Merge branch 'tb/shortlog-group'

"git shortlog" learned to group by the "format" string.

* tb/shortlog-group:
  shortlog: implement `--group=committer` in terms of `--group=<format>`
  shortlog: implement `--group=author` in terms of `--group=<format>`
  shortlog: extract `shortlog_finish_setup()`
  shortlog: support arbitrary commit format `--group`s
  shortlog: extract `--group` fragment for translation
  shortlog: make trailer insertion a noop when appropriate
  shortlog: accept `--date`-related options

Documentation/git-shortlog.txt

@@ -47,6 +47,11 @@ OPTIONS
 
 	Each pretty-printed commit will be rewrapped before it is shown.
 
+--date=<format>::
+	Show dates formatted according to the given date string. (See
+	the `--date` option in the "Commit Formatting" section of
+	linkgit:git-log[1]). Useful with `--group=format:<format>`.
+
 --group=<type>::
 	Group commits based on `<type>`. If no `--group` option is
 	specified, the default is `author`. `<type>` is one of:
@@ -59,6 +64,9 @@ OPTIONS
    example, if your project uses `Reviewed-by` trailers, you might want
    to see who has been reviewing with
    `git shortlog -ns --group=trailer:reviewed-by`.
+ - `format:<format>`, any string accepted by the `--format` option of
+   'git log'. (See the "PRETTY FORMATS" section of
+   linkgit:git-log[1].)
 +
 Note that commits that do not include the trailer will not be counted.
 Likewise, commits with multiple trailers (e.g., multiple signoffs) may

builtin/log.c

@@ -1334,6 +1334,7 @@ static void make_cover_letter(struct rev_info *rev, int use_separate_file,
 	log.in2 = 4;
 	log.file = rev->diffopt.file;
 	log.groups = SHORTLOG_GROUP_AUTHOR;
+	shortlog_finish_setup(&log);
 	for (i = 0; i < nr; i++)
 		shortlog_add_commit(&log, list[i]);
 

builtin/shortlog.c

@@ -132,7 +132,9 @@ static void read_from_stdin(struct shortlog *log)
 		match = committer_match;
 		break;
 	case SHORTLOG_GROUP_TRAILER:
-		die(_("using --group=trailer with stdin is not supported"));
+		die(_("using %s with stdin is not supported"), "--group=trailer");
+	case SHORTLOG_GROUP_FORMAT:
+		die(_("using %s with stdin is not supported"), "--group=format");
 	default:
 		BUG("unhandled shortlog group");
 	}
@@ -170,6 +172,9 @@ static void insert_records_from_trailers(struct shortlog *log,
 	const char *commit_buffer, *body;
 	struct strbuf ident = STRBUF_INIT;
 
+	if (!log->trailers.nr)
+		return;
+
 	/*
 	 * Using format_commit_message("%B") would be simpler here, but
 	 * this saves us copying the message.
@@ -200,9 +205,34 @@ static void insert_records_from_trailers(struct shortlog *log,
 	unuse_commit_buffer(commit, commit_buffer);
 }
 
+static int shortlog_needs_dedup(const struct shortlog *log)
+{
+	return HAS_MULTI_BITS(log->groups) || log->format.nr > 1 || log->trailers.nr;
+}
+
+static void insert_records_from_format(struct shortlog *log,
+				       struct strset *dups,
+				       struct commit *commit,
+				       struct pretty_print_context *ctx,
+				       const char *oneline)
+{
+	struct strbuf buf = STRBUF_INIT;
+	struct string_list_item *item;
+
+	for_each_string_list_item(item, &log->format) {
+		strbuf_reset(&buf);
+
+		format_commit_message(commit, item->string, &buf, ctx);
+
+		if (!shortlog_needs_dedup(log) || strset_add(dups, buf.buf))
+			insert_one_record(log, buf.buf, oneline);
+	}
+
+	strbuf_release(&buf);
+}
+
 void shortlog_add_commit(struct shortlog *log, struct commit *commit)
 {
-	struct strbuf ident = STRBUF_INIT;
 	struct strbuf oneline = STRBUF_INIT;
 	struct strset dups = STRSET_INIT;
 	struct pretty_print_context ctx = {0};
@@ -211,7 +241,7 @@ void shortlog_add_commit(struct shortlog *log, struct commit *commit)
 	ctx.fmt = CMIT_FMT_USERFORMAT;
 	ctx.abbrev = log->abbrev;
 	ctx.print_email_subject = 1;
-	ctx.date_mode.type = DATE_NORMAL;
+	ctx.date_mode = log->date_mode;
 	ctx.output_encoding = get_log_output_encoding();
 
