From e6258e07cc6b983f0280aae21c55808fb8597239 Mon Sep 17 00:00:00 2001
From: Andreas Gohr <andi@splitbrain.org>
Date: Sun, 11 Sep 2005 23:08:01 +0200
Subject: fixed UTF-8 handling in Acronyms #478

darcs-hash:20050911210801-7ad00-f571ad2eeb07ce2e62ae55775b49c0e9be523166.gz
---
 inc/parser/parser.php | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

(limited to 'inc/parser')

diff --git a/inc/parser/parser.php b/inc/parser/parser.php
index 991031a30..22f836709 100644
--- a/inc/parser/parser.php
+++ b/inc/parser/parser.php
@@ -623,11 +623,9 @@ class Doku_Parser_Mode_acronym extends Doku_Parser_Mode {
     }
     
     function preConnect() {
-        $sep = '';
-        foreach ( $this->acronyms as $acronym ) {
-            $this->pattern .= $sep.'(?<=\b)'.Doku_Lexer_Escape($acronym).'(?=\b)';
-            $sep = '|';
-        }
+        $bound = '[\x00-\x2f\x3a-\x3f\x5b-\x7f]';
+        $acronyms = array_map('Doku_Lexer_Escape',$this->acronyms);
+        $this->pattern = '(?<='.$bound.')(?:'.join('|',$acronyms).')(?='.$bound.')';
     }
     
     function connectTo($mode) {
-- 
cgit v1.2.3