/ Artifact [d7a61c1d]
Login

Artifact d7a61c1dfdac3eb091d43341a674032dca5a34e122f78ef0b5bd2d5a31967dde:


1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535
/*
** 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.
**
** 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"

#if !defined(SQLITE_AMALGAMATION) && SQLITE_BYTEORDER==0
/*
** The following constant value is used by the SQLITE_BIGENDIAN and
** SQLITE_LITTLEENDIAN macros.
*/
const int sqlite3one = 1;
#endif /* SQLITE_AMALGAMATION && SQLITE_BYTEORDER==0 */

/*
** This lookup table is used to help decode the first byte of
** a multi-byte UTF8 character.
*/
static const unsigned char sqlite3Utf8Trans1[] = {
  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++ = (u8)(c&0xFF);                            \
  }                                                    \
  else if( c<0x00800 ){                                \
    *zOut++ = 0xC0 + (u8)((c>>6)&0x1F);                \
    *zOut++ = 0x80 + (u8)(c & 0x3F);                   \
  }                                                    \
  else if( c<0x10000 ){                                \
    *zOut++ = 0xE0 + (u8)((c>>12)&0x0F);               \
    *zOut++ = 0x80 + (u8)((c>>6) & 0x3F);              \
    *zOut++ = 0x80 + (u8)(c & 0x3F);                   \
  }else{                                               \
    *zOut++ = 0xF0 + (u8)((c>>18) & 0x07);             \
    *zOut++ = 0x80 + (u8)((c>>12) & 0x3F);             \
    *zOut++ = 0x80 + (u8)((c>>6) & 0x3F);              \
    *zOut++ = 0x80 + (u8)(c & 0x3F);                   \
  }                                                    \
}

#define WRITE_UTF16LE(zOut, c) {                                    \
  if( c<=0xFFFF ){                                                  \
    *zOut++ = (u8)(c&0x00FF);                                       \
    *zOut++ = (u8)((c>>8)&0x00FF);                                  \
  }else{                                                            \
    *zOut++ = (u8)(((c>>10)&0x003F) + (((c-0x10000)>>10)&0x00C0));  \
    *zOut++ = (u8)(0x00D8 + (((c-0x10000)>>18)&0x03));              \
    *zOut++ = (u8)(c&0x00FF);                                       \
    *zOut++ = (u8)(0x00DC + ((c>>8)&0x03));                         \
  }                                                                 \
}

#define WRITE_UTF16BE(zOut, c) {                                    \
  if( c<=0xFFFF ){                                                  \
    *zOut++ = (u8)((c>>8)&0x00FF);                                  \
    *zOut++ = (u8)(c&0x00FF);                                       \
  }else{                                                            \
    *zOut++ = (u8)(0x00D8 + (((c-0x10000)>>18)&0x03));              \
    *zOut++ = (u8)(((c>>10)&0x003F) + (((c-0x10000)>>10)&0x00C0));  \
    *zOut++ = (u8)(0x00DC + ((c>>8)&0x03));                         \
    *zOut++ = (u8)(c&0x00FF);                                       \
  }                                                                 \
}

/*
** 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 over-length UTF8 encodings
**     for unicode values 0x80 and greater.  It does not change over-length
**     encodings to 0xfffd as some systems recommend.
*/
#define READ_UTF8(zIn, zTerm, c)                           \
  c = *(zIn++);                                            \
  if( c>=0xc0 ){                                           \
    c = sqlite3Utf8Trans1[c-0xc0];                         \
    while( zIn!=zTerm && (*zIn & 0xc0)==0x80 ){            \
      c = (c<<6) + (0x3f & *(zIn++));                      \
    }                                                      \
    if( c<0x80                                             \
        || (c&0xFFFFF800)==0xD800                          \
        || (c&0xFFFFFFFE)==0xFFFE ){  c = 0xFFFD; }        \
  }
u32 sqlite3Utf8Read(
  const unsigned char **pz    /* Pointer to string from which to read char */
){
  unsigned int c;

