SQLite

Check-in [bfc35ce867]
Login

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

Overview
Comment:Fix handling of utf-16 encoding of code point 0xE000. (CVS 4017)
Downloads: Tarball | ZIP archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA1: bfc35ce8673ce51f726535b90c1d86be272848bb
User & Date: danielk1977 2007-05-16 18:11:41.000
Context
2007-05-16
18:23
Remove the SKIP_UTF16 macros (they are no longer in use). (CVS 4018) (check-in: 73e654fbdc user: danielk1977 tags: trunk)
18:11
Fix handling of utf-16 encoding of code point 0xE000. (CVS 4017) (check-in: bfc35ce867 user: danielk1977 tags: trunk)
17:50
Avoid passing a negative value to isspace() in a couple places. (CVS 4016) (check-in: d5db8be368 user: danielk1977 tags: trunk)
Changes
Unified Diff Ignore Whitespace Patch
Changes to src/utf.c.
︙︙
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22

**    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 1.48 2007/05/15 14:40:11 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








|








8
9
10
11
12
13
14
15
16
17
18
19
20
21
22

**    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 1.49 2007/05/16 18:11:41 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
︙︙
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

    *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;                             \
  }                                                                   \
}









|










|








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

    *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;                             \
  }                                                                   \
}
︙︙
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

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








|










|













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

    t = i;
    if( i>=0xD800 && i<=0xDFFF ) t = 0xFFFD;
    if( (i&0xFFFFFFFE)==0xFFFE ) t = 0xFFFD;
    assert( c==t );
    assert( (z-zBuf)==n );
  }
  for(i=0; i<0x00110000; i++){
    if( i>=0xD800 && i<0xE000 ) continue;
    z = zBuf;
    WRITE_UTF16LE(z, i);
    n = z-zBuf;
    z[0] = 0;
    z = zBuf;
    READ_UTF16LE(z, 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 = z-zBuf;
    z[0] = 0;
    z = zBuf;
    READ_UTF16BE(z, c);
    assert( c==i );
    assert( (z-zBuf)==n );
  }
}
#endif /* SQLITE_TEST */
#endif /* SQLITE_OMIT_UTF16 */
Changes to test/enc.test.
︙︙
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23

#
#***********************************************************************
# This file implements regression tests for SQLite library.  The focus of
# this file is testing the SQLite routines used for converting between the
# various suported unicode encodings (UTF-8, UTF-16, UTF-16le and
# UTF-16be).
#
# $Id: enc.test,v 1.5 2004/11/14 21:56:31 drh Exp $

set testdir [file dirname $argv0]
source $testdir/tester.tcl

# Skip this test if the build does not support multiple encodings.
#
ifcapable {!utf16} {








|








9
10
11
12
13
14
15
16
17
18
19
20
21
22
23

#
#***********************************************************************
# This file implements regression tests for SQLite library.  The focus of
# this file is testing the SQLite routines used for converting between the
# various suported unicode encodings (UTF-8, UTF-16, UTF-16le and
# UTF-16be).
#
# $Id: enc.test,v 1.6 2007/05/16 18:11:41 danielk1977 Exp $

set testdir [file dirname $argv0]
source $testdir/tester.tcl

# Skip this test if the build does not support multiple encodings.
#
ifcapable {!utf16} {
︙︙
144
145
146
147
148
149
150
151


152

test_conversion enc-X "\u0100"
test_conversion enc-4 "\u1234"
test_conversion enc-5 "\u4321abc"
test_conversion enc-6 "\u4321\u1234"
test_conversion enc-7 [string repeat "abcde\u00EF\u00EE\uFFFCabc" 100]
test_conversion enc-8 [string repeat "\u007E\u007F\u0080\u0081" 100]
test_conversion enc-9 [string repeat "\u07FE\u07FF\u0800\u0801\uFFF0" 100]



finish_test









>
>


144
145
146
147
148
149
150
151
152
153
154

test_conversion enc-X "\u0100"
test_conversion enc-4 "\u1234"
test_conversion enc-5 "\u4321abc"
test_conversion enc-6 "\u4321\u1234"
test_conversion enc-7 [string repeat "abcde\u00EF\u00EE\uFFFCabc" 100]
test_conversion enc-8 [string repeat "\u007E\u007F\u0080\u0081" 100]
test_conversion enc-9 [string repeat "\u07FE\u07FF\u0800\u0801\uFFF0" 100]

test_conversion enc-10 [string repeat "\uE000" 100]

finish_test