grep: support NUL chars in search strings for -F

Search patterns in a file specified with -f can contain NUL characters.
The current code ignores all characters on a line after a NUL.

Pass the actual length of the line all the way from the pattern file to
fixmatch() and use it for case-sensitive fixed string matching.

Signed-off-by: Rene Scharfe <rene.scharfe@lsrfire.ath.cx>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/builtin/grep.c b/builtin/grep.c
index 8e928e217041a159f4a962f0883d740aa84536d7..7653d8492a9f26b47cfaeec64f717107ffa204bc 100644 (file)
--- a/builtin/grep.c
+++ b/builtin/grep.c
@@ -724,11 +724,15 @@ static int file_callback(const struct option *opt, const char *arg, int unset)
        if (!patterns)
                die_errno("cannot open '%s'", arg);
        while (strbuf_getline(&sb, patterns, '\n') == 0) {
+               char *s;
+               size_t len;
+
                /* ignore empty line like grep does */
                if (sb.len == 0)
                        continue;
-               append_grep_pattern(grep_opt, strbuf_detach(&sb, NULL), arg,
-                                   ++lno, GREP_PATTERN);
+
+               s = strbuf_detach(&sb, &len);
+               append_grep_pat(grep_opt, s, len, arg, ++lno, GREP_PATTERN);
        }
        fclose(patterns);
        strbuf_release(&sb);

diff --git a/grep.c b/grep.c
index 70a776f6fece05687bd684aeb7047615aa5a0064..82fb349be6f6ef8211d4828101cd8e88bcbb304f 100644 (file)
--- a/grep.c
+++ b/grep.c
@@ -7,6 +7,7 @@ void append_header_grep_pattern(struct grep_opt *opt, enum grep_header_field fie
 {
        struct grep_pat *p = xcalloc(1, sizeof(*p));
        p->pattern = pat;
+       p->patternlen = strlen(pat);
        p->origin = "header";
        p->no = 0;
        p->token = GREP_PATTERN_HEAD;
@@ -18,9 +19,16 @@ void append_header_grep_pattern(struct grep_opt *opt, enum grep_header_field fie
 
 void append_grep_pattern(struct grep_opt *opt, const char *pat,
                         const char *origin, int no, enum grep_pat_token t)
+{
+       append_grep_pat(opt, pat, strlen(pat), origin, no, t);
+}
+
+void append_grep_pat(struct grep_opt *opt, const char *pat, size_t patlen,
+                    const char *origin, int no, enum grep_pat_token t)
 {
        struct grep_pat *p = xcalloc(1, sizeof(*p));
        p->pattern = pat;
+       p->patternlen = patlen;
        p->origin = origin;
        p->no = no;
        p->token = t;
@@ -44,8 +52,8 @@ struct grep_opt *grep_opt_dup(const struct grep_opt *opt)
                        append_header_grep_pattern(ret, pat->field,
                                                   pat->pattern);
                else
-                       append_grep_pattern(ret, pat->pattern, pat->origin,
-                                           pat->no, pat->token);
+                       append_grep_pat(ret, pat->pattern, pat->patternlen,
+                                       pat->origin, pat->no, pat->token);
        }
 
        return ret;
@@ -329,21 +337,21 @@ static void show_name(struct grep_opt *opt, const char *name)
        opt->output(opt, opt->null_following_name ? "\0" : "\n", 1);
 }
 
-static int fixmatch(const char *pattern, char *line, char *eol,
-                   int ignore_case, regmatch_t *match)
+static int fixmatch(struct grep_pat *p, char *line, char *eol,
+                   regmatch_t *match)
 {
        char *hit;
 
