regex + locale bug - Mailing list pgsql-hackers

I am using postgres 6.4.2 on BSD/OS 3.1 with  a Greek locale  that I
have developed. I knew that regexes with postgress would not work because
of something I did but a posting from another follow from Sweden gave me a
clue that the problem must be with the regex package and not the locale.

So I investigated the code and found out the pg_isdigit(int ch),
pg_isalpha(int ch) and the associated functions do a comparison of
characters as ints. I changed a few crucial points with a cast to
(unsigned char) and voila , regexs in Greek with full locale support. My
guess is that an int != unsigned char when comparing, the sign bit is
probably the culprit.

Please test the patch on some other language too, Swedish or Finish
would be a nice touch.

Patch follows, but it is trivial really. 

--------------------------------------------------------------------------------
*** regcomp.c    Tue Sep  1 07:31:25 1998
--- regcomp.c.patched    Wed Feb 10 19:57:11 1999
***************
*** 1038,1046 **** {     assert(pg_isalpha(ch));     if (pg_isupper(ch))
!         return tolower(ch);     else if (pg_islower(ch))
!         return toupper(ch);     else /* peculiar, but could happen */         return ch;
--- 1038,1046 ---- {     assert(pg_isalpha(ch));     if (pg_isupper(ch))
!         return tolower((unsigned char)ch);     else if (pg_islower(ch))
!         return toupper((unsigned char)ch);     else /* peculiar, but could happen */         return ch;
***************
*** 1055,1067 **** static void bothcases(p, ch) struct parse *p;
! int            ch; {     pg_wchar   *oldnext = p->next;     pg_wchar   *oldend = p->end;     pg_wchar    bracket[3];

!     assert(othercase(ch) != ch);/* p_bracket() would recurse */     p->next = bracket;     p->end = bracket + 2;
bracket[0]= ch;
 
--- 1055,1067 ---- static void bothcases(p, ch) struct parse *p;
! int        ch; {     pg_wchar   *oldnext = p->next;     pg_wchar   *oldend = p->end;     pg_wchar    bracket[3]; 
!     assert(othercase(ch) != (unsigned char)ch);/* p_bracket() would recurse */     p->next = bracket;     p->end =
bracket+ 2;     bracket[0] = ch;
 
***************
*** 1084,1090 **** {     cat_t       *cap = p->g->categories; 
!     if ((p->g->cflags & REG_ICASE) && pg_isalpha(ch) && othercase(ch) != ch)         bothcases(p, ch);     else
{
--- 1084,1090 ---- {     cat_t       *cap = p->g->categories; 
!     if ((p->g->cflags & REG_ICASE) && pg_isalpha(ch) && othercase(ch) != (unsigned char)ch)         bothcases(p, ch);
   else     {
 
***************
*** 1862,1868 **** #ifdef MULTIBYTE     return (c >= 0 && c <= UCHAR_MAX && isdigit(c)); #else
!     return (isdigit(c)); #endif } 
--- 1862,1868 ---- #ifdef MULTIBYTE     return (c >= 0 && c <= UCHAR_MAX && isdigit(c)); #else
!     return (isdigit((unsigned char)c)); #endif } 
***************
*** 1872,1878 **** #ifdef MULTIBYTE     return (c >= 0 && c <= UCHAR_MAX && isalpha(c)); #else
!     return (isalpha(c)); #endif } 
--- 1872,1878 ---- #ifdef MULTIBYTE     return (c >= 0 && c <= UCHAR_MAX && isalpha(c)); #else
!     return (isalpha((unsigned char)c)); #endif } 
***************
*** 1882,1888 **** #ifdef MULTIBYTE     return (c >= 0 && c <= UCHAR_MAX && isupper(c)); #else
!     return (isupper(c)); #endif } 
--- 1882,1888 ---- #ifdef MULTIBYTE     return (c >= 0 && c <= UCHAR_MAX && isupper(c)); #else
!     return (isupper((unsigned char)c)); #endif } 
***************
*** 1892,1897 **** #ifdef MULTIBYTE     return (c >= 0 && c <= UCHAR_MAX && islower(c)); #else
!     return (islower(c)); #endif }
--- 1892,1897 ---- #ifdef MULTIBYTE     return (c >= 0 && c <= UCHAR_MAX && islower(c)); #else
!     return (islower((unsigned char)c)); #endif }

-- 
Incredible Networks LTD       Angelos Karageorgiou
20 Karea st,                  +30.1.92.12.312 (voice)
116 36 Athens, Greece.        +30.1.92.12.314 (fax)
http://www.incredible.com     angelos@incredible.com (e-mail)