312,4 @@ invalid_kvpair:
     | a=expression !(':') {
         RAISE_ERROR_KNOWN_LOCATION(p, PyExc_SyntaxError, a->lineno, a->end_col_offset - 1, a->end_lineno, -1, "':' expected after dictionary key") }
     | expression ':' a='*' bitwise_or { RAISE_SYNTAX_ERROR_STARTING_FROM(a, "cannot use a starred expression in a dictionary value") }
-    | expression a=':' {RAISE_SYNTAX_ERROR_KNOWN_LOCATION(a, "expression expected after dictionary key and ':'") }
\ No newline at end of file
+    | expression a=':' {RAISE_SYNTAX_ERROR_KNOWN_LOCATION(a, "expression expected after dictionary key and ':'") }

diff --git a/Lib/test/test_patma.py b/Lib/test/test_patma.py
index 57d3b1ec701ca4c1072b827fb90cf16d33c951de..db198f7715783142aa37037d121a466cefa01550 100644 (file)
--- a/Lib/test/test_patma.py
+++ b/Lib/test/test_patma.py
@@ -3151,6 +3151,27 @@ class TestTracing(unittest.TestCase):
         self.assertListEqual(self._trace(f, "go x"), [1, 2, 3])
         self.assertListEqual(self._trace(f, "spam"), [1, 2, 3])
 
+    def test_parser_deeply_nested_patterns(self):
+        # Deeply nested patterns can cause exponential backtracking when parsing.
+        # See gh-93671 for more information.
+
+        levels = 100
+
+        patterns = [
+            "A" + "(" * levels + ")" * levels,
+            "{1:" * levels + "1" + "}" * levels,
+            "[" * levels + "1" + "]" * levels,
+        ]
+
+        for pattern in patterns:
+            with self.subTest(pattern):
+                code = inspect.cleandoc("""
+                    match None:
+                        case {}:
+                            pass
+                """.format(pattern))
+                compile(code, "<string>", "exec")
+
 
 if __name__ == "__main__":
     """

diff --git a/Misc/NEWS.d/next/Core and Builtins/2022-06-10-12-03-17.gh-issue-93671.idkQqG.rst b/Misc/NEWS.d/next/Core and Builtins/2022-06-10-12-03-17.gh-issue-93671.idkQqG.rst
new file mode 100644 (file)
index 0000000..a775715
--- /dev/null
+++ b/Misc/NEWS.d/next/Core and Builtins/2022-06-10-12-03-17.gh-issue-93671.idkQqG.rst
@@ -0,0 +1,2 @@
+Fix some exponential backtrace case happening with deeply nested sequence
+patterns in match statements. Patch by Pablo Galindo

diff --git a/Parser/parser.c b/Parser/parser.c
index 31ad9a0ce7a72127f3227cf3d0eed6f27c9481b8..50fd03c15ce6d5cb3d6761580115ac49cc886e7b 100644 (file)
--- a/Parser/parser.c
+++ b/Parser/parser.c
@@ -7945,6 +7945,10 @@ closed_pattern_rule(Parser *p)
         return NULL;
     }
     pattern_ty _res = NULL;
+    if (_PyPegen_is_memoized(p, closed_pattern_type, &_res)) {
+        p->level--;
+        return _res;
+    }
     int _mark = p->mark;
     { // literal_pattern
         if (p->error_indicator) {
@@ -8100,6 +8104,7 @@ closed_pattern_rule(Parser *p)
     }
     _res = NULL;
   done:
+    _PyPegen_insert_memo(p, _mark, closed_pattern_type, _res);
     p->level--;
     return _res;
 }
@@ -9623,6 +9628,10 @@ star_pattern_rule(Parser *p)
         return NULL;
     }
     pattern_ty _res = NULL;
+    if (_PyPegen_is_memoized(p, star_pattern_type, &_res)) {
+        p->level--;
+        return _res;
+    }
     int _mark = p->mark;
     if (p->mark == p->fill && _PyPegen_fill_token(p) < 0) {
         p->error_indicator = 1;
@@ -9707,6 +9716,7 @@ star_pattern_rule(Parser *p)
     }
     _res = NULL;
   done:
+    _PyPegen_insert_memo(p, _mark, star_pattern_type, _res);
     p->level--;
     return _res;
 }