mirror/postgresql
2
0
Fork 0
mirror of https://git.postgresql.org/git/postgresql.git synced 2024-11-27 07:21:09 +08:00
Code Issues Packages Projects Releases Wiki Activity
105f3ef492
postgresql/contrib/tsearch2/ts_locale.h

80 lines
1.8 KiB
C
Raw Normal View History

Text parser rewritten: - supports multibyte encodings - more strict rules for lexemes - flex isn't used Add: - tsquery plainto_tsquery(text) Function makes tsquery from plain text. - &&, ||, !! operation for tsquery for combining tsquery from it's parts: 'foo & bar' || 'asd' => 'foo & bar | asd'
2005-11-21 20:27:57 +08:00
#ifndef __TSLOCALE_H__
#define __TSLOCALE_H__
#include "postgres.h"
Improve support of multibyte encoding: - tsvector_(in|out) - tsquery_(in|out) - to_tsvector - to_tsquery, plainto_tsquery - 'simple' dictionary
2005-12-12 19:10:12 +08:00
#include "utils/pg_locale.h"
#include "mb/pg_wchar.h"
Text parser rewritten: - supports multibyte encodings - more strict rules for lexemes - flex isn't used Add: - tsquery plainto_tsquery(text) Function makes tsquery from plain text. - &&, ||, !! operation for tsquery for combining tsquery from it's parts: 'foo & bar' || 'asd' => 'foo & bar | asd'
2005-11-21 20:27:57 +08:00
#include <ctype.h>
#include <limits.h>
/*
* towlower() and friends should be in <wctype.h>, but some pre-C99 systems
* declare them in <wchar.h>.
*/
#ifdef HAVE_WCHAR_H
#include <wchar.h>
#endif
#ifdef HAVE_WCTYPE_H
#include <wctype.h>
#endif
#if defined(HAVE_WCSTOMBS) && defined(HAVE_TOWLOWER)
#define TS_USE_WIDE
Improve support of multibyte encoding: - tsvector_(in|out) - tsquery_(in|out) - to_tsvector - to_tsquery, plainto_tsquery - 'simple' dictionary
2005-12-12 19:10:12 +08:00
#endif
#ifdef TS_USE_WIDE
#endif /* TS_USE_WIDE */
#define TOUCHAR(x) (*((unsigned char*)(x)))
#ifdef TS_USE_WIDE
Fix localization support for multibyte encoding and C locale. Slightly reworked patch from Tatsuo Ishii
2007-01-15 23:16:11 +08:00
size_t char2wchar(wchar_t *to, const char *from, size_t len);
Text parser rewritten: - supports multibyte encodings - more strict rules for lexemes - flex isn't used Add: - tsquery plainto_tsquery(text) Function makes tsquery from plain text. - &&, ||, !! operation for tsquery for combining tsquery from it's parts: 'foo & bar' || 'asd' => 'foo & bar | asd'
2005-11-21 20:27:57 +08:00
#ifdef WIN32
Re-run pgindent, fixing a problem where comment lines after a blank comment line where output as too long, and update typedefs for /lib directory. Also fix case where identifiers were used as variable names in the backend, but as typedefs in ecpg (favor the backend for indenting). Backpatch to 8.1.X.
2005-11-23 02:17:34 +08:00
size_t wchar2char(char *to, const wchar_t *from, size_t len);
Fix localization support for multibyte encoding and C locale. Slightly reworked patch from Tatsuo Ishii
2007-01-15 23:16:11 +08:00
pgindent run for 8.2.
2006-10-04 08:30:14 +08:00
#else /* WIN32 */
Text parser rewritten: - supports multibyte encodings - more strict rules for lexemes - flex isn't used Add: - tsquery plainto_tsquery(text) Function makes tsquery from plain text. - &&, ||, !! operation for tsquery for combining tsquery from it's parts: 'foo & bar' || 'asd' => 'foo & bar | asd'
2005-11-21 20:27:57 +08:00
Fix localization support for multibyte encoding and C locale. Slightly reworked patch from Tatsuo Ishii
2007-01-15 23:16:11 +08:00
/* correct wcstombs */
Text parser rewritten: - supports multibyte encodings - more strict rules for lexemes - flex isn't used Add: - tsquery plainto_tsquery(text) Function makes tsquery from plain text. - &&, ||, !! operation for tsquery for combining tsquery from it's parts: 'foo & bar' || 'asd' => 'foo & bar | asd'
2005-11-21 20:27:57 +08:00
#define wchar2char wcstombs
Fix localization support for multibyte encoding and C locale. Slightly reworked patch from Tatsuo Ishii
2007-01-15 23:16:11 +08:00
Re-run pgindent, fixing a problem where comment lines after a blank comment line where output as too long, and update typedefs for /lib directory. Also fix case where identifiers were used as variable names in the backend, but as typedefs in ecpg (favor the backend for indenting). Backpatch to 8.1.X.
2005-11-23 02:17:34 +08:00
#endif /* WIN32 */
Improve support of multibyte encoding: - tsvector_(in|out) - tsquery_(in|out) - to_tsvector - to_tsquery, plainto_tsquery - 'simple' dictionary
2005-12-12 19:10:12 +08:00
pgindent run for 8.2.
2006-10-04 08:30:14 +08:00
#define t_isdigit(x) ( pg_mblen(x)==1 && isdigit( TOUCHAR(x) ) )
#define t_isspace(x) ( pg_mblen(x)==1 && isspace( TOUCHAR(x) ) )
extern int _t_isalpha(const char *ptr);
#define t_isalpha(x) ( (pg_mblen(x)==1) ? isalpha( TOUCHAR(x) ) : _t_isalpha(x) )
extern int _t_isprint(const char *ptr);
#define t_isprint(x) ( (pg_mblen(x)==1) ? isprint( TOUCHAR(x) ) : _t_isprint(x) )
Improve support of multibyte encoding: - tsvector_(in|out) - tsquery_(in|out) - to_tsvector - to_tsquery, plainto_tsquery - 'simple' dictionary
2005-12-12 19:10:12 +08:00
/*
pgindent run for 8.2.
2006-10-04 08:30:14 +08:00
* t_iseq() should be called only for ASCII symbols
Improve support of multibyte encoding: - tsvector_(in|out) - tsquery_(in|out) - to_tsvector - to_tsquery, plainto_tsquery - 'simple' dictionary
2005-12-12 19:10:12 +08:00
*/
pgindent run for 8.2.
2006-10-04 08:30:14 +08:00
#define t_iseq(x,c) ( (pg_mblen(x)==1) ? ( TOUCHAR(x) == ((unsigned char)(c)) ) : false )
Improve support of multibyte encoding: - tsvector_(in|out) - tsquery_(in|out) - to_tsvector - to_tsquery, plainto_tsquery - 'simple' dictionary
2005-12-12 19:10:12 +08:00
Fix localization support for multibyte encoding and C locale. Slightly reworked patch from Tatsuo Ishii
2007-01-15 23:16:11 +08:00
#define COPYCHAR(d,s) do { \
int lll = pg_mblen( s ); \
\
while( lll-- ) \
Multibyte encodings support for ISpell dictionary
2005-12-21 21:05:49 +08:00
TOUCHAR((d)+lll) = TOUCHAR((s)+lll); \
Improve support of multibyte encoding: - tsvector_(in|out) - tsquery_(in|out) - to_tsvector - to_tsquery, plainto_tsquery - 'simple' dictionary
2005-12-12 19:10:12 +08:00
} while(0)
pgindent run for 8.2.
2006-10-04 08:30:14 +08:00
#else /* not def TS_USE_WIDE */
Improve support of multibyte encoding: - tsvector_(in|out) - tsquery_(in|out) - to_tsvector - to_tsquery, plainto_tsquery - 'simple' dictionary
2005-12-12 19:10:12 +08:00
pgindent run for 8.2.
2006-10-04 08:30:14 +08:00
#define t_isdigit(x) isdigit( TOUCHAR(x) )
#define t_isspace(x) isspace( TOUCHAR(x) )
#define t_isalpha(x) isalpha( TOUCHAR(x) )
#define t_isprint(x) isprint( TOUCHAR(x) )
#define t_iseq(x,c) ( TOUCHAR(x) == ((unsigned char)(c)) )
Improve support of multibyte encoding: - tsvector_(in|out) - tsquery_(in|out) - to_tsvector - to_tsquery, plainto_tsquery - 'simple' dictionary
2005-12-12 19:10:12 +08:00
pgindent run for 8.2.
2006-10-04 08:30:14 +08:00
#define COPYCHAR(d,s) TOUCHAR(d) = TOUCHAR(s)
Improve support of multibyte encoding: - tsvector_(in|out) - tsquery_(in|out) - to_tsvector - to_tsquery, plainto_tsquery - 'simple' dictionary
2005-12-12 19:10:12 +08:00
#endif
pgindent run for 8.2.
2006-10-04 08:30:14 +08:00
char *lowerstr(char *str);
Text parser rewritten: - supports multibyte encodings - more strict rules for lexemes - flex isn't used Add: - tsquery plainto_tsquery(text) Function makes tsquery from plain text. - &&, ||, !! operation for tsquery for combining tsquery from it's parts: 'foo & bar' || 'asd' => 'foo & bar | asd'
2005-11-21 20:27:57 +08:00
Re-run pgindent, fixing a problem where comment lines after a blank comment line where output as too long, and update typedefs for /lib directory. Also fix case where identifiers were used as variable names in the backend, but as typedefs in ecpg (favor the backend for indenting). Backpatch to 8.1.X.
2005-11-23 02:17:34 +08:00
#endif /* __TSLOCALE_H__ */
Reference in New Issue Copy Permalink