mirror of
https://github.com/hrydgard/ppsspp.git
synced 2026-10-01 14:58:14 +00:00
Delete dead code from Utf8.cpp
This commit is contained in:
Henrik Rydgård committed
1 parent
c60074d1d5
commit
073a6fef0e
1 file changed
+6
-221
@@ -50,102 +50,6 @@ static const uint8_t trailingBytesForUTF8[256] = {
|
||||
2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2, 3,3,3,3,3,3,3,3,4,4,4,4,5,5,5,5,
|
||||
};
|
||||
|
||||
/* conversions without error checking
|
||||
only works for valid UTF-8, i.e. no 5- or 6-byte sequences
|
||||
srcsz = source size in bytes, or -1 if 0-terminated
|
||||
sz = dest size in # of wide characters
|
||||
|
||||
returns # characters converted
|
||||
dest will always be L'\0'-terminated, even if there isn't enough room
|
||||
for all the characters.
|
||||
if sz = srcsz+1 (i.e. 4*srcsz+4 bytes), there will always be enough space.
|
||||
*/
|
||||
int u8_toucs(uint32_t *dest, int sz, const char *src, int srcsz)
|
||||
{
|
||||
uint32_t ch;
|
||||
const char *src_end = src + srcsz;
|
||||
int nb;
|
||||
int i=0;
|
||||
|
||||
while (i < sz-1) {
|
||||
nb = trailingBytesForUTF8[(unsigned char)*src];
|
||||
if (srcsz == -1) {
|
||||
if (*src == 0)
|
||||
goto done_toucs;
|
||||
}
|
||||
else {
|
||||
if (src + nb >= src_end)
|
||||
goto done_toucs;
|
||||
}
|
||||
ch = 0;
|
||||
switch (nb) {
|
||||
/* these fall through deliberately */
|
||||
case 3: ch += (unsigned char)*src++; ch <<= 6;
|
||||
case 2: ch += (unsigned char)*src++; ch <<= 6;
|
||||
case 1: ch += (unsigned char)*src++; ch <<= 6;
|
||||
case 0: ch += (unsigned char)*src++;
|
||||
}
|
||||
ch -= offsetsFromUTF8[nb];
|
||||
dest[i++] = ch;
|
||||
}
|
||||
done_toucs:
|
||||
dest[i] = 0;
|
||||
return i;
|
||||
}
|
||||
|
||||
/* srcsz = number of source characters, or -1 if 0-terminated
|
||||
sz = size of dest buffer in bytes
|
||||
|
||||
returns # characters converted
|
||||
dest will only be '\0'-terminated if there is enough space. this is
|
||||
for consistency; imagine there are 2 bytes of space left, but the next
|
||||
character requires 3 bytes. in this case we could NUL-terminate, but in
|
||||
general we can't when there's insufficient space. therefore this function
|
||||
only NUL-terminates if all the characters fit, and there's space for
|
||||
the NUL as well.
|
||||
the destination string will never be bigger than the source string.
|
||||
*/
|
||||
int u8_toutf8(char *dest, int sz, const uint32_t *src, int srcsz)
|
||||
{
|
||||
uint32_t ch;
|
||||
int i = 0;
|
||||
char *dest_end = dest + sz;
|
||||
|
||||
while (srcsz<0 ? src[i]!=0 : i < srcsz) {
|
||||
ch = src[i];
|
||||
if (ch < 0x80) {
|
||||
if (dest >= dest_end)
|
||||
return i;
|
||||
*dest++ = (char)ch;
|
||||
}
|
||||
else if (ch < 0x800) {
|
||||
if (dest >= dest_end-1)
|
||||
return i;
|
||||
*dest++ = (ch>>6) | 0xC0;
|
||||
*dest++ = (ch & 0x3F) | 0x80;
|
||||
}
|
||||
else if (ch < 0x10000) {
|
||||
if (dest >= dest_end-2)
|
||||
return i;
|
||||
*dest++ = (ch>>12) | 0xE0;
|
||||
*dest++ = ((ch>>6) & 0x3F) | 0x80;
|
||||
*dest++ = (ch & 0x3F) | 0x80;
|
||||
}
|
||||
else if (ch < 0x110000) {
|
||||
if (dest >= dest_end-3)
|
||||
return i;
|
||||
*dest++ = (ch>>18) | 0xF0;
|
||||
*dest++ = ((ch>>12) & 0x3F) | 0x80;
|
||||
*dest++ = ((ch>>6) & 0x3F) | 0x80;
|
||||
*dest++ = (ch & 0x3F) | 0x80;
|
||||
}
|
||||
i++;
|
||||
}
|
||||
if (dest < dest_end)
|
||||
*dest = '\0';
|
||||
return i;
|
||||
}
|
||||
|
||||
int u8_wc_toutf8(char *dest, uint32_t ch)
|
||||
{
|
||||
if (ch < 0x80) {
|
||||
@@ -237,133 +141,14 @@ uint32_t u8_nextchar_unsafe(const char *s, int *i) {
|
||||
return ch;
|
||||
}
|
||||
|
||||
void u8_inc(const char *s, int *i)
|
||||
{
|
||||
(void)(isutf(s[++(*i)]) || isutf(s[++(*i)]) ||
