Merge branch 'rs/color-grep'

* rs/color-grep:
  grep: prefer builtin over external one when coloring results
  grep: cast printf %.*s "precision" argument explicitly to int
  grep: add support for coloring with external greps
  grep: color patterns in output
  grep: add pmatch and eflags arguments to match_one_pattern()
  grep: remove grep_opt argument from match_expr_eval()
  grep: micro-optimize hit collection for AND nodes

5 files changed, 205 insertions, 42 deletions

diff --git a/Documentation/config.txt b/Documentation/config.txt
index 44916b9e7..12540b605 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -553,6 +553,25 @@ color.diff.<slot>::
 	whitespace errors). The values of these variables may be specified as
 	in color.branch.<slot>.
 
+color.grep::
+	When set to `always`, always highlight matches.  When `false` (or
+	`never`), never.  When set to `true` or `auto`, use color only
+	when the output is written to the terminal.  Defaults to `false`.
+
+color.grep.external::
+	The string value of this variable is passed to an external 'grep'
+	command as a command line option if match highlighting is turned
+	on.  If set to an empty string, no option is passed at all,
+	turning off coloring for external 'grep' calls; this is the default.
+	For GNU grep, set it to `--color=always` to highlight matches even
+	when a pager is used.
+
+color.grep.match::
+	Use customized color for matches.  The value of this variable
+	may be specified as in color.branch.<slot>.  It is passed using
+	the environment variables 'GREP_COLOR' and 'GREP_COLORS' when
+	calling an external 'grep'.
+
 color.interactive::
 	When set to `always`, always use colors for interactive prompts
 	and displays (such as those used by "git-add --interactive").
diff --git a/Documentation/git-grep.txt b/Documentation/git-grep.txt
index 553da6cbb..fccb82deb 100644
--- a/Documentation/git-grep.txt
+++ b/Documentation/git-grep.txt
@@ -17,6 +17,7 @@ SYNOPSIS
 	   [-l | --files-with-matches] [-L | --files-without-match]
 	   [-z | --null]
 	   [-c | --count] [--all-match]
+	   [--color | --no-color]
 	   [-A <post-context>] [-B <pre-context>] [-C <context>]
 	   [-f <file>] [-e] <pattern>
 	   [--and|--or|--not|(|)|-e <pattern>...] [<tree>...]
@@ -105,6 +106,13 @@ OPTIONS
 	Instead of showing every matched line, show the number of
 	lines that match.
 
+--color::
+	Show colored matches.
+
+--no-color::
+	Turn off match highlighting, even when the configuration file
+	gives the default to color output.
+
 -[ABC] <context>::
 	Show `context` trailing (`A` -- after), or leading (`B`
 	-- before), or both (`C` -- context) lines, and place a
diff --git a/builtin-grep.c b/builtin-grep.c
index 3f12ba382..89489ddcf 100644
--- a/builtin-grep.c
+++ b/builtin-grep.c
@@ -22,6 +22,28 @@
 
 static int builtin_grep;
 
+static int grep_config(const char *var, const char *value, void *cb)
+{
+	struct grep_opt *opt = cb;
+
+	if (!strcmp(var, "grep.color") || !strcmp(var, "color.grep")) {
+		opt->color = git_config_colorbool(var, value, -1);
+		return 0;
+	}
+	if (!strcmp(var, "grep.color.external") ||
+	    !strcmp(var, "color.grep.external")) {
+		return git_config_string(&(opt->color_external), var, value);
+	}
+	if (!strcmp(var, "grep.color.match") ||
+	    !strcmp(var, "color.grep.match")) {
+		if (!value)
+			return config_error_nonbool(var);
+		color_parse(value, var, opt->color_match);
+		return 0;
+	}
+	return git_color_default_config(var, value, cb);
+}
+
 /*
  * git grep pathspecs are somewhat different from diff-tree pathspecs;
  * pathname wildcards are allowed.
@@ -269,6 +291,21 @@ static int flush_grep(struct grep_opt *opt,
 	return status;
 }
 
