[PATCH v4] grep.c: teach 'git grep --only-matching'

[Taylor Blau <me@ttaylorr.com>]

Teach 'git grep --only-matching', a new option to only print the
matching part(s) of a line.

For instance, a line containing the following (taken from README.md:27):

  (`man gitcvs-migration` or `git help cvs-migration` if git is

Is printed as follows:

  $ git grep --line-number --column --only-matching -e git -- \
    README.md | grep ":27"
  README.md:27:7:git
  README.md:27:16:git
  README.md:27:38:git

The patch works mostly as one would expect, with the exception of a few
considerations that are worth mentioning here.

Like GNU grep, this patch ignores --only-matching when --invert (-v) is
given. There is a sensible answer here, but parity with the behavior of
other tools is preferred.

Because a line might contain more than one match, there are special
considerations pertaining to when to print line headers, newlines, and
how to increment the match column offset. The line header and newlines
are handled as a special case within the main loop to avoid polluting
the surrounding code with conditionals that have large blocks.

Signed-off-by: Taylor Blau <me@ttaylorr.com>
---
 Documentation/git-grep.txt |  7 +++++-
 builtin/grep.c             |  6 +++++
 grep.c                     | 51 ++++++++++++++++++++++++++------------
 grep.h                     |  1 +
 t/t7810-grep.sh            | 15 +++++++++++
 5 files changed, 63 insertions(+), 17 deletions(-)

diff --git a/Documentation/git-grep.txt b/Documentation/git-grep.txt
index 0de3493b80..a3049af1a3 100644
--- a/Documentation/git-grep.txt
+++ b/Documentation/git-grep.txt
@@ -17,7 +17,7 @@ SYNOPSIS
 	   [-l | --files-with-matches] [-L | --files-without-match]
 	   [(-O | --open-files-in-pager) [<pager>]]
 	   [-z | --null]
-	   [-c | --count] [--all-match] [-q | --quiet]
+	   [ -o | --only-matching ] [-c | --count] [--all-match] [-q | --quiet]
 	   [--max-depth <depth>]
 	   [--color[=<when>] | --no-color]
 	   [--break] [--heading] [-p | --show-function]
@@ -201,6 +201,11 @@ providing this option will cause it to die.
 	Output \0 instead of the character that normally follows a
 	file name.
 
+-o::
+--only-matching::
+	Print only the matched (non-empty) parts of a matching line, with each such
+	part on a separate output line.
+
 -c::
 --count::
 	Instead of showing every matched line, show the number of
diff --git a/builtin/grep.c b/builtin/grep.c
index 61bcaf6e58..228b83990f 100644
--- a/builtin/grep.c
+++ b/builtin/grep.c
@@ -843,6 +843,8 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		OPT_BOOL_F('z', "null", &opt.null_following_name,
 			   N_("print NUL after filenames"),
 			   PARSE_OPT_NOCOMPLETE),
+		OPT_BOOL('o', "only-matching", &opt.only_matching,
+			N_("show only matching parts of a line")),
 		OPT_BOOL('c', "count", &opt.count,
 			N_("show the number of matches instead of matching lines")),
 		OPT__COLOR(&opt.color, N_("highlight matches")),
@@ -962,6 +964,10 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 	if (!opt.pattern_list)
 		die(_("no pattern given."));
 
+	/* --only-matching has no effect with --invert. */
+	if (opt.invert)
+		opt.only_matching = 0;
+
 	/*
 	 * We have to find "--" in a separate pass, because its presence
 	 * influences how we will parse arguments that come before it.
diff --git a/grep.c b/grep.c
index 4ff8a73043..49a744f96b 100644
--- a/grep.c
+++ b/grep.c
@@ -51,6 +51,7 @@ void init_grep_defaults(void)
 	color_set(opt->color_match_selected, GIT_COLOR_BOLD_RED);
 	color_set(opt->color_selected, "");
 	color_set(opt->color_sep, GIT_COLOR_CYAN);
+	opt->only_matching = 0;
 	opt->color = -1;
 	opt->output = std_output;
 }
@@ -158,6 +159,7 @@ void grep_init(struct grep_opt *opt, const char *prefix)
 	opt->pattern_tail = &opt->pattern_list;
 	opt->header_tail = &opt->header_list;
 
