swiutfconversions.c

OSB-PIK-OpenVXI-3.0.0源代码 “中国XML论坛 - 专业的XML技术讨论区--XML在语音技术中的应用”

     case 0xD3:  w = 0x0136;  break; // LATIN CAPITAL LETTER K WITH CEDILLA
     case 0xD9:  w = 0x0172;  break; // LATIN CAPITAL LETTER U WITH OGONEK
     case 0xDD:  w = 0x0168;  break; // LATIN CAPITAL LETTER U WITH TILDE
     case 0xDE:  w = 0x016A;  break; // LATIN CAPITAL LETTER U WITH MACRON
     case 0xE0:  w = 0x0101;  break; // LATIN SMALL LETTER A WITH MACRON
     case 0xE7:  w = 0x012F;  break; // LATIN SMALL LETTER I WITH OGONEK
     case 0xE8:  w = 0x010D;  break; // LATIN SMALL LETTER C WITH CARON
     case 0xEA:  w = 0x0119;  break; // LATIN SMALL LETTER E WITH OGONEK
     case 0xEC:  w = 0x0117;  break; // LATIN SMALL LETTER E WITH DOT ABOVE
     case 0xEF:  w = 0x012B;  break; // LATIN SMALL LETTER I WITH MACRON
     case 0xF0:  w = 0x0111;  break; // LATIN SMALL LETTER D WITH STROKE
     case 0xF1:  w = 0x0146;  break; // LATIN SMALL LETTER N WITH CEDILLA
     case 0xF2:  w = 0x014D;  break; // LATIN SMALL LETTER O WITH MACRON
     case 0xF3:  w = 0x0137;  break; // LATIN SMALL LETTER K WITH CEDILLA
     case 0xF9:  w = 0x0173;  break; // LATIN SMALL LETTER U WITH OGONEK
     case 0xFD:  w = 0x0169;  break; // LATIN SMALL LETTER U WITH TILDE
     case 0xFE:  w = 0x016B;  break; // LATIN SMALL LETTER U WITH MACRON
     case 0xFF:  w = 0x02D9;  break; // DOT ABOVE
     default:
       w = wchar_t(*in);
       break;
     }
     out += w;
     ++in;
   }
 
   return true;
 }
 
 
 bool DecodeISO8859_15(const char * in, std::basic_string<wchar_t> & out)
 {
   out.erase();
 
   wchar_t w;
 
   while (*in != '\0') {
     switch (*in) {
     case 0xA4:  w = 0x20AC;  break; // EURO SIGN
     case 0xA6:  w = 0x0160;  break; // LATIN CAPITAL LETTER S WITH CARON
     case 0xA8:  w = 0x0161;  break; // LATIN SMALL LETTER S WITH CARON
     case 0xB4:  w = 0x017D;  break; // LATIN CAPITAL LETTER Z WITH CARON
     case 0xB8:  w = 0x017E;  break; // LATIN SMALL LETTER Z WITH CARON
     case 0xBC:  w = 0x0152;  break; // LATIN CAPITAL LIGATURE OE
     case 0xBD:  w = 0x0153;  break; // LATIN SMALL LIGATURE OE
     case 0xBE:  w = 0x0178;  break; // LATIN CAPITAL LETTER Y WITH DIAERESIS
     default:
       w = wchar_t(*in);
       break;
     }
     out += w;
     ++in;
   }
 
   return true;
 }
 #endif
 
 // ---------------------------------------------------------------------------
 // Jerry Carter writes:
 //
 // The UTF-8 encoding / decoding routines were modified from the Apache Xerces
 // project.  The original translated from UTF-8 to UTF-16.  In this version, I
 // have removed support for surrogate characters.  This removes the difference
 // between platforms which treat wchar_t as UTF-16 (Windows) and those which
 // use UTF-32 (Linux, MacOS, etc.).
 //
 // The Apache license appears below (as required).
 
