Merge branch 'hm/paint-hits-in-log-grep'

"git log --grep=string --author=name" learns to highlight hits just
like "git grep string" does.

* hm/paint-hits-in-log-grep:
  grep/pcre2: fix an edge case concerning ascii patterns and UTF-8 data
  pretty: colorize pattern matches in commit messages
  grep: refactor next_match() and match_one_pattern() for external use

6 files changed, 255 insertions, 46 deletions

diff --git a/Documentation/config/color.txt b/Documentation/config/color.txt
index 6e817f6047..1795b2d16b 100644
--- a/Documentation/config/color.txt
+++ b/Documentation/config/color.txt
@@ -105,9 +105,12 @@ color.grep.<slot>::
 `matchContext`;;
 	matching text in context lines
 `matchSelected`;;
-	matching text in selected lines
+	matching text in selected lines. Also, used to customize the following
+	linkgit:git-log[1] subcommands: `--grep`, `--author` and `--committer`.
 `selected`;;
-	non-matching text in selected lines
+	non-matching text in selected lines. Also, used to customize the
+	following linkgit:git-log[1] subcommands: `--grep`, `--author` and
+	`--committer`.
 `separator`;;
 	separators between fields on a line (`:`, `-`, and `=`)
 	and between hunks (`--`)
diff --git a/grep.c b/grep.c
index 14fe8a0fd2..f6e113e9f0 100644
--- a/grep.c
+++ b/grep.c
@@ -382,8 +382,10 @@ static void compile_pcre2_pattern(struct grep_pat *p, const struct grep_opt *opt
 		}
 		options |= PCRE2_CASELESS;
 	}
-	if (!opt->ignore_locale && is_utf8_locale() && has_non_ascii(p->pattern) &&
-	    !(!opt->ignore_case && (p->fixed || p->is_fixed)))
+	if ((!opt->ignore_locale && !has_non_ascii(p->pattern)) ||
+	    (!opt->ignore_locale && is_utf8_locale() &&
+	     has_non_ascii(p->pattern) && !(!opt->ignore_case &&
+					    (p->fixed || p->is_fixed))))
 		options |= (PCRE2_UTF | PCRE2_MATCH_INVALID_UTF);
 
 #ifdef GIT_PCRE2_VERSION_10_36_OR_HIGHER
@@ -944,10 +946,10 @@ static struct {
 	{ "reflog ", 7 },
 };
 
-static int match_one_pattern(struct grep_pat *p,
-			     const char *bol, const char *eol,
-			     enum grep_context ctx,
-			     regmatch_t *pmatch, int eflags)
+static int headerless_match_one_pattern(struct grep_pat *p,
+					const char *bol, const char *eol,
+					enum grep_context ctx,
+					regmatch_t *pmatch, int eflags)
 {
 	int hit = 0;
 	const char *start = bol;
@@ -956,25 +958,6 @@ static int match_one_pattern(struct grep_pat *p,
 	    ((p->token == GREP_PATTERN_HEAD) != (ctx == GREP_CONTEXT_HEAD)))
 		return 0;
 
-	if (p->token == GREP_PATTERN_HEAD) {
-		const char *field;
-		size_t len;
-		assert(p->field < ARRAY_SIZE(header_field));
-		field = header_field[p->field].field;
-		len = header_field[p->field].len;
-		if (strncmp(bol, field, len))
-			return 0;
-		bol += len;
-		switch (p->field) {
-		case GREP_HEADER_AUTHOR:
-		case GREP_HEADER_COMMITTER:
-			strip_timestamp(bol, &eol);
-			break;
-		default:
-			break;
-		}
-	}
-
  again:
 	hit = patmatch(p, bol, eol, pmatch, eflags);
 
@@ -1025,6 +1008,36 @@ static int match_one_pattern(struct grep_pat *p,
 	return hit;
 }
 
