Fixed bug #470582, using a modified version of patch #527371,

niemeyer · niemeyer · commit 4e7be06a6526 · 2002-11-06T14:06:53.000Z
from Greg Chapman.

* Modules/_sre.c
  (lastmark_restore): New function, implementing algorithm to restore
  a state to a given lastmark. In addition to the similar algorithm used
  in a few places of SRE_MATCH, restore lastindex when restoring lastmark.
  (SRE_MATCH): Replace lastmark inline restoring by lastmark_restore(),
  function. Also include it where missing. In SRE_OP_MARK, set lastindex
  only if i &gt; lastmark.

* Lib/test/re_tests.py
* Lib/test/test_sre.py
  Included regression tests for the fixed bugs.

* Misc/NEWS
  Mention fixes.
diff --git a/Lib/test/re_tests.py b/Lib/test/re_tests.py
@@ -646,6 +646,8 @@
     (r'a[^>]*?b', 'a>b', FAIL),
     # bug 490573: minimizing repeat problem
     (r'^a*?$', 'foo', FAIL),
+    # bug 470582: nested groups problem
+    (r'^((a)c)?(ab)$', 'ab', SUCCEED, 'g1+"-"+g2+"-"+g3', 'None-None-ab'),
 ]
 
 try:
diff --git a/Lib/test/test_sre.py b/Lib/test/test_sre.py
@@ -78,6 +78,11 @@ def test(expression, result, exception=None):
 test(r"""sre.match(r'(a)|(b)', 'b').end(1)""", -1)
 test(r"""sre.match(r'(a)|(b)', 'b').span(1)""", (-1, -1))
 
+# bug described in patch 527371
+test(r"""sre.match(r'(a)?a','a').lastindex""", None)
+test(r"""sre.match(r'(a)(b)?b','ab').lastindex""", 1)
+test(r"""sre.match(r'(?P<a>a)(?P<b>b)?b','ab').lastgroup""", 'a')
+
 if verbose:
     print 'Running tests on sre.sub'
 
diff --git a/Misc/NEWS b/Misc/NEWS
@@ -352,6 +352,13 @@ Extension modules
   to the value of the PYTHON_API_VERSION macro with which the
   interpreter was compiled.
 
+- Fixed bug #470582: sre module would return a tuple (None, 'a', 'ab')
+  when applying the regular expression '^((a)c)?(ab)$' on 'ab'. It now
+  returns (None, None, 'ab'), as expected. Also fixed handling of
+  lastindex/lastgroup match attributes in a similar cases. For example,
+  when running the expression r'(a)(b)?b' over 'ab', lastindex must be
+  1, not 2.
+
 Library
 -------
 
diff --git a/Modules/_sre.c b/Modules/_sre.c
@@ -353,6 +353,18 @@ mark_restore(SRE_STATE* state, int lo, int hi)
     return 0;
 }
 
+void lastmark_restore(SRE_STATE *state, int lastmark)
+{
+    if (state->lastmark > lastmark) {
+        memset(
+            state->mark + lastmark + 1, 0,
+            (state->lastmark - lastmark) * sizeof(void*)
+            );
+        state->lastmark = lastmark;
+        state->lastindex = (lastmark == 0) ? -1 : (lastmark-1)/2+1;
+    }
+}
+
 /* generate 8-bit version */
 
 #define SRE_CHAR unsigned char
@@ -860,10 +872,11 @@ SRE_MATCH(SRE_STATE* state, SRE_CODE* pattern, int level)
             /* <MARK> <gid> */
             TRACE(("|%p|%p|MARK %d\n", pattern, ptr, pattern[0]));
             i = pattern[0];
-            if (i & 1)
-                state->lastindex = i/2 + 1;
-            if (i > state->lastmark)
+            if (i > state->lastmark) {
                 state->lastmark = i;
+                if (i & 1)
+                    state->lastindex = i/2 + 1;
+            }
             state->mark[i] = ptr;
             pattern++;
             break;
@@ -920,13 +933,7 @@ SRE_MATCH(SRE_STATE* state, SRE_CODE* pattern, int level)
                 i = SRE_MATCH(state, pattern + 1, level + 1);
                 if (i)
                     return i;
-                if (state->lastmark > lastmark) {
-                    memset(
-                        state->mark + lastmark + 1, 0,
-                        (state->lastmark - lastmark) * sizeof(void*)
-                        );
-                    state->lastmark = lastmark;
-                }
+                lastmark_restore(state, lastmark);
             }
             return 0;
 
@@ -997,13 +1004,7 @@ SRE_MATCH(SRE_STATE* state, SRE_CODE* pattern, int level)
                         return i;
                     ptr--;
                     count--;
-                    if (state->lastmark > lastmark) {
-                        memset(
-                            state->mark + lastmark + 1, 0,
-                            (state->lastmark - lastmark) * sizeof(void*)
-                            );
-                        state->lastmark = lastmark;
-                    }
+                    lastmark_restore(state, lastmark);
                 }
             }
             return 0;
@@ -1071,9 +1072,9 @@ SRE_MATCH(SRE_STATE* state, SRE_CODE* pattern, int level)
                 if (i)
                     return i;
                 i = mark_restore(state, 0, lastmark);
-                state->lastmark = lastmark;
                 if (i < 0)
                     return i;
+                lastmark_restore(state, lastmark);
                 rp->count = count - 1;
                 state->ptr = ptr;
             }

Original file line number	Diff line number	Diff line change
`@@ -646,6 +646,8 @@`
`646`	`646`	`(r'a[^>]*?b', 'a>b', FAIL),`
`647`	`647`	`# bug 490573: minimizing repeat problem`
`648`	`648`	`(r'^a*?$', 'foo', FAIL),`
	`649`	`+ # bug 470582: nested groups problem`
	`650`	`+ (r'^((a)c)?(ab)$', 'ab', SUCCEED, 'g1+"-"+g2+"-"+g3', 'None-None-ab'),`
`649`	`651`	`]`
`650`	`652`
`651`	`653`	`try:`