grep: disable lookahead on error

regexec(3) can fail.  E.g. on macOS it fails if it is used with an UTF-8
locale to match a valid regex against a buffer containing invalid UTF-8
characters.

git grep has two ways to search for matches in a file: Either it splits
its contents into lines and matches them separately, or it matches the
whole content and figures out line boundaries later.  The latter is done
by look_ahead() and it's quicker in the common case where most files
don't contain a match.

Fall back to line-by-line matching if look_ahead() encounters an
regexec(3) error by propagating errors out of patmatch() and bailing out
of look_ahead() if there is one.  This way we at least can find matches
in lines that contain only valid characters.  That matches the behavior
of grep(1) on macOS.

pcre2match() dies if pcre2_jit_match() or pcre2_match() fail, but since
we use the flag PCRE2_MATCH_INVALID_UTF it handles invalid UTF-8
characters gracefully.  So implement the fall-back only for regexec(3)
and leave the PCRE2 matching unchanged.

Reported-by: David Gstir <david@sigma-star.at>
Signed-off-by: René Scharfe <l.s.r@web.de>
Tested-by: David Gstir <david@sigma-star.at>
Signed-off-by: Taylor Blau <me@ttaylorr.com>

diff --git a/grep.c b/grep.c
index 701e58de04ef61d5c183200d96919cbc794f5d53..506f0423c8013b12db18c47764c23ca06ea0d118 100644 (file)
--- a/grep.c
+++ b/grep.c
@@ -906,15 +906,17 @@ static int patmatch(struct grep_pat *p,
                    const char *line, const char *eol,
                    regmatch_t *match, int eflags)
 {
-       int hit;
-
        if (p->pcre2_pattern)
-               hit = !pcre2match(p, line, eol, match, eflags);
-       else
-               hit = !regexec_buf(&p->regexp, line, eol - line, 1, match,
-                                  eflags);
+               return !pcre2match(p, line, eol, match, eflags);
 
-       return hit;
+       switch (regexec_buf(&p->regexp, line, eol - line, 1, match, eflags)) {
+       case 0:
+               return 1;
+       case REG_NOMATCH:
+               return 0;
+       default:
+               return -1;
+       }
 }
 
 static void strip_timestamp(const char *bol, const char **eol_p)
@@ -952,6 +954,8 @@ static int headerless_match_one_pattern(struct grep_pat *p,
 
  again:
        hit = patmatch(p, bol, eol, pmatch, eflags);
+       if (hit < 0)
+               hit = 0;
 
        if (hit && p->word_regexp) {
                if ((pmatch[0].rm_so < 0) ||
@@ -1461,6 +1465,8 @@ static int look_ahead(struct grep_opt *opt,
                regmatch_t m;
 
                hit = patmatch(p, bol, bol + *left_p, &m, 0);
+               if (hit < 0)
+                       return -1;
                if (!hit || m.rm_so < 0 || m.rm_eo < 0)
                        continue;
                if (earliest < 0 || m.rm_so < earliest)
@@ -1655,9 +1661,13 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle
                if (try_lookahead
                    && !(last_hit
                         && (show_function ||
-                            lno <= last_hit + opt->post_context))
-                   && look_ahead(opt, &left, &lno, &bol))
-                       break;
+                            lno <= last_hit + opt->post_context))) {
+                       hit = look_ahead(opt, &left, &lno, &bol);
+                       if (hit < 0)
+                               try_lookahead = 0;
+                       else if (hit)
+                               break;
+               }
                eol = end_of_line(bol, &left);
 
                if ((ctx == GREP_CONTEXT_HEAD) && (eol == bol))

diff --git a/t/t7810-grep.sh b/t/t7810-grep.sh
index af2cf2f78ab890662c3743ae407aa6ac101b5d8d..64ac4f04ee97ad5ec51a17f240ad3fccb17c559f 100755 (executable)
--- a/t/t7810-grep.sh
+++ b/t/t7810-grep.sh
@@ -87,6 +87,7 @@ test_expect_success setup '
        # Still a no-op.
        function dummy() {}
        EOF
+       printf "\200\nASCII\n" >invalid-utf8 &&
        if test_have_prereq FUNNYNAMES
        then
                echo unusual >"\"unusual\" pathname" &&
@@ -534,6 +535,14 @@ do
                test_cmp expected actual
        '
 
+       test_expect_success "grep $L searches past invalid lines on UTF-8 locale" '
+               LC_ALL=en_US.UTF-8 git grep A. invalid-utf8 >actual &&
+               cat >expected <<-EOF &&
+               invalid-utf8:ASCII
+               EOF
+               test_cmp expected actual
+       '
+
        test_expect_success FUNNYNAMES "grep $L should quote unusual pathnames" '
                cat >expected <<-EOF &&
                ${HC}"\"unusual\" pathname":unusual