database/postgres
1
0
Fork 0
mirror of https://github.com/postgres/postgres.git synced 2025-06-14 18:42:34 +03:00
Code Activity

From: t-ishii@sra.co.jp

Browse Source 
Included are patches intended for allowing PostgreSQL to handle
multi-byte charachter sets such as EUC(Extende Unix Code), Unicode and
Mule internal code. With the MB patch you can use multi-byte character
sets in regexp and LIKE. The encoding system chosen is determined at
the compile time.

To enable the MB extension, you need to define a variable "MB" in
Makefile.global or in Makefile.custom. For further information please
take a look at README.mb under doc directory.

(Note that unlike "jp patch" I do not use modified GNU regexp any
more. I changed Henry Spencer's regexp coming with PostgreSQL.)
This commit is contained in:
Marc G. Fournier
1998-03-15 07:39:04 +00:00
parent 31a925c4d0
commit 661ecf3c48
23 changed files with 1104 additions and 135 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
src/include/regex/regex2.h
View File

@ -127,12 +127,29 @@ typedef struct
{
uch *ptr; /* -> uch [csetsize] */
uch mask; /* bit within array */
uch hash; /* hash code */
#ifdef MB
pg_wchar hash; /* hash code */
unsigned int lc; /* leading character (character-set) */
#else
uch hash; /* hash code */
#endif
size_t smultis;
char *multis; /* -> char[smulti] ab\0cd\0ef\0\0 */
} cset;
/* note that CHadd and CHsub are unsafe, and CHIN doesn't yield 0/1 */
#ifdef MB
#define CHlc(c) (((unsigned)(c)&0xff0000)>>16)
#define CHadd(cs, c) ((cs)->ptr[(unsigned)(c)&0xffff] |= (cs)->mask, (cs)->hash += (unsigned)(c)&0xffff,\
(cs)->lc = CHlc(c))
#define CHsub(cs, c) ((cs)->ptr[(unsigned)(c)&0xffff] &= ~(cs)->mask, (cs)->hash -= (unsigned)(c)&0xffff)
#define CHIN(cs, c) ((cs)->ptr[(unsigned)(c)&0xffff] & (cs)->mask && \
((cs)->lc == CHlc(c)))
#define MCadd(p, cs, cp) mcadd(p, cs, cp) /* regcomp() internal
* fns */
#define MCsub(p, cs, cp) mcsub(p, cs, cp)
#define MCin(p, cs, cp) mcin(p, cs, cp)
#else
#define CHadd(cs, c) ((cs)->ptr[(uch)(c)] |= (cs)->mask, (cs)->hash += (c))
#define CHsub(cs, c) ((cs)->ptr[(uch)(c)] &= ~(cs)->mask, (cs)->hash -= (c))
#define CHIN(cs, c) ((cs)->ptr[(uch)(c)] & (cs)->mask)
@ -140,6 +157,7 @@ typedef struct
* fns */
#define MCsub(p, cs, cp) mcsub(p, cs, cp)
#define MCin(p, cs, cp) mcin(p, cs, cp)
#endif
/* stuff for character categories */
typedef unsigned char cat_t;
@ -168,7 +186,7 @@ struct re_guts
int neol; /* number of $ used */
int ncategories; /* how many character categories */
cat_t *categories; /* ->catspace[-CHAR_MIN] */
char *must; /* match must contain this string */
pg_wchar *must; /* match must contain this string */
int mlen; /* length of must */
size_t nsub; /* copy of re_nsub */
int backrefs; /* does it use back references? */
@ -178,5 +196,21 @@ struct re_guts
};
/* misc utilities */
#define OUT (CHAR_MAX+1) /* a non-character value */
#define ISWORD(c) (isalnum(c) || (c) == '_')
#ifdef MB
# if MB == MULE_INTERNAL
# define OUT (16777216+1) /* 16777216 == 2^24 == 3 bytes */
# elif MB == EUC_JP || MB == EUC_CN || MB == EUC_KR || MB == EUC_TW
# define OUT (USHRT_MAX+1) /* 2 bytes */
# elif MB == UNICODE
# define OUT (USHRT_MAX+1) /* 2 bytes. assuming UCS-2 */
# endif
#else
# define OUT (CHAR_MAX+1) /* a non-character value */
#endif
#ifdef MB
#define ISWORD(c) ((c >= 0 && c <= UCHAR_MAX) && \
(isalnum(c) || (c) == '_'))
#else
#define ISWORD(c) (isalnum(c) || (c) == '_')
#endif