+static void grep_add_color(struct strbuf *sb, const char *escape_seq)
+{
+	size_t orig_len = sb->len;
+
+	while (*escape_seq) {
+		if (*escape_seq == 'm')
+			strbuf_addch(sb, ';');
+		else if (*escape_seq != '\033' && *escape_seq  != '[')
+			strbuf_addch(sb, *escape_seq);
+		escape_seq++;
+	}
+	if (sb->len > orig_len && sb->buf[sb->len - 1] == ';')
+		strbuf_setlen(sb, sb->len - 1);
+}
+
 static int external_grep(struct grep_opt *opt, const char **paths, int cached)
 {
 	int i, nr, argc, hit, len, status;
@@ -339,6 +376,23 @@ static int external_grep(struct grep_opt *opt, const char **paths, int cached)
 		push_arg("-e");
 		push_arg(p->pattern);
 	}
+	if (opt->color) {
+		struct strbuf sb = STRBUF_INIT;
+
+		grep_add_color(&sb, opt->color_match);
+		setenv("GREP_COLOR", sb.buf, 1);
+
+		strbuf_reset(&sb);
+		strbuf_addstr(&sb, "mt=");
+		grep_add_color(&sb, opt->color_match);
+		strbuf_addstr(&sb, ":sl=:cx=:fn=:ln=:bn=:se=");
+		setenv("GREP_COLORS", sb.buf, 1);
+
+		strbuf_release(&sb);
+
+		if (opt->color_external && strlen(opt->color_external) > 0)
+			push_arg(opt->color_external);
+	}
 
 	hit = 0;
 	argc = nr;
@@ -536,6 +590,12 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 	opt.pattern_tail = &opt.pattern_list;
 	opt.regflags = REG_NEWLINE;
 
+	strcpy(opt.color_match, GIT_COLOR_RED GIT_COLOR_BOLD);
+	opt.color = -1;
+	git_config(grep_config, &opt);
+	if (opt.color == -1)
+		opt.color = git_use_color_default;
+
 	/*
 	 * If there is no -- then the paths must exist in the working
 	 * tree.  If there is no explicit pattern specified with -e or
@@ -732,6 +792,14 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 			opt.relative = 0;
 			continue;
 		}
+		if (!strcmp("--color", arg)) {
+			opt.color = 1;
+			continue;
+		}
+		if (!strcmp("--no-color", arg)) {
+			opt.color = 0;
+			continue;
+		}
 		if (!strcmp("--", arg)) {
 			/* later processing wants to have this at argv[1] */
 			argv--;
@@ -757,6 +825,8 @@ int cmd_grep(int argc, const char **argv, const char *prefix)
 		}
 	}
 
+	if (opt.color && !opt.color_external)
+		builtin_grep = 1;
 	if (!opt.pattern_list)
 		die("no pattern given.");
 	if ((opt.regflags != REG_NEWLINE) && opt.fixed)
diff --git a/grep.c b/grep.c
index 062b2b6f2..be99b3416 100644
--- a/grep.c
+++ b/grep.c
@@ -39,6 +39,8 @@ static void compile_regexp(struct grep_pat *p, struct grep_opt *opt)
 {
 	int err;
 
+	p->word_regexp = opt->word_regexp;
+
 	if (opt->fixed || is_fixed(p->pattern))
 		p->fixed = 1;
 	if (opt->regflags & REG_ICASE)
@@ -251,18 +253,6 @@ static int word_char(char ch)
 	return isalnum(ch) || ch == '_';
 }
 
-static void show_line(struct grep_opt *opt, const char *bol, const char *eol,
-		      const char *name, unsigned lno, char sign)
-{
-	if (opt->null_following_name)
-		sign = '\0';
-	if (opt->pathname)
-		printf("%s%c", name, sign);
-	if (opt->linenum)
-		printf("%d%c", lno, sign);
-	printf("%.*s\n", (int)(eol-bol), bol);
-}
-
 static void show_name(struct grep_opt *opt, const char *name)
 {
 	printf("%s%c", name, opt->null_following_name ? '\0' : '\n');
@@ -306,11 +296,12 @@ static struct {
 	{ "committer ", 10 },
 };
 
