From 1b5290b125fca91f620aadbc1a5e3c559d4a5313 Mon Sep 17 00:00:00 2001
From: Jeff King <peff@peff.net>
Date: Wed, 31 Aug 2016 01:03:10 -0400
Subject: [PATCH] diff-highlight: add multi-byte tests

Now that we have a test suite for diff highlight, we can
show off the improvements from 8d00662 (diff-highlight: do
not split multibyte characters, 2015-04-03).

While we're at it, we can also add another case that
_doesn't_ work: combining code points are treated as their
own unit, which means that we may stick colors between them
and the character they are modifying (with the result that
the color is not shown in an xterm, though it's possible
that other terminals err the other way, and show the color
but not the accent).  There's no fix here, but let's
document it as a failure.

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
---
 .../diff-highlight/t/t9400-diff-highlight.sh  | 36 ++++++++++++++++++-
 1 file changed, 35 insertions(+), 1 deletion(-)

diff --git a/contrib/diff-highlight/t/t9400-diff-highlight.sh b/contrib/diff-highlight/t/t9400-diff-highlight.sh
index e42ff31f3d..b0fe7cc8aa 100755
--- a/contrib/diff-highlight/t/t9400-diff-highlight.sh
+++ b/contrib/diff-highlight/t/t9400-diff-highlight.sh
@@ -207,7 +207,41 @@ test_expect_failure 'diff-highlight highlights mismatched hunk size' '
 	EOF
 '
 
-# TODO add multi-byte test
+# These two code points share the same leading byte in UTF-8 representation;
+# a naive byte-wise diff would highlight only the second byte.
+#
+#   - U+00f3 ("o" with acute)
+o_accent=$(printf '\303\263')
+#   - U+00f8 ("o" with stroke)
+o_stroke=$(printf '\303\270')
+
+test_expect_success 'diff-highlight treats multibyte utf-8 as a unit' '
+	echo "unic${o_accent}de" >a &&
+	echo "unic${o_stroke}de" >b &&
+	dh_test a b <<-EOF
+		@@ -1 +1 @@
+		-unic${CW}${o_accent}${CR}de
+		+unic${CW}${o_stroke}${CR}de
+	EOF
+'
+
+# Unlike the UTF-8 above, these are combining code points which are meant
+# to modify the character preceding them:
+#
+#   - U+0301 (combining acute accent)
+combine_accent=$(printf '\314\201')
+#   - U+0302 (combining circumflex)
+combine_circum=$(printf '\314\202')
+
+test_expect_failure 'diff-highlight treats combining code points as a unit' '
+	echo "unico${combine_accent}de" >a &&
+	echo "unico${combine_circum}de" >b &&
+	dh_test a b <<-EOF
+		@@ -1 +1 @@
+		-unic${CW}o${combine_accent}${CR}de
+		+unic${CW}o${combine_circum}${CR}de
+	EOF
+'
 
 test_expect_success 'diff-highlight works with the --graph option' '
 	dh_test_setup_history &&
-- 
2.43.2