shortlog: respect commit encoding

Don't take the author name information without re-encoding from the raw
commit object buffer.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

2 files changed, 39 insertions, 9 deletions

diff --git a/builtin-shortlog.c b/builtin-shortlog.c
index 4d4a3c82d6..b98edc3ba6 100644
--- a/builtin-shortlog.c
+++ b/builtin-shortlog.c
@@ -139,8 +139,12 @@ static void read_from_stdin(struct shortlog *log)
 void shortlog_add_commit(struct shortlog *log, struct commit *commit)
 {
 	const char *author = NULL, *buffer;
+	struct strbuf buf = STRBUF_INIT;
+	struct strbuf ufbuf = STRBUF_INIT;
 
-	buffer = commit->buffer;
+	pretty_print_commit(CMIT_FMT_RAW, commit, &buf,
+			    0, NULL, NULL, DATE_NORMAL, 0);
+	buffer = buf.buf;
 	while (*buffer && *buffer != '\n') {
 		const char *eol = strchr(buffer, '\n');
 
@@ -157,17 +161,15 @@ void shortlog_add_commit(struct shortlog *log, struct commit *commit)
 		die("Missing author: %s",
 		    sha1_to_hex(commit->object.sha1));
 	if (log->user_format) {
-		struct strbuf buf = STRBUF_INIT;
-
-		pretty_print_commit(CMIT_FMT_USERFORMAT, commit, &buf,
+		pretty_print_commit(CMIT_FMT_USERFORMAT, commit, &ufbuf,
 			DEFAULT_ABBREV, "", "", DATE_NORMAL, 0);
-		insert_one_record(log, author, buf.buf);
-		strbuf_release(&buf);
-		return;
-	}
-	if (*buffer)
+		buffer = ufbuf.buf;
+	} else if (*buffer) {
 		buffer++;
+	}
 	insert_one_record(log, author, !*buffer ? "<none>" : buffer);
+	strbuf_release(&ufbuf);
+	strbuf_release(&buf);
 }
 
 static void get_from_rev(struct rev_info *rev, struct shortlog *log)
diff --git a/t/t4201-shortlog.sh b/t/t4201-shortlog.sh
index 405b971191..dd818f6fd6 100755
--- a/t/t4201-shortlog.sh
+++ b/t/t4201-shortlog.sh
@@ -52,4 +52,32 @@ GIT_DIR=non-existing git shortlog -w < log > out
 
 test_expect_success 'shortlog from non-git directory' 'test_cmp expect out'
 
+iconvfromutf8toiso88591() {
+	printf "%s" "$*" | iconv -f UTF-8 -t ISO-8859-1
+}
+
+DSCHO="Jöhännës \"Dschö\" Schindëlin"
+DSCHOE="$DSCHO <Johannes.Schindelin@gmx.de>"
+MSG1="set a1 to 2 and some non-ASCII chars: Äßø"
+MSG2="set a1 to 3 and some non-ASCII chars: áæï"
+cat > expect << EOF
+$DSCHO (2):
+      $MSG1
+      $MSG2
+
+EOF
+
+test_expect_success 'shortlog encoding' '
+	git reset --hard "$commit" &&
+	git config --unset i18n.commitencoding &&
+	echo 2 > a1 &&
+	git commit --quiet -m "$MSG1" --author="$DSCHOE" a1 &&
+	git config i18n.commitencoding "ISO-8859-1" &&
+	echo 3 > a1 &&
+	git commit --quiet -m "$(iconvfromutf8toiso88591 "$MSG2")" \
+		--author="$(iconvfromutf8toiso88591 "$DSCHOE")" a1 &&
+	git config --unset i18n.commitencoding &&
+	git shortlog HEAD~2.. > out &&
+test_cmp expect out'
+
 test_done