grep: drop support for \0 in --fixed-strings <pattern>

Change "-f <file>" to not support patterns with a NUL-byte in them
under --fixed-strings. We'll now only support these under
"--perl-regexp" with PCRE v2.

A previous change to grep's documentation changed the description of
"-f <file>" to be vague enough as to not promise that this would work.
By dropping support for this we make it a whole lot easier to move
away from the kwset backend, which we'll do in a subsequent change.

Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/grep.c b/grep.c
index d6603bc950ff0d79e47f7c8ea5d7c3a6f75fbec9..8d0fff316c7c2d0705bd35b72985c93e9f159051 100644 (file)
--- a/grep.c
+++ b/grep.c
@@ -644,6 +644,9 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
        p->word_regexp = opt->word_regexp;
        p->ignore_case = opt->ignore_case;
 
+       if (memchr(p->pattern, 0, p->patternlen) && !opt->pcre2)
+               die(_("given pattern contains NULL byte (via -f <file>). This is only supported with -P under PCRE v2"));
+
        /*
         * Even when -F (fixed) asks us to do a non-regexp search, we
         * may not be able to correctly case-fold when -i
@@ -666,9 +669,6 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
                return;
        }
 
-       if (memchr(p->pattern, 0, p->patternlen) && !opt->pcre2)
-               die(_("given pattern contains NULL byte (via -f <file>). This is only supported with -P under PCRE v2"));
-
        if (opt->fixed) {
                /*
                 * We come here when the pattern has the non-ascii

diff --git a/t/t7816-grep-binary-pattern.sh b/t/t7816-grep-binary-pattern.sh
index 9e09bd5d6ace8794b2fcf5cb79faf6500ca9d79c..60bab291e49c61ede2926deca6224b988ad32746 100755 (executable)
--- a/t/t7816-grep-binary-pattern.sh
+++ b/t/t7816-grep-binary-pattern.sh
@@ -60,23 +60,23 @@ test_expect_success 'setup' "
 "
 
 # Simple fixed-string matching that can use kwset (no -i && non-ASCII)
-nul_match 1 1 1 '-F' 'yQf'
-nul_match 0 0 0 '-F' 'yQx'
-nul_match 1 1 1 '-Fi' 'YQf'
-nul_match 0 0 0 '-Fi' 'YQx'
-nul_match 1 1 1 '' 'yQf'
-nul_match 0 0 0 '' 'yQx'
-nul_match 1 1 1 '' 'æQð'
-nul_match 1 1 1 '-F' 'eQm[*]c'
-nul_match 1 1 1 '-Fi' 'EQM[*]C'
+nul_match P P P '-F' 'yQf'
+nul_match P P P '-F' 'yQx'
+nul_match P P P '-Fi' 'YQf'
+nul_match P P P '-Fi' 'YQx'
+nul_match P P 1 '' 'yQf'
+nul_match P P 0 '' 'yQx'
+nul_match P P 1 '' 'æQð'
+nul_match P P P '-F' 'eQm[*]c'
+nul_match P P P '-Fi' 'EQM[*]C'
 
 # Regex patterns that would match but shouldn't with -F
-nul_match 0 0 0 '-F' 'yQ[f]'
-nul_match 0 0 0 '-F' '[y]Qf'
-nul_match 0 0 0 '-Fi' 'YQ[F]'
-nul_match 0 0 0 '-Fi' '[Y]QF'
-nul_match 0 0 0 '-F' 'æQ[ð]'
-nul_match 0 0 0 '-F' '[æ]Qð'
+nul_match P P P '-F' 'yQ[f]'
+nul_match P P P '-F' '[y]Qf'
+nul_match P P P '-Fi' 'YQ[F]'
+nul_match P P P '-Fi' '[Y]QF'
+nul_match P P P '-F' 'æQ[ð]'
+nul_match P P P '-F' '[æ]Qð'
 
