diff: do not chomp hunk-header in the middle of a character
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 pick_one_utf8_char() function to make sure we do not cut a character in the middle. This assumes that the internal representation of the text is UTF-8. This needs to be extended in the future but the optimal direction has not been decided yet. Signed-off-by: Junio C Hamano <gitster@pobox.com>
This commit is contained in:

committed by
Junio C Hamano

parent
44b25b872f
commit
23707811c5
25
diff.c
25
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
|
||||
@ -469,10 +470,13 @@ 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;
|
||||
@ -525,6 +529,24 @@ 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 allot;
|
||||
size_t l = len;
|
||||
|
||||
if (ecb->truncate)
|
||||
return ecb->truncate(line, len);
|
||||
cp = line;
|
||||
allot = l;
|
||||
while (0 < l) {
|
||||
(void) utf8_width(&cp, &l);
|
||||
if (!cp)
|
||||
break; /* truncated in the middle? */
|
||||
}
|
||||
return allot - l;
|
||||
}
|
||||
|
||||
static void fn_out_consume(void *priv, char *line, unsigned long len)
|
||||
{
|
||||
int i;
|
||||
@ -555,8 +577,11 @@ 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;
|
||||
}
|
||||
|
||||
|
Reference in New Issue
Block a user