 /*
  * The Apache Software License, Version 1.1
  * 
  * Copyright (c) 1999-2000 The Apache Software Foundation.  All rights
  * reserved.
  * 
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions
  * are met:
  * 
  * 1. Redistributions of source code must retain the above copyright
  *    notice, this list of conditions and the following disclaimer. 
  * 
  * 2. Redistributions in binary form must reproduce the above copyright
  *    notice, this list of conditions and the following disclaimer in
  *    the documentation and/or other materials provided with the
  *    distribution.
  * 
  * 3. The end-user documentation included with the redistribution,
  *    if any, must include the following acknowledgment:  
  *       "This product includes software developed by the
  *        Apache Software Foundation (http://www.apache.org/)."
  *    Alternately, this acknowledgment may appear in the software itself,
  *    if and wherever such third-party acknowledgments normally appear.
  * 
  * 4. The names "Xerces" and "Apache Software Foundation" must
  *    not be used to endorse or promote products derived from this
  *    software without prior written permission. For written 
  *    permission, please contact apache\@apache.org.
  * 
  * 5. Products derived from this software may not be called "Apache",
  *    nor may "Apache" appear in their name, without prior written
  *    permission of the Apache Software Foundation.
  * 
  * THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESSED OR IMPLIED
  * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
  * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
  * DISCLAIMED.  IN NO EVENT SHALL THE APACHE SOFTWARE FOUNDATION OR
  * ITS CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
  * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
  * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF
  * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
  * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
  * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT
  * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
  * SUCH DAMAGE.
  * ====================================================================
  * 
  * This software consists of voluntary contributions made by many
  * individuals on behalf of the Apache Software Foundation, and was
  * originally based on software copyright (c) 1999, International
  * Business Machines, Inc., http://www.ibm.com .  For more information
  * on the Apache Software Foundation, please see
  * <http://www.apache.org/>.
  */
 
 //  gUTFBytes
 //      A list of counts of trailing bytes for each initial byte in the input.
 //
 //  gUTFOffsets
 //      A list of values to offset each result char type, according to how
 //      many source bytes when into making it.
 //
 //  gFirstByteMark
 //      A list of values to mask onto the first byte of an encoded sequence,
 //      indexed by the number of bytes used to create the sequence.
 
 static const char gUTFBytes[256] =
 {
         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
     ,   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
     ,   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
     ,   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
     ,   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
     ,   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
     ,   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
     ,   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
     ,   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
     ,   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
     ,   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
     ,   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
     ,   1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1
     ,   1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1
     ,   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
 };
 
 static const unsigned long gUTFOffsets[6] =
 {  0, 0x3080, 0xE2080, 0x3C82080, 0xFA082080, 0x82082080 };
 
 static const unsigned char gFirstByteMark[7] =
 {  0x00, 0x00, 0xC0, 0xE0,
    0xF0, 0xF8, 0xFC };
 
 
 int SWIutf8towcslen(const unsigned char* src)
 {
   int len = 0;
 
   while (*src != '\0') {
     unsigned int trailingBytes;
 
     // Get the next leading byte out
     const unsigned char firstByte = (unsigned char) *src;
 
     // See how many trailing src bytes this sequence is going to require
     trailingBytes = gUTFBytes[firstByte];
 
     src += trailingBytes + 1;
     len++;
   }
   return len;
 }
 
 
 SWIcharResult SWIutf8towcs( const unsigned char *src, wchar_t *dst, int maxdstlen )
 {
   // Get pointers to our start and end points of the input buffer
   const unsigned char* srcPtr = src;
   const unsigned char* srcEnd = src + strlen((const char *)src);
   wchar_t *dstSave = dst;
   wchar_t *dstEnd = dst+maxdstlen;  /* leave room for null */
 
   //  We now loop until we run out of input data.
   while (srcPtr < srcEnd) {
     unsigned int trailingBytes;
     unsigned long tmpVal = 0;
 
     // Get the next leading byte out
     const unsigned char firstByte = (unsigned char) *srcPtr;
 
     // Special-case ASCII, which is a leading byte value of <= 127
     if (firstByte <= 127) {
       *dst++ = (wchar_t) firstByte;
       srcPtr++;
       continue;
     }
 
     // See how many trailing src bytes this sequence is going to require
     trailingBytes = gUTFBytes[firstByte];
     
     //  If there are not enough source bytes to do this one, then we
     //  are done. Note that we done >= here because we are implicitly
     //  counting the 1 byte we get no matter what.
     if (srcPtr + trailingBytes >= srcEnd)
       return SWIchar_FAIL;  // ??
 