  /* Same as READ_UTF8() above but without the zTerm parameter.
  ** For this routine, we assume the UTF8 string is always zero-terminated.
  */
  c = *((*pz)++);
  if( c>=0xc0 ){
    c = sqlite3Utf8Trans1[c-0xc0];
    while( (*(*pz) & 0xc0)==0x80 ){
      c = (c<<6) + (0x3f & *((*pz)++));
    }
    if( c<0x80
        || (c&0xFFFFF800)==0xD800
        || (c&0xFFFFFFFE)==0xFFFE ){  c = 0xFFFD; }
  }
  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.
*/
SQLITE_NOINLINE int sqlite3VdbeMemTranslate(Mem *pMem, u8 desiredEnc){
  sqlite3_int64 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)
  {
    StrAccum acc;
    char zBuf[1000];
    sqlite3StrAccumInit(&acc, 0, zBuf, sizeof(zBuf), 0);  
    sqlite3VdbeMemPrettyPrint(pMem, &acc);
    fprintf(stderr, "INPUT:  %s\n", sqlite3StrAccumFinish(&acc));
  }
#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_BKPT;
    }
    zIn = (u8*)pMem->z;
    zTerm = &zIn[pMem->n&~1];
    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.
    */
    pMem->n &= ~1;
    len = 2 * (sqlite3_int64)pMem->n + 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 = 2 * (sqlite3_int64)pMem->n + 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, space obtained
  ** from sqlite3_malloc().
  */
  zIn = (u8*)pMem->z;
  zTerm = &zIn[pMem->n];
  zOut = sqlite3DbMallocRaw(pMem->db, len);
  if( !zOut ){
    return SQLITE_NOMEM_BKPT;
  }
  z = zOut;

  if( pMem->enc==SQLITE_UTF8 ){
    if( desiredEnc==SQLITE_UTF16LE ){
      /* UTF-8 -> UTF-16 Little-endian */
      while( zIn<zTerm ){
        READ_UTF8(zIn, zTerm, c);
        WRITE_UTF16LE(z, c);
      }
    }else{
      assert( desiredEnc==SQLITE_UTF16BE );
      /* UTF-8 -> UTF-16 Big-endian */
      while( zIn<zTerm ){
        READ_UTF8(zIn, zTerm, c);
        WRITE_UTF16BE(z, c);
      }
    }
    pMem->n = (int)(z - zOut);
    *z++ = 0;
  }else{
    assert( desiredEnc==SQLITE_UTF8 );
    if( pMem->enc==SQLITE_UTF16LE ){
      /* UTF-16 Little-endian -> UTF-8 */
      while( zIn<zTerm ){
        c = *(zIn++);
        c += (*(zIn++))<<8;
        if( c>=0xd800 && c<0xe000 ){
#ifdef SQLITE_REPLACE_INVALID_UTF
          if( c>=0xdc00 || zIn>=zTerm ){
            c = 0xfffd;
          }else{
            int c2 = *(zIn++);
            c2 += (*(zIn++))<<8;
            if( c2<0xdc00 || c2>=0xe000 ){
              zIn -= 2;
              c = 0xfffd;
            }else{
              c = ((c&0x3ff)<<10) + (c2&0x3ff) + 0x10000;
            }
          }
#else
          if( zIn<zTerm ){
            int c2 = (*zIn++);
            c2 += ((*zIn++)<<8);
            c = (c2&0x03FF) + ((c&0x003F)<<10) + (((c&0x03C0)+0x0040)<<10);
          }
#endif
        }
        WRITE_UTF8(z, c);
      }
    }else{
      /* UTF-16 Big-endian -> UTF-8 */
      while( zIn<zTerm ){
        c = (*(zIn++))<<8;
        c += *(zIn++);
        if( c>=0xd800 && c<0xe000 ){
#ifdef SQLITE_REPLACE_INVALID_UTF
          if( c>=0xdc00 || zIn>=zTerm ){
            c = 0xfffd;
          }else{
            int c2 = (*(zIn++))<<8;
            c2 += *(zIn++);
            if( c2<0xdc00 || c2>=0xe000 ){
              zIn -= 2;
              c = 0xfffd;
            }else{
              c = ((c&0x3ff)<<10) + (c2&0x3ff) + 0x10000;
            }
          }
#else
          if( zIn<zTerm ){
            int c2 = ((*zIn++)<<8);
            c2 += (*zIn++);
            c = (c2&0x03FF) + ((c&0x003F)<<10) + (((c&0x03C0)+0x0040)<<10);
          }
#endif
        }
        WRITE_UTF8(z, c);
      }
    }
    pMem->n = (int)(z - zOut);
  }
  *z = 0;
  assert( (pMem->n+(desiredEnc==SQLITE_UTF8?1:2))<=len );

