![[tokkee]](http://tokkee.org/images/avatar.png){kind=avatar}
index 9efcdb9c09970127ebe37923879274b95efd526c..ddfdc5e2b88d346886f64e39a93ced85cc10a78e 100644 (file)
--- a/utf8.c
+++ b/utf8.c
/* 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;
}
/*
- * 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. When remainder_p is not NULL, the location
+ * holds the number of bytes remaining in the string that we are allowed
+ * to pick from. Otherwise we are allowed to pick up to the NUL that
+ * would eventually appear in the string. *remainder_p is also reduced
+ * by the number of bytes we have consumed.
+ *
+ * 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, size_t *remainder_p)
{
unsigned char *s = (unsigned char *)*start;
ucs_char_t ch;
+ size_t remainder, incr;
+
+ /*
+ * A caller that assumes NUL terminated text can choose
+ * not to bother with the remainder length. We will
+ * stop at the first NUL.
+ */
+ remainder = (remainder_p ? *remainder_p : 999);
- if (*s < 0x80) {
+ if (remainder < 1) {
+ goto invalid;
+ } else if (*s < 0x80) {
/* 0xxxxxxx */
ch = *s;
- *start += 1;
+ incr = 1;
} else if ((s[0] & 0xe0) == 0xc0) {
/* 110XXXXx 10xxxxxx */
- if ((s[1] & 0xc0) != 0x80 ||
- /* overlong? */
- (s[0] & 0xfe) == 0xc0)
+ if (remainder < 2 ||
+ (s[1] & 0xc0) != 0x80 ||
+ (s[0] & 0xfe) == 0xc0)
goto invalid;
ch = ((s[0] & 0x1f) << 6) | (s[1] & 0x3f);
- *start += 2;
+ incr = 2;
} else if ((s[0] & 0xf0) == 0xe0) {
/* 1110XXXX 10Xxxxxx 10xxxxxx */
- if ((s[1] & 0xc0) != 0x80 ||
- (s[2] & 0xc0) != 0x80 ||
- /* overlong? */
- (s[0] == 0xe0 && (s[1] & 0xe0) == 0x80) ||
- /* surrogate? */
- (s[0] == 0xed && (s[1] & 0xe0) == 0xa0) ||
- /* U+FFFE or U+FFFF? */
- (s[0] == 0xef && s[1] == 0xbf &&
- (s[2] & 0xfe) == 0xbe))
+ if (remainder < 3 ||
+ (s[1] & 0xc0) != 0x80 ||
+ (s[2] & 0xc0) != 0x80 ||
+ /* overlong? */
+ (s[0] == 0xe0 && (s[1] & 0xe0) == 0x80) ||
+ /* surrogate? */
+ (s[0] == 0xed && (s[1] & 0xe0) == 0xa0) ||
+ /* U+FFFE or U+FFFF? */
+ (s[0] == 0xef && s[1] == 0xbf &&
+ (s[2] & 0xfe) == 0xbe))
goto invalid;
ch = ((s[0] & 0x0f) << 12) |
((s[1] & 0x3f) << 6) | (s[2] & 0x3f);
- *start += 3;
+ incr = 3;
} else if ((s[0] & 0xf8) == 0xf0) {
/* 11110XXX 10XXxxxx 10xxxxxx 10xxxxxx */
- if ((s[1] & 0xc0) != 0x80 ||
- (s[2] & 0xc0) != 0x80 ||
- (s[3] & 0xc0) != 0x80 ||
- /* overlong? */
- (s[0] == 0xf0 && (s[1] & 0xf0) == 0x80) ||
- /* > U+10FFFF? */
- (s[0] == 0xf4 && s[1] > 0x8f) || s[0] > 0xf4)
+ if (remainder < 4 ||
+ (s[1] & 0xc0) != 0x80 ||
+ (s[2] & 0xc0) != 0x80 ||
+ (s[3] & 0xc0) != 0x80 ||
+ /* overlong? */
+ (s[0] == 0xf0 && (s[1] & 0xf0) == 0x80) ||
+ /* > U+10FFFF? */
+ (s[0] == 0xf4 && s[1] > 0x8f) || s[0] > 0xf4)
goto invalid;
ch = ((s[0] & 0x07) << 18) | ((s[1] & 0x3f) << 12) |
((s[2] & 0x3f) << 6) | (s[3] & 0x3f);
- *start += 4;
+ incr = 4;
} else {
invalid:
*start = NULL;
return 0;
}
+ *start += incr;
+ if (remainder_p)
+ *remainder_p = remainder - incr;
+ 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. When remainder_p is not NULL, it points at the
+ * location that stores the number of remaining bytes we can use to pick
+ * a character (see pick_one_utf8_char() above).
+ */
+int utf8_width(const char **start, size_t *remainder_p)
+{
+ ucs_char_t ch = pick_one_utf8_char(start, remainder_p);
+ if (!*start)
+ return 0;
return git_wcwidth(ch);
}
+/*
+ * Returns the total number of columns required by a null-terminated
+ * string, assuming that the string is utf8. Returns strlen() instead
+ * if the string does not look like a valid utf8 string.
+ */
+int utf8_strwidth(const char *string)
+{
+ int width = 0;
+ const char *orig = string;
+
+ while (1) {
+ if (!string)
+ return strlen(orig);
+ if (!*string)
+ return width;
+ width += utf8_width(&string, NULL);
+ }
+}
+
int is_utf8(const char *text)
{
while (*text) {
text++;
continue;
}
- utf8_width(&text);
+ utf8_width(&text, NULL);
if (!text)
return 0;
}
continue;
}
if (assume_utf8)
- w += utf8_width(&text);
+ w += utf8_width(&text, NULL);
else {
w++;
text++;