+static int match_one_pattern(struct grep_pat *p,
+			     const char *bol, const char *eol,
+			     enum grep_context ctx, regmatch_t *pmatch,
+			     int eflags)
+{
+	const char *field;
+	size_t len;
+
+	if (p->token == GREP_PATTERN_HEAD) {
+		assert(p->field < ARRAY_SIZE(header_field));
+		field = header_field[p->field].field;
+		len = header_field[p->field].len;
+		if (strncmp(bol, field, len))
+			return 0;
+		bol += len;
+
+		switch (p->field) {
+		case GREP_HEADER_AUTHOR:
+		case GREP_HEADER_COMMITTER:
+			strip_timestamp(bol, &eol);
+			break;
+		default:
+			break;
+		}
+	}
+
+	return headerless_match_one_pattern(p, bol, eol, ctx, pmatch, eflags);
+}
+
+
 static int match_expr_eval(struct grep_opt *opt, struct grep_expr *x,
 			   const char *bol, const char *eol,
 			   enum grep_context ctx, ssize_t *col,
@@ -1143,7 +1156,7 @@ static int match_next_pattern(struct grep_pat *p,
 {
 	regmatch_t match;
 
-	if (!match_one_pattern(p, bol, eol, ctx, &match, eflags))
+	if (!headerless_match_one_pattern(p, bol, eol, ctx, &match, eflags))
 		return 0;
 	if (match.rm_so < 0 || match.rm_eo < 0)
 		return 0;
@@ -1158,19 +1171,26 @@ static int match_next_pattern(struct grep_pat *p,
 	return 1;
 }
 
-static int next_match(struct grep_opt *opt,
-		      const char *bol, const char *eol,
-		      enum grep_context ctx, regmatch_t *pmatch, int eflags)
+int grep_next_match(struct grep_opt *opt,
+		    const char *bol, const char *eol,
+		    enum grep_context ctx, regmatch_t *pmatch,
+		    enum grep_header_field field, 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) {
+		for (p = ((ctx == GREP_CONTEXT_HEAD)
+			   ? opt->header_list : opt->pattern_list);
+			  p; p = p->next) {
 			switch (p->token) {
-			case GREP_PATTERN: /* atom */
 			case GREP_PATTERN_HEAD:
+				if ((field != GREP_HEADER_FIELD_MAX) &&
+				    (p->field != field))
+					continue;
+				/* fall thru */
+			case GREP_PATTERN: /* atom */
 			case GREP_PATTERN_BODY:
 				hit |= match_next_pattern(p, bol, eol, ctx,
 							  pmatch, eflags);
@@ -1261,7 +1281,8 @@ static void show_line(struct grep_opt *opt,
 			else if (sign == '=')
 				line_color = opt->colors[GREP_COLOR_FUNCTION];
 		}
-		while (next_match(opt, bol, eol, ctx, &match, eflags)) {
+		while (grep_next_match(opt, bol, eol, ctx, &match,
+				       GREP_HEADER_FIELD_MAX, eflags)) {
 			if (match.rm_so == match.rm_eo)
 				break;
 
diff --git a/grep.h b/grep.h
index 3c75ed1fd8..3e8815c347 100644
--- a/grep.h
+++ b/grep.h
@@ -191,6 +191,15 @@ void compile_grep_patterns(struct grep_opt *opt);
 void free_grep_patterns(struct grep_opt *opt);
 int grep_buffer(struct grep_opt *opt, const char *buf, unsigned long size);
 
+/* The field parameter is only used to filter header patterns
+ * (where appropriate). If filtering isn't desirable
+ * GREP_HEADER_FIELD_MAX should be supplied.
+ */
+int grep_next_match(struct grep_opt *opt,
+		    const char *bol, const char *eol,
+		    enum grep_context ctx, regmatch_t *pmatch,
+		    enum grep_header_field field, int eflags);
+
 struct grep_source {
 	char *name;
 
diff --git a/pretty.c b/pretty.c
index be477bd51f..1af5b093ae 100644
--- a/pretty.c
+++ b/pretty.c
@@ -431,6 +431,52 @@ const char *show_ident_date(const struct ident_split *ident,
 	return show_date(date, tz, mode);
 }
 
