[BACK]Return to encoding.c CVS log [TXT] [DIR] Up to [Public] / XML

Diff for /XML/encoding.c between versions 1.44 and 1.45

version 1.44, 2000/07/05 14:03:39 version 1.45, 2000/07/10 23:00:21
Line 48  xmlCharEncodingHandlerPtr xmlUTF16LEHand Line 48  xmlCharEncodingHandlerPtr xmlUTF16LEHand
 xmlCharEncodingHandlerPtr xmlUTF16BEHandler = NULL;  xmlCharEncodingHandlerPtr xmlUTF16BEHandler = NULL;
   
 #ifdef LIBXML_ICONV_ENABLED  #ifdef LIBXML_ICONV_ENABLED
 #if 0  #if 1
 #define DEBUG_ENCODING  /* Define this to get encoding traces */  #define DEBUG_ENCODING  /* Define this to get encoding traces */
 #endif  #endif
 #endif  #endif
Line 195  int Line 195  int
 isolat1ToUTF8(unsigned char* out, int *outlen,  isolat1ToUTF8(unsigned char* out, int *outlen,
               const unsigned char* in, int *inlen) {                const unsigned char* in, int *inlen) {
     unsigned char* outstart = out;      unsigned char* outstart = out;
       const unsigned char* base = in;
     const unsigned char* processed = in;      const unsigned char* processed = in;
     unsigned char* outend = out + *outlen;      unsigned char* outend = out + *outlen;
     const unsigned char* inend = in + *inlen;      const unsigned char* inend;
     unsigned char c;      unsigned int c;
       int bits;
   
     while (in < inend) {      inend = in + (*inlen);
         c= *in++;      while ((in < inend) && (out - outstart + 5 < *outlen)) {
         if (c < 0x80) {          c= *in++;
   
           /* assertion: c is a single UTF-4 value */
           if (out >= outend)
               break;
           if      (c <    0x80) {  *out++=  c;                bits= -6; }
           else                  {  *out++= ((c >>  6) & 0x1F) | 0xC0;  bits=  0; }
    
           for ( ; bits >= 0; bits-= 6) {
             if (out >= outend)              if (out >= outend)
                 break;                  break;
             *out++ = c;              *out++= ((c >> bits) & 0x3F) | 0x80;
         }  
         else {  
             if (out + 1 >= outend)  break;  
             *out++ = 0xC0 | (c >> 6);  
             *out++ = 0x80 | (0x3F & c);  
         }          }
         processed = in;          processed = (const unsigned char*) in;
     }      }
     *outlen = out - outstart;      *outlen = out - outstart;
     *inlen = processed - in;      *inlen = processed - base;
   
     return(0);      return(0);
 }  }
   
Line 239  isolat1ToUTF8(unsigned char* out, int *o Line 243  isolat1ToUTF8(unsigned char* out, int *o
 int  int
 UTF8Toisolat1(unsigned char* out, int *outlen,  UTF8Toisolat1(unsigned char* out, int *outlen,
               const unsigned char* in, int *inlen) {                const unsigned char* in, int *inlen) {
     unsigned char* outstart = out;  
     const unsigned char* processed = in;      const unsigned char* processed = in;
     unsigned char* outend = out + *outlen;      const unsigned char* outend;
     const unsigned char* inend = in + *inlen;      const unsigned char* outstart = out;
     unsigned char c;      const unsigned char* instart = in;
       const unsigned char* inend;
       unsigned int c, d;
       int trailing;
   