-static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol, char *eol, enum grep_context ctx)
+static int match_one_pattern(struct grep_pat *p, char *bol, char *eol,
+			     enum grep_context ctx,
+			     regmatch_t *pmatch, int eflags)
 {
 	int hit = 0;
 	int saved_ch = 0;
-	regmatch_t pmatch[10];
 
 	if ((p->token != GREP_PATTERN) &&
 	    ((p->token == GREP_PATTERN_HEAD) != (ctx == GREP_CONTEXT_HEAD)))
@@ -329,16 +320,12 @@ static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol
 	}
 
  again:
-	if (!p->fixed) {
-		regex_t *exp = &p->regexp;
-		hit = !regexec(exp, bol, ARRAY_SIZE(pmatch),
-			       pmatch, 0);
-	}
-	else {
+	if (p->fixed)
 		hit = !fixmatch(p->pattern, bol, pmatch);
-	}
+	else
+		hit = !regexec(&p->regexp, bol, 1, pmatch, eflags);
 
-	if (hit && opt->word_regexp) {
+	if (hit && p->word_regexp) {
 		if ((pmatch[0].rm_so < 0) ||
 		    (eol - bol) <= pmatch[0].rm_so ||
 		    (pmatch[0].rm_eo < 0) ||
@@ -378,39 +365,33 @@ static int match_one_pattern(struct grep_opt *opt, struct grep_pat *p, char *bol
 	return hit;
 }
 
-static int match_expr_eval(struct grep_opt *o,
-			   struct grep_expr *x,
-			   char *bol, char *eol,
-			   enum grep_context ctx,
-			   int collect_hits)
+static int match_expr_eval(struct grep_expr *x, char *bol, char *eol,
+			   enum grep_context ctx, int collect_hits)
 {
 	int h = 0;
+	regmatch_t match;
 
 	switch (x->node) {
 	case GREP_NODE_ATOM:
-		h = match_one_pattern(o, x->u.atom, bol, eol, ctx);
+		h = match_one_pattern(x->u.atom, bol, eol, ctx, &match, 0);
 		break;
 	case GREP_NODE_NOT:
-		h = !match_expr_eval(o, x->u.unary, bol, eol, ctx, 0);
+		h = !match_expr_eval(x->u.unary, bol, eol, ctx, 0);
 		break;
 	case GREP_NODE_AND:
-		if (!collect_hits)
-			return (match_expr_eval(o, x->u.binary.left,
-						bol, eol, ctx, 0) &&
-				match_expr_eval(o, x->u.binary.right,
-						bol, eol, ctx, 0));
-		h = match_expr_eval(o, x->u.binary.left, bol, eol, ctx, 0);
-		h &= match_expr_eval(o, x->u.binary.right, bol, eol, ctx, 0);
+		if (!match_expr_eval(x->u.binary.left, bol, eol, ctx, 0))
+			return 0;
+		h = match_expr_eval(x->u.binary.right, bol, eol, ctx, 0);
 		break;
 	case GREP_NODE_OR:
 		if (!collect_hits)
-			return (match_expr_eval(o, x->u.binary.left,
+			return (match_expr_eval(x->u.binary.left,
 						bol, eol, ctx, 0) ||
-				match_expr_eval(o, x->u.binary.right,
+				match_expr_eval(x->u.binary.right,
 						bol, eol, ctx, 0));
-		h = match_expr_eval(o, x->u.binary.left, bol, eol, ctx, 0);
+		h = match_expr_eval(x->u.binary.left, bol, eol, ctx, 0);
 		x->u.binary.left->hit |= h;
-		h |= match_expr_eval(o, x->u.binary.right, bol, eol, ctx, 1);
+		h |= match_expr_eval(x->u.binary.right, bol, eol, ctx, 1);
 		break;
 	default:
 		die("Unexpected node type (internal error) %d", x->node);
@@ -424,24 +405,104 @@ static int match_expr(struct grep_opt *opt, char *bol, char *eol,
 		      enum grep_context ctx, int collect_hits)
 {
 	struct grep_expr *x = opt->pattern_expression;
-	return match_expr_eval(opt, x, bol, eol, ctx, collect_hits);
+	return match_expr_eval(x, bol, eol, ctx, collect_hits);
 }
 
 static int match_line(struct grep_opt *opt, char *bol, char *eol,
 		      enum grep_context ctx, int collect_hits)
 {
 	struct grep_pat *p;
+	regmatch_t match;
+
 	if (opt->extended)
 		return match_expr(opt, bol, eol, ctx, collect_hits);
 