     // Looks ok, so lets build up the value
     switch (trailingBytes) {
     case 5: tmpVal += *srcPtr++; tmpVal <<= 6;
     case 4: tmpVal += *srcPtr++; tmpVal <<= 6;
     case 3: tmpVal += *srcPtr++; tmpVal <<= 6;
     case 2: tmpVal += *srcPtr++; tmpVal <<= 6;
     case 1: tmpVal += *srcPtr++; tmpVal <<= 6;
     case 0: tmpVal += *srcPtr++;
       break;
     default:
       return SWIchar_ERROR;
     }
     tmpVal -= gUTFOffsets[trailingBytes];
 
     // If surrogate pairs would be required for 16-bit characters, fail.
     if (tmpVal & 0xFFFF0000)
       return SWIchar_FAIL;
 
     if ( dst >= dstEnd ) {
       return SWIchar_BUFFER_OVERFLOW;
     }
 
     *dst++ = (wchar_t)tmpVal;
   }
 
   *dst = L'\0';
   
  // return dst-dstSave;
 
   return SWIchar_SUCCESS;   // check this (CARO)
 }
 
 int SWIwcstoutf8len(const wchar_t* src)
 {
   int len = 0;
 
   //  Get pointers to our start and end points of the input buffer.
   const wchar_t* srcPtr = src;
   const wchar_t* srcEnd = srcPtr + wcslen(src);
 
   while (*src != 0) {
     unsigned int encodedBytes;
     wchar_t curVal = (*src++) & 0x0000FFFF;
 
     // Watchout for surrogates.
     if ((curVal >= 0xD800 && curVal <= 0xDBFF) || curVal == 0xFFFE ||
 	curVal == 0xFFFF)
       return -2;
 
     // Figure out how many bytes we need
     if (curVal < 0x80)                encodedBytes = 1;
     else if (curVal < 0x800)          encodedBytes = 2;
     else if (curVal < 0x10000)        encodedBytes = 3;
     else if (curVal < 0x200000)       encodedBytes = 4;
     else if (curVal < 0x4000000)      encodedBytes = 5;
     else if (curVal <= 0x7FFFFFFF)    encodedBytes = 6;
     else {
       // THIS SHOULD NOT HAPPEN!
       return -2;
     }
 
     //  And spit out the bytes. We spit them out in reverse order
     //  here, so bump up the output pointer and work down as we go.
     len += encodedBytes;
   }
 
   return len;
 }
 
 
 SWIcharResult SWIwcstoutf8(const wchar_t *src, unsigned char *dst, int maxdstlen)
 {
   //  Get pointers to our start and end points of the input buffer.
   const wchar_t* srcPtr = src;
   const wchar_t* srcEnd = srcPtr + wcslen(src);
   unsigned char *dstSave = dst;
   unsigned char *dstEnd = dst+maxdstlen;
 
   while (srcPtr < srcEnd) {
     unsigned int encodedBytes;
     wchar_t curVal = (*srcPtr++) & 0x0000FFFF;
 
     // Watchout for surrogates.
     if ( ((curVal >= 0xD800) && (curVal <= 0xDFFF)) ||
          ((curVal == 0xFFFE) || curVal == 0xFFFF) )
       return SWIchar_FAIL;
 
     // Figure out how many bytes we need
     if (curVal < 0x80)                encodedBytes = 1;
     else if (curVal < 0x800)          encodedBytes = 2;
     else if (curVal < 0x10000)        encodedBytes = 3;
     else if (curVal < 0x200000)       encodedBytes = 4;
     else if (curVal < 0x4000000)      encodedBytes = 5;
     else if (curVal <= 0x7FFFFFFF)    encodedBytes = 6;
     else {
       // THIS SHOULD NOT HAPPEN!
       return SWIchar_ERROR;
     }
 
     //  And spit out the bytes. We spit them out in reverse order
     //  here, so bump up the output pointer and work down as we go.
     dst += encodedBytes;
 
     if ( dst > dstEnd ) {
       return SWIchar_BUFFER_OVERFLOW;
     }
 
     switch(encodedBytes) {
     case 6 : *--dst = (unsigned char) ((curVal | 0x80) & 0xBF);
       curVal >>= 6;
     case 5 : *--dst = (unsigned char)((curVal | 0x80) & 0xBF);
       curVal >>= 6;
     case 4 : *--dst = (unsigned char)((curVal | 0x80) & 0xBF);
       curVal >>= 6;
     case 3 : *--dst = (unsigned char)((curVal | 0x80) & 0xBF);
       curVal >>= 6;
     case 2 : *--dst = (unsigned char)((curVal | 0x80) & 0xBF);
       curVal >>= 6;
     case 1 : *--dst = (unsigned char)(curVal | gFirstByteMark[encodedBytes]);
     }
 
     dst += encodedBytes;
   }
   *dst = '\0';
 
   // return dst-dstSave
 
   return SWIchar_SUCCESS; // check this (CARO)
 }