Fixing bug #817234, which made SRE get into an infinite loop on

niemeyer · niemeyer · commit 0506c64086e2 · 2004-09-03T18:11:59.000Z
empty final matches with finditer(). New test cases included
for this bug and for #581080.
diff --git a/Lib/test/test_re.py b/Lib/test/test_re.py
@@ -567,6 +567,22 @@ def test_bug_931848(self):
         self.assertEqual(re.compile(pattern).split("a.b.c"),
                          ['a','b','c'])
 
+    def test_bug_581080(self):
+        iter = re.finditer(r"\s", "a b")
+        self.assertEqual(iter.next().span(), (1,2))
+        self.assertRaises(StopIteration, iter.next)
+
+        scanner = re.compile(r"\s").scanner("a b")
+        self.assertEqual(scanner.search().span(), (1, 2))
+        self.assertEqual(scanner.search(), None)
+
+    def test_bug_817234(self):
+        iter = re.finditer(r".*", "asdf")
+        self.assertEqual(iter.next().span(), (0, 4))
+        self.assertEqual(iter.next().span(), (4, 4))
+        self.assertRaises(StopIteration, iter.next)
+
+
 def run_re_tests():
     from test.re_tests import benchmarks, tests, SUCCEED, FAIL, SYNTAX_ERROR
     if verbose:
diff --git a/Modules/_sre.c b/Modules/_sre.c
@@ -539,7 +539,7 @@ SRE_COUNT(SRE_STATE* state, SRE_CODE* pattern, int maxcount)
         break;
 
     case SRE_OP_ANY_ALL:
-        /* repeated dot wildcare.  skip to the end of the target
+        /* repeated dot wildcard.  skip to the end of the target
            string, and backtrack from there */
         TRACE(("|%p|%p|COUNT ANY_ALL\n", pattern, ptr));
         ptr = end;
@@ -3244,8 +3244,7 @@ scanner_match(ScannerObject* self, PyObject* args)
     match = pattern_new_match((PatternObject*) self->pattern,
                                state, status);
 
-    if ((status == 0 || state->ptr == state->start) &&
-        state->ptr < state->end)
+    if (status == 0 || state->ptr == state->start)
         state->start = (void*) ((char*) state->ptr + state->charsize);
     else
         state->start = state->ptr;
@@ -3276,8 +3275,7 @@ scanner_search(ScannerObject* self, PyObject* args)
     match = pattern_new_match((PatternObject*) self->pattern,
                                state, status);
 
-    if ((status == 0 || state->ptr == state->start) &&
-        state->ptr < state->end)
+    if (status == 0 || state->ptr == state->start)
         state->start = (void*) ((char*) state->ptr + state->charsize);
     else
         state->start = state->ptr;
