utf.c

这是一个开源的数据库系统,值得学习啊, 里面用了SQL语句,与微软的SQL SERVIER,差不了多少

/*
** 2004 April 13
**
** The author disclaims copyright to this source code.  In place of
** a legal notice, here is a blessing:
**
**    May you do good and not evil.
**    May you find forgiveness for yourself and forgive others.
**    May you share freely, never taking more than you give.
**
*************************************************************************
** This file contains routines used to translate between UTF-8, 
** UTF-16, UTF-16BE, and UTF-16LE.
**
** $Id: utf.c,v 1.57 2007/09/01 11:04:27 danielk1977 Exp $
**
** Notes on UTF-8:
**
**   Byte-0    Byte-1    Byte-2    Byte-3    Value
**  0xxxxxxx                                 00000000 00000000 0xxxxxxx
**  110yyyyy  10xxxxxx                       00000000 00000yyy yyxxxxxx
**  1110zzzz  10yyyyyy  10xxxxxx             00000000 zzzzyyyy yyxxxxxx
**  11110uuu  10uuzzzz  10yyyyyy  10xxxxxx   000uuuuu zzzzyyyy yyxxxxxx
**
**
** Notes on UTF-16:  (with wwww+1==uuuuu)
**
**      Word-0               Word-1          Value
**  110110ww wwzzzzyy   110111yy yyxxxxxx    000uuuuu zzzzyyyy yyxxxxxx
**  zzzzyyyy yyxxxxxx                        00000000 zzzzyyyy yyxxxxxx
**
**
** BOM or Byte Order Mark:
**     0xff 0xfe   little-endian utf-16 follows
**     0xfe 0xff   big-endian utf-16 follows
**
*/
#include "sqliteInt.h"
#include <assert.h>
#include "vdbeInt.h"

/*
** The following constant value is used by the SQLITE_BIGENDIAN and
** SQLITE_LITTLEENDIAN macros.
*/
const int sqlite3one = 1;

/*
** This lookup table is used to help decode the first byte of
** a multi-byte UTF8 character.
*/
static const unsigned char sqlite3UtfTrans1[] = {
  0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
  0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
  0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17,
  0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
  0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
  0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
  0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07,
  0x00, 0x01, 0x02, 0x03, 0x00, 0x01, 0x00, 0x00,
};


#define WRITE_UTF8(zOut, c) {                          \
  if( c<0x00080 ){                                     \
    *zOut++ = (c&0xFF);                                \
  }                                                    \
  else if( c<0x00800 ){                                \
    *zOut++ = 0xC0 + ((c>>6)&0x1F);                    \
    *zOut++ = 0x80 + (c & 0x3F);                       \
  }                                                    \
  else if( c<0x10000 ){                                \
    *zOut++ = 0xE0 + ((c>>12)&0x0F);                   \
    *zOut++ = 0x80 + ((c>>6) & 0x3F);                  \
    *zOut++ = 0x80 + (c & 0x3F);                       \
  }else{                                               \
    *zOut++ = 0xF0 + ((c>>18) & 0x07);                 \
    *zOut++ = 0x80 + ((c>>12) & 0x3F);                 \
    *zOut++ = 0x80 + ((c>>6) & 0x3F);                  \
    *zOut++ = 0x80 + (c & 0x3F);                       \
  }                                                    \
}

#define WRITE_UTF16LE(zOut, c) {                                \
  if( c<=0xFFFF ){                                              \
    *zOut++ = (c&0x00FF);                                       \
    *zOut++ = ((c>>8)&0x00FF);                                  \
  }else{                                                        \
    *zOut++ = (((c>>10)&0x003F) + (((c-0x10000)>>10)&0x00C0));  \
    *zOut++ = (0x00D8 + (((c-0x10000)>>18)&0x03));              \
    *zOut++ = (c&0x00FF);                                       \
    *zOut++ = (0x00DC + ((c>>8)&0x03));                         \
  }                                                             \
}

#define WRITE_UTF16BE(zOut, c) {                                \
  if( c<=0xFFFF ){                                              \
    *zOut++ = ((c>>8)&0x00FF);                                  \
    *zOut++ = (c&0x00FF);                                       \
  }else{                                                        \
    *zOut++ = (0x00D8 + (((c-0x10000)>>18)&0x03));              \
    *zOut++ = (((c>>10)&0x003F) + (((c-0x10000)>>10)&0x00C0));  \
    *zOut++ = (0x00DC + ((c>>8)&0x03));                         \
    *zOut++ = (c&0x00FF);                                       \
  }                                                             \
}

#define READ_UTF16LE(zIn, c){                                         \
  c = (*zIn++);                                                       \
  c += ((*zIn++)<<8);                                                 \
  if( c>=0xD800 && c<0xE000 ){                                       \
    int c2 = (*zIn++);                                                \
    c2 += ((*zIn++)<<8);                                              \
    c = (c2&0x03FF) + ((c&0x003F)<<10) + (((c&0x03C0)+0x0040)<<10);   \
    if( (c & 0xFFFF0000)==0 ) c = 0xFFFD;                             \
  }                                                                   \
}

#define READ_UTF16BE(zIn, c){                                         \
  c = ((*zIn++)<<8);                                                  \
  c += (*zIn++);                                                      \
  if( c>=0xD800 && c<0xE000 ){                                       \
    int c2 = ((*zIn++)<<8);                                           \
    c2 += (*zIn++);                                                   \
    c = (c2&0x03FF) + ((c&0x003F)<<10) + (((c&0x03C0)+0x0040)<<10);   \
    if( (c & 0xFFFF0000)==0 ) c = 0xFFFD;                             \
  }                                                                   \
}

