/ Check-in [86a08bb7]
Login

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

Overview
Comment:Fix UTF conversions for -O2 on gcc 4.1.1. Ticket #2008. (CVS 3464)
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA1: 86a08bb7c5da42fbeb5a026287d67912a2ffb7f1
User & Date: drh 2006-10-04 15:23:22
Context
2006-10-04
17:35
The snippet generator adds ellipsis between text from different columns. (CVS 3465) check-in: 6cf1fb9f user: drh tags: trunk
15:23
Fix UTF conversions for -O2 on gcc 4.1.1. Ticket #2008. (CVS 3464) check-in: 86a08bb7 user: drh tags: trunk
11:55
Tests cases automatically remove many of their temporary files. (CVS 3463) check-in: eef0ec0d user: drh tags: trunk
Changes
Hide Diffs Unified Diffs Show Whitespace Changes Patch

Changes to src/utf.c.

8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
...
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
...
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
...
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
**    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 1.40 2006/07/26 14:57:30 drh 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
................................................................................
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 */
  int c;

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

#if defined(TRANSLATE_TRACE) && defined(SQLITE_DEBUG)
................................................................................
** pZ is a UTF-16 encoded unicode string. If nChar is less than zero,
** return the number of bytes up to (but not including), the first pair
** of consecutive 0x00 bytes in pZ. If nChar is not less than zero,
** then return the number of bytes in the first nChar unicode characters
** in pZ (or up until the first pair of 0x00 bytes, whichever comes first).
*/
int sqlite3utf16ByteLen(const void *zIn, int nChar){
  int c = 1;
  char const *z = zIn;
  int n = 0;
  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 
................................................................................
** characters in each encoding are inverses of each other.
*/
void sqlite3utfSelfTest(){
  int i;
  unsigned char zBuf[20];
  unsigned char *z;
  int n;
  int c;

  for(i=0; i<0x00110000; i++){
    z = zBuf;
    WRITE_UTF8(z, i);
    n = z-zBuf;
    z = zBuf;
    READ_UTF8(z, c);







|







 







|







 







|







 







|







8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
...
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
...
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
...
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
**    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 1.41 2006/10/04 15:23:22 drh 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
................................................................................
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->flags&MEM_Str );
  assert( pMem->enc!=desiredEnc );
  assert( pMem->enc!=0 );
  assert( pMem->n>=0 );

#if defined(TRANSLATE_TRACE) && defined(SQLITE_DEBUG)
................................................................................
** pZ is a UTF-16 encoded unicode string. If nChar is less than zero,
** return the number of bytes up to (but not including), the first pair
** of consecutive 0x00 bytes in pZ. If nChar is not less than zero,
** then return the number of bytes in the first nChar unicode characters
** in pZ (or up until the first pair of 0x00 bytes, whichever comes first).
*/
int sqlite3utf16ByteLen(const void *zIn, int nChar){
  unsigned int c = 1;
  char const *z = zIn;
  int n = 0;
  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 
................................................................................
** characters in each encoding are inverses of each other.
*/
void sqlite3utfSelfTest(){
  int i;
  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 = z-zBuf;
    z = zBuf;
    READ_UTF8(z, c);