/ Check-in [6cfd9af5]
Login

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

Overview
Comment:Up until now the fts4 "unicode61" tokenizer has treated all private use codepoints except the first and last of each of the three ranges as alphanumeric (eligible to be part of tokens). This commit fixes this so that all private use codepoints are considered alphanumeric. In other words, it fixes the handling of codepoints 0xE000, 0xF8FF, 0xF0000, 0xFFFFD, 0x100000 and 0x10FFFD.
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA1: 6cfd9af5250029c0d275be027b4208c48954a8a1
User & Date: dan 2013-06-05 16:17:21
Context
2013-06-07
22:12
Improve manual cleaning step performed by the multi-platform build tool for MSVC. check-in: d5bc1fe1 user: mistachkin tags: trunk
2013-06-05
16:17
Up until now the fts4 "unicode61" tokenizer has treated all private use codepoints except the first and last of each of the three ranges as alphanumeric (eligible to be part of tokens). This commit fixes this so that all private use codepoints are considered alphanumeric. In other words, it fixes the handling of codepoints 0xE000, 0xF8FF, 0xF0000, 0xFFFFD, 0x100000 and 0x10FFFD. check-in: 6cfd9af5 user: dan tags: trunk
2013-06-03
20:39
Fix a typo in a collating function inside the e_reindex.test script. check-in: 4d74fccf user: drh tags: trunk
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Changes to ext/fts3/fts3_unicode2.c.

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
    0x02A00801, 0x02A01801, 0x02A02C01, 0x02A08C09, 0x02A0D804,
    0x02A1D004, 0x02A20002, 0x02A2D011, 0x02A33802, 0x02A38012,
    0x02A3E003, 0x02A4980A, 0x02A51C0D, 0x02A57C01, 0x02A60004,
    0x02A6CC1B, 0x02A77802, 0x02A8A40E, 0x02A90C01, 0x02A93002,
    0x02A97004, 0x02A9DC03, 0x02A9EC01, 0x02AAC001, 0x02AAC803,
    0x02AADC02, 0x02AAF802, 0x02AB0401, 0x02AB7802, 0x02ABAC07,
    0x02ABD402, 0x02AF8C0B, 0x03600001, 0x036DFC02, 0x036FFC02,
    0x037FFC02, 0x03E3FC01, 0x03EC7801, 0x03ECA401, 0x03EEC810,
    0x03F4F802, 0x03F7F002, 0x03F8001A, 0x03F88007, 0x03F8C023,
    0x03F95013, 0x03F9A004, 0x03FBFC01, 0x03FC040F, 0x03FC6807,
    0x03FCEC06, 0x03FD6C0B, 0x03FF8007, 0x03FFA007, 0x03FFE405,
    0x04040003, 0x0404DC09, 0x0405E411, 0x0406400C, 0x0407402E,
    0x040E7C01, 0x040F4001, 0x04215C01, 0x04247C01, 0x0424FC01,
    0x04280403, 0x04281402, 0x04283004, 0x0428E003, 0x0428FC01,
    0x04294009, 0x0429FC01, 0x042CE407, 0x04400003, 0x0440E016,
    0x04420003, 0x0442C012, 0x04440003, 0x04449C0E, 0x04450004,
    0x04460003, 0x0446CC0E, 0x04471404, 0x045AAC0D, 0x0491C004,
    0x05BD442E, 0x05BE3C04, 0x074000F6, 0x07440027, 0x0744A4B5,
    0x07480046, 0x074C0057, 0x075B0401, 0x075B6C01, 0x075BEC01,
    0x075C5401, 0x075CD401, 0x075D3C01, 0x075DBC01, 0x075E2401,
    0x075EA401, 0x075F0C01, 0x07BBC002, 0x07C0002C, 0x07C0C064,
    0x07C2800F, 0x07C2C40E, 0x07C3040F, 0x07C3440F, 0x07C4401F,
    0x07C4C03C, 0x07C5C02B, 0x07C7981D, 0x07C8402B, 0x07C90009,
    0x07C94002, 0x07CC0021, 0x07CCC006, 0x07CCDC46, 0x07CE0014,
    0x07CE8025, 0x07CF1805, 0x07CF8011, 0x07D0003F, 0x07D10001,
    0x07D108B6, 0x07D3E404, 0x07D4003E, 0x07D50004, 0x07D54018,
    0x07D7EC46, 0x07D9140B, 0x07DA0046, 0x07DC0074, 0x38000401,
    0x38008060, 0x380400F0, 0x3C000001, 0x3FFFF401, 0x40000001,
    0x43FFF401,
  };
  static const unsigned int aAscii[4] = {
    0xFFFFFFFF, 0xFC00FFFF, 0xF8000001, 0xF8000001,
  };

