[Python-checkins] cpython (merge 3.4 -> default): Issue #20998: Fixed re.fullmatch() of repeated single character pattern

serhiy.storchaka python-checkins at python.org
Wed May 14 20:52:09 CEST 2014


http://hg.python.org/cpython/rev/bcf64c1c92f6
changeset:   90710:bcf64c1c92f6
parent:      90708:4041d4077a85
parent:      90709:6267428afbdb
user:        Serhiy Storchaka <storchaka at gmail.com>
date:        Wed May 14 21:51:37 2014 +0300
summary:
  Issue #20998: Fixed re.fullmatch() of repeated single character pattern
with ignore case.  Original patch by Matthew Barnett.

files:
  Lib/test/test_re.py |   5 +++++
  Misc/NEWS           |   3 +++
  Modules/_sre.c      |  15 +++++++--------
  Modules/sre.h       |   1 -
  Modules/sre_lib.h   |  20 ++++++++++----------
  5 files changed, 25 insertions(+), 19 deletions(-)


diff --git a/Lib/test/test_re.py b/Lib/test/test_re.py
--- a/Lib/test/test_re.py
+++ b/Lib/test/test_re.py
@@ -1223,6 +1223,11 @@
             pat.scanner(string='abracadabra', pos=3, endpos=10).search().span(),
             (7, 9))
 
+    def test_bug_20998(self):
+        # Issue #20998: Fullmatch of repeated single character pattern
+        # with ignore case.
+        self.assertEqual(re.fullmatch('[a-c]+', 'ABC', re.I).span(), (0, 3))
+
 
 class PatternReprTests(unittest.TestCase):
     def check(self, pattern, expected):
diff --git a/Misc/NEWS b/Misc/NEWS
--- a/Misc/NEWS
+++ b/Misc/NEWS
@@ -84,6 +84,9 @@
 Library
 -------
 
+- Issue #20998: Fixed re.fullmatch() of repeated single character pattern
+  with ignore case.  Original patch by Matthew Barnett.
+
 - Issue #21075: fileinput.FileInput now reads bytes from standard stream if
   binary mode is specified.  Patch by Sam Kimbrel.
 
diff --git a/Modules/_sre.c b/Modules/_sre.c
--- a/Modules/_sre.c
+++ b/Modules/_sre.c
@@ -505,14 +505,14 @@
 }
 
 LOCAL(Py_ssize_t)
-sre_match(SRE_STATE* state, SRE_CODE* pattern)
+sre_match(SRE_STATE* state, SRE_CODE* pattern, int match_all)
 {
     if (state->charsize == 1)
-        return sre_ucs1_match(state, pattern);
+        return sre_ucs1_match(state, pattern, match_all);
     if (state->charsize == 2)
-        return sre_ucs2_match(state, pattern);
+        return sre_ucs2_match(state, pattern, match_all);
     assert(state->charsize == 4);
-    return sre_ucs4_match(state, pattern);
+    return sre_ucs4_match(state, pattern, match_all);
 }
 
 LOCAL(Py_ssize_t)
@@ -576,7 +576,7 @@
 
     TRACE(("|%p|%p|MATCH\n", PatternObject_GetCode(self), state.ptr));
 
-    status = sre_match(&state, PatternObject_GetCode(self));
+    status = sre_match(&state, PatternObject_GetCode(self), 0);
 
     TRACE(("|%p|%p|END\n", PatternObject_GetCode(self), state.ptr));
     if (PyErr_Occurred())
@@ -609,12 +609,11 @@
     if (!string)
         return NULL;
 
-    state.match_all = 1;
     state.ptr = state.start;
 
     TRACE(("|%p|%p|FULLMATCH\n", PatternObject_GetCode(self), state.ptr));
 
-    status = sre_match(&state, PatternObject_GetCode(self));
+    status = sre_match(&state, PatternObject_GetCode(self), 1);
 
     TRACE(("|%p|%p|END\n", PatternObject_GetCode(self), state.ptr));
     if (PyErr_Occurred())
@@ -2572,7 +2571,7 @@
 
     state->ptr = state->start;
 
