@matheusbsbs / matheus-bagliano / commits / ce025ae4f6

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>

René Scharfe committed Oct 20, 2024 at 13:02 UTC ce025ae4f61e8e32b2ae6589e43e03e60f713f2d

2 files changed +29 -10

grep.c

+20 -10

@@ -906,15 +906,17 @@ static int patmatch(struct grep_pat *p,

906 const char *line, const char *eol,

907 regmatch_t *match, int eflags)

908 {

909 - int hit;

910 -

909 if (p->pcre2_pattern)

912 - hit = !pcre2match(p, line, eol, match, eflags);

913 - else

914 - hit = !regexec_buf(&p->regexp, line, eol - line, 1, match,

915 - eflags);

910 + return !pcre2match(p, line, eol, match, eflags);

911

917 - return hit;

912 + switch (regexec_buf(&p->regexp, line, eol - line, 1, match, eflags)) {

913 + case 0:

914 + return 1;

915 + case REG_NOMATCH:

916 + return 0;

917 + default:

918 + return -1;

919 + }

920 }

921

922 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,

954

955 again:

956 hit = patmatch(p, bol, eol, pmatch, eflags);

957 + if (hit < 0)

958 + hit = 0;

959

960 if (hit && p->word_regexp) {

961 if ((pmatch[0].rm_so < 0) ||

@@ -1461,6 +1465,8 @@ static int look_ahead(struct grep_opt *opt,

1465 regmatch_t m;

1466

1467 hit = patmatch(p, bol, bol + *left_p, &m, 0);

1468 + if (hit < 0)

1469 + return -1;

1470 if (!hit || m.rm_so < 0 || m.rm_eo < 0)

1471 continue;

1472 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

1661 if (try_lookahead

1662 && !(last_hit

1663 && (show_function ||

1658 - lno <= last_hit + opt->post_context))

1659 - && look_ahead(opt, &left, &lno, &bol))

1660 - break;

1664 + lno <= last_hit + opt->post_context))) {

1665 + hit = look_ahead(opt, &left, &lno, &bol);

1666 + if (hit < 0)

1667 + try_lookahead = 0;

1668 + else if (hit)

1669 + break;

1670 + }

1671 eol = end_of_line(bol, &left);

1672

1673 if ((ctx == GREP_CONTEXT_HEAD) && (eol == bol))

t/t7810-grep.sh

@@ -87,6 +87,7 @@ test_expect_success setup '

87 # Still a no-op.

88 function dummy() {}

89 EOF

90 + printf "\200\nASCII\n" >invalid-utf8 &&

91 if test_have_prereq FUNNYNAMES

92 then

93 echo unusual >"\"unusual\" pathname" &&

@@ -534,6 +535,14 @@ do

535 test_cmp expected actual

536 '

537

538 + test_expect_success "grep $L searches past invalid lines on UTF-8 locale" '

539 + LC_ALL=en_US.UTF-8 git grep A. invalid-utf8 >actual &&

540 + cat >expected <<-EOF &&

541 + invalid-utf8:ASCII

542 + EOF

543 + test_cmp expected actual

544 + '

545 +

546 test_expect_success FUNNYNAMES "grep $L should quote unusual pathnames" '

547 cat >expected <<-EOF &&

548 ${HC}"\"unusual\" pathname":unusual