 # The -F kwset codepath can't handle -i && non-ASCII...
 nul_match P 1 1 '-i' '[æ]Qð'
@@ -90,38 +90,38 @@ nul_match P 0 1 '-i' '[Æ]Qð'
 nul_match P 0 1 '-i' 'ÆQÐ'
 
 # \0 in regexes can only work with -P & PCRE v2
-nul_match P 1 1 '' 'yQ[f]'
-nul_match P 1 1 '' '[y]Qf'
-nul_match P 1 1 '-i' 'YQ[F]'
-nul_match P 1 1 '-i' '[Y]Qf'
-nul_match P 1 1 '' 'æQ[ð]'
-nul_match P 1 1 '' '[æ]Qð'
-nul_match P 0 1 '-i' 'ÆQ[Ð]'
-nul_match P 1 1 '' 'eQm.*cQ'
-nul_match P 1 1 '-i' 'EQM.*cQ'
-nul_match P 0 0 '' 'eQm[*]c'
-nul_match P 0 0 '-i' 'EQM[*]C'
+nul_match P P 1 '' 'yQ[f]'
+nul_match P P 1 '' '[y]Qf'
+nul_match P P 1 '-i' 'YQ[F]'
+nul_match P P 1 '-i' '[Y]Qf'
+nul_match P P 1 '' 'æQ[ð]'
+nul_match P P 1 '' '[æ]Qð'
+nul_match P P 1 '-i' 'ÆQ[Ð]'
+nul_match P P 1 '' 'eQm.*cQ'
+nul_match P P 1 '-i' 'EQM.*cQ'
+nul_match P P 0 '' 'eQm[*]c'
+nul_match P P 0 '-i' 'EQM[*]C'
 
 # Assert that we're using REG_STARTEND and the pattern doesn't match
 # just because it's cut off at the first \0.
-nul_match 0 0 0 '-i' 'NOMATCHQð'
-nul_match P 0 0 '-i' '[Æ]QNOMATCH'
-nul_match P 0 0 '-i' '[æ]QNOMATCH'
+nul_match P P 0 '-i' 'NOMATCHQð'
+nul_match P P 0 '-i' '[Æ]QNOMATCH'
+nul_match P P 0 '-i' '[æ]QNOMATCH'
 
 # Ensure that the matcher doesn't regress to something that stops at
 # \0
-nul_match 0 0 0 '-F' 'yQ[f]'
-nul_match 0 0 0 '-Fi' 'YQ[F]'
-nul_match 0 0 0 '' 'yQNOMATCH'
-nul_match 0 0 0 '' 'QNOMATCH'
-nul_match 0 0 0 '-i' 'YQNOMATCH'
-nul_match 0 0 0 '-i' 'QNOMATCH'
-nul_match 0 0 0 '-F' 'æQ[ð]'
+nul_match P P P '-F' 'yQ[f]'
+nul_match P P P '-Fi' 'YQ[F]'
+nul_match P P 0 '' 'yQNOMATCH'
+nul_match P P 0 '' 'QNOMATCH'
+nul_match P P 0 '-i' 'YQNOMATCH'
+nul_match P P 0 '-i' 'QNOMATCH'
+nul_match P P P '-F' 'æQ[ð]'
 nul_match P P P '-Fi' 'ÆQ[Ð]'
-nul_match P 0 1 '-i' 'ÆQ[Ð]'
-nul_match 0 0 0 '' 'yQNÓMATCH'
-nul_match 0 0 0 '' 'QNÓMATCH'
-nul_match 0 0 0 '-i' 'YQNÓMATCH'
-nul_match 0 0 0 '-i' 'QNÓMATCH'
+nul_match P P 1 '-i' 'ÆQ[Ð]'
+nul_match P P 0 '' 'yQNÓMATCH'
+nul_match P P 0 '' 'QNÓMATCH'
+nul_match P P 0 '-i' 'YQNÓMATCH'
+nul_match P P 0 '-i' 'QNÓMATCH'
 
 test_done