 	if (!log->summary) {
@@ -222,30 +252,10 @@ void shortlog_add_commit(struct shortlog *log, struct commit *commit)
 	}
 	oneline_str = oneline.len ? oneline.buf : "<none>";
 
-	if (log->groups & SHORTLOG_GROUP_AUTHOR) {
-		strbuf_reset(&ident);
-		format_commit_message(commit,
-				      log->email ? "%aN <%aE>" : "%aN",
-				      &ident, &ctx);
-		if (!HAS_MULTI_BITS(log->groups) ||
-		    strset_add(&dups, ident.buf))
-			insert_one_record(log, ident.buf, oneline_str);
-	}
-	if (log->groups & SHORTLOG_GROUP_COMMITTER) {
-		strbuf_reset(&ident);
-		format_commit_message(commit,
-				      log->email ? "%cN <%cE>" : "%cN",
-				      &ident, &ctx);
-		if (!HAS_MULTI_BITS(log->groups) ||
-		    strset_add(&dups, ident.buf))
-			insert_one_record(log, ident.buf, oneline_str);
-	}
-	if (log->groups & SHORTLOG_GROUP_TRAILER) {
-		insert_records_from_trailers(log, &dups, commit, &ctx, oneline_str);
-	}
+	insert_records_from_trailers(log, &dups, commit, &ctx, oneline_str);
+	insert_records_from_format(log, &dups, commit, &ctx, oneline_str);
 
 	strset_clear(&dups);
-	strbuf_release(&ident);
 	strbuf_release(&oneline);
 }
 
@@ -314,6 +324,7 @@ static int parse_group_option(const struct option *opt, const char *arg, int uns
 	if (unset) {
 		log->groups = 0;
 		string_list_clear(&log->trailers, 0);
+		string_list_clear(&log->format, 0);
 	} else if (!strcasecmp(arg, "author"))
 		log->groups |= SHORTLOG_GROUP_AUTHOR;
 	else if (!strcasecmp(arg, "committer"))
@@ -321,8 +332,15 @@ static int parse_group_option(const struct option *opt, const char *arg, int uns
 	else if (skip_prefix(arg, "trailer:", &field)) {
 		log->groups |= SHORTLOG_GROUP_TRAILER;
 		string_list_append(&log->trailers, field);
-	} else
+	} else if (skip_prefix(arg, "format:", &field)) {
+		log->groups |= SHORTLOG_GROUP_FORMAT;
+		string_list_append(&log->format, field);
+	} else if (strchr(arg, '%')) {
+		log->groups |= SHORTLOG_GROUP_FORMAT;
+		string_list_append(&log->format, arg);
+	} else {
 		return error(_("unknown group type: %s"), arg);
+	}
 
 	return 0;
 }
@@ -340,6 +358,19 @@ void shortlog_init(struct shortlog *log)
 	log->in2 = DEFAULT_INDENT2;
 	log->trailers.strdup_strings = 1;
 	log->trailers.cmp = strcasecmp;
+	log->format.strdup_strings = 1;
+}
+
+void shortlog_finish_setup(struct shortlog *log)
+{
+	if (log->groups & SHORTLOG_GROUP_AUTHOR)
+		string_list_append(&log->format,
+				   log->email ? "%aN <%aE>" : "%aN");
+	if (log->groups & SHORTLOG_GROUP_COMMITTER)
+		string_list_append(&log->format,
+				   log->email ? "%cN <%cE>" : "%cN");
+
+	string_list_sort(&log->trailers);
 }
 
 int cmd_shortlog(int argc, const char **argv, const char *prefix)
@@ -407,10 +438,11 @@ parse_done:
 	log.user_format = rev.commit_format == CMIT_FMT_USERFORMAT;
 	log.abbrev = rev.abbrev;
 	log.file = rev.diffopt.file;
+	log.date_mode = rev.date_mode;
 
 	if (!log.groups)
 		log.groups = SHORTLOG_GROUP_AUTHOR;
-	string_list_sort(&log.trailers);
+	shortlog_finish_setup(&log);
 