+static inline void strbuf_add_with_color(struct strbuf *sb, const char *color,
+					 const char *buf, size_t buflen)
+{
+	strbuf_addstr(sb, color);
+	strbuf_add(sb, buf, buflen);
+	if (*color)
+		strbuf_addstr(sb, GIT_COLOR_RESET);
+}
+
+static void append_line_with_color(struct strbuf *sb, struct grep_opt *opt,
+				   const char *line, size_t linelen,
+				   int color, enum grep_context ctx,
+				   enum grep_header_field field)
+{
+	const char *buf, *eol, *line_color, *match_color;
+	regmatch_t match;
+	int eflags = 0;
+
+	buf = line;
+	eol = buf + linelen;
+
+	if (!opt || !want_color(color) || opt->invert)
+		goto end;
+
+	line_color = opt->colors[GREP_COLOR_SELECTED];
+	match_color = opt->colors[GREP_COLOR_MATCH_SELECTED];
+
+	while (grep_next_match(opt, buf, eol, ctx, &match, field, eflags)) {
+		if (match.rm_so == match.rm_eo)
+			break;
+
+		strbuf_add_with_color(sb, line_color, buf, match.rm_so);
+		strbuf_add_with_color(sb, match_color, buf + match.rm_so,
+				      match.rm_eo - match.rm_so);
+		buf += match.rm_eo;
+		eflags = REG_NOTBOL;
+	}
+
+	if (eflags)
+		strbuf_add_with_color(sb, line_color, buf, eol - buf);
+	else {
+end:
+		strbuf_add(sb, buf, eol - buf);
+	}
+}
+
 void pp_user_info(struct pretty_print_context *pp,
 		  const char *what, struct strbuf *sb,
 		  const char *line, const char *encoding)
@@ -496,9 +542,26 @@ void pp_user_info(struct pretty_print_context *pp,
 			strbuf_addch(sb, '\n');
 		strbuf_addf(sb, " <%.*s>\n", (int)maillen, mailbuf);
 	} else {
-		strbuf_addf(sb, "%s: %.*s%.*s <%.*s>\n", what,
-			    (pp->fmt == CMIT_FMT_FULLER) ? 4 : 0, "    ",
-			    (int)namelen, namebuf, (int)maillen, mailbuf);
+		struct strbuf id = STRBUF_INIT;
+		enum grep_header_field field = GREP_HEADER_FIELD_MAX;
+		struct grep_opt *opt = pp->rev ? &pp->rev->grep_filter : NULL;
+
+		if (!strcmp(what, "Author"))
+			field = GREP_HEADER_AUTHOR;
+		else if (!strcmp(what, "Commit"))
+			field = GREP_HEADER_COMMITTER;
+
+		strbuf_addf(sb, "%s: ", what);
+		if (pp->fmt == CMIT_FMT_FULLER)
+			strbuf_addchars(sb, ' ', 4);
+
+		strbuf_addf(&id, "%.*s <%.*s>", (int)namelen, namebuf,
+			    (int)maillen, mailbuf);
+
+		append_line_with_color(sb, opt, id.buf, id.len, pp->color,
+				       GREP_CONTEXT_HEAD, field);
+		strbuf_addch(sb, '\n');
+		strbuf_release(&id);
 	}
 
 	switch (pp->fmt) {
@@ -1935,8 +1998,9 @@ static int pp_utf8_width(const char *start, const char *end)
 	return width;
 }
 
-static void strbuf_add_tabexpand(struct strbuf *sb, int tabwidth,
-				 const char *line, int linelen)
+static void strbuf_add_tabexpand(struct strbuf *sb, struct grep_opt *opt,
+				 int color, int tabwidth, const char *line,
+				 int linelen)
 {
 	const char *tab;
 
@@ -1953,7 +2017,9 @@ static void strbuf_add_tabexpand(struct strbuf *sb, int tabwidth,
 			break;
 
 		/* Output the data .. */
-		strbuf_add(sb, line, tab - line);
+		append_line_with_color(sb, opt, line, tab - line, color,
+				       GREP_CONTEXT_BODY,
+				       GREP_HEADER_FIELD_MAX);
 