-    status = sre_match(state, PatternObject_GetCode(self->pattern));
+    status = sre_match(state, PatternObject_GetCode(self->pattern), 0);
     if (PyErr_Occurred())
         return NULL;
 
diff --git a/Modules/sre.h b/Modules/sre.h
--- a/Modules/sre.h
+++ b/Modules/sre.h
@@ -86,7 +86,6 @@
     SRE_REPEAT *repeat;
     /* hooks */
     SRE_TOLOWER_HOOK lower;
-    int match_all;
 } SRE_STATE;
 
 typedef struct {
diff --git a/Modules/sre_lib.h b/Modules/sre_lib.h
--- a/Modules/sre_lib.h
+++ b/Modules/sre_lib.h
@@ -173,7 +173,7 @@
     }
 }
 
-LOCAL(Py_ssize_t) SRE(match)(SRE_STATE* state, SRE_CODE* pattern);
+LOCAL(Py_ssize_t) SRE(match)(SRE_STATE* state, SRE_CODE* pattern, int match_all);
 
 LOCAL(Py_ssize_t)
 SRE(count)(SRE_STATE* state, SRE_CODE* pattern, Py_ssize_t maxcount)
@@ -259,7 +259,7 @@
         /* repeated single character pattern */
         TRACE(("|%p|%p|COUNT SUBPATTERN\n", pattern, ptr));
         while ((SRE_CHAR*) state->ptr < end) {
-            i = SRE(match)(state, pattern);
+            i = SRE(match)(state, pattern, 0);
             if (i < 0)
                 return i;
             if (!i)
@@ -490,7 +490,7 @@
 /* check if string matches the given pattern.  returns <0 for
    error, 0 for failure, and 1 for success */
 LOCAL(Py_ssize_t)
-SRE(match)(SRE_STATE* state, SRE_CODE* pattern)
+SRE(match)(SRE_STATE* state, SRE_CODE* pattern, int match_all)
 {
     SRE_CHAR* end = (SRE_CHAR *)state->end;
     Py_ssize_t alloc_pos, ctx_pos = -1;
@@ -507,7 +507,7 @@
     ctx->last_ctx_pos = -1;
     ctx->jump = JUMP_NONE;
     ctx->pattern = pattern;
-    ctx->match_all = state->match_all;
+    ctx->match_all = match_all;
     ctx_pos = alloc_pos;
 
 entrance:
@@ -739,7 +739,7 @@
                 RETURN_FAILURE;
 
             if (ctx->pattern[ctx->pattern[0]] == SRE_OP_SUCCESS &&
-                (!ctx->match_all || ctx->ptr == state->end)) {
+                ctx->ptr == state->end) {
                 /* tail is empty.  we're finished */
                 state->ptr = ctx->ptr;
                 RETURN_SUCCESS;
@@ -824,7 +824,7 @@
             }
 
             if (ctx->pattern[ctx->pattern[0]] == SRE_OP_SUCCESS &&
-                (!ctx->match_all || ctx->ptr == state->end)) {
+                (!match_all || ctx->ptr == state->end)) {
                 /* tail is empty.  we're finished */
                 state->ptr = ctx->ptr;
                 RETURN_SUCCESS;
@@ -1269,7 +1269,7 @@
                     state->ptr = ptr - (prefix_len - prefix_skip - 1);
                     if (flags & SRE_INFO_LITERAL)
                         return 1; /* we got all of it */
-                    status = SRE(match)(state, pattern + 2*prefix_skip);
+                    status = SRE(match)(state, pattern + 2*prefix_skip, 0);
                     if (status != 0)
                         return status;
                     /* close but no cigar -- try again */
@@ -1302,7 +1302,7 @@
             state->ptr = ++ptr;
             if (flags & SRE_INFO_LITERAL)
                 return 1; /* we got all of it */
-            status = SRE(match)(state, pattern + 2);
+            status = SRE(match)(state, pattern + 2, 0);
             if (status != 0)
                 break;
         }
@@ -1317,7 +1317,7 @@
             TRACE(("|%p|%p|SEARCH CHARSET\n", pattern, ptr));
             state->start = ptr;
             state->ptr = ptr;
-            status = SRE(match)(state, pattern);
+            status = SRE(match)(state, pattern, 0);
             if (status != 0)
                 break;
             ptr++;
@@ -1327,7 +1327,7 @@
         while (ptr <= end) {
             TRACE(("|%p|%p|SEARCH\n", pattern, ptr));
             state->start = state->ptr = ptr++;
-            status = SRE(match)(state, pattern);
+            status = SRE(match)(state, pattern, 0);
             if (status != 0)
                 break;
         }

-- 
Repository URL: http://hg.python.org/cpython


More information about the Python-checkins mailing list