shortlog: allow multiple groups to be specified

Now that shortlog supports reading from trailers, it can be useful to
combine counts from multiple trailers, or between trailers and authors.
This can be done manually by post-processing the output from multiple
runs, but it's non-trivial to make sure that each name/commit pair is
counted only once.

This patch teaches shortlog to accept multiple --group options on the
command line, and pull data from all of them. That makes it possible to
run:

  git shortlog -ns --group=author --group=trailer:co-authored-by

to get a shortlog that counts authors and co-authors equally.

The implementation is mostly straightforward. The "group" enum becomes a
bitfield, and the trailer key becomes a list. I didn't bother
implementing the multi-group semantics for reading from stdin. It would
be possible to do, but the existing matching code makes it awkward, and
I doubt anybody cares.

The duplicate suppression we used for trailers now covers authors and
committers as well (though in non-trailer single-group mode we can skip
the hash insertion and lookup, since we only see one value per commit).

There is one subtlety: we now care about the case when no group bit is
set (in which case we default to showing the author). The caller in
builtin/log.c needs to be adapted to ask explicitly for authors, rather
than relying on shortlog_init(). It would be possible with some
gymnastics to make this keep working as-is, but it's not worth it for a
single caller.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 40 insertions, 24 deletions

diff --git a/builtin/shortlog.c b/builtin/shortlog.c
index 28133aec685..0a5c4968f64 100644
--- a/builtin/shortlog.c
+++ b/builtin/shortlog.c
@@ -130,7 +130,10 @@ static void read_from_stdin(struct shortlog *log)
 	static const char *committer_match[2] = { "Commit: ", "committer " };
 	const char **match;
 
-	switch (log->group) {
+	if (HAS_MULTI_BITS(log->groups))
+		die(_("using multiple --group options with stdin is not supported"));
+
+	switch (log->groups) {
 	case SHORTLOG_GROUP_AUTHOR:
 		match = author_match;
 		break;
@@ -221,13 +224,13 @@ static void strset_clear(struct strset *ss)
 }
 
 static void insert_records_from_trailers(struct shortlog *log,
+					 struct strset *dups,
 					 struct commit *commit,
 					 struct pretty_print_context *ctx,
 					 const char *oneline)
 {
 	struct trailer_iterator iter;
 	const char *commit_buffer, *body;
-	struct strset dups = STRSET_INIT;
 	struct strbuf ident = STRBUF_INIT;
 
 	/*
@@ -243,21 +246,20 @@ static void insert_records_from_trailers(struct shortlog *log,
 	while (trailer_iterator_advance(&iter)) {
 		const char *value = iter.val.buf;
 
-		if (strcasecmp(iter.key.buf, log->trailer))
+		if (!string_list_has_string(&log->trailers, iter.key.buf))
 			continue;
 
 		strbuf_reset(&ident);
 		if (!parse_ident(log, &ident, value))
 			value = ident.buf;
 
-		if (strset_check_and_add(&dups, value))
+		if (strset_check_and_add(dups, value))
 			continue;
 		insert_one_record(log, value, oneline);
 	}
 	trailer_iterator_release(&iter);
 
 	strbuf_release(&ident);
-	strset_clear(&dups);
 	unuse_commit_buffer(commit, commit_buffer);
 }
 
@@ -265,6 +267,7 @@ 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};
 	const char *oneline_str;
 
@@ -282,24 +285,29 @@ void shortlog_add_commit(struct shortlog *log, struct commit *commit)
 	}
 	oneline_str = oneline.len ? oneline.buf : "<none>";
 
-	switch (log->group) {
-	case SHORTLOG_GROUP_AUTHOR:
+	if (log->groups & SHORTLOG_GROUP_AUTHOR) {
+		strbuf_reset(&ident);
 		format_commit_message(commit,
 				      log->email ? "%aN <%aE>" : "%aN",
 				      &ident, &ctx);
-		insert_one_record(log, ident.buf, oneline_str);
-		break;
-	case SHORTLOG_GROUP_COMMITTER:
+		if (!HAS_MULTI_BITS(log->groups) ||
+		    !strset_check_and_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);
-		insert_one_record(log, ident.buf, oneline_str);
-		break;
-	case SHORTLOG_GROUP_TRAILER:
-		insert_records_from_trailers(log, commit, &ctx, oneline_str);
-		break;
+		if (!HAS_MULTI_BITS(log->groups) ||
+		    !strset_check_and_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);
 	}
 
+	strset_clear(&dups);
 	strbuf_release(&ident);
 	strbuf_release(&oneline);
 }
@@ -366,14 +374,16 @@ static int parse_group_option(const struct option *opt, const char *arg, int uns
 	struct shortlog *log = opt->value;
 	const char *field;
 
-	if (unset || !strcasecmp(arg, "author"))
-		log->group = SHORTLOG_GROUP_AUTHOR;
+	if (unset) {
+		log->groups = 0;
+		string_list_clear(&log->trailers, 0);
+	} else if (!strcasecmp(arg, "author"))
+		log->groups |= SHORTLOG_GROUP_AUTHOR;
 	else if (!strcasecmp(arg, "committer"))
-		log->group = SHORTLOG_GROUP_COMMITTER;
+		log->groups |= SHORTLOG_GROUP_COMMITTER;
 	else if (skip_prefix(arg, "trailer:", &field)) {
-		log->group = SHORTLOG_GROUP_TRAILER;
-		free(log->trailer);
-		log->trailer = xstrdup(field);
+		log->groups |= SHORTLOG_GROUP_TRAILER;
+		string_list_append(&log->trailers, field);
 	} else
 		return error(_("unknown group type: %s"), arg);
 
@@ -391,6 +401,8 @@ void shortlog_init(struct shortlog *log)
 	log->wrap = DEFAULT_WRAPLEN;
 	log->in1 = DEFAULT_INDENT1;
 	log->in2 = DEFAULT_INDENT2;
+	log->trailers.strdup_strings = 1;
+	log->trailers.cmp = strcasecmp;
 }
 
 int cmd_shortlog(int argc, const char **argv, const char *prefix)
@@ -400,9 +412,9 @@ int cmd_shortlog(int argc, const char **argv, const char *prefix)
 	int nongit = !startup_info->have_repository;
 
 	const struct option options[] = {
-		OPT_SET_INT('c', "committer", &log.group,
-			    N_("Group by committer rather than author"),
-			    SHORTLOG_GROUP_COMMITTER),
+		OPT_BIT('c', "committer", &log.groups,
+			N_("Group by committer rather than author"),
+			SHORTLOG_GROUP_COMMITTER),
 		OPT_BOOL('n', "numbered", &log.sort_by_number,
 			 N_("sort output according to the number of commits per author")),
 		OPT_BOOL('s', "summary", &log.summary,
@@ -454,6 +466,10 @@ parse_done:
 	log.abbrev = rev.abbrev;
 	log.file = rev.diffopt.file;
 
+	if (!log.groups)
+		log.groups = SHORTLOG_GROUP_AUTHOR;
+	string_list_sort(&log.trailers);
+
 	/* assume HEAD if from a tty */
 	if (!nongit && !rev.pending.nr && isatty(0))
 		add_head_to_pending(&rev);