 		/* .. and the de-tabified tab */
 		strbuf_addchars(sb, ' ', tabwidth - (width % tabwidth));
@@ -1968,7 +2034,8 @@ static void strbuf_add_tabexpand(struct strbuf *sb, int tabwidth,
 	 * worrying about width - there's nothing more to
 	 * align.
 	 */
-	strbuf_add(sb, line, linelen);
+	append_line_with_color(sb, opt, line, linelen, color, GREP_CONTEXT_BODY,
+			       GREP_HEADER_FIELD_MAX);
 }
 
 /*
@@ -1980,11 +2047,16 @@ static void pp_handle_indent(struct pretty_print_context *pp,
 			     struct strbuf *sb, int indent,
 			     const char *line, int linelen)
 {
+	struct grep_opt *opt = pp->rev ? &pp->rev->grep_filter : NULL;
+
 	strbuf_addchars(sb, ' ', indent);
 	if (pp->expand_tabs_in_log)
-		strbuf_add_tabexpand(sb, pp->expand_tabs_in_log, line, linelen);
+		strbuf_add_tabexpand(sb, opt, pp->color, pp->expand_tabs_in_log,
+				     line, linelen);
 	else
-		strbuf_add(sb, line, linelen);
+		append_line_with_color(sb, opt, line, linelen, pp->color,
+				       GREP_CONTEXT_BODY,
+				       GREP_HEADER_FIELD_MAX);
 }
 
 static int is_mboxrd_from(const char *line, int len)
@@ -2002,7 +2074,9 @@ void pp_remainder(struct pretty_print_context *pp,
 		  struct strbuf *sb,
 		  int indent)
 {
+	struct grep_opt *opt = pp->rev ? &pp->rev->grep_filter : NULL;
 	int first = 1;
+
 	for (;;) {
 		const char *line = *msg_p;
 		int linelen = get_one_line(line);
@@ -2023,14 +2097,17 @@ void pp_remainder(struct pretty_print_context *pp,
 		if (indent)
 			pp_handle_indent(pp, sb, indent, line, linelen);
 		else if (pp->expand_tabs_in_log)
-			strbuf_add_tabexpand(sb, pp->expand_tabs_in_log,
-					     line, linelen);
+			strbuf_add_tabexpand(sb, opt, pp->color,
+					     pp->expand_tabs_in_log, line,
+					     linelen);
 		else {
 			if (pp->fmt == CMIT_FMT_MBOXRD &&
 					is_mboxrd_from(line, linelen))
 				strbuf_addch(sb, '>');
 
-			strbuf_add(sb, line, linelen);
+			append_line_with_color(sb, opt, line, linelen,
+					       pp->color, GREP_CONTEXT_BODY,
+					       GREP_HEADER_FIELD_MAX);
 		}
 		strbuf_addch(sb, '\n');
 	}
diff --git a/t/t4202-log.sh b/t/t4202-log.sh
index 6a650dacd6..7884e3d46b 100755
--- a/t/t4202-log.sh
+++ b/t/t4202-log.sh
@@ -449,6 +449,57 @@ test_expect_success !FAIL_PREREQS 'log with various grep.patternType configurati
 	)
 '
 
