Last active
August 20, 2023 09:02
-
-
Save assyrianic/c17af7cbe506ddf6fbd23c0992ffd74d to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#if defined _utf8_included | |
#endinput | |
#endif | |
#define _utf8_included | |
#include <sourcemod> | |
stock int GetUTF8Len(int c) { | |
for( int i=7; i < 8; i-- ) { | |
if( !(c & (1 << i)) ) { | |
return (7 - i)==0? 1 : 7 - i; | |
} | |
} | |
return -1; | |
} | |
stock int GetRuneBytes(int rune) { | |
if( rune < 0x80 ) { | |
return 1; | |
} else if( rune < 0x800 ) { | |
return 2; | |
} else if( rune < 0x10000 ) { | |
return 3; | |
} else if( rune < 0x110000 ) { | |
return 4; | |
} | |
return 0; | |
} | |
stock int UTF8CharToRune(const char[] cstr, int &read=0) { | |
read = GetUTF8Len(cstr[0]); | |
if( read <= 1 ) { | |
return cstr[0]; | |
} | |
int rune; | |
for( int i=1; i < read; i++ ) { | |
if( (cstr[i] & 0xc0) != 0x80 ) { | |
return 0; | |
} | |
} | |
switch( read ) { | |
case 2: rune = ((cstr[0] & 0x1F) << 6) | (cstr[1] & 0x3F); | |
case 3: rune = ((cstr[0] & 0xF) << 12) | ((cstr[1] & 0x3F) << 6) | (cstr[2] & 0x3F); | |
case 4: rune = ((cstr[0] & 0x7) << 18) | ((cstr[1] & 0x3F) << 12) | ((cstr[2] & 0x3F) << 6) | (cstr[3] & 0x3F); | |
default: return 0; | |
} | |
return rune; | |
} | |
stock int GetUTF8StrLen(const char[] str) { | |
int runes = 0; | |
for( int i; str[i] != 0; ) { | |
i += GetUTF8Len(str[i]); | |
runes++; | |
} | |
return runes + 1; | |
} | |
stock void UTF8StrToRunes(const char[] str, int[] runes) { | |
int i, n; | |
while( str[i] != 0 ) { | |
int bytes_read; | |
int chr = UTF8CharToRune(str[i], bytes_read); | |
if( chr==0 ) { | |
break; | |
} | |
i += bytes_read; | |
runes[n] = chr; | |
n++; | |
} | |
runes[n] = 0; | |
} | |
stock int GetRuneStrLen(const int[] runes) { | |
int bytes; | |
for( int i; runes[i] != 0; i++ ) { | |
bytes += GetRuneBytes(runes[i]); | |
} | |
return bytes + 1; | |
} | |
stock bool RunesToUTF8Str(const int[] runes, char[] buf) { | |
int n; | |
for( int i; runes[i] != 0; i++ ) { | |
int rune = runes[i]; | |
int bytes = GetRuneBytes(rune); | |
switch( bytes ) { | |
case 1: { | |
buf[n] = rune; | |
} | |
case 2: { | |
buf[ n ] = (0xC0 | (rune >> 6)); | |
buf[n+1] = (0x80 | (rune & 0x3F)); | |
} | |
case 3: { | |
buf[ n ] = (0xE0 | (rune >> 12)); | |
buf[n+1] = (0x80 | ((rune >> 6) & 0x3F)); | |
buf[n+2] = (0x80 | (rune & 0x3F)); | |
} | |
case 4: { | |
buf[ n ] = (0xF0 | (rune >> 18)); | |
buf[n+1] = (0x80 | ((rune >> 12) & 0x3F)); | |
buf[n+2] = (0x80 | ((rune >> 6) & 0x3F)); | |
buf[n+3] = (0x80 | (rune & 0x3F)); | |
} | |
default: { | |
return false; | |
} | |
} | |
n += bytes; | |
} | |
buf[n] = 0; | |
return n > 0; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment