Merge branch 'rs/grep-binary'

* rs/grep-binary:
  grep: support NUL chars in search strings for -F
  grep: use REG_STARTEND for all matching if available
  grep: continue case insensitive fixed string search after NUL chars
  grep: use memmem() for fixed string search
  grep: --name-only over binary
  grep: --count over binary
  grep: grep: refactor handling of binary mode options
  grep: add test script for binary file handling

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);

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,
+			append_grep_pat(ret, pat->pattern, pat->patternlen,
-					    pat->no, pat->token);
+					pat->origin, pat->no, pat->token);
 	}
 
 	return ret;
@@ -329,14 +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(struct grep_pat *p, char *line, char *eol,
-static int fixmatch(const char *pattern, char *line, int ignore_case, regmatch_t *match)
+		    regmatch_t *match)
 {
 	char *hit;
-	if (ignore_case)
+
-		hit = strcasestr(line, pattern);
+	if (p->ignore_case) {
-	else
+		char *s = line;
-		hit = strstr(line, pattern);
+		do {
+			hit = strcasestr(s, p->pattern);
+			if (hit)
+				break;
+			s += strlen(s) + 1;
+		} while (s < eol);
+	} else
+		hit = memmem(line, eol - line, p->pattern, p->patternlen);
 
 	if (!hit) {
 		match->rm_so = match->rm_eo = -1;
@@ -344,11 +359,22 @@ static int fixmatch(const char *pattern, char *line, int ignore_case, regmatch_t
 	}
 	else {
 		match->rm_so = hit - line;
-		match->rm_eo = match->rm_so + strlen(pattern);
+		match->rm_eo = match->rm_so + p->patternlen;
 		return 0;
 	}
 }
 
+static int regmatch(const regex_t *preg, char *line, char *eol,
+		    regmatch_t *match, int eflags)
+{
+#ifdef REG_STARTEND
+	match->rm_so = 0;
+	match->rm_eo = eol - line;
+	eflags |= REG_STARTEND;
+#endif
+	return regexec(preg, line, 1, match, eflags);
+}
+
 static int strip_timestamp(char *bol, char **eol_p)
 {
 	char *eol = *eol_p;
@@ -399,9 +425,9 @@ static int match_one_pattern(struct grep_pat *p, char *bol, char *eol,
 
  again:
 	if (p->fixed)
-		hit = !fixmatch(p->pattern, bol, p->ignore_case, pmatch);
+		hit = !fixmatch(p, bol, eol, pmatch);
 	else
-		hit = !regexec(&p->regexp, bol, 1, pmatch, eflags);
+		hit = !regmatch(&p->regexp, bol, eol, pmatch, eflags);
 
 	if (hit && p->word_regexp) {
 		if ((pmatch[0].rm_so < 0) ||
@@ -726,16 +752,9 @@ static int look_ahead(struct grep_opt *opt,
 		regmatch_t m;
 
 		if (p->fixed)
-			hit = !fixmatch(p->pattern, bol, p->ignore_case, &m);
+			hit = !fixmatch(p, bol, bol + *left_p, &m);
-		else {
+		else
-#ifdef REG_STARTEND
+			hit = !regmatch(&p->regexp, bol, bol + *left_p, &m, 0);
-			m.rm_so = 0;
-			m.rm_eo = *left_p;
-			hit = !regexec(&p->regexp, bol, 1, &m, REG_STARTEND);
-#else
-			hit = !regexec(&p->regexp, bol, 1, &m, 0);
-#endif
-		}
 		if (!hit || m.rm_so < 0 || m.rm_eo < 0)
 			continue;
 		if (earliest < 0 || m.rm_so < earliest)
@@ -800,17 +819,19 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
 		opt->show_hunk_mark = 1;
 	opt->last_shown = 0;
 
-	if (buffer_is_binary(buf, size)) {
+	switch (opt->binary) {
-		switch (opt->binary) {
+	case GREP_BINARY_DEFAULT:
-		case GREP_BINARY_DEFAULT:
+		if (buffer_is_binary(buf, size))
 			binary_match_only = 1;
-			break;
+		break;
-		case GREP_BINARY_NOMATCH:
+	case GREP_BINARY_NOMATCH:
+		if (buffer_is_binary(buf, size))
 			return 0; /* Assume unmatch */
-			break;
+		break;
-		default:
+	case GREP_BINARY_TEXT:
-			break;
+		break;
-		}
+	default:
+		die("bug: unknown binary handling mode");
 	}
 
 	memset(&xecfg, 0, sizeof(xecfg));
@@ -871,6 +892,12 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
 			count++;
 			if (opt->status_only)
 				return 1;
+			if (opt->name_only) {
+				show_name(opt, name);
+				return 1;
+			}
+			if (opt->count)
+				goto next_line;
 			if (binary_match_only) {
 				opt->output(opt, "Binary file ", 12);
 				output_color(opt, name, strlen(name),
@@ -878,22 +905,14 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
 				opt->output(opt, " matches\n", 9);
 				return 1;
 			}
-			if (opt->name_only) {
-				show_name(opt, name);
-				return 1;
-			}
 			/* Hit at this line.  If we haven't shown the
 			 * pre-context lines, we would need to show them.
-			 * When asked to do "count", this still show
-			 * the context which is nonsense, but the user
-			 * deserves to get that ;-).
 			 */
 			if (opt->pre_context)
 				show_pre_context(opt, name, buf, bol, lno);
 			else if (opt->funcname)
 				show_funcname_line(opt, name, buf, bol, lno);
-			if (!opt->count)
+			show_line(opt, bol, eol, name, lno, ':');
-				show_line(opt, bol, eol, name, lno, ':');
 			last_hit = lno;
 		}
 		else if (last_hit &&
@@ -937,6 +956,7 @@ static int grep_buffer_1(struct grep_opt *opt, const char *name,
 		output_sep(opt, ':');
 		snprintf(buf, sizeof(buf), "%u\n", count);
 		opt->output(opt, buf, strlen(buf));
+		return 1;
 	}
 	return !!last_hit;
 }

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);

t/t7008-grep-binary.sh

@@ -0,0 +1,102 @@
+#!/bin/sh
+
+test_description='git grep in binary files'
+
+. ./test-lib.sh
+
+test_expect_success 'setup' "
+	printf 'binary\000file\n' >a &&
+	git add a &&
+	git commit -m.
+"
+
+test_expect_success 'git grep ina a' '
+	echo Binary file a matches >expect &&
+	git grep ina a >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'git grep -ah ina a' '
+	git grep -ah ina a >actual &&
+	test_cmp a actual
+'
+
+test_expect_success 'git grep -I ina a' '
+	: >expect &&
+	test_must_fail git grep -I ina a >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'git grep -c ina a' '
+	echo a:1 >expect &&
+	git grep -c ina a >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'git grep -l ina a' '
+	echo a >expect &&
+	git grep -l ina a >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'git grep -L bar a' '
+	echo a >expect &&
+	git grep -L bar a >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'git grep -q ina a' '
+	: >expect &&
+	git grep -q ina a >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'git grep -F ile a' '
+	git grep -F ile a
+'
+
+test_expect_success 'git grep -Fi iLE a' '
+	git grep -Fi iLE a
+'
+
+# This test actually passes on platforms where regexec() supports the
+# flag REG_STARTEND.
+test_expect_failure 'git grep ile a' '
+	git grep ile a
+'
+
+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