summaryrefslogtreecommitdiff
path: root/src/regex.c
diff options
context:
space:
mode:
authorPaul Eggert <eggert@cs.ucla.edu>2016-10-23 02:50:48 -0700
committerPaul Eggert <eggert@cs.ucla.edu>2016-10-23 02:50:48 -0700
commit394bdb8f2317e312d39e071b588581802dd3027a (patch)
tree159fc5496fbecff8760a3c434e82f95f67e99e61 /src/regex.c
parent46288dd6321e2ff4028781383660786050933304 (diff)
parent50fa7d64d36c3f2d6ab11e7136575fbca7012cae (diff)
downloademacs-394bdb8f2317e312d39e071b588581802dd3027a.tar.gz
Merge from origin/emacs-25
50fa7d6 ;* src/w32heap.c: Fix typo and wording of the comments. 6f1325e electric-quote mode no longer worries about coding c2a1792 * src/regex.c (re_search_2): Make new code safe for -Wjump-mi... f6134bb Port to GCC 6.2.1 + --enable-gcc-warnings b2ba630 Explain how to debug emacsclient lisp errors 9da53e2 Let describe-function work for lambda again 5c2da93 Fix kill-line's docstring ad66b3f Fix handling of allocation in regex matching 5a26c9b * lisp/electric.el (electric-quote-mode): Improve doc (Bug#24... 3877c91 vc-region-history: Search just on lines intersecting the region 8988327 Fix documentation of 'alist-get' b6998ea * src/regex.h (re_match_object): Improve commentary. # Conflicts: # etc/NEWS # lisp/help-fns.el
Diffstat (limited to 'src/regex.c')
-rw-r--r--src/regex.c79
1 files changed, 77 insertions, 2 deletions
diff --git a/src/regex.c b/src/regex.c
index 1917a8480ae..8bc830356d0 100644
--- a/src/regex.c
+++ b/src/regex.c
@@ -153,6 +153,8 @@
/* Converts the pointer to the char to BEG-based offset from the start. */
# define PTR_TO_OFFSET(d) POS_AS_IN_BUFFER (POINTER_TO_OFFSET (d))
+/* Strings are 0-indexed, buffers are 1-indexed; we pun on the boolean
+ result to get the right base index. */
# define POS_AS_IN_BUFFER(p) ((p) + (NILP (re_match_object) || BUFFERP (re_match_object)))
# define RE_MULTIBYTE_P(bufp) ((bufp)->multibyte)
@@ -1363,11 +1365,62 @@ typedef struct
#define NEXT_FAILURE_HANDLE(h) fail_stack.stack[(h) - 3].integer
#define TOP_FAILURE_HANDLE() fail_stack.frame
+#ifdef emacs
+# define STR_BASE_PTR(obj) \
+ (NILP (obj) ? current_buffer->text->beg \
+ : STRINGP (obj) ? SDATA (obj) \
+ : NULL)
+#else
+# define STR_BASE_PTR(obj) NULL
+#endif
#define ENSURE_FAIL_STACK(space) \
while (REMAINING_AVAIL_SLOTS <= space) { \
+ re_char *orig_base = STR_BASE_PTR (re_match_object); \
+ bool might_relocate = orig_base != NULL; \
+ ptrdiff_t string1_off, end1_off, end_match_1_off; \
+ ptrdiff_t string2_off, end2_off, end_match_2_off; \
+ ptrdiff_t d_off, dend_off, dfail_off; \
+ if (might_relocate) \
+ { \
+ if (string1) \
+ { \
+ string1_off = string1 - orig_base; \
+ end1_off = end1 - orig_base; \
+ end_match_1_off = end_match_1 - orig_base; \
+ } \
+ if (string2) \
+ { \
+ string2_off = string2 - orig_base; \
+ end2_off = end2 - orig_base; \
+ end_match_2_off = end_match_2 - orig_base; \
+ } \
+ d_off = d - orig_base; \
+ dend_off = dend - orig_base; \
+ dfail_off = dfail - orig_base; \
+ } \
if (!GROW_FAIL_STACK (fail_stack)) \
return -2; \
+ /* In Emacs, GROW_FAIL_STACK might relocate string pointers. */ \
+ if (might_relocate) \
+ { \
+ re_char *new_base = STR_BASE_PTR (re_match_object); \
+ if (string1) \
+ { \
+ string1 = new_base + string1_off; \
+ end1 = new_base + end1_off; \
+ end_match_1 = new_base + end_match_1_off; \
+ } \
+ if (string2) \
+ { \
+ string2 = new_base + string2_off; \
+ end2 = new_base + end2_off; \
+ end_match_2 = new_base + end_match_2_off; \
+ } \
+ d = new_base + d_off; \
+ dend = new_base + dend_off; \
+ dfail = new_base + dfail_off; \
+ } \
DEBUG_PRINT ("\n Doubled stack; size now: %zd\n", (fail_stack).size);\
DEBUG_PRINT (" slots available: %zd\n", REMAINING_AVAIL_SLOTS);\
}
@@ -4293,6 +4346,10 @@ re_search_2 (struct re_pattern_buffer *bufp, const char *str1, size_t size1,
/* Loop through the string, looking for a place to start matching. */
for (;;)
{
+ ptrdiff_t offset1, offset2;
+ re_char *orig_base;
+ bool might_relocate;
+
/* If the pattern is anchored,
skip quickly past places we cannot match.
We don't bother to treat startpos == 0 specially
@@ -4409,6 +4466,17 @@ re_search_2 (struct re_pattern_buffer *bufp, const char *str1, size_t size1,
&& !bufp->can_be_null)
return -1;
+ /* re_match_2_internal may allocate, relocating the Lisp text
+ object that we're searching. */
+ IF_LINT (offset2 = 0); /* Work around GCC bug 78081. */
+ orig_base = STR_BASE_PTR (re_match_object);
+ might_relocate = orig_base != NULL;
+ if (might_relocate)
+ {
+ if (string1) offset1 = string1 - orig_base;
+ if (string2) offset2 = string2 - orig_base;
+ }
+
val = re_match_2_internal (bufp, string1, size1, string2, size2,
startpos, regs, stop);
@@ -4418,6 +4486,13 @@ re_search_2 (struct re_pattern_buffer *bufp, const char *str1, size_t size1,
if (val == -2)
return -2;
+ if (might_relocate)
+ {
+ re_char *new_base = STR_BASE_PTR (re_match_object);
+ if (string1) string1 = offset1 + new_base;
+ if (string2) string2 = offset2 + new_base;
+ }
+
advance:
if (!range)
break;
@@ -4905,8 +4980,8 @@ WEAK_ALIAS (__re_match, re_match)
#endif /* not emacs */
#ifdef emacs
-/* In Emacs, this is the string or buffer in which we
- are matching. It is used for looking up syntax properties. */
+/* In Emacs, this is the string or buffer in which we are matching.
+ See the declaration in regex.h for details. */
Lisp_Object re_match_object;
#endif