Re: regexp character class locale awareness patch - Mailing list pgsql-hackers

Can someone who is multbyte-aware comment on this patch?  Thanks.

---------------------------------------------------------------------------

Manuel Sugawara wrote:
> Attached is a pacth against 7.2 which adds locale awareness to
> the character classes of the regular expression engine. Please
> consider including this feature to postgreSQL.
>
> Regards, Manuel.

Content-Description: regexp character class locale awareness patch

[ Attachment, skipping... ]

>
> ---------------------------(end of broadcast)---------------------------
> TIP 1: subscribe and unsubscribe commands go to majordomo@postgresql.org

--
  Bruce Momjian                        |  http://candle.pha.pa.us
  pgman@candle.pha.pa.us               |  (610) 853-3000
  +  If your life is a hard drive,     |  830 Blythe Avenue
  +  Christ can be your backup.        |  Drexel Hill, Pennsylvania 19026
*** src/backend/regex/regcomp.c.org    Sun Mar 17 16:39:13 2002
--- src/backend/regex/regcomp.c    Sun Mar 17 16:53:43 2002
***************
*** 47,53 ****
--- 47,64 ----
  #include "regex/regex.h"
  #include "regex/utils.h"
  #include "regex/regex2.h"
+ #ifdef USE_LOCALE
+ struct cclass
+ {
+     char *name;
+     char *chars;
+     char *multis;
+ };
+ static struct cclass* cclasses = NULL;
+ static struct cclass* cclass_init(void);
+ #else
  #include "regex/cclass.h"
+ #endif /* USE_LOCALE */
  #include "regex/cname.h"

  /*
***************
*** 174,179 ****
--- 185,195 ----
      pg_wchar   *wcp;
  #endif

+ #ifdef USE_LOCALE
+     if ( cclasses == NULL )
+         cclasses = cclass_init();
+ #endif /* USE_LOCALE */
+
  #ifdef REDEBUG
  #define  GOODFLAGS(f)     (f)
  #else
***************
*** 884,890 ****
      struct cclass *cp;
      size_t        len;
      char       *u;
!     char        c;

      while (MORE() && pg_isalpha(PEEK()))
          NEXT();
--- 900,906 ----
      struct cclass *cp;
      size_t        len;
      char       *u;
!     unsigned char        c;

      while (MORE() && pg_isalpha(PEEK()))
          NEXT();
***************
*** 905,911 ****

      u = cp->chars;
      while ((c = *u++) != '\0')
!         CHadd(cs, c);
      for (u = cp->multis; *u != '\0'; u += strlen(u) + 1)
          MCadd(p, cs, u);
  }
--- 921,927 ----

      u = cp->chars;
      while ((c = *u++) != '\0')
!         CHadd(cs, c);
      for (u = cp->multis; *u != '\0'; u += strlen(u) + 1)
          MCadd(p, cs, u);
  }
***************
*** 1716,1718 ****
--- 1732,1796 ----
      return (islower((unsigned char) c));
  #endif
  }
+
+ #ifdef USE_LOCALE
+ static struct cclass *
+ cclass_init(void)
+ {
+     struct cclass *cp = NULL;
+     struct cclass *classes = NULL;
+     struct cclass_factory
+     {
+         char *name;
+         int (*func)(int);
+         char *chars;
+     } cclass_factories [] =
+         {
+             { "alnum", isalnum, NULL },
+             { "alpha", isalpha, NULL },
+             { "blank", NULL, " \t" },
+             { "cntrl", iscntrl, NULL },
+             { "digit", NULL, "0123456789" },
+             { "graph", isgraph, NULL },
+             { "lower", islower, NULL },
+             { "print", isprint, NULL },
+             { "punct", ispunct, NULL },
+             { "space", NULL, "\t\n\v\f\r " },
+             { "upper", isupper, NULL },
+             { "xdigit", isxdigit, NULL },
+             { NULL, NULL, NULL }
+         };
+     struct cclass_factory *cf = NULL;
+
+     classes = malloc(sizeof(struct cclass) * (sizeof(cclass_factories) / sizeof(struct cclass_factory)));
+     if (classes == NULL)
+         elog(ERROR,"cclass_init: out of memory");
+
+     cp = classes;
+     for(cf = cclass_factories; cf->name != NULL; cf++)
+         {
+             cp->name = strdup(cf->name);
+             if ( cf->chars )
+                 cp->chars = strdup(cf->chars);
+             else
+                 {
+                     int x = 0, y = 0;
+                     cp->chars = malloc(sizeof(char) * 256);
+                     if (cp->chars == NULL)
+                         elog(ERROR,"cclass_init: out of memory");
+                     for (x = 0; x < 256; x++)
+                         {
+                             if((cf->func)(x))
+                                 *(cp->chars + y++) = x;
+                         }
+                     *(cp->chars + y) = '\0';
+                 }
+             cp->multis = "";
+             cp++;
+         }
+     cp->name = cp->chars = NULL;
+     cp->multis = "";
+
+     return classes;
+ }
+ #endif /* USE_LOCALE */