197 lines
5.0 KiB
Diff
197 lines
5.0 KiB
Diff
|
--- grep-2.5.1/src/search.c.fgrep 2001-04-19 04:42:14.000000000 +0100
|
||
|
+++ grep-2.5.1/src/search.c 2004-02-26 13:09:32.000000000 +0000
|
||
|
@@ -360,13 +360,7 @@
|
||
|
/* Find a possible match using the KWset matcher. */
|
||
|
size_t offset = kwsexec (kwset, beg, buflim - beg, &kwsm);
|
||
|
if (offset == (size_t) -1)
|
||
|
- {
|
||
|
-#ifdef MBS_SUPPORT
|
||
|
- if (MB_CUR_MAX > 1)
|
||
|
- free(mb_properties);
|
||
|
-#endif
|
||
|
- return (size_t)-1;
|
||
|
- }
|
||
|
+ goto failure;
|
||
|
beg += offset;
|
||
|
/* Narrow down to the line containing the candidate, and
|
||
|
run it through DFA. */
|
||
|
@@ -379,7 +373,7 @@
|
||
|
while (beg > buf && beg[-1] != eol)
|
||
|
--beg;
|
||
|
if (kwsm.index < kwset_exact_matches)
|
||
|
- goto success;
|
||
|
+ goto success_in_beg_and_end;
|
||
|
if (dfaexec (&dfa, beg, end - beg, &backref) == (size_t) -1)
|
||
|
continue;
|
||
|
}
|
||
|
@@ -398,7 +392,7 @@
|
||
|
}
|
||
|
/* Successful, no backreferences encountered! */
|
||
|
if (!backref)
|
||
|
- goto success;
|
||
|
+ goto success_in_beg_and_end;
|
||
|
}
|
||
|
else
|
||
|
end = beg + size;
|
||
|
@@ -413,14 +407,11 @@
|
||
|
end - beg - 1, &(patterns[i].regs))))
|
||
|
{
|
||
|
len = patterns[i].regs.end[0] - start;
|
||
|
- if (exact)
|
||
|
- {
|
||
|
- *match_size = len;
|
||
|
- return start;
|
||
|
- }
|
||
|
+ if (exact && !match_words)
|
||
|
+ goto success_in_start_and_len;
|
||
|
if ((!match_lines && !match_words)
|
||
|
|| (match_lines && len == end - beg - 1))
|
||
|
- goto success;
|
||
|
+ goto success_in_beg_and_end;
|
||
|
/* If -w, check if the match aligns with word boundaries.
|
||
|
We do this iteratively because:
|
||
|
(a) the line may contain more than one occurence of the
|
||
|
@@ -434,7 +425,7 @@
|
||
|
if ((start == 0 || !WCHAR ((unsigned char) beg[start - 1]))
|
||
|
&& (len == end - beg - 1
|
||
|
|| !WCHAR ((unsigned char) beg[start + len])))
|
||
|
- goto success;
|
||
|
+ goto success_in_start_and_len;
|
||
|
if (len > 0)
|
||
|
{
|
||
|
/* Try a shorter length anchored at the same place. */
|
||
|
@@ -461,19 +452,26 @@
|
||
|
}
|
||
|
} /* for Regex patterns. */
|
||
|
} /* for (beg = end ..) */
|
||
|
+
|
||
|
+ failure:
|
||
|
#ifdef MBS_SUPPORT
|
||
|
if (MB_CUR_MAX > 1 && mb_properties)
|
||
|
free (mb_properties);
|
||
|
#endif /* MBS_SUPPORT */
|
||
|
return (size_t) -1;
|
||
|
|
||
|
- success:
|
||
|
+ success_in_beg_and_end:
|
||
|
+ len = end - beg;
|
||
|
+ start = beg - buf;
|
||
|
+ /* FALLTHROUGH */
|
||
|
+
|
||
|
+ success_in_start_and_len:
|
||
|
#ifdef MBS_SUPPORT
|
||
|
if (MB_CUR_MAX > 1 && mb_properties)
|
||
|
free (mb_properties);
|
||
|
#endif /* MBS_SUPPORT */
|
||
|
- *match_size = end - beg;
|
||
|
- return beg - buf;
|
||
|
+ *match_size = len;
|
||
|
+ return start;
|
||
|
}
|
||
|
|
||
|