 	/* assume HEAD if from a tty */
 	if (!nongit && !rev.pending.nr && isatty(0))
@@ -479,4 +511,5 @@ void shortlog_output(struct shortlog *log)
 	log->list.strdup_strings = 1;
 	string_list_clear(&log->list, 1);
 	clear_mailmap(&log->mailmap);
+	string_list_clear(&log->format, 0);
 }

shortlog.h

@@ -2,6 +2,7 @@
 #define SHORTLOG_H
 
 #include "string-list.h"
+#include "date.h"
 
 struct commit;
 
@@ -15,13 +16,16 @@ struct shortlog {
 	int in2;
 	int user_format;
 	int abbrev;
+	struct date_mode date_mode;
 
 	enum {
 		SHORTLOG_GROUP_AUTHOR = (1 << 0),
 		SHORTLOG_GROUP_COMMITTER = (1 << 1),
 		SHORTLOG_GROUP_TRAILER = (1 << 2),
+		SHORTLOG_GROUP_FORMAT = (1 << 3),
 	} groups;
 	struct string_list trailers;
+	struct string_list format;
 
 	int email;
 	struct string_list mailmap;
@@ -29,6 +33,7 @@ struct shortlog {
 };
 
 void shortlog_init(struct shortlog *log);
+void shortlog_finish_setup(struct shortlog *log);
 
 void shortlog_add_commit(struct shortlog *log, struct commit *commit);
 

t/t4201-shortlog.sh

@@ -83,6 +83,13 @@ test_expect_success 'pretty format' '
 	test_cmp expect log.predictable
 '
 
+test_expect_success 'pretty format (with --date)' '
+	sed "s/SUBJECT/2005-04-07 OBJECT_NAME/" expect.template >expect &&
+	git shortlog --format="%ad %H" --date=short HEAD >log &&
+	fuzz log >log.predictable &&
+	test_cmp expect log.predictable
+'
+
 test_expect_success '--abbrev' '
 	sed s/SUBJECT/OBJID/ expect.template >expect &&
 	git shortlog --format="%h" --abbrev=35 HEAD >log &&
@@ -237,6 +244,26 @@ test_expect_success 'shortlog --group=trailer:signed-off-by' '
 	test_cmp expect actual
 '
 
+test_expect_success 'shortlog --group=format' '
+	git shortlog -s --date="format:%Y" --group="format:%cN (%cd)" \
+		HEAD >actual &&
+	cat >expect <<-\EOF &&
+	     4	C O Mitter (2005)
+	     1	Sin Nombre (2005)
+	EOF
+	test_cmp expect actual
+'
+
+test_expect_success 'shortlog --group=<format> DWIM' '
+	git shortlog -s --date="format:%Y" --group="%cN (%cd)" HEAD >actual &&
+	test_cmp expect actual
+'
+
+test_expect_success 'shortlog bogus --group' '
+	test_must_fail git shortlog --group=bogus HEAD 2>err &&
+	grep "unknown group type" err
+'
+
 test_expect_success 'trailer idents are split' '
 	cat >expect <<-\EOF &&
 	     2	C O Mitter
@@ -319,6 +346,18 @@ test_expect_success 'shortlog can match multiple groups' '
 	test_cmp expect actual
 '
 
+test_expect_success 'shortlog can match multiple format groups' '
+	GIT_COMMITTER_NAME="$GIT_AUTHOR_NAME" \
+		git commit --allow-empty -m "identical names" &&
+	test_tick &&
+	cat >expect <<-\EOF &&
+	     2	A U Thor
+	     1	C O Mitter
+	EOF
+	git shortlog -ns --group="%cn" --group="%an" -2 HEAD >actual &&
+	test_cmp expect actual
+'
+
 test_expect_success 'set up option selection tests' '
 	git commit --allow-empty -F - <<-\EOF
 	subject