Re: Simplify formatting.c

Bruce Momjian <[email protected]>
Newsgroups gmane.comp.db.postgresql.devel.patches
Message-ID <[email protected]> 
Alvaro Herrera wrote:
> Bruce Momjian wrote:
> 
> > I moved str_initcap() over into oracle_compat.c and then had initcap()
> > convert to/from TEXT to call it.  The code is a little weird because
> > str_initcap() needs to convert to text to use texttowcs(), so in
> > multibyte encodings initcap converts the string to text, then to char,
> > then to text to call texttowcs().  I didn't see a cleaner way to do
> > this.
> 
> Why not use wchar2char?  It seems there's room for extra cleanup here.
> 
> Also, the prototype of str_initcap in builtins.h looks out of place.

I talked to Alvaro on IM, and there is certainly much more cleanup to do
in this area. I will work from the bottom up.  First, is moving the
USE_WIDE_UPPER_LOWER define to c.h, and removing TS_USE_WIDE and using
USE_WIDE_UPPER_LOWER instead.  Patch attached and applied.

-- 
  Bruce Momjian  <[email protected]>        http://momjian.us
  EnterpriseDB                             http://enterprisedb.com

  + If your life is a hard drive, Christ can be your backup. +


-- 
Sent via pgsql-patches mailing list ([email protected])
To make changes to your subscription:
http://www.postgresql.org/mailpref/pgsql-patches
/rtmp/diff (text/x-diff, 9.7 KB) 
Index: src/backend/tsearch/regis.c
===================================================================
RCS file: /cvsroot/pgsql/src/backend/tsearch/regis.c,v
retrieving revision 1.4
diff -c -c -r1.4 regis.c
*** src/backend/tsearch/regis.c	21 Jan 2008 02:46:10 -0000	1.4
--- src/backend/tsearch/regis.c	17 Jun 2008 16:06:54 -0000
***************
*** 178,184 ****
  	r->node = NULL;
  }
  
! #ifdef TS_USE_WIDE
  static bool
  mb_strchr(char *str, char *c)
  {
--- 178,184 ----
  	r->node = NULL;
  }
  
! #ifdef USE_WIDE_UPPER_LOWER
  static bool
  mb_strchr(char *str, char *c)
  {
Index: src/backend/tsearch/ts_locale.c
===================================================================
RCS file: /cvsroot/pgsql/src/backend/tsearch/ts_locale.c,v
retrieving revision 1.7
diff -c -c -r1.7 ts_locale.c
*** src/backend/tsearch/ts_locale.c	1 Jan 2008 19:45:52 -0000	1.7
--- src/backend/tsearch/ts_locale.c	17 Jun 2008 16:06:54 -0000
***************
*** 17,23 ****
  #include "tsearch/ts_public.h"
  
  
! #ifdef TS_USE_WIDE
  
  /*
   * wchar2char --- convert wide characters to multibyte format
--- 17,23 ----
  #include "tsearch/ts_public.h"
  
  
! #ifdef USE_WIDE_UPPER_LOWER
  
  /*
   * wchar2char --- convert wide characters to multibyte format
***************
*** 190,196 ****
  
  	return iswprint((wint_t) character[0]);
  }
! #endif   /* TS_USE_WIDE */
  
  
  /*
--- 190,196 ----
  
  	return iswprint((wint_t) character[0]);
  }
! #endif   /* USE_WIDE_UPPER_LOWER */
  
  
  /*
***************
*** 260,266 ****
  	if (len == 0)
  		return pstrdup("");
  
! #ifdef TS_USE_WIDE
  
  	/*
  	 * Use wide char code only when max encoding length > 1 and ctype != C.
--- 260,266 ----
  	if (len == 0)
  		return pstrdup("");
  
! #ifdef USE_WIDE_UPPER_LOWER
  
  	/*
  	 * Use wide char code only when max encoding length > 1 and ctype != C.
***************
*** 307,313 ****
  		Assert(wlen < len);
  	}
  	else
! #endif   /* TS_USE_WIDE */
  	{
  		const char *ptr = str;
  		char	   *outptr;
--- 307,313 ----
  		Assert(wlen < len);
  	}
  	else
! #endif   /* USE_WIDE_UPPER_LOWER */
  	{
  		const char *ptr = str;
  		char	   *outptr;
Index: src/backend/tsearch/wparser_def.c
===================================================================
RCS file: /cvsroot/pgsql/src/backend/tsearch/wparser_def.c,v
retrieving revision 1.14
diff -c -c -r1.14 wparser_def.c
*** src/backend/tsearch/wparser_def.c	1 Jan 2008 19:45:52 -0000	1.14
--- src/backend/tsearch/wparser_def.c	17 Jun 2008 16:06:54 -0000
***************
*** 238,244 ****
  	/* string and position information */
  	char	   *str;			/* multibyte string */
  	int			lenstr;			/* length of mbstring */
! #ifdef TS_USE_WIDE
  	wchar_t    *wstr;			/* wide character string */
  	int			lenwstr;		/* length of wsting */
  #endif
--- 238,244 ----
  	/* string and position information */
  	char	   *str;			/* multibyte string */
  	int			lenstr;			/* length of mbstring */
! #ifdef USE_WIDE_UPPER_LOWER
  	wchar_t    *wstr;			/* wide character string */
  	int			lenwstr;		/* length of wsting */
  #endif
***************
*** 291,297 ****
  	prs->str = str;
  	prs->lenstr = len;
  