-       if (ignore_case) {
+       if (p->ignore_case) {
                char *s = line;
                do {
-                       hit = strcasestr(s, pattern);
+                       hit = strcasestr(s, p->pattern);
                        if (hit)
                                break;
                        s += strlen(s) + 1;
                } while (s < eol);
        } else
-               hit = memmem(line, eol - line, pattern, strlen(pattern));
+               hit = memmem(line, eol - line, p->pattern, p->patternlen);
 
        if (!hit) {
                match->rm_so = match->rm_eo = -1;
@@ -351,7 +359,7 @@ static int fixmatch(const char *pattern, char *line, char *eol,
        }
        else {
                match->rm_so = hit - line;
-               match->rm_eo = match->rm_so + strlen(pattern);
+               match->rm_eo = match->rm_so + p->patternlen;
                return 0;
        }
 }
@@ -417,7 +425,7 @@ static int match_one_pattern(struct grep_pat *p, char *bol, char *eol,
 
  again:
        if (p->fixed)
-               hit = !fixmatch(p->pattern, bol, eol, p->ignore_case, pmatch);
+               hit = !fixmatch(p, bol, eol, pmatch);
        else
                hit = !regmatch(&p->regexp, bol, eol, pmatch, eflags);
 
@@ -743,10 +751,9 @@ static int look_ahead(struct grep_opt *opt,
                int hit;
                regmatch_t m;
 
-               if (p->fixed) {
-                       hit = !fixmatch(p->pattern, bol, bol + *left_p,
-                                       p->ignore_case, &m);
-               } else
+               if (p->fixed)
+                       hit = !fixmatch(p, bol, bol + *left_p, &m);
+               else
                        hit = !regmatch(&p->regexp, bol, bol + *left_p, &m, 0);
                if (!hit || m.rm_so < 0 || m.rm_eo < 0)
                        continue;

diff --git a/grep.h b/grep.h
index 89342e5b47f6d63dd546e738e4cbf023c447b382..0aebebd96692f94877259bf64a1fece9e47d222e 100644 (file)
--- a/grep.h
+++ b/grep.h
@@ -29,6 +29,7 @@ struct grep_pat {
        int no;
        enum grep_pat_token token;
        const char *pattern;
+       size_t patternlen;
        enum grep_header_field field;
        regex_t regexp;
        unsigned fixed:1;
@@ -104,6 +105,7 @@ struct grep_opt {
        void *output_priv;
 };
 
+extern void append_grep_pat(struct grep_opt *opt, const char *pat, size_t patlen, const char *origin, int no, enum grep_pat_token t);
 extern void append_grep_pattern(struct grep_opt *opt, const char *pat, const char *origin, int no, enum grep_pat_token t);
 extern void append_header_grep_pattern(struct grep_opt *, enum grep_header_field, const char *);
 extern void compile_grep_patterns(struct grep_opt *opt);

diff --git a/t/t7008-grep-binary.sh b/t/t7008-grep-binary.sh
index 4f5e74fed77a484c4c0b7bd9de7f0b95cf714a22..eb8ca88cce59c234d8ee43cc94421024f6b1e0b5 100755 (executable)
--- a/t/t7008-grep-binary.sh
+++ b/t/t7008-grep-binary.sh
@@ -69,4 +69,34 @@ test_expect_failure 'git grep .fi a' '
        git grep .fi a
 '
 
+test_expect_success 'git grep -F y<NUL>f a' "
+       printf 'y\000f' >f &&
+       git grep -f f -F a
+"
+
+test_expect_success 'git grep -F y<NUL>x a' "
+       printf 'y\000x' >f &&
+       test_must_fail git grep -f f -F a
+"
+
+test_expect_success 'git grep -Fi Y<NUL>f a' "
+       printf 'Y\000f' >f &&
+       git grep -f f -Fi a
+"
+
+test_expect_failure 'git grep -Fi Y<NUL>x a' "
+       printf 'Y\000x' >f &&
+       test_must_fail git grep -f f -Fi a
+"
+
+test_expect_success 'git grep y<NUL>f a' "
+       printf 'y\000f' >f &&
+       git grep -f f a
+"
+
+test_expect_failure 'git grep y<NUL>x a' "
+       printf 'y\000x' >f &&
+       test_must_fail git grep -f f a
+"
+
 test_done