|
||||
isutf(s[++(*i)]) || ++(*i));
|
||||
void u8_inc(const char *s, int *i) {
|
||||
(void)(isutf(s[++(*i)]) || isutf(s[++(*i)]) ||
|
||||
isutf(s[++(*i)]) || ++(*i));
|
||||
}
|
||||
|
||||
void u8_dec(const char *s, int *i)
|
||||
{
|
||||
(void)(isutf(s[--(*i)]) || isutf(s[--(*i)]) ||
|
||||
isutf(s[--(*i)]) || --(*i));
|
||||
}
|
||||
|
||||
int octal_digit(char c)
|
||||
{
|
||||
return (c >= '0' && c <= '7');
|
||||
}
|
||||
|
||||
int hex_digit(char c)
|
||||
{
|
||||
return ((c >= '0' && c <= '9') ||
|
||||
(c >= 'A' && c <= 'F') ||
|
||||
(c >= 'a' && c <= 'f'));
|
||||
}
|
||||
|
||||
/* assumes that src points to the character after a backslash
|
||||
returns number of input characters processed */
|
||||
int u8_read_escape_sequence(const char *str, uint32_t *dest)
|
||||
{
|
||||
long ch;
|
||||
char digs[9]="\0\0\0\0\0\0\0\0";
|
||||
int dno=0, i=1;
|
||||
|
||||
ch = (uint32_t)str[0]; /* take literal character */
|
||||
if (str[0] == 'n')
|
||||
ch = L'\n';
|
||||
else if (str[0] == 't')
|
||||
ch = L'\t';
|
||||
else if (str[0] == 'r')
|
||||
ch = L'\r';
|
||||
else if (str[0] == 'b')
|
||||
ch = L'\b';
|
||||
else if (str[0] == 'f')
|
||||
ch = L'\f';
|
||||
else if (str[0] == 'v')
|
||||
ch = L'\v';
|
||||
else if (str[0] == 'a')
|
||||
ch = L'\a';
|
||||
else if (octal_digit(str[0])) {
|
||||
i = 0;
|
||||
do {
|
||||
digs[dno++] = str[i++];
|
||||
} while (octal_digit(str[i]) && dno < 3);
|
||||
ch = strtol(digs, NULL, 8);
|
||||
}
|
||||
else if (str[0] == 'x') {
|
||||
while (hex_digit(str[i]) && dno < 2) {
|
||||
digs[dno++] = str[i++];
|
||||
}
|
||||
if (dno > 0)
|
||||
ch = strtol(digs, NULL, 16);
|
||||
}
|
||||
else if (str[0] == 'u') {
|
||||
while (hex_digit(str[i]) && dno < 4) {
|
||||
digs[dno++] = str[i++];
|
||||
}
|
||||
if (dno > 0)
|
||||
ch = strtol(digs, NULL, 16);
|
||||
}
|
||||
else if (str[0] == 'U') {
|
||||
while (hex_digit(str[i]) && dno < 8) {
|
||||
digs[dno++] = str[i++];
|
||||
}
|
||||
if (dno > 0)
|
||||
ch = strtol(digs, NULL, 16);
|
||||
}
|
||||
*dest = (uint32_t)ch;
|
||||
|
||||
return i;
|
||||
}
|
||||
|
||||
/* convert a string with literal \uxxxx or \Uxxxxxxxx characters to UTF-8
|
||||
example: u8_unescape(mybuf, 256, "hello\\u220e")
|
||||
note the double backslash is needed if called on a C string literal */
|
||||
int u8_unescape(char *buf, int sz, char *src)
|
||||
{
|
||||
int c=0, amt;
|
||||
uint32_t ch;
|
||||
char temp[4];
|
||||
|
||||
while (*src && c < sz) {
|
||||
if (*src == '\\') {
|
||||
src++;
|
||||
amt = u8_read_escape_sequence(src, &ch);
|
||||
}
|
||||
else {
|
||||
ch = (uint32_t)*src;
|
||||
amt = 1;
|
||||
}
|
||||
src += amt;
|
||||
amt = u8_wc_toutf8(temp, ch);
|
||||
if (amt > sz-c)
|
||||
break;
|
||||
memcpy(&buf[c], temp, amt);
|
||||
c += amt;
|
||||
}
|
||||
if (c < sz)
|
||||
buf[c] = '\0';
|
||||
return c;
|
||||
}
|
||||
|
||||
int u8_is_locale_utf8(const char *locale)
|
||||
{
|
||||
/* this code based on libutf8 */
|
||||
const char* cp = locale;
|
||||
|
||||
for (; *cp != '\0' && *cp != '@' && *cp != '+' && *cp != ','; cp++) {
|
||||
if (*cp == '.') {
|
||||
const char* encoding = ++cp;
|
||||
for (; *cp != '\0' && *cp != '@' && *cp != '+' && *cp != ','; cp++)
|
||||
;
|
||||
if ((cp-encoding == 5 && !strncmp(encoding, "UTF-8", 5))
|
||||
|| (cp-encoding == 4 && !strncmp(encoding, "utf8", 4)))
|
||||
return 1; /* it's UTF-8 */
|
||||
break;
|
||||
}
|
||||
}
|
||||
return 0;
|
||||
void u8_dec(const char *s, int *i) {
|
||||
(void)(isutf(s[--(*i)]) || isutf(s[--(*i)]) ||
|
||||
isutf(s[--(*i)]) || --(*i));
|
||||
}
|
||||
|
||||
bool AnyEmojiInString(std::string_view str, size_t byteCount) {
|
||||
|
||||
Reference in new issue
Block a user