  if( c<128 ){
    return ( (aAscii[c >> 5] & (1 << (c & 0x001F)))==0 );







|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<







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
    0x02A00801, 0x02A01801, 0x02A02C01, 0x02A08C09, 0x02A0D804,
    0x02A1D004, 0x02A20002, 0x02A2D011, 0x02A33802, 0x02A38012,
    0x02A3E003, 0x02A4980A, 0x02A51C0D, 0x02A57C01, 0x02A60004,
    0x02A6CC1B, 0x02A77802, 0x02A8A40E, 0x02A90C01, 0x02A93002,
    0x02A97004, 0x02A9DC03, 0x02A9EC01, 0x02AAC001, 0x02AAC803,
    0x02AADC02, 0x02AAF802, 0x02AB0401, 0x02AB7802, 0x02ABAC07,
    0x02ABD402, 0x02AF8C0B, 0x03600001, 0x036DFC02, 0x036FFC02,
    0x037FFC01, 0x03EC7801, 0x03ECA401, 0x03EEC810, 0x03F4F802,
    0x03F7F002, 0x03F8001A, 0x03F88007, 0x03F8C023, 0x03F95013,
    0x03F9A004, 0x03FBFC01, 0x03FC040F, 0x03FC6807, 0x03FCEC06,
    0x03FD6C0B, 0x03FF8007, 0x03FFA007, 0x03FFE405, 0x04040003,
    0x0404DC09, 0x0405E411, 0x0406400C, 0x0407402E, 0x040E7C01,
    0x040F4001, 0x04215C01, 0x04247C01, 0x0424FC01, 0x04280403,
    0x04281402, 0x04283004, 0x0428E003, 0x0428FC01, 0x04294009,
    0x0429FC01, 0x042CE407, 0x04400003, 0x0440E016, 0x04420003,
    0x0442C012, 0x04440003, 0x04449C0E, 0x04450004, 0x04460003,
    0x0446CC0E, 0x04471404, 0x045AAC0D, 0x0491C004, 0x05BD442E,
    0x05BE3C04, 0x074000F6, 0x07440027, 0x0744A4B5, 0x07480046,
    0x074C0057, 0x075B0401, 0x075B6C01, 0x075BEC01, 0x075C5401,
    0x075CD401, 0x075D3C01, 0x075DBC01, 0x075E2401, 0x075EA401,
    0x075F0C01, 0x07BBC002, 0x07C0002C, 0x07C0C064, 0x07C2800F,
    0x07C2C40E, 0x07C3040F, 0x07C3440F, 0x07C4401F, 0x07C4C03C,
    0x07C5C02B, 0x07C7981D, 0x07C8402B, 0x07C90009, 0x07C94002,
    0x07CC0021, 0x07CCC006, 0x07CCDC46, 0x07CE0014, 0x07CE8025,
    0x07CF1805, 0x07CF8011, 0x07D0003F, 0x07D10001, 0x07D108B6,
    0x07D3E404, 0x07D4003E, 0x07D50004, 0x07D54018, 0x07D7EC46,
    0x07D9140B, 0x07DA0046, 0x07DC0074, 0x38000401, 0x38008060,
    0x380400F0,

  };
  static const unsigned int aAscii[4] = {
    0xFFFFFFFF, 0xFC00FFFF, 0xF8000001, 0xF8000001,
  };

  if( c<128 ){
    return ( (aAscii[c >> 5] & (1 << (c & 0x001F)))==0 );

Changes to ext/fts3/unicode/mkunicode.tcl.

235
236
237
238
239
240
241

242


243
244
245
246
247
248
249
...
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
...
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
...
801
802
803
804
805
806
807
808
    if {$line == ""} continue

    set fields [split $line ";"]
    if {[llength $fields] != [llength $lField]} { error "parse error: $line" }
    foreach $lField $fields {}

    set iCode [expr "0x$code"]

    set bAlnum [expr {[lsearch {L N} [string range $general_category 0 0]]>=0}]



    if { !$bAlnum } { lappend lRet $iCode }
  }

  close $fd
  set lRet
}
................................................................................
        iLo = iTest+1;
      }else{
        iHi = iTest-1;
      }
    }
    assert( aEntry[0]<key );
    assert( key>=aEntry[iRes] );
    return (c >= ((aEntry[iRes]>>10) + (aEntry[iRes]&0x3FF)));
  }
  return 1;}
  puts "\}"
}

proc print_test_isalnum {zFunc lRange} {
  foreach range $lRange {
................................................................................
*/