+	opt->only_matching = def->only_matching;
 	opt->color = def->color;
 	opt->extended_regexp_option = def->extended_regexp_option;
 	opt->pattern_type_option = def->pattern_type_option;
@@ -1446,7 +1448,8 @@ static void show_line(struct grep_opt *opt, char *bol, char *eol,
 		      const char *name, unsigned lno, ssize_t cno, char sign)
 {
 	int rest = eol - bol;
-	const char *match_color, *line_color = NULL;
+	const char *match_color = NULL;
+	const char *line_color = NULL;
 
 	if (opt->file_break && opt->last_shown == 0) {
 		if (opt->show_hunk_mark)
@@ -1462,39 +1465,55 @@ static void show_line(struct grep_opt *opt, char *bol, char *eol,
 			opt->output(opt, "\n", 1);
 		}
 	}
-	show_line_header(opt, name, lno, cno, sign);
-	if (opt->color) {
+	if (!opt->only_matching) {
+		/*
+		 * In case the line we're being called with contains more than
+		 * one match, leave printing each header to the loop below.
+		 */
+		show_line_header(opt, name, lno, cno, sign);
+	}
+	if (opt->color || opt->only_matching) {
 		regmatch_t match;
 		enum grep_context ctx = GREP_CONTEXT_BODY;
 		int ch = *eol;
 		int eflags = 0;
 
-		if (sign == ':')
-			match_color = opt->color_match_selected;
-		else
-			match_color = opt->color_match_context;
-		if (sign == ':')
-			line_color = opt->color_selected;
-		else if (sign == '-')
-			line_color = opt->color_context;
-		else if (sign == '=')
-			line_color = opt->color_function;
+		if (opt->color) {
+			if (sign == ':')
+				match_color = opt->color_match_selected;
+			else
+				match_color = opt->color_match_context;
+			if (sign == ':')
+				line_color = opt->color_selected;
+			else if (sign == '-')
+				line_color = opt->color_context;
+			else if (sign == '=')
+				line_color = opt->color_function;
+		}
 		*eol = '\0';
 		while (next_match(opt, bol, eol, ctx, &match, eflags)) {
 			if (match.rm_so == match.rm_eo)
 				break;
 
-			output_color(opt, bol, match.rm_so, line_color);
+			if (opt->only_matching)
+				show_line_header(opt, name, lno, cno, sign);
+			else
+				output_color(opt, bol, match.rm_so, line_color);
 			output_color(opt, bol + match.rm_so,
 				     match.rm_eo - match.rm_so, match_color);
+			if (opt->only_matching)
+				opt->output(opt, "\n", 1);
 			bol += match.rm_eo;
+			cno += match.rm_eo;
 			rest -= match.rm_eo;
 			eflags = REG_NOTBOL;
 		}
 		*eol = ch;
 	}
-	output_color(opt, bol, rest, line_color);
-	opt->output(opt, "\n", 1);
+	if (!opt->only_matching) {
+		output_color(opt, bol, rest, line_color);
+		opt->output(opt, "\n", 1);
+	}
 }
 
 #ifndef NO_PTHREADS
diff --git a/grep.h b/grep.h
index 08a0b391c5..4d474d8ec4 100644
--- a/grep.h
+++ b/grep.h
@@ -150,6 +150,7 @@ struct grep_opt {
 	int relative;
 	int pathname;
 	int null_following_name;
+	int only_matching;
 	int color;
 	int max_depth;
 	int funcname;
diff --git a/t/t7810-grep.sh b/t/t7810-grep.sh
index 9312c8daf5..d8c232dbf4 100755
--- a/t/t7810-grep.sh
+++ b/t/t7810-grep.sh
@@ -262,6 +262,21 @@ do
 		fi
 	'
 
+	test_expect_success "grep $L (with --column, --only-matching)" '
+		{
+			echo ${HC}file:1:5:mmap
+			echo ${HC}file:2:5:mmap
+			echo ${HC}file:3:5:mmap
+			echo ${HC}file:3:13:mmap
+			echo ${HC}file:4:5:mmap
+			echo ${HC}file:4:13:mmap
+			echo ${HC}file:5:5:mmap
+			echo ${HC}file:5:13:mmap
+		} >expected &&
+		git grep --column -n -o -e mmap $H >actual &&
+		test_cmp expected actual
+	'
+
 	test_expect_success "grep $L (t-1)" '
 		echo "${HC}t/t:1:test" >expected &&
 		git grep -n -e test $H >actual &&
-- 
2.18.0