/*
** Translate a single UTF-8 character.  Return the unicode value.
**
** During translation, assume that the byte that zTerm points
** is a 0x00.
**
** Write a pointer to the next unread byte back into *pzNext.
**
** Notes On Invalid UTF-8:
**
**  *  This routine never allows a 7-bit character (0x00 through 0x7f) to
**     be encoded as a multi-byte character.  Any multi-byte character that
**     attempts to encode a value between 0x00 and 0x7f is rendered as 0xfffd.
**
**  *  This routine never allows a UTF16 surrogate value to be encoded.
**     If a multi-byte character attempts to encode a value between
**     0xd800 and 0xe000 then it is rendered as 0xfffd.
**
**  *  Bytes in the range of 0x80 through 0xbf which occur as the first
**     byte of a character are interpreted as single-byte characters
**     and rendered as themselves even though they are technically
**     invalid characters.
**
**  *  This routine accepts an infinite number of different UTF8 encodings
**     for unicode values 0x80 and greater.  It do not change over-length
**     encodings to 0xfffd as some systems recommend.
*/
int sqlite3Utf8Read(
  const unsigned char *z,         /* First byte of UTF-8 character */
  const unsigned char *zTerm,     /* Pretend this byte is 0x00 */
  const unsigned char **pzNext    /* Write first byte past UTF-8 char here */
){
  int c = *(z++);
  if( c>=0xc0 ){
    c = sqlite3UtfTrans1[c-0xc0];
    while( z!=zTerm && (*z & 0xc0)==0x80 ){
      c = (c<<6) + (0x3f & *(z++));
    }
    if( c<0x80
        || (c&0xFFFFF800)==0xD800
        || (c&0xFFFFFFFE)==0xFFFE ){  c = 0xFFFD; }
  }
  *pzNext = z;
  return c;
}



/*
** If the TRANSLATE_TRACE macro is defined, the value of each Mem is
** printed on stderr on the way into and out of sqlite3VdbeMemTranslate().
*/ 
/* #define TRANSLATE_TRACE 1 */

#ifndef SQLITE_OMIT_UTF16
/*
** This routine transforms the internal text encoding used by pMem to
** desiredEnc. It is an error if the string is already of the desired
** encoding, or if *pMem does not contain a string value.
*/
int sqlite3VdbeMemTranslate(Mem *pMem, u8 desiredEnc){
  unsigned char zShort[NBFS]; /* Temporary short output buffer */
  int len;                    /* Maximum length of output string in bytes */
  unsigned char *zOut;                  /* Output buffer */
  unsigned char *zIn;                   /* Input iterator */
  unsigned char *zTerm;                 /* End of input */
  unsigned char *z;                     /* Output iterator */
  unsigned int c;

  assert( pMem->db==0 || sqlite3_mutex_held(pMem->db->mutex) );
  assert( pMem->flags&MEM_Str );
  assert( pMem->enc!=desiredEnc );
  assert( pMem->enc!=0 );
  assert( pMem->n>=0 );

#if defined(TRANSLATE_TRACE) && defined(SQLITE_DEBUG)
  {
    char zBuf[100];
    sqlite3VdbeMemPrettyPrint(pMem, zBuf);
    fprintf(stderr, "INPUT:  %s\n", zBuf);
  }
#endif

  /* If the translation is between UTF-16 little and big endian, then 
  ** all that is required is to swap the byte order. This case is handled
  ** differently from the others.
  */
  if( pMem->enc!=SQLITE_UTF8 && desiredEnc!=SQLITE_UTF8 ){
    u8 temp;
    int rc;
    rc = sqlite3VdbeMemMakeWriteable(pMem);
    if( rc!=SQLITE_OK ){
      assert( rc==SQLITE_NOMEM );
      return SQLITE_NOMEM;
    }
    zIn = (u8*)pMem->z;
    zTerm = &zIn[pMem->n];
    while( zIn<zTerm ){
      temp = *zIn;
      *zIn = *(zIn+1);
      zIn++;
      *zIn++ = temp;
    }
    pMem->enc = desiredEnc;
    goto translate_out;
  }

  /* Set len to the maximum number of bytes required in the output buffer. */
  if( desiredEnc==SQLITE_UTF8 ){
    /* When converting from UTF-16, the maximum growth results from
    ** translating a 2-byte character to a 4-byte UTF-8 character.
    ** A single byte is required for the output string
    ** nul-terminator.
    */
    len = pMem->n * 2 + 1;
  }else{
    /* When converting from UTF-8 to UTF-16 the maximum growth is caused
    ** when a 1-byte UTF-8 character is translated into a 2-byte UTF-16
    ** character. Two bytes are required in the output buffer for the
    ** nul-terminator.
    */
    len = pMem->n * 2 + 2;
  }

  /* Set zIn to point at the start of the input buffer and zTerm to point 1
  ** byte past the end.
  **
  ** Variable zOut is set to point at the output buffer. This may be space
  ** obtained from sqlite3_malloc(), or Mem.zShort, if it large enough and
  ** not in use, or the zShort array on the stack (see above).
  */
  zIn = (u8*)pMem->z;
  zTerm = &zIn[pMem->n];
  if( len>NBFS ){
    zOut = sqlite3DbMallocRaw(pMem->db, len);
    if( !zOut ){
      return SQLITE_NOMEM;
    }
  }else{
    zOut = zShort;
  }
  z = zOut;