SQLite

Check-in [a96b4e8c01]
Login

Many hyperlinks are disabled.
Use anonymous login to enable hyperlinks.

Overview
Comment:Another attempt at getting the pTail pointer computations correct for sqlite3_prepare16(). Ticket [3fe897352e].
Downloads: Tarball | ZIP archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA1: a96b4e8c01d167d35b9ec08ee6603e52ead601b6
User & Date: drh 2009-10-24 03:04:10.000
Context
2009-10-24
15:51
Fix a compiler warning that occurs when building the TCL interface. (check-in: fc36034bdc user: drh tags: trunk)
03:04
Another attempt at getting the pTail pointer computations correct for sqlite3_prepare16(). Ticket [3fe897352e]. (check-in: a96b4e8c01 user: drh tags: trunk)
02:06
In shell, modified to not print informational messages during startup while in "batch mode". Ticket [2cb66577f6]. (check-in: e3898e25cf user: shane tags: trunk)
Changes
Unified Diff Ignore Whitespace Patch
Changes to src/utf.c.
︙︙
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

    *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);                                       \
  }                                                                 \
}

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

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

/*








|


|






|


|








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

    *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);                                       \
  }                                                                 \
}

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

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

/*
︙︙
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321

    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 ){
        READ_UTF16LE(zIn, zTerm, c); 
        WRITE_UTF8(z, c);
      }
    }else{
      /* UTF-16 Big-endian -> UTF-8 */
      while( zIn<zTerm ){
        READ_UTF16BE(zIn, zTerm, c); 
        WRITE_UTF8(z, c);
      }
    }
    pMem->n = (int)(z - zOut);
  }
  *z = 0;
  assert( (pMem->n+(desiredEnc==SQLITE_UTF8?1:2))<=len );








|





|








301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321

    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 ){
        READ_UTF16LE(zIn, zIn<zTerm, c); 
        WRITE_UTF8(z, c);
      }
    }else{
      /* UTF-16 Big-endian -> UTF-8 */
      while( zIn<zTerm ){
        READ_UTF16BE(zIn, zIn<zTerm, c); 
        WRITE_UTF8(z, c);
      }
    }
    pMem->n = (int)(z - zOut);
  }
  *z = 0;
  assert( (pMem->n+(desiredEnc==SQLITE_UTF8?1:2))<=len );
︙︙
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

  assert( m.z==m.zMalloc );
  *pnOut = m.n;
  return m.z;
}
#endif

/*
** pZ 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;
  unsigned char const *zTerm;
  int n = 0;

  /* Some of the characters might be surrogates.  Be careful not to terminate
  ** the string too early because of them.   In the worst case, all characters
  ** or surrogates so make the terminator 2*nChar from the beginning. */
  zTerm = &z[nChar*2];
  
  if( SQLITE_UTF16NATIVE==SQLITE_UTF16BE ){
    /* Using an "if (SQLITE_UTF16NATIVE==SQLITE_UTF16BE)" construct here
    ** and in other parts of this file means that at one branch will
    ** not be covered by coverage testing on any single host. But coverage
    ** will be complete if the tests are run on both a little-endian and 
    ** big-endian host. Because both the UTF16NATIVE and SQLITE_UTF16BE
    ** macros are constant at compile time the compiler can determine
    ** which branch will be followed. It is therefore assumed that no runtime
    ** penalty is paid for this "if" statement.
    */
    while( n<nChar ){
      READ_UTF16BE(z, zTerm, c);
      n++;
    }
  }else{
    while( n<nChar ){
      READ_UTF16LE(z, zTerm, c);
      n++;
    }
  }
  return (int)(z-(unsigned char const *)zIn);
}

#if defined(SQLITE_TEST)








|






<

|
<
<
<
<
<

<
<
<
<
<
<
<
<
<

|




|








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

  assert( m.z==m.zMalloc );
  *pnOut = m.n;
  return m.z;
}
#endif

/*
** 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_UTF16BE ){









    while( n<nChar ){
      READ_UTF16BE(z, 1, c);
      n++;
    }
  }else{
    while( n<nChar ){
      READ_UTF16LE(z, 1, c);
      n++;
    }
  }
  return (int)(z-(unsigned char const *)zIn);
}

#if defined(SQLITE_TEST)
︙︙
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575

    if( i>=0xD800 && i<0xE000 ) continue;
    z = zBuf;
    WRITE_UTF16LE(z, i);
    n = (int)(z-zBuf);
    assert( n>0 && n<=4 );
    z[0] = 0;
    z = zBuf;
    READ_UTF16LE(z, &zBuf[n], c);
    assert( c==i );
    assert( (z-zBuf)==n );
  }
  for(i=0; i<0x00110000; i++){
    if( i>=0xD800 && i<0xE000 ) continue;
    z = zBuf;
    WRITE_UTF16BE(z, i);
    n = (int)(z-zBuf);
    assert( n>0 && n<=4 );
    z[0] = 0;
    z = zBuf;
    READ_UTF16BE(z, &zBuf[n], c);
    assert( c==i );
    assert( (z-zBuf)==n );
  }
}
#endif /* SQLITE_TEST */
#endif /* SQLITE_OMIT_UTF16 */








|











|







535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560

    if( i>=0xD800 && i<0xE000 ) continue;
    z = zBuf;
    WRITE_UTF16LE(z, i);
    n = (int)(z-zBuf);
    assert( n>0 && n<=4 );
    z[0] = 0;
    z = zBuf;
    READ_UTF16LE(z, 1, c);
    assert( c==i );
    assert( (z-zBuf)==n );
  }
  for(i=0; i<0x00110000; i++){
    if( i>=0xD800 && i<0xE000 ) continue;
    z = zBuf;
    WRITE_UTF16BE(z, i);
    n = (int)(z-zBuf);
    assert( n>0 && n<=4 );
    z[0] = 0;
    z = zBuf;
    READ_UTF16BE(z, 1, c);
    assert( c==i );
    assert( (z-zBuf)==n );
  }
}
#endif /* SQLITE_TEST */
#endif /* SQLITE_OMIT_UTF16 */