[PATCH 2/2] diff: do not chomp hunk-header in the middle of a character

[Junio C Hamano <junio@pobox.com>]

We truncate hunk-header line at 80 bytes, but that 80th byte
could be in the middle of a character, which is bad.  This uses
utf8_width() function to make sure we do not cut a character in
the middle.

Signed-off-by: Junio C Hamano <gitster@pobox.com>
---

 * And this implements the sane_truncate_line() that
   unconditionally assumes UTF-8.

   The 80-byte cutoff is meant to chomp at 80 display columns,
   and in many encodings including UTF-8 80 cols are usually
   more than 80 bytes.  To implement 80 column chomping, we
   would need to tweak the low level xdl_find_func() interface
   further so that it gives us back more than 80-bytes.  Ideally
   that layer should not be doing any chomping.

   Another thing I noticed but did not bother to fix was that
   the emit_line() interface is doing bad things with color.
   It emits:

	start-color text (= line, len) reset-color

   and the text often ends with LF.  We should emit reset-color
   before the terminating LF instead.

 diff.c |   28 ++++++++++++++++++++++++++++
 1 files changed, 28 insertions(+), 0 deletions(-)

diff --git a/diff.c b/diff.c
index 5bdc111..b9159bc 100644
--- a/diff.c
+++ b/diff.c
@@ -10,6 +10,7 @@
 #include "color.h"
 #include "attr.h"
 #include "run-command.h"
+#include "utf8.h"
 
 #ifdef NO_FAST_WORKING_DIRECTORY
 #define FAST_WORKING_DIRECTORY 0
@@ -465,10 +466,13 @@ static void diff_words_show(struct diff_words_data *diff_words)
 	}
 }
 
+typedef unsigned long (*sane_truncate_fn)(char *line, unsigned long len);
+
 struct emit_callback {
 	struct xdiff_emit_state xm;
 	int nparents, color_diff;
 	unsigned ws_rule;
+	sane_truncate_fn truncate;
 	const char **label_path;
 	struct diff_words_data *diff_words;
 	int *found_changesp;
@@ -521,6 +525,27 @@ static void emit_add_line(const char *reset, struct emit_callback *ecbdata, cons
 	}
 }
 
+static unsigned long sane_truncate_line(struct emit_callback *ecb, char *line, unsigned long len)
+{
+	const char *cp;
+	unsigned long width, allot;
+
+	if (ecb->truncate)
+		return ecb->truncate(line, len);
+	cp = line;
+	width = 0;
+	allot = len;
+	while (0 < len) {
+		int w = utf8_width(&cp, &len);
+		if (!cp)
+			break; /* truncated in the middle? */
+		width += w;
+		if (allot <= width)
+			break;
+	}
+	return allot - len;
+}
+
 static void fn_out_consume(void *priv, char *line, unsigned long len)
 {
 	int i;
@@ -551,8 +576,11 @@ static void fn_out_consume(void *priv, char *line, unsigned long len)
 		;
 	if (2 <= i && i < len && line[i] == ' ') {
 		ecbdata->nparents = i - 1;
+		len = sane_truncate_line(ecbdata, line, len);
 		emit_line(diff_get_color(ecbdata->color_diff, DIFF_FRAGINFO),
 			  reset, line, len);
+		if (line[len-1] != '\n')
+			putchar('\n');
 		return;
 	}
 
-- 
1.5.4.rc2.13.g690bd