aboutsummaryrefslogtreecommitdiff
path: root/usr.bin/grep/util.c
diff options
context:
space:
mode:
authorEd Maste <emaste@FreeBSD.org>2017-05-02 02:32:10 +0000
committerEd Maste <emaste@FreeBSD.org>2017-05-02 02:32:10 +0000
commit945fc991b2dc3385fb2a91cd0189b074ca1fad63 (patch)
tree342c645afa4954e93dcd07a93003ffa082b1b5a7 /usr.bin/grep/util.c
parentdf5be97c1aec5b18feec87eb06c1e11de7ac2b14 (diff)
downloadsrc-945fc991b2dc3385fb2a91cd0189b074ca1fad63.tar.gz
src-945fc991b2dc3385fb2a91cd0189b074ca1fad63.zip
bsdgrep: fix -w -v matching improperly with certain patterns
-w and -v flag matching was mostly functional but had some minor problems: 1. -w flag processing only allowed one iteration through pattern matching on a line. This was problematic if one pattern could match more than once, or if there were multiple patterns and the earliest/ longest match was not the most ideal, and 2. Previous work "fixed" things to not further process a line if the first iteration through patterns produced no matches. This is clearly wrong if we're dealing with the more restrictive -w matching. #2 breakage could have also occurred before recent broad rewrites, but it would be more arbitrary based on input patterns as to whether or not it actually affected things. Fix both of these by forcing a retry of the patterns after advancing just past the start of the first match if we're doing more restrictive -w matching and we didn't get any hits to start with. Also move -v flag processing outside of the loop so that we have a greater change to match in the more restrictive cases. This wasn't strictly wrong, but it could be a little more error prone. While here, introduce some regressions tests for this behavior and fix some excessive wrapping nearby that hindered readability. GNU grep passes these new tests. PR: 218467, 218811 Submitted by: Kyle Evans <kevans91 at ksu.edu> Reviewed by: cem, ngie Differential Revision: https://reviews.freebsd.org/D10329
Notes
Notes: svn path=/head/; revision=317665
Diffstat (limited to 'usr.bin/grep/util.c')
-rw-r--r--usr.bin/grep/util.c27
1 files changed, 24 insertions, 3 deletions
diff --git a/usr.bin/grep/util.c b/usr.bin/grep/util.c
index 8815d4f34227..dd9a753aac4e 100644
--- a/usr.bin/grep/util.c
+++ b/usr.bin/grep/util.c
@@ -305,6 +305,7 @@ procline(struct str *l, int nottext)
unsigned int i;
int c = 0, m = 0, r = 0, lastmatches = 0, leflags = eflags;
int startm = 0;
+ int retry;
/* Initialize to avoid a false positive warning from GCC. */
lastmatch.rm_so = lastmatch.rm_eo = 0;
@@ -313,6 +314,7 @@ procline(struct str *l, int nottext)
while (st <= l->len) {
lastmatches = 0;
startm = m;
+ retry = 0;
if (st > 0)
leflags |= REG_NOTBOL;
/* Loop to compare with all the patterns */
@@ -356,6 +358,17 @@ procline(struct str *l, int nottext)
else if (iswword(wbegin) ||
iswword(wend))
r = REG_NOMATCH;
+ /*
+ * If we're doing whole word matching and we
+ * matched once, then we should try the pattern
+ * again after advancing just past the start of
+ * the earliest match. This allows the pattern
+ * to match later on in the line and possibly
+ * still match a whole word.
+ */
+ if (r == REG_NOMATCH &&
+ (retry == 0 || pmatch.rm_so + 1 < retry))
+ retry = pmatch.rm_so + 1;
}
if (r == 0) {
lastmatches++;
@@ -385,9 +398,14 @@ procline(struct str *l, int nottext)
}
}
- if (vflag) {
- c = !c;
- break;
+ /*
+ * Advance to just past the start of the earliest match, try
+ * again just in case we still have a chance to match later in
+ * the string.
+ */
+ if (lastmatches == 0 && retry > 0) {
+ st = retry;
+ continue;
}
/* One pass if we are not recording matches */
@@ -410,6 +428,9 @@ procline(struct str *l, int nottext)
}
+ if (vflag)
+ c = !c;
+
/* Count the matches if we have a match limit */
if (mflag)
mcount -= c;