  c = pMem->flags;
  sqlite3VdbeMemRelease(pMem);
  pMem->flags = MEM_Str|MEM_Term|(c&(MEM_AffMask|MEM_Subtype));
  pMem->enc = desiredEnc;
  pMem->z = (char*)zOut;
  pMem->zMalloc = pMem->z;
  pMem->szMalloc = sqlite3DbMallocSize(pMem->db, pMem->z);

translate_out:
#if defined(TRANSLATE_TRACE) && defined(SQLITE_DEBUG)
  {
    StrAccum acc;
    char zBuf[1000];
    sqlite3StrAccumInit(&acc, 0, zBuf, sizeof(zBuf), 0);  
    sqlite3VdbeMemPrettyPrint(pMem, &acc);
    fprintf(stderr, "OUTPUT: %s\n", sqlite3StrAccumFinish(&acc));
  }
#endif
  return SQLITE_OK;
}
#endif /* SQLITE_OMIT_UTF16 */

#ifndef SQLITE_OMIT_UTF16
/*
** This routine checks for a byte-order mark at the beginning of the 
** UTF-16 string stored in *pMem. If one is present, it is removed and
** the encoding of the Mem adjusted. This routine does not do any
** byte-swapping, it just sets Mem.enc appropriately.
**
** The allocation (static, dynamic etc.) and encoding of the Mem may be
** changed by this function.
*/
int sqlite3VdbeMemHandleBom(Mem *pMem){
  int rc = SQLITE_OK;
  u8 bom = 0;

  assert( pMem->n>=0 );
  if( pMem->n>1 ){
    u8 b1 = *(u8 *)pMem->z;
    u8 b2 = *(((u8 *)pMem->z) + 1);
    if( b1==0xFE && b2==0xFF ){
      bom = SQLITE_UTF16BE;
    }
    if( b1==0xFF && b2==0xFE ){
      bom = SQLITE_UTF16LE;
    }
  }
  
  if( bom ){
    rc = sqlite3VdbeMemMakeWriteable(pMem);
    if( rc==SQLITE_OK ){
      pMem->n -= 2;
      memmove(pMem->z, &pMem->z[2], pMem->n);
      pMem->z[pMem->n] = '\0';
      pMem->z[pMem->n+1] = '\0';
      pMem->flags |= MEM_Term;
      pMem->enc = bom;
    }
  }
  return rc;
}
#endif /* SQLITE_OMIT_UTF16 */

/*
** pZ is a UTF-8 encoded unicode string. If nByte is less than zero,
** return the number of unicode characters in pZ up to (but not including)
** the first 0x00 byte. If nByte is not less than zero, return the
** number of unicode characters in the first nByte of pZ (or up to 
** the first 0x00, whichever comes first).
*/
int sqlite3Utf8CharLen(const char *zIn, int nByte){
  int r = 0;
  const u8 *z = (const u8*)zIn;
  const u8 *zTerm;
  if( nByte>=0 ){
    zTerm = &z[nByte];
  }else{
    zTerm = (const u8*)(-1);
  }
  assert( z<=zTerm );
  while( *z!=0 && z<zTerm ){
    SQLITE_SKIP_UTF8(z);
    r++;
  }
  return r;
}

