Fossil

Check-in [e4ca677a]
Login

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

Overview
Comment:Off-by-one error in regexp \u escape sequence parsing. Regexp \x escape sequence should only accept exactly 2 hex digits.
Downloads: Tarball | ZIP archive | SQL archive
Timelines: family | ancestors | descendants | both | trunk
Files: files | file ages | folders
SHA1:e4ca677a6c9d066bf4a6f51df4c7ed8e7131ce36
User & Date: drh 2013-01-11 18:12:53
Context
2013-01-13
02:01
Allow the FOSSIL_USER environment variable to be used as a fallback when creating a new repository. check-in: a0dd51e9 user: mistachkin tags: trunk
2013-01-11
18:12
Off-by-one error in regexp \u escape sequence parsing. Regexp \x escape sequence should only accept exactly 2 hex digits. check-in: e4ca677a user: drh tags: trunk
18:03
Enhancements to the TICKETCHNG table: (1) Add the tkt_rid column and populate it (if present) with the recordID of the artifact. (2) For columns that appear in both TICKET and TICKETCHNG but are missing from the artifact, fill in the TICKETCHNG value with the value from TICKET at that point in time. (3) Add the test-ticket-rebuild command for testing the above. check-in: a18a49c8 user: drh tags: trunk
08:10
Off-by-one error in regexp \u escape sequence parsing. Regexp \x escape sequence should only accept exactly 2 hex digits. Typo. Closed-Leaf check-in: bef9a956 user: jan.nijtmans tags: regexp-x
Changes
Hide Diffs Unified Diffs Ignore Whitespace Patch

Changes to src/regexp.c.

30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
...
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
407
408
409
410
411
412

413
414
415
416
417
418
419
**     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
................................................................................
    return 0;
  }
  *pV = (*pV)*16 + (c & 0xff);
  return 1;
}

/* A backslash character has been seen, read the next character and
** return its intepretation.
*/
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++;
  }else{







|







 







|








|

<










|
|
|
|
|
>







30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
...
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
407
408
409
410
411
412
413
414
415
416
417
418
419
**     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
................................................................................
    return 0;
  }
  *pV = (*pV)*16 + (c & 0xff);
  return 1;
}

/* A backslash character has been seen, read the next character and
** return its interpretation.
*/
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' ){
    const unsigned char *zIn = p->sIn.z + p->sIn.i;
    if( p->sIn.i+2<p->sIn.mx ){
      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++;
  }else{