! #ifdef TS_USE_WIDE
  
  	/*
  	 * Use wide char code only when max encoding length > 1.
--- 291,297 ----
  	prs->str = str;
  	prs->lenstr = len;
  
! #ifdef USE_WIDE_UPPER_LOWER
  
  	/*
  	 * Use wide char code only when max encoding length > 1.
***************
*** 328,334 ****
  		prs->state = ptr;
  	}
  
! #ifdef TS_USE_WIDE
  	if (prs->wstr)
  		pfree(prs->wstr);
  #endif
--- 328,334 ----
  		prs->state = ptr;
  	}
  
! #ifdef USE_WIDE_UPPER_LOWER
  	if (prs->wstr)
  		pfree(prs->wstr);
  #endif
***************
*** 344,350 ****
   * often are used for Asian languages
   */
  
! #ifdef TS_USE_WIDE
  
  #define p_iswhat(type)														\
  static int																	\
--- 344,350 ----
   * often are used for Asian languages
   */
  
! #ifdef USE_WIDE_UPPER_LOWER
  
  #define p_iswhat(type)														\
  static int																	\
***************
*** 439,445 ****
  	Assert(prs->state);
  	return ((prs->state->charlen == 1 && *(prs->str + prs->state->posbyte) == c)) ? 1 : 0;
  }
! #else							/* TS_USE_WIDE */
  
  #define p_iswhat(type)														\
  static int																	\
--- 439,445 ----
  	Assert(prs->state);
  	return ((prs->state->charlen == 1 && *(prs->str + prs->state->posbyte) == c)) ? 1 : 0;
  }
! #else							/* USE_WIDE_UPPER_LOWER */
  
  #define p_iswhat(type)														\
  static int																	\
***************
*** 463,469 ****
  
  p_iswhat(alnum)
  p_iswhat(alpha)
! #endif   /* TS_USE_WIDE */
  
  p_iswhat(digit)
  p_iswhat(lower)
--- 463,469 ----
  
  p_iswhat(alnum)
  p_iswhat(alpha)
! #endif   /* USE_WIDE_UPPER_LOWER */
  
  p_iswhat(digit)
  p_iswhat(lower)
Index: src/backend/utils/adt/formatting.c
===================================================================
RCS file: /cvsroot/pgsql/src/backend/utils/adt/formatting.c,v
retrieving revision 1.141
diff -c -c -r1.141 formatting.c
*** src/backend/utils/adt/formatting.c	20 May 2008 01:41:02 -0000	1.141
--- src/backend/utils/adt/formatting.c	17 Jun 2008 16:06:54 -0000
***************
*** 948,955 ****
  static NUMCacheEntry *NUM_cache_getnew(char *str);
  static void NUM_cache_remove(NUMCacheEntry *ent);
  
! #if defined(HAVE_WCSTOMBS) && defined(HAVE_TOWLOWER)
! #define USE_WIDE_UPPER_LOWER
  /* externs are in oracle_compat.c */
  extern char *wstring_upper(char *str);
  extern char *wstring_lower(char *str);
--- 948,954 ----
  static NUMCacheEntry *NUM_cache_getnew(char *str);
  static void NUM_cache_remove(NUMCacheEntry *ent);
  