+test_expect_success 'log --author' '
+	cat >expect <<-\EOF &&
+	Author: <BOLD;RED>A U<RESET> Thor <author@example.com>
+	EOF
+	git log -1 --color=always --author="A U" >log &&
+	grep Author log >actual.raw &&
+	test_decode_color <actual.raw >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'log --committer' '
+	cat >expect <<-\EOF &&
+	Commit:     C O Mitter <committer@<BOLD;RED>example<RESET>.com>
+	EOF
+	git log -1 --color=always --pretty=fuller --committer="example" >log &&
+	grep "Commit:" log >actual.raw &&
+	test_decode_color <actual.raw >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'log -i --grep with color' '
+	cat >expect <<-\EOF &&
+	    <BOLD;RED>Sec<RESET>ond
+	    <BOLD;RED>sec<RESET>ond
+	EOF
+	git log --color=always -i --grep=^sec >log &&
+	grep -i sec log >actual.raw &&
+	test_decode_color <actual.raw >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success '-c color.grep.selected log --grep' '
+	cat >expect <<-\EOF &&
+	    <GREEN>th<RESET><BOLD;RED>ir<RESET><GREEN>d<RESET>
+	EOF
+	git -c color.grep.selected="green" log --color=always --grep=ir >log &&
+	grep ir log >actual.raw &&
+	test_decode_color <actual.raw >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success '-c color.grep.matchSelected log --grep' '
+	cat >expect <<-\EOF &&
+	    <BLUE>i<RESET>n<BLUE>i<RESET>t<BLUE>i<RESET>al
+	EOF
+	git -c color.grep.matchSelected="blue" log --color=always --grep=i >log &&
+	grep al log >actual.raw &&
+	test_decode_color <actual.raw >actual &&
+	test_cmp expect actual
+'
+
 cat > expect <<EOF
 * Second
 * sixth
diff --git a/t/t7812-grep-icase-non-ascii.sh b/t/t7812-grep-icase-non-ascii.sh
index e5d1e4ea68..22487d90fd 100755
--- a/t/t7812-grep-icase-non-ascii.sh
+++ b/t/t7812-grep-icase-non-ascii.sh
@@ -53,6 +53,54 @@ test_expect_success REGEX_LOCALE 'pickaxe -i on non-ascii' '
 	test_cmp expected actual
 '
 
+test_expect_success GETTEXT_LOCALE,PCRE 'log --author with an ascii pattern on UTF-8 data' '
+	cat >expected <<-\EOF &&
+	Author: <BOLD;RED>À Ú Thor<RESET> <author@example.com>
+	EOF
+	test_write_lines "forth" >file4 &&
+	git add file4 &&
+	git commit --author="À Ú Thor <author@example.com>" -m sécond &&
+	git log -1 --color=always --perl-regexp --author=".*Thor" >log &&
+	grep Author log >actual.raw &&
+	test_decode_color <actual.raw >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success GETTEXT_LOCALE,PCRE 'log --committer with an ascii pattern on ISO-8859-1 data' '
+	cat >expected <<-\EOF &&
+	Commit:     Ç<BOLD;RED> O Mîtter <committer@example.com><RESET>
+	EOF
+	test_write_lines "fifth" >file5 &&
+	git add file5 &&
+	GIT_COMMITTER_NAME="Ç O Mîtter" &&
+	GIT_COMMITTER_EMAIL="committer@example.com" &&
+	git -c i18n.commitEncoding=latin1 commit -m thïrd &&
+	git -c i18n.logOutputEncoding=latin1 log -1 --pretty=fuller --color=always --perl-regexp --committer=" O.*" >log &&
+	grep Commit: log >actual.raw &&
+	test_decode_color <actual.raw >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success GETTEXT_LOCALE,PCRE 'log --grep with an ascii pattern on UTF-8 data' '
+	cat >expected <<-\EOF &&
+	    sé<BOLD;RED>con<RESET>d
+	EOF
+	git log -1 --color=always --perl-regexp --grep="con" >log &&
+	grep con log >actual.raw &&
+	test_decode_color <actual.raw >actual &&
+	test_cmp expected actual
+'
+
+test_expect_success GETTEXT_LOCALE,PCRE 'log --grep with an ascii pattern on ISO-8859-1 data' '
+	cat >expected <<-\EOF &&
+	    <BOLD;RED>thïrd<RESET>
+	EOF
+	git -c i18n.logOutputEncoding=latin1 log -1 --color=always --perl-regexp --grep="th.*rd" >log &&
+	grep "th.*rd" log >actual.raw &&
+	test_decode_color <actual.raw >actual &&
+	test_cmp expected actual
+'
+
 test_expect_success GETTEXT_LOCALE,LIBPCRE2 'PCRE v2: setup invalid UTF-8 data' '
 	printf "\\200\\n" >invalid-0x80 &&
 	echo "ævar" >expected &&