SQLite
Check-in [82957495aa0729468a020c2a0a45ed60019b6e07]
Not logged in
Overview
SHA1 Hash:82957495aa0729468a020c2a0a45ed60019b6e07
Date: 2013-01-18 03:35:14
User: drh
Comment:The \xXX escape in the test_regexp.c must be followed by exactly two hex digits.
Tags And Properties
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Changes to src/test_regexp.c

22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
...
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
**     X|Y     X or Y
**     ^X      X occurring at the beginning of the string
**     X$      X occurring at the end of the string
**     .       Match any single character
**     \c      Character c where c is one of \{}()[]|*+?.
**     \c      C-language escapes for c in afnrtv.  ex: \t or \n
**     \uXXXX  Where XXXX is exactly 4 hex digits, unicode value XXXX
**     \xXXX   Where XXX is any number of hex digits, unicode value XXX
**     [abc]   Any single character from the set abc
**     [^abc]  Any single character not in the set abc
**     [a-z]   Any single character in the range a-z
**     [^a-z]  Any single character not in the range a-z
**     \b      Word boundary
**     \w      Word character.  [A-Za-z0-9_]
**     \W      Non-word character
................................................................................
static unsigned re_esc_char(ReCompiled *p){
  static const char zEsc[] = "afnrtv\\()*.+?[$^{|}]";
  static const char zTrans[] = "\a\f\n\r\t\v";
  int i, v = 0;
  char c;
  if( p->sIn.i>=p->sIn.mx ) return 0;
  c = p->sIn.z[p->sIn.i];
  if( c=='u' && p->sIn.i+5<p->sIn.mx ){
    const unsigned char *zIn = p->sIn.z + p->sIn.i;
    v = 0;
    if( re_hex(zIn[1],&v)
     && re_hex(zIn[2],&v)
     && re_hex(zIn[3],&v)
     && re_hex(zIn[4],&v)
    ){
      p->sIn.i += 5;
      return v;
    }
  }
  if( c=='x' ){
    v = 0;
    for(i=1; p->sIn.i<p->sIn.mx && re_hex(p->sIn.z[p->sIn.i+i], &v); i++){}
    if( i>1 ){

      p->sIn.i += i;
      return v;
    }
  }
  for(i=0; zEsc[i] && zEsc[i]!=c; i++){}
  if( zEsc[i] ){
    if( i<6 ) c = zTrans[i];
    p->sIn.i++;







|







 







|

<









|
|
|
|
>
|







22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
...
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
**     X|Y     X or Y
**     ^X      X occurring at the beginning of the string
**     X$      X occurring at the end of the string
**     .       Match any single character
**     \c      Character c where c is one of \{}()[]|*+?.
**     \c      C-language escapes for c in afnrtv.  ex: \t or \n
**     \uXXXX  Where XXXX is exactly 4 hex digits, unicode value XXXX
**     \xXX    Where XX is exactly 2 hex digits, unicode value XX
**     [abc]   Any single character from the set abc
**     [^abc]  Any single character not in the set abc
**     [a-z]   Any single character in the range a-z
**     [^a-z]  Any single character not in the range a-z
**     \b      Word boundary
**     \w      Word character.  [A-Za-z0-9_]
**     \W      Non-word character
................................................................................
static unsigned re_esc_char(ReCompiled *p){
  static const char zEsc[] = "afnrtv\\()*.+?[$^{|}]";
  static const char zTrans[] = "\a\f\n\r\t\v";
  int i, v = 0;
  char c;
  if( p->sIn.i>=p->sIn.mx ) return 0;
  c = p->sIn.z[p->sIn.i];
  if( c=='u' && p->sIn.i+4<p->sIn.mx ){
    const unsigned char *zIn = p->sIn.z + p->sIn.i;

    if( re_hex(zIn[1],&v)
     && re_hex(zIn[2],&v)
     && re_hex(zIn[3],&v)
     && re_hex(zIn[4],&v)
    ){
      p->sIn.i += 5;
      return v;
    }
  }
  if( c=='x' && p->sIn.i+2<p->sIn.mx ){
    const unsigned char *zIn = p->sIn.z + p->sIn.i;
    if( re_hex(zIn[1],&v)
     && re_hex(zIn[2],&v)
    ){
      p->sIn.i += 3;
      return v;
    }
  }
  for(i=0; zEsc[i] && zEsc[i]!=c; i++){}
  if( zEsc[i] ){
    if( i<6 ) c = zTrans[i];
    p->sIn.i++;

Changes to test/regexp1.test

193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
         'abc{4}x' REGEXP '^abc\{4\}x$',
         'abc|def' REGEXP '^abc\|def$'
} {1 1 1 1 1 1 1 1 1 1 1 1}

do_execsql_test regexp1-2.20 {
  SELECT 'abc$¢€xyz' REGEXP '^abc\u0024\u00a2\u20acxyz$',
         'abc$¢€xyz' REGEXP '^abc\u0024\u00A2\u20ACxyz$',
         'abc$¢€xyz' REGEXP '^abc\x24\xa2\x20acxyz$'
} {1 1 1}
do_execsql_test regexp1-2.21 {
  SELECT 'abc$¢€xyz' REGEXP '^abc[\u0024][\u00a2][\u20ac]xyz$',
         'abc$¢€xyz' REGEXP '^abc[\u0024\u00A2\u20AC]{3}xyz$',
         'abc$¢€xyz' REGEXP '^abc[\x24][\xa2\x20ac]+xyz$'
} {1 1 1}
do_execsql_test regexp1-2.22 {
  SELECT 'abc$¢€xyz' REGEXP '^abc[^\u0025-X][^ -\u007f][^\u20ab]xyz$'
} {1}

finish_test







|




|






193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
         'abc{4}x' REGEXP '^abc\{4\}x$',
         'abc|def' REGEXP '^abc\|def$'
} {1 1 1 1 1 1 1 1 1 1 1 1}

do_execsql_test regexp1-2.20 {
  SELECT 'abc$¢€xyz' REGEXP '^abc\u0024\u00a2\u20acxyz$',
         'abc$¢€xyz' REGEXP '^abc\u0024\u00A2\u20ACxyz$',
         'abc$¢€xyz' REGEXP '^abc\x24\xa2\u20acxyz$'
} {1 1 1}
do_execsql_test regexp1-2.21 {
  SELECT 'abc$¢€xyz' REGEXP '^abc[\u0024][\u00a2][\u20ac]xyz$',
         'abc$¢€xyz' REGEXP '^abc[\u0024\u00A2\u20AC]{3}xyz$',
         'abc$¢€xyz' REGEXP '^abc[\x24][\xa2\u20ac]+xyz$'
} {1 1 1}
do_execsql_test regexp1-2.22 {
  SELECT 'abc$¢€xyz' REGEXP '^abc[^\u0025-X][^ -\u007f][^\u20ab]xyz$'
} {1}

finish_test