summaryrefslogtreecommitdiff
path: root/builtin-grep.c
diff options
context:
space:
mode:
authorJunio C Hamano <junkio@cox.net>2006-08-05 05:16:42 (GMT)
committerJunio C Hamano <junkio@cox.net>2006-08-06 08:37:08 (GMT)
commitf25b79397c9775df9eeef3d59d0cc3b1f913bc60 (patch)
treed3506d5985b0d529ac87e6b1d3cb69cb3451c7fd /builtin-grep.c
parent0d958ac47a333b68b79cdc3ea206bb9a9b7486ad (diff)
downloadgit-f25b79397c9775df9eeef3d59d0cc3b1f913bc60.zip
git-f25b79397c9775df9eeef3d59d0cc3b1f913bc60.tar.gz
git-f25b79397c9775df9eeef3d59d0cc3b1f913bc60.tar.bz2
Fix "grep -w"
We used to find the first match of the pattern and then if the match is not for the entire word, declared that the whole line does not match. But that is wrong. The command "git grep -w -e mmap" should find that a line "foo_mmap bar mmap baz" matches, by tring the second instance of pattern "mmap" on the same line. Problems an earlier round of "fix" had were pointed out by Morten Welinder, which have been incorporated in the t7002 tests. Signed-off-by: Junio C Hamano <junkio@cox.net>
Diffstat (limited to 'builtin-grep.c')
-rw-r--r--builtin-grep.c35
1 files changed, 25 insertions, 10 deletions
diff --git a/builtin-grep.c b/builtin-grep.c
index 69b7c48..93b7e07 100644
--- a/builtin-grep.c
+++ b/builtin-grep.c
@@ -410,8 +410,10 @@ static int fixmatch(const char *pattern, char *line, regmatch_t *match)
static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol, char *eol)
{
int hit = 0;
+ int at_true_bol = 1;
regmatch_t pmatch[10];
+ again:
if (!opt->fixed) {
regex_t *exp = &p->regexp;
hit = !regexec(exp, bol, ARRAY_SIZE(pmatch),
@@ -422,22 +424,35 @@ static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol
}
if (hit && opt->word_regexp) {
- /* Match beginning must be either
- * beginning of the line, or at word
- * boundary (i.e. the last char must
- * not be alnum or underscore).
- */
if ((pmatch[0].rm_so < 0) ||
(eol - bol) <= pmatch[0].rm_so ||
(pmatch[0].rm_eo < 0) ||
(eol - bol) < pmatch[0].rm_eo)
die("regexp returned nonsense");
- if (pmatch[0].rm_so != 0 &&
- word_char(bol[pmatch[0].rm_so-1]))
- hit = 0;
- if (pmatch[0].rm_eo != (eol-bol) &&
- word_char(bol[pmatch[0].rm_eo]))
+
+ /* Match beginning must be either beginning of the
+ * line, or at word boundary (i.e. the last char must
+ * not be a word char). Similarly, match end must be
+ * either end of the line, or at word boundary
+ * (i.e. the next char must not be a word char).
+ */
+ if ( ((pmatch[0].rm_so == 0 && at_true_bol) ||
+ !word_char(bol[pmatch[0].rm_so-1])) &&
+ ((pmatch[0].rm_eo == (eol-bol)) ||
+ !word_char(bol[pmatch[0].rm_eo])) )
+ ;
+ else
hit = 0;
+
+ if (!hit && pmatch[0].rm_so + bol + 1 < eol) {
+ /* There could be more than one match on the
+ * line, and the first match might not be
+ * strict word match. But later ones could be!
+ */
+ bol = pmatch[0].rm_so + bol + 1;
+ at_true_bol = 0;
+ goto again;
+ }
}
return hit;
}