static void
|
||
|
@@ -516,28 +514,15 @@
|
||
|
{
|
||
|
size_t offset = kwsexec (kwset, beg, buf + size - beg, &kwsmatch);
|
||
|
if (offset == (size_t) -1)
|
||
|
- {
|
||
|
-#ifdef MBS_SUPPORT
|
||
|
- if (MB_CUR_MAX > 1)
|
||
|
- free(mb_properties);
|
||
|
-#endif /* MBS_SUPPORT */
|
||
|
- return offset;
|
||
|
- }
|
||
|
+ goto failure;
|
||
|
#ifdef MBS_SUPPORT
|
||
|
if (MB_CUR_MAX > 1 && mb_properties[offset+beg-buf] == 0)
|
||
|
continue; /* It is a part of multibyte character. */
|
||
|
#endif /* MBS_SUPPORT */
|
||
|
beg += offset;
|
||
|
len = kwsmatch.size[0];
|
||
|
- if (exact)
|
||
|
- {
|
||
|
- *match_size = len;
|
||
|
-#ifdef MBS_SUPPORT
|
||
|
- if (MB_CUR_MAX > 1)
|
||
|
- free (mb_properties);
|
||
|
-#endif /* MBS_SUPPORT */
|
||
|
- return beg - buf;
|
||
|
- }
|
||
|
+ if (exact && !match_words)
|
||
|
+ goto success_in_beg_and_len;
|
||
|
if (match_lines)
|
||
|
{
|
||
|
if (beg > buf && beg[-1] != eol)
|
||
|
@@ -547,31 +532,37 @@
|
||
|
goto success;
|
||
|
}
|
||
|
else if (match_words)
|
||
|
- for (try = beg; len; )
|
||
|
- {
|
||
|
- if (try > buf && WCHAR((unsigned char) try[-1]))
|
||
|
- break;
|
||
|
- if (try + len < buf + size && WCHAR((unsigned char) try[len]))
|
||
|
- {
|
||
|
- offset = kwsexec (kwset, beg, --len, &kwsmatch);
|
||
|
- if (offset == (size_t) -1)
|
||
|
- {
|
||
|
-#ifdef MBS_SUPPORT
|
||
|
- if (MB_CUR_MAX > 1)
|
||
|
- free (mb_properties);
|
||
|
-#endif /* MBS_SUPPORT */
|
||
|
- return offset;
|
||
|
- }
|
||
|
- try = beg + offset;
|
||
|
- len = kwsmatch.size[0];
|
||
|
- }
|
||
|
- else
|
||
|
- goto success;
|
||
|
- }
|
||
|
+ {
|
||
|
+ while (offset >= 0)
|
||
|
+ {
|
||
|
+ if ((offset == 0 || !WCHAR ((unsigned char) beg[-1]))
|
||
|
+ && (len == end - beg - 1 || !WCHAR ((unsigned char) beg[len])))
|
||
|
+ {
|
||
|
+ if (!exact)
|
||
|
+ /* Returns the whole line now we know there's a word match. */
|
||
|
+ goto success;
|
||
|
+ else
|
||
|
+ /* Returns just this word match. */
|
||
|
+ goto success_in_beg_and_len;
|
||
|
+ }
|
||
|
+ if (len > 0)
|
||
|
+ {
|
||
|
+ /* Try a shorter length anchored at the same place. */
|
||
|
+ --len;
|
||
|
+ offset = kwsexec (kwset, beg, len, &kwsmatch);
|
||
|
+ if (offset == -1) {
|
||
|
+ break; /* Try a different anchor. */
|
||
|
+ }
|
||
|
+ beg += offset;
|
||
|
+ len = kwsmatch.size[0];
|
||
|
+ }
|
||
|
+ }
|
||
|
+ }
|
||
|
else
|
||
|
goto success;
|
||
|
}
|
||
|
|
||
|
+ failure:
|
||
|
#ifdef MBS_SUPPORT
|
||
|
if (MB_CUR_MAX > 1)
|
||
|
free (mb_properties);
|
||
|
@@ -583,7 +574,11 @@
|
||
|
end++;
|
||
|
while (buf < beg && beg[-1] != eol)
|
||
|
--beg;
|
||
|
- *match_size = end - beg;
|
||
|
+ len = end - beg;
|
||
|
+ /* FALLTHROUGH */
|
||
|
+
|
||
|
+ success_in_beg_and_len:
|
||
|
+ *match_size = len;
|
||
|
#ifdef MBS_SUPPORT
|
||
|
if (MB_CUR_MAX > 1)
|
||
|
free (mb_properties);
|