grep: add --max-count command line option

This patch adds a command line option analogous to that of GNU
grep(1)'s -m / --max-count, which users might already be used to.
This makes it possible to limit the amount of matches shown in the
output while keeping the functionality of other options such as -C
(show code context) or -p (show containing function), which would be
difficult to do with a shell pipeline (e.g. head(1)).

Signed-off-by: Carlos López 00xc@protonmail.com
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Documentation/git-grep.txt

@@ -23,6 +23,7 @@ SYNOPSIS
 	   [--break] [--heading] [-p | --show-function]
 	   [-A <post-context>] [-B <pre-context>] [-C <context>]
 	   [-W | --function-context]
+	   [(-m | --max-count) <num>]
 	   [--threads <num>]
 	   [-f <file>] [-e] <pattern>
 	   [--and|--or|--not|(|)|-e <pattern>...]
@@ -238,6 +239,14 @@ providing this option will cause it to die.
 	`git diff` works out patch hunk headers (see 'Defining a
 	custom hunk-header' in linkgit:gitattributes[5]).
 
+-m <num>::
+--max-count <num>::
+	Limit the amount of matches per file. When using the `-v` or
+	`--invert-match` option, the search stops after the specified
+	number of non-matches. A value of -1 will return unlimited
+	results (the default). A value of 0 will exit immediately with
+	a non-zero status.
+
 --threads <num>::
 	Number of grep worker threads to use.
 	See `grep.threads` in 'CONFIGURATION' for more information.

builtin/grep.c

@@ -961,6 +961,8 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		OPT_BOOL_F(0, "ext-grep", &external_grep_allowed__ignored,
 			   N_("allow calling of grep(1) (ignored by this build)"),
 			   PARSE_OPT_NOCOMPLETE),
+		OPT_INTEGER('m', "max-count", &opt.max_count,
+			N_("maximum number of results per file")),
 		OPT_END()
 	};
 	grep_prefix = prefix;
@@ -1101,6 +1103,13 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 	if (recurse_submodules && untracked)
 		die(_("--untracked not supported with --recurse-submodules"));
 
+	/*
+	 * Optimize out the case where the amount of matches is limited to zero.
+	 * We do this to keep results consistent with GNU grep(1).
+	 */
+	if (opt.max_count == 0)
+		return 1;
+
 	if (show_in_pager) {
 		if (num_threads > 1)
 			warning(_("invalid option combination, ignoring --threads"));

grep.c

@@ -1615,7 +1615,7 @@ static int grep_source_1(struct grep_opt *opt, struct grep_source *gs, int colle
 				return 0;
 			goto next_line;
 		}
-		if (hit) {
+		if (hit && (opt->max_count < 0 || count < opt->max_count)) {
 			count++;
 			if (opt->status_only)
 				return 1;

grep.h

@@ -171,6 +171,7 @@ struct grep_opt {
 	int show_hunk_mark;
 	int file_break;
 	int heading;
+	int max_count;
 	void *priv;
 
 	void (*output)(struct grep_opt *opt, const void *data, size_t size);
@@ -181,6 +182,7 @@ struct grep_opt {
 	.relative = 1, \
 	.pathname = 1, \
 	.max_depth = -1, \
+	.max_count = -1, \
 	.pattern_type_option = GREP_PATTERN_TYPE_UNSPECIFIED, \
 	.colors = { \
 		[GREP_COLOR_CONTEXT] = "", \

t/t7810-grep.sh

@@ -77,6 +77,7 @@ test_expect_success setup '
 	# Say hello.
 	function hello() {
 	  echo "Hello world."
+	  echo "Hello again."
 	} # hello
 
 	# Still a no-op.
@@ -595,6 +596,92 @@ test_expect_success 'grep --files-without-match --quiet' '
 	test_must_be_empty actual
 '
 
+test_expect_success 'grep --max-count 0 (must exit with non-zero)' '
+	test_must_fail git grep --max-count 0 foo >actual &&
+	test_must_be_empty actual
+'
+
+test_expect_success 'grep --max-count 3' '
+	cat >expected <<-EOF &&
+	file:foo mmap bar
+	file:foo_mmap bar
+	file:foo_mmap bar mmap
+	EOF
+	git grep --max-count 3 foo >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'grep --max-count -1 (no limit)' '
+	cat >expected <<-EOF &&
+	file:foo mmap bar
+	file:foo_mmap bar
+	file:foo_mmap bar mmap
+	file:foo mmap bar_mmap
+	file:foo_mmap bar mmap baz
+	EOF
+	git grep --max-count -1 foo >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'grep --max-count 1 --context 2' '
+	cat >expected <<-EOF &&
+	file-foo mmap bar
+	file:foo_mmap bar
+	file-foo_mmap bar mmap
+	EOF
+	git grep --max-count 1 --context 1 foo_mmap >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'grep --max-count 1 --show-function' '
+	cat >expected <<-EOF &&
+	hello.ps1=function hello() {
+	hello.ps1:  echo "Hello world."
+	EOF
+	git grep --max-count 1 --show-function Hello hello.ps1 >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'grep --max-count 2 --show-function' '
+	cat >expected <<-EOF &&
+	hello.ps1=function hello() {
+	hello.ps1:  echo "Hello world."
+	hello.ps1:  echo "Hello again."
+	EOF
+	git grep --max-count 2 --show-function Hello hello.ps1 >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'grep --max-count 1 --count' '
+	cat >expected <<-EOF &&
+	hello.ps1:1
+	EOF
+	git grep --max-count 1 --count Hello hello.ps1 >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'grep --max-count 1 (multiple files)' '
+	cat >expected <<-EOF &&
+	hello.c:#include <stdio.h>
+	hello.ps1:# No-op.
+	EOF
+	git grep --max-count 1 -e o -- hello.\* >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success 'grep --max-count 1 --context 1 (multiple files)' '
+	cat >expected <<-EOF &&
+	hello.c-#include <assert.h>
+	hello.c:#include <stdio.h>
+	hello.c-
+	--
+	hello.ps1:# No-op.
+	hello.ps1-function dummy() {}
+	EOF
+	git grep --max-count 1 --context 1 -e o -- hello.\* >actual &&
+	test_cmp expected actual
+'
+
 cat >expected <<EOF
 file:foo mmap bar_mmap
 EOF