swunicod.cpp Source File

00001 /*
00002  *
00003  * Copyright 1998 CrossWire Bible Society (http://www.crosswire.org)
00004  *      CrossWire Bible Society
00005  *      P. O. Box 2528
00006  *      Tempe, AZ  85280-2528
00007  *
00008  * This program is free software; you can redistribute it and/or modify it
00009  * under the terms of the GNU General Public License as published by the
00010  * Free Software Foundation version 2.
00011  *
00012  * This program is distributed in the hope that it will be useful, but
00013  * WITHOUT ANY WARRANTY; without even the implied warranty of
00014  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
00015  * General Public License for more details.
00016  *
00017  */
00018 
00019 #include "swunicod.h"
00020 unsigned char* UTF32to8 (unsigned long utf32, unsigned char * utf8) {
00021   unsigned int i;
00022   for (i = 0; i < 6; i++) utf8[i] = 0;
00023 
00024   if (utf32 < 0x80) {
00025     utf8[0] = (char)utf32;
00026   }
00027   else if (utf32 < 0x800) {
00028     i = utf32 & 0x3f;
00029     utf8[1] = 0x80 | i;
00030     utf32 >>= 6;
00031    
00032     i = utf32 & 0x1f;
00033     utf8[0] = 0xc0 | i;
00034   }
00035   else if (utf32 < 0x10000) {
00036     i = utf32 & 0x3f;
00037     utf8[2] = 0x80 | i;
00038     utf32 >>= 6;
00039 
00040     i = utf32 & 0x3f;
00041     utf8[1] = 0x80 | i;
00042     utf32 >>= 6;
00043    
00044     i = utf32 & 0x0f;
00045     utf8[0] = 0xe0 | i;
00046   }
00047   else if (utf32 < 0x200000) {
00048     i = utf32 & 0x3f;
00049     utf8[3] = 0x80 | i;
00050     utf32 >>= 6;
00051 
00052     i = utf32 & 0x3f;
00053     utf8[2] = 0x80 | i;
00054     utf32 >>= 6;
00055 
00056     i = utf32 & 0x3f;
00057     utf8[1] = 0x80 | i;
00058     utf32 >>= 6;
00059    
00060     i = utf32 & 0x07;
00061     utf8[0] = 0xf0 | i;
00062   }
00063   else if (utf32 < 0x4000000) {
00064     i = utf32 & 0x3f;
00065     utf8[4] = 0x80 | i;
00066     utf32 >>= 6;
00067 
00068     i = utf32 & 0x3f;
00069     utf8[3] = 0x80 | i;
00070     utf32 >>= 6;
00071 
00072     i = utf32 & 0x3f;
00073     utf8[2] = 0x80 | i;
00074     utf32 >>= 6;
00075 
00076     i = utf32 & 0x3f;
00077     utf8[1] = 0x80 | i;
00078     utf32 >>= 6;
00079    
00080     i = utf32 & 0x03;
00081     utf8[0] = 0xf8 | i;
00082   }
00083   else if (utf32 < 0x80000000) {
00084     i = utf32 & 0x3f;
00085     utf8[5] = 0x80 | i;
00086     utf32 >>= 6;
00087 
00088     i = utf32 & 0x3f;
00089     utf8[4] = 0x80 | i;
00090     utf32 >>= 6;
00091 
00092     i = utf32 & 0x3f;
00093     utf8[3] = 0x80 | i;
00094     utf32 >>= 6;
00095 
00096     i = utf32 & 0x3f;
00097     utf8[2] = 0x80 | i;
00098     utf32 >>= 6;
00099 
00100     i = utf32 & 0x3f;
00101     utf8[1] = 0x80 | i;
00102     utf32 >>= 6;
00103    
00104     i = utf32 & 0x01;
00105     utf8[0] = 0xfc | i;
00106   }
00107   return utf8;
00108 }
00109 
00114 unsigned long UTF8to32 (unsigned char * utf8) {
00115 
00116   unsigned char i = utf8[0];
00117   unsigned char count;
00118   unsigned long utf32 = 0;
00119 
00120   for (count = 0; i & 0x80; count++) i <<= 1;
00121   if (!count) {
00122     return utf8[0];
00123   }
00124   else if (count == 1) {
00125     return 0xffff;
00126   }
00127   else {
00128     count--;
00129     utf32 = i >> count;
00130     for (i = 1; i <= count; i++) {
00131       if (0xc0 & utf8[i] != 0x80) {
00132         return  0xffff;
00133       }
00134       utf32 <<= 6;
00135       utf32 |= (utf8[i] & 0x3f);
00136     }
00137   }
00138   return utf32;
00139 }