 	/* we do not call with collect_hits without being extended */
 	for (p = opt->pattern_list; p; p = p->next) {
-		if (match_one_pattern(opt, p, bol, eol, ctx))
+		if (match_one_pattern(p, bol, eol, ctx, &match, 0))
 			return 1;
 	}
 	return 0;
 }
 
+static int match_next_pattern(struct grep_pat *p, char *bol, char *eol,
+			      enum grep_context ctx,
+			      regmatch_t *pmatch, int eflags)
+{
+	regmatch_t match;
+
+	if (!match_one_pattern(p, bol, eol, ctx, &match, eflags))
+		return 0;
+	if (match.rm_so < 0 || match.rm_eo < 0)
+		return 0;
+	if (pmatch->rm_so >= 0 && pmatch->rm_eo >= 0) {
+		if (match.rm_so > pmatch->rm_so)
+			return 1;
+		if (match.rm_so == pmatch->rm_so && match.rm_eo < pmatch->rm_eo)
+			return 1;
+	}
+	pmatch->rm_so = match.rm_so;
+	pmatch->rm_eo = match.rm_eo;
+	return 1;
+}
+
+static int next_match(struct grep_opt *opt, char *bol, char *eol,
+		      enum grep_context ctx, regmatch_t *pmatch, int eflags)
+{
+	struct grep_pat *p;
+	int hit = 0;
+
+	pmatch->rm_so = pmatch->rm_eo = -1;
+	if (bol < eol) {
+		for (p = opt->pattern_list; p; p = p->next) {
+			switch (p->token) {
+			case GREP_PATTERN: /* atom */
+			case GREP_PATTERN_HEAD:
+			case GREP_PATTERN_BODY:
+				hit |= match_next_pattern(p, bol, eol, ctx,
+							  pmatch, eflags);
+				break;
+			default:
+				break;
+			}
+		}
+	}
+	return hit;
+}
+
+static void show_line(struct grep_opt *opt, char *bol, char *eol,
+		      const char *name, unsigned lno, char sign)
+{
+	int rest = eol - bol;
+
+	if (opt->null_following_name)
+		sign = '\0';
+	if (opt->pathname)
+		printf("%s%c", name, sign);
+	if (opt->linenum)
+		printf("%d%c", lno, sign);
+	if (opt->color) {
+		regmatch_t match;
+		enum grep_context ctx = GREP_CONTEXT_BODY;
+		int ch = *eol;
+		int eflags = 0;
+
+		*eol = '\0';
+		while (next_match(opt, bol, eol, ctx, &match, eflags)) {
+			printf("%.*s%s%.*s%s",
+			       (int)match.rm_so, bol,
+			       opt->color_match,
+			       (int)(match.rm_eo - match.rm_so), bol + match.rm_so,
+			       GIT_COLOR_RESET);
+			bol += match.rm_eo;
+			rest -= match.rm_eo;
+			eflags = REG_NOTBOL;
+		}
+		*eol = ch;
+	}
+	printf("%.*s\n", rest, bol);
+}
+
 static int grep_buffer_1(struct grep_opt *opt, const char *name,
 			 char *buf, unsigned long size, int collect_hits)
 {
diff --git a/grep.h b/grep.h
index 5102ce335..a67005de6 100644
--- a/grep.h
+++ b/grep.h
@@ -1,5 +1,6 @@
 #ifndef GREP_H
 #define GREP_H
+#include "color.h"
 
 enum grep_pat_token {
 	GREP_PATTERN,
@@ -31,6 +32,7 @@ struct grep_pat {
 	enum grep_header_field field;
 	regex_t regexp;
 	unsigned fixed:1;
+	unsigned word_regexp:1;
 };
 
 enum grep_expr_node {
@@ -76,6 +78,9 @@ struct grep_opt {
 	unsigned relative:1;
 	unsigned pathname:1;
 	unsigned null_following_name:1;
+	int color;
+	char color_match[COLOR_MAXLEN];
+	const char *color_external;
 	int regflags;
 	unsigned pre_context;
 	unsigned post_context;