1
0
mirror of https://git.tartarus.org/simon/putty.git synced 2025-01-09 17:38:00 +00:00

Factor out encode_utf8 from luni_send into utils.c.

I knew there had to already be a UTF-8 encoder _somewhere_ in this
code base, but it took me a while to find it! Now it's reusable in
other contexts.
This commit is contained in:
Simon Tatham 2019-03-05 07:24:17 +00:00
parent 0dcdb1b5a3
commit 511eea450a
3 changed files with 28 additions and 15 deletions

View File

@ -65,21 +65,7 @@ void luni_send(Ldisc *ldisc, const wchar_t *widebuf, int len, bool interactive)
}
}
if (ch < 0x80) {
*p++ = (char) (ch);
} else if (ch < 0x800) {
*p++ = (char) (0xC0 | (ch >> 6));
*p++ = (char) (0x80 | (ch & 0x3F));
} else if (ch < 0x10000) {
*p++ = (char) (0xE0 | (ch >> 12));
*p++ = (char) (0x80 | ((ch >> 6) & 0x3F));
*p++ = (char) (0x80 | (ch & 0x3F));
} else {
*p++ = (char) (0xF0 | (ch >> 18));
*p++ = (char) (0x80 | ((ch >> 12) & 0x3F));
*p++ = (char) (0x80 | ((ch >> 6) & 0x3F));
*p++ = (char) (0x80 | (ch & 0x3F));
}
p += encode_utf8(p, ch);
}
} else {
int rv;

5
misc.h
View File

@ -199,6 +199,11 @@ void smemclr(void *b, size_t len);
* hinted at by the 'eq' in the name. */
bool smemeq(const void *av, const void *bv, size_t len);
/* Encode a single UTF-8 character. Assumes that illegal characters
* (such as things in the surrogate range, or > 0x10FFFF) have already
* been removed. */
size_t encode_utf8(void *output, unsigned long ch);
char *buildinfo(const char *newline);
/*

22
utils.c
View File

@ -958,3 +958,25 @@ bool strendswith(const char *s, const char *t)
size_t slen = strlen(s), tlen = strlen(t);
return slen >= tlen && !strcmp(s + (slen - tlen), t);
}
size_t encode_utf8(void *output, unsigned long ch)
{
unsigned char *start = (unsigned char *)output, *p = start;
if (ch < 0x80) {
*p++ = ch;
} else if (ch < 0x800) {
*p++ = 0xC0 | (ch >> 6);
*p++ = 0x80 | (ch & 0x3F);
} else if (ch < 0x10000) {
*p++ = 0xE0 | (ch >> 12);
*p++ = 0x80 | ((ch >> 6) & 0x3F);
*p++ = 0x80 | (ch & 0x3F);
} else {
*p++ = 0xF0 | (ch >> 18);
*p++ = 0x80 | ((ch >> 12) & 0x3F);
*p++ = 0x80 | ((ch >> 6) & 0x3F);
*p++ = 0x80 | (ch & 0x3F);
}
return p - start;
}