! #ifdef USE_WIDE_UPPER_LOWER
  /* externs are in oracle_compat.c */
  extern char *wstring_upper(char *str);
  extern char *wstring_lower(char *str);
Index: src/backend/utils/adt/oracle_compat.c
===================================================================
RCS file: /cvsroot/pgsql/src/backend/utils/adt/oracle_compat.c,v
retrieving revision 1.79
diff -c -c -r1.79 oracle_compat.c
*** src/backend/utils/adt/oracle_compat.c	19 May 2008 18:08:16 -0000	1.79
--- src/backend/utils/adt/oracle_compat.c	17 Jun 2008 16:06:54 -0000
***************
*** 40,51 ****
   * functions, which of course will not work as desired in multibyte character
   * sets.  Note that in either case we are effectively assuming that the
   * database character encoding matches the encoding implied by LC_CTYPE.
-  *
-  * We assume if we have these two functions, we have their friends too, and
-  * can use the wide-character method.
   */
! #if defined(HAVE_WCSTOMBS) && defined(HAVE_TOWLOWER)
! #define USE_WIDE_UPPER_LOWER
  char	   *wstring_lower(char *str);
  char	   *wstring_upper(char *str);
  wchar_t	   *texttowcs(const text *txt);
--- 40,47 ----
   * functions, which of course will not work as desired in multibyte character
   * sets.  Note that in either case we are effectively assuming that the
   * database character encoding matches the encoding implied by LC_CTYPE.
   */
! #ifdef USE_WIDE_UPPER_LOWER
  char	   *wstring_lower(char *str);
  char	   *wstring_upper(char *str);
  wchar_t	   *texttowcs(const text *txt);
Index: src/include/c.h
===================================================================
RCS file: /cvsroot/pgsql/src/include/c.h,v
retrieving revision 1.226
diff -c -c -r1.226 c.h
*** src/include/c.h	21 Apr 2008 00:26:46 -0000	1.226
--- src/include/c.h	17 Jun 2008 16:06:55 -0000
***************
*** 813,818 ****
--- 813,826 ----
  #define HAVE_STRTOULL 1
  #endif
  
+ /*
+  * We assume if we have these two functions, we have their friends too, and
+  * can use the wide-character functions.
+  */
+ #if defined(HAVE_WCSTOMBS) && defined(HAVE_TOWLOWER)
+ #define USE_WIDE_UPPER_LOWER
+ #endif
+    
  /* EXEC_BACKEND defines */
  #ifdef EXEC_BACKEND
  #define NON_EXEC_STATIC
Index: src/include/tsearch/ts_locale.h
===================================================================
RCS file: /cvsroot/pgsql/src/include/tsearch/ts_locale.h,v
retrieving revision 1.5
diff -c -c -r1.5 ts_locale.h
*** src/include/tsearch/ts_locale.h	1 Jan 2008 19:45:59 -0000	1.5
--- src/include/tsearch/ts_locale.h	17 Jun 2008 16:06:55 -0000
***************
*** 29,41 ****
  #include <wctype.h>
  #endif
  
- #if defined(HAVE_WCSTOMBS) && defined(HAVE_TOWLOWER)
- #define TS_USE_WIDE
- #endif
- 
  #define TOUCHAR(x)	(*((const unsigned char *) (x)))
  
! #ifdef TS_USE_WIDE
  
  extern size_t wchar2char(char *to, const wchar_t *from, size_t tolen);
  extern size_t char2wchar(wchar_t *to, size_t tolen, const char *from, size_t fromlen);
--- 29,37 ----
  #include <wctype.h>
  #endif
  
  #define TOUCHAR(x)	(*((const unsigned char *) (x)))
  
! #ifdef USE_WIDE_UPPER_LOWER
  
  extern size_t wchar2char(char *to, const wchar_t *from, size_t tolen);
  extern size_t char2wchar(wchar_t *to, size_t tolen, const char *from, size_t fromlen);
***************
*** 49,55 ****
  #define t_iseq(x,c)		(TOUCHAR(x) == (unsigned char) (c))
  
  #define COPYCHAR(d,s)	memcpy(d, s, pg_mblen(s))
! #else							/* not TS_USE_WIDE */
  
  #define t_isdigit(x)	isdigit(TOUCHAR(x))
  #define t_isspace(x)	isspace(TOUCHAR(x))
--- 45,51 ----
  #define t_iseq(x,c)		(TOUCHAR(x) == (unsigned char) (c))
  
  #define COPYCHAR(d,s)	memcpy(d, s, pg_mblen(s))
! #else							/* not USE_WIDE_UPPER_LOWER */
  
  #define t_isdigit(x)	isdigit(TOUCHAR(x))
  #define t_isspace(x)	isspace(TOUCHAR(x))
***************
*** 58,64 ****
  #define t_iseq(x,c)		(TOUCHAR(x) == (unsigned char) (c))
  
  #define COPYCHAR(d,s)	(*((unsigned char *) (d)) = TOUCHAR(s))
! #endif   /* TS_USE_WIDE */
  
  extern char *lowerstr(const char *str);
  extern char *lowerstr_with_len(const char *str, int len);
--- 54,60 ----
  #define t_iseq(x,c)		(TOUCHAR(x) == (unsigned char) (c))
  
  #define COPYCHAR(d,s)	(*((unsigned char *) (d)) = TOUCHAR(s))
! #endif   /* USE_WIDE_UPPER_LOWER */
  
  extern char *lowerstr(const char *str);
  extern char *lowerstr_with_len(const char *str, int len);
lmpx.com only provides a reader for public news (NNTP) servers. It is not affiliated with the servers or forums shown here and is not responsible for the content of articles, which is written by their respective authors.