/*
* Returns first character length in bytes for multi-byte `text` according to
* `encoding`.
*
* - The `text` pointer is updated to point at the next character.
* - When `remainder_p` is not NULL, on entry `*remainder_p` is how much bytes
* we can consume from text, and on exit `*remainder_p` is reduced by returned
* character length. Otherwise `text` is treated as limited by NUL.
*/
int mbs_chrlen(const char **text, size_t *remainder_p, const char *encoding)
{
int chrlen;
const char *p = *text;
size_t r = (remainder_p ? *remainder_p : SIZE_MAX);
if (r < 1)
return 0;
if (is_encoding_utf8(encoding)) {
pick_one_utf8_char(&p, &r);
chrlen = p ? (p - *text)
: 1 /* not valid UTF-8 -> raw byte sequence */;
}
else {
/*
* TODO use iconv to decode one char and obtain its chrlen
* for now, let's treat encodings != UTF-8 as one-byte
*/
chrlen = 1;
}
*text += chrlen;
if (remainder_p)
*remainder_p -= chrlen;
return chrlen;
}
/*
* 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);
}
/*
* Pick the next char from the stream, folding as an HFS+ filename comparison
* would. Note that this is _not_ complete by any means. It's just enough
* to make is_hfs_dotgit() work, and should not be used otherwise.
*/
static ucs_char_t next_hfs_char(const char **in)
{
while (1) {
ucs_char_t out = pick_one_utf8_char(in, NULL);
/*
* check for malformed utf8. Technically this
* gets converted to a percent-sequence, but
* returning 0 is good enough for is_hfs_dotgit
* to realize it cannot be .git
*/
if (!*in)
return 0;
/* these code points are ignored completely */
switch (out) {
case 0x200c: /* ZERO WIDTH NON-JOINER */
case 0x200d: /* ZERO WIDTH JOINER */
case 0x200e: /* LEFT-TO-RIGHT MARK */
case 0x200f: /* RIGHT-TO-LEFT MARK */
case 0x202a: /* LEFT-TO-RIGHT EMBEDDING */
case 0x202b: /* RIGHT-TO-LEFT EMBEDDING */
case 0x202c: /* POP DIRECTIONAL FORMATTING */
case 0x202d: /* LEFT-TO-RIGHT OVERRIDE */
case 0x202e: /* RIGHT-TO-LEFT OVERRIDE */
case 0x206a: /* INHIBIT SYMMETRIC SWAPPING */
case 0x206b: /* ACTIVATE SYMMETRIC SWAPPING */
case 0x206c: /* INHIBIT ARABIC FORM SHAPING */
case 0x206d: /* ACTIVATE ARABIC FORM SHAPING */
case 0x206e: /* NATIONAL DIGIT SHAPES */
case 0x206f: /* NOMINAL DIGIT SHAPES */
case 0xfeff: /* ZERO WIDTH NO-BREAK SPACE */
continue;
}
/*
* there's a great deal of other case-folding that occurs,
* but this is enough to catch anything that will convert
* to ".git"
*/
return tolower(out);
}
}
