summaryrefslogtreecommitdiff
path: root/utf8.c
diff options
context:
space:
mode:
authorJunio C Hamano <gitster@pobox.com>2008-01-07 03:02:22 (GMT)
committerJunio C Hamano <gitster@pobox.com>2008-01-07 04:27:35 (GMT)
commit396ccf1fcb91f31d5060555cbffc35bf24172a35 (patch)
tree8fb86e72df7bb26569f81f6c0a1dd12c41be060c /utf8.c
parent40f162b04b3d5155a7e41d27c9f52383a5fa5a9f (diff)
downloadgit-396ccf1fcb91f31d5060555cbffc35bf24172a35.zip
git-396ccf1fcb91f31d5060555cbffc35bf24172a35.tar.gz
git-396ccf1fcb91f31d5060555cbffc35bf24172a35.tar.bz2
utf8: pick_one_utf8_char()
utf8_width() function was doing two different things. To pick a valid character from UTF-8 stream, and compute the display width of that character. This splits the former to a separate function pick_one_utf8_char(). Signed-off-by: Junio C Hamano <gitster@pobox.com>
Diffstat (limited to 'utf8.c')
-rw-r--r--utf8.c27
1 files changed, 21 insertions, 6 deletions
diff --git a/utf8.c b/utf8.c
index 9efcdb9..24d2ec6 100644
--- a/utf8.c
+++ b/utf8.c
@@ -3,8 +3,6 @@
/* This code is originally from http://www.cl.cam.ac.uk/~mgk25/ucs/ */
-typedef unsigned int ucs_char_t; /* assuming 32bit int */
-
struct interval {
int first;
int last;
@@ -153,11 +151,14 @@ static int git_wcwidth(ucs_char_t ch)
}
/*
- * This function returns the number of columns occupied by the character
- * pointed to by the variable start. The pointer is updated to point at
- * the next character. If it was not valid UTF-8, the pointer is set to NULL.
+ * Pick one ucs character starting from the location *start points at,
+ * and return it, while updating the *start pointer to point at the
+ * end of that character.
+ *
+ * If the string was not a valid UTF-8, *start pointer is set to NULL
+ * and the return value is undefined.
*/
-int utf8_width(const char **start)
+ucs_char_t pick_one_utf8_char(const char **start)
{
unsigned char *s = (unsigned char *)*start;
ucs_char_t ch;
@@ -208,6 +209,20 @@ invalid:
return 0;
}
+ return ch;
+}
+
+/*
+ * This function returns the number of columns occupied by the character
+ * pointed to by the variable start. The pointer is updated to point at
+ * the next character. If it was not valid UTF-8, the pointer is set to
+ * NULL.
+ */
+int utf8_width(const char **start)
+{
+ ucs_char_t ch = pick_one_utf8_char(start);
+ if (!*start)
+ return 0;
return git_wcwidth(ch);
}