mirror of
				https://github.com/postgres/postgres.git
				synced 2025-11-03 09:13:20 +03:00 
			
		
		
		
	Check whether the datctype is C to determine whether t_isspace() and related functions use isspace() or iswspace(). Previously, t_isspace() checked whether the database default collation was C; which is incorrect when the default collation uses the ICU provider. Discussion: https://postgr.es/m/79e4354d9eccfdb00483146a6b9f6295202e7890.camel@j-davis.com Reviewed-by: Peter Eisentraut Backpatch-through: 15
		
			
				
	
	
		
			35 lines
		
	
	
		
			1.1 KiB
		
	
	
	
		
			SQL
		
	
	
	
	
	
			
		
		
	
	
			35 lines
		
	
	
		
			1.1 KiB
		
	
	
	
		
			SQL
		
	
	
	
	
	
CREATE EXTENSION unaccent;
 | 
						||
 | 
						||
-- must have a UTF8 database
 | 
						||
SELECT getdatabaseencoding();
 | 
						||
 | 
						||
SET client_encoding TO 'UTF8';
 | 
						||
 | 
						||
SELECT unaccent('foobar');
 | 
						||
SELECT unaccent('ёлка');
 | 
						||
SELECT unaccent('ЁЖИК');
 | 
						||
SELECT unaccent('˃˖˗˜');
 | 
						||
SELECT unaccent('À');  -- Remove combining diacritical 0x0300
 | 
						||
SELECT unaccent('℃℉'); -- degree signs
 | 
						||
SELECT unaccent('℗'); -- sound recording copyright
 | 
						||
 | 
						||
SELECT unaccent('unaccent', 'foobar');
 | 
						||
SELECT unaccent('unaccent', 'ёлка');
 | 
						||
SELECT unaccent('unaccent', 'ЁЖИК');
 | 
						||
SELECT unaccent('unaccent', '˃˖˗˜');
 | 
						||
SELECT unaccent('unaccent', 'À');
 | 
						||
SELECT unaccent('unaccent', '℃℉');
 | 
						||
SELECT unaccent('unaccent', '℗');
 | 
						||
 | 
						||
SELECT ts_lexize('unaccent', 'foobar');
 | 
						||
SELECT ts_lexize('unaccent', 'ёлка');
 | 
						||
SELECT ts_lexize('unaccent', 'ЁЖИК');
 | 
						||
SELECT ts_lexize('unaccent', '˃˖˗˜');
 | 
						||
SELECT ts_lexize('unaccent', 'À');
 | 
						||
SELECT ts_lexize('unaccent', '℃℉');
 | 
						||
SELECT ts_lexize('unaccent', '℗');
 | 
						||
 | 
						||
-- Controversial case.  Black-Letter Capital H (U+210C) is translated by
 | 
						||
-- Latin-ASCII.xml as 'x', but it should be 'H'.
 | 
						||
SELECT unaccent('ℌ');
 |