       if (in == NULL) {
           /*
            * initialization nothing to do
            */
           *outlen = 0;
           *inlen = 0;
           return(0);
       }
       inend = in + (*inlen);
       outend = out + (*outlen);
     while (in < inend) {      while (in < inend) {
         c= *in++;          d = *in++;
         if (c < 0x80) {          if      (d < 0x80)  { c= d; trailing= 0; }
             if (out >= outend)  return(-1);          else if (d < 0xC0) {
             *out++= c;              /* trailing byte in leading position */
         }              *outlen = out - outstart;
         else if (in == inend) {              *inlen = processed - instart;
             break;              return(-2);
           } else if (d < 0xE0)  { c= d & 0x1F; trailing= 1; }
           else if (d < 0xF0)  { c= d & 0x0F; trailing= 2; }
           else if (d < 0xF8)  { c= d & 0x07; trailing= 3; }
           else {
               /* no chance for this in IsoLat1 */
               *outlen = out - outstart;
               *inlen = processed - instart;
               return(-2);
         }          }
         else if (((c & 0xFC) == 0xC0) && ((*in & 0xC0) == 0x80)) {  
             /* a two byte utf-8 and can be encoding as isolate1 */          if (inend - in < trailing) {
             *out++= ((c & 0x03) << 6) | (*in++ & 0x3F);              break;
           } 
   
           for ( ; trailing; trailing--) {
               if ((in >= inend) || (((d= *in++) & 0xC0) != 0x80))
                   break;
               c <<= 6;
               c |= d & 0x3F;
         }          }
         else {  
           /* assertion: c is a single UTF-4 value */
           if (c <= 0xFF) {
               if (out >= outend)
                   break;
               *out++ = c;
           } else {
               /* no chance for this in IsoLat1 */
             *outlen = out - outstart;              *outlen = out - outstart;
             *inlen = processed - in;              *inlen = processed - instart;
             return(-2);              return(-2);
         }          }
         processed = in;          processed = in;
     }      }
     *outlen = out - outstart;      *outlen = out - outstart;
     *inlen = processed - in;      *inlen = processed - instart;
     return(0);      return(0);
 }  }
   
Line 410  UTF8ToUTF16LE(unsigned char* outb, int * Line 448  UTF8ToUTF16LE(unsigned char* outb, int *
       if      (d < 0x80)  { c= d; trailing= 0; }        if      (d < 0x80)  { c= d; trailing= 0; }
       else if (d < 0xC0) {        else if (d < 0xC0) {
           /* trailing byte in leading position */            /* trailing byte in leading position */
           *outlen = out - outstart;            *outlen = (out - outstart) * 2;
           *inlen = processed - in;            *inlen = processed - in;
           return(-2);            return(-2);
       } else if (d < 0xE0)  { c= d & 0x1F; trailing= 1; }        } else if (d < 0xE0)  { c= d & 0x1F; trailing= 1; }
Line 418  UTF8ToUTF16LE(unsigned char* outb, int * Line 456  UTF8ToUTF16LE(unsigned char* outb, int *
       else if (d < 0xF8)  { c= d & 0x07; trailing= 3; }        else if (d < 0xF8)  { c= d & 0x07; trailing= 3; }
       else {        else {
         /* no chance for this in UTF-16 */          /* no chance for this in UTF-16 */
         *outlen = out - outstart;          *outlen = (out - outstart) * 2;
         *inlen = processed - in;          *inlen = processed - in;
         return(-2);          return(-2);
       }        }
Line 973  xmlInitCharEncodingHandlers(void) { Line 1011  xmlInitCharEncodingHandlers(void) {
           xmlNewCharEncodingHandler("UTF-16LE", UTF16LEToUTF8, UTF8ToUTF16LE);            xmlNewCharEncodingHandler("UTF-16LE", UTF16LEToUTF8, UTF8ToUTF16LE);
     xmlUTF16BEHandler =       xmlUTF16BEHandler = 
           xmlNewCharEncodingHandler("UTF-16BE", UTF16BEToUTF8, UTF8ToUTF16BE);            xmlNewCharEncodingHandler("UTF-16BE", UTF16BEToUTF8, UTF8ToUTF16BE);
 #if 0  #if 1
     xmlNewCharEncodingHandler("ISO-8859-1", isolat1ToUTF8, UTF8Toisolat1);      xmlNewCharEncodingHandler("ISO-8859-1", isolat1ToUTF8, UTF8Toisolat1);
 #endif  #endif
 }  }
Removed from v.1.44  
changed lines
  Added in v.1.45

Webmaster