/* This test function is not currently used by the automated test-suite. 
** Hence it is only available in debug builds.
*/
#if defined(SQLITE_TEST) && defined(SQLITE_DEBUG)
/*
** Translate UTF-8 to UTF-8.
**
** This has the effect of making sure that the string is well-formed
** UTF-8.  Miscoded characters are removed.
**
** The translation is done in-place and aborted if the output
** overruns the input.
*/
int sqlite3Utf8To8(unsigned char *zIn){
  unsigned char *zOut = zIn;
  unsigned char *zStart = zIn;
  u32 c;

  while( zIn[0] && zOut<=zIn ){
    c = sqlite3Utf8Read((const u8**)&zIn);
    if( c!=0xfffd ){
      WRITE_UTF8(zOut, c);
    }
  }
  *zOut = 0;
  return (int)(zOut - zStart);
}
#endif

#ifndef SQLITE_OMIT_UTF16
/*
** Convert a UTF-16 string in the native encoding into a UTF-8 string.
** Memory to hold the UTF-8 string is obtained from sqlite3_malloc and must
** be freed by the calling function.
**
** NULL is returned if there is an allocation error.
*/
char *sqlite3Utf16to8(sqlite3 *db, const void *z, int nByte, u8 enc){
  Mem m;
  memset(&m, 0, sizeof(m));
  m.db = db;
  sqlite3VdbeMemSetStr(&m, z, nByte, enc, SQLITE_STATIC);
  sqlite3VdbeChangeEncoding(&m, SQLITE_UTF8);
  if( db->mallocFailed ){
    sqlite3VdbeMemRelease(&m);
    m.z = 0;
  }
  assert( (m.flags & MEM_Term)!=0 || db->mallocFailed );
  assert( (m.flags & MEM_Str)!=0 || db->mallocFailed );
  assert( m.z || db->mallocFailed );
  return m.z;
}

/*
** zIn is a UTF-16 encoded unicode string at least nChar characters long.
** Return the number of bytes in the first nChar unicode characters
** in pZ.  nChar must be non-negative.
*/
int sqlite3Utf16ByteLen(const void *zIn, int nChar){
  int c;
  unsigned char const *z = zIn;
  int n = 0;
  
  if( SQLITE_UTF16NATIVE==SQLITE_UTF16LE ) z++;
  while( n<nChar ){
    c = z[0];
    z += 2;
    if( c>=0xd8 && c<0xdc && z[0]>=0xdc && z[0]<0xe0 ) z += 2;
    n++;
  }
  return (int)(z-(unsigned char const *)zIn) 
              - (SQLITE_UTF16NATIVE==SQLITE_UTF16LE);
}

#if defined(SQLITE_TEST)
/*
** This routine is called from the TCL test function "translate_selftest".
** It checks that the primitives for serializing and deserializing
** characters in each encoding are inverses of each other.
*/
void sqlite3UtfSelfTest(void){
  unsigned int i, t;
  unsigned char zBuf[20];
  unsigned char *z;
  int n;
  unsigned int c;

  for(i=0; i<0x00110000; i++){
    z = zBuf;
    WRITE_UTF8(z, i);
    n = (int)(z-zBuf);
    assert( n>0 && n<=4 );
    z[0] = 0;
    z = zBuf;
    c = sqlite3Utf8Read((const u8**)&z);
    t = i;
    if( i>=0xD800 && i<=0xDFFF ) t = 0xFFFD;
    if( (i&0xFFFFFFFE)==0xFFFE ) t = 0xFFFD;
    assert( c==t );
    assert( (z-zBuf)==n );
  }
}
#endif /* SQLITE_TEST */
#endif /* SQLITE_OMIT_UTF16 */