/*
** DO NOT EDIT THIS MACHINE GENERATED FILE.
*/
  }]
  puts ""
  puts "#if !defined(SQLITE_DISABLE_FTS3_UNICODE)"
  puts "#if defined(SQLITE_ENABLE_FTS3) || defined(SQLITE_ENABLE_FTS4)"
  puts ""
  puts "#include <assert.h>"
  puts ""
}

proc print_test_main {} {
................................................................................
if {$::generate_test_code} {
  print_test_isalnum sqlite3FtsUnicodeIsalnum $lRange
  print_fold_test sqlite3FtsUnicodeFold $mappings
  print_test_main 
}

puts "#endif /* defined(SQLITE_ENABLE_FTS3) || defined(SQLITE_ENABLE_FTS4) */"
puts "#endif /* !defined(SQLITE_DISABLE_FTS3_UNICODE) */"







>
|
>
>







 







|







 







|







 







|
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
...
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
...
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
...
804
805
806
807
808
809
810
811
    if {$line == ""} continue

    set fields [split $line ";"]
    if {[llength $fields] != [llength $lField]} { error "parse error: $line" }
    foreach $lField $fields {}

    set iCode [expr "0x$code"]
    set bAlnum [expr {
         [lsearch {L N} [string range $general_category 0 0]] >= 0
      || $general_category=="Co"
    }]

    if { !$bAlnum } { lappend lRet $iCode }
  }

  close $fd
  set lRet
}
................................................................................
        iLo = iTest+1;
      }else{
        iHi = iTest-1;
      }
    }
    assert( aEntry[0]<key );
    assert( key>=aEntry[iRes] );
    return (((unsigned int)c) >= ((aEntry[iRes]>>10) + (aEntry[iRes]&0x3FF)));
  }
  return 1;}
  puts "\}"
}

proc print_test_isalnum {zFunc lRange} {
  foreach range $lRange {
................................................................................
*/

/*
** DO NOT EDIT THIS MACHINE GENERATED FILE.
*/
  }]
  puts ""
  puts "#if defined(SQLITE_ENABLE_FTS4_UNICODE61)"
  puts "#if defined(SQLITE_ENABLE_FTS3) || defined(SQLITE_ENABLE_FTS4)"
  puts ""
  puts "#include <assert.h>"
  puts ""
}

proc print_test_main {} {
................................................................................
if {$::generate_test_code} {
  print_test_isalnum sqlite3FtsUnicodeIsalnum $lRange
  print_fold_test sqlite3FtsUnicodeFold $mappings
  print_test_main 
}

puts "#endif /* defined(SQLITE_ENABLE_FTS3) || defined(SQLITE_ENABLE_FTS4) */"
puts "#endif /* !defined(SQLITE_ENABLE_FTS4_UNICODE61) */"

Changes to test/fts4unicode.test.

379
380
381
382
383
384
385


















386
387
388

  do_isspace_test 6.$T.19 $T   {32 160 5760 6158}
  do_isspace_test 6.$T.19 $T   {8192 8193 8194 8195}
  do_isspace_test 6.$T.19 $T   {8196 8197 8198 8199}
  do_isspace_test 6.$T.19 $T   {8200 8201 8202 8239}
  do_isspace_test 6.$T.19 $T   {8287 12288}
}




















finish_test







>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>
>



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

  do_isspace_test 6.$T.19 $T   {32 160 5760 6158}
  do_isspace_test 6.$T.19 $T   {8192 8193 8194 8195}
  do_isspace_test 6.$T.19 $T   {8196 8197 8198 8199}
  do_isspace_test 6.$T.19 $T   {8200 8201 8202 8239}
  do_isspace_test 6.$T.19 $T   {8287 12288}
}

#-------------------------------------------------------------------------
# Test that the private use ranges are treated as alphanumeric.
#
breakpoint
foreach {tn1 c} {
  1 \ue000 2 \ue001 3 \uf000 4 \uf8fe 5 \uf8ff
} {
  foreach {tn2 config res} {
    1 ""             "0 hello*world hello*world"
    2 "separators=*" "0 hello hello 1 world world"
  } {
    set config [string map [list * $c] $config]
    set input  [string map [list * $c] "hello*world"]
    set output [string map [list * $c] $res]
    do_unicode_token_test3 7.$tn1.$tn2 {*}$config $input $output
  }
}


finish_test