utf8proc

diff pgsql/utf8proc_pgsql.c @ 2:aaad485d5335
Version 0.3

- changed normalization from NFC to NFKC for postgresql unifold function
- added support to mark the beginning of a grapheme cluster with 0xFF (option: CHARBOUND)
- added the ruby method String#chars, which is returning an array of UTF-8 encoded grapheme clusters
- added NLF2LF transformation in postgresql unifold function
- added the DECOMPOSE option, if you neither use COMPOSE or DECOMPOSE, no normalization will be performed (different from previous versions)
- using integer constants rather than C-strings for character properties
- fixed (hopefully) a problem with the ruby library on Mac OS X, which occured when compiler optimization was switched on
author: jbe
date: Fri Aug 04 12:00:00 2006 +0200 (2006-08-04)
parents: 61a89ecc2fb9
children: 4ee0d5f54af1
     1.1 --- a/pgsql/utf8proc_pgsql.c	Tue Jun 20 12:00:00 2006 +0200
     1.2 +++ b/pgsql/utf8proc_pgsql.c	Fri Aug 04 12:00:00 2006 +0200
     1.3 @@ -33,8 +33,8 @@
     1.4  
     1.5  /*
     1.6   *  File name:    pgsql/utf8proc_pgsql.c
     1.7 - *  Version:      0.2
     1.8 - *  Last changed: 2006-06-05
     1.9 + *  Version:      0.3
    1.10 + *  Last changed: 2006-08-04
    1.11   *
    1.12   *  Description:
    1.13   *  PostgreSQL extension to provide a function 'unifold', which can be used
    1.14 @@ -51,8 +51,9 @@
    1.15  #include <unistd.h>
    1.16  #include <utils/builtins.h>
    1.17  
    1.18 -#define UTF8PROC_PGSQL_OPTS ( UTF8PROC_REJECTNA | \
    1.19 -  UTF8PROC_COMPOSE | UTF8PROC_IGNORE | UTF8PROC_STRIPCC | UTF8PROC_CASEFOLD)
    1.20 +#define UTF8PROC_PGSQL_OPTS ( UTF8PROC_REJECTNA | UTF8PROC_COMPAT | \
    1.21 +  UTF8PROC_COMPOSE | UTF8PROC_STABLE | UTF8PROC_IGNORE | UTF8PROC_STRIPCC | \
    1.22 +  UTF8PROC_NLF2LF | UTF8PROC_CASEFOLD )
    1.23  
    1.24  PG_FUNCTION_INFO_V1(utf8proc_pgsql_unifold);
    1.25  Datum utf8proc_pgsql_unifold(PG_FUNCTION_ARGS) {
author	jbe
date	Fri Aug 04 12:00:00 2006 +0200 (2006-08-04)
parents	61a89ecc2fb9
children	4ee0d5f54af1