Issue #9669: Protect re against infinite loops on zero-width matching in

serhiy-storchaka · serhiy-storchaka · commit fa4681691591 · 2013-02-16T21:23:53.000+02:00
non-greedy repeat.  Patch by Matthew Barnett.
diff --git a/Lib/test/test_re.py b/Lib/test/test_re.py
@@ -616,6 +616,15 @@ def test_stack_overflow(self):
         self.assertEqual(re.match('(x)*y', 50000*'x'+'y').group(1), 'x')
         self.assertEqual(re.match('(x)*?y', 50000*'x'+'y').group(1), 'x')
 
+    def test_unlimited_zero_width_repeat(self):
+        # Issue #9669
+        self.assertIsNone(re.match(r'(?:a?)*y', 'z'))
+        self.assertIsNone(re.match(r'(?:a?)+y', 'z'))
+        self.assertIsNone(re.match(r'(?:a?){2,}y', 'z'))
+        self.assertIsNone(re.match(r'(?:a?)*?y', 'z'))
+        self.assertIsNone(re.match(r'(?:a?)+?y', 'z'))
+        self.assertIsNone(re.match(r'(?:a?){2,}?y', 'z'))
+
     def test_scanner(self):
         def s_ident(scanner, token): return token
         def s_operator(scanner, token): return "op%s" % token
diff --git a/Misc/NEWS b/Misc/NEWS
@@ -224,6 +224,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #9669: Protect re against infinite loops on zero-width matching in
+  non-greedy repeat.  Patch by Matthew Barnett.
+
 - Issue #13169: The maximal repetition number in a regular expression has been
   increased from 65534 to 2147483647 (on 32-bit platform) or 4294967294 (on
   64-bit).
diff --git a/Modules/_sre.c b/Modules/_sre.c
@@ -1295,13 +1295,18 @@ SRE_MATCH(SRE_STATE* state, SRE_CODE* pattern)
 
             LASTMARK_RESTORE();
 
-            if (ctx->count >= ctx->u.rep->pattern[2]
-                && ctx->u.rep->pattern[2] != SRE_MAXREPEAT)
+            if ((ctx->count >= ctx->u.rep->pattern[2]
+                && ctx->u.rep->pattern[2] != SRE_MAXREPEAT) ||
+                state->ptr == ctx->u.rep->last_ptr)
                 RETURN_FAILURE;
 
             ctx->u.rep->count = ctx->count;
+            /* zero-width match protection */
+            DATA_PUSH(&ctx->u.rep->last_ptr);
+            ctx->u.rep->last_ptr = state->ptr;
             DO_JUMP(JUMP_MIN_UNTIL_3,jump_min_until_3,
                     ctx->u.rep->pattern+3);
+            DATA_POP(&ctx->u.rep->last_ptr);
             if (ret) {
                 RETURN_ON_ERROR(ret);
                 RETURN_SUCCESS;
