From 91bb5faaff4ff41771606c58f608afd76263b8c7 Mon Sep 17 00:00:00 2001
From: Andreas Gohr <andi@splitbrain.org>
Date: Sun, 9 Oct 2005 14:48:33 +0200
Subject: [PATCH] ignore regexp failures when handling asian chars
The new handling of asian chars as single words needs a recent PCRE library
(PHP 4.3.10 is known work). If this support isn't available the regexp
compilation will fail. This patch adds a workaround - this means the search
will not work as expected with asian words on older PHP versions.
darcs-hash:20051009124833-7ad00-1319829be5cb73246e13eb65e4c950d43c6ce5bf.gz
---
inc/fulltext.php | 2 +-
inc/indexer.php | 22 ++++++++++++----------
2 files changed, 13 insertions(+), 11 deletions(-)
diff --git a/inc/fulltext.php b/inc/fulltext.php
index 89fa5b259..4d4b8138c 100644
--- a/inc/fulltext.php
+++ b/inc/fulltext.php
@@ -265,7 +265,7 @@ function ft_queryParser($query){
if(count($token)) $q['not'] = array_merge($q['not'],$token);
}else{
// asian "words" need to be searched as phrases
- if(preg_match_all('/('.IDX_ASIAN.'+)/u',$w,$matches)){
+ if(@preg_match_all('/('.IDX_ASIAN.'+)/u',$w,$matches)){
$q['phrases'] = array_merge($q['phrases'],$matches[1]);
}
diff --git a/inc/indexer.php b/inc/indexer.php
index a8511b1ee..22bd8566b 100644
--- a/inc/indexer.php
+++ b/inc/indexer.php
@@ -17,12 +17,12 @@
// Ranges taken from http://en.wikipedia.org/wiki/Unicode_block
// I'm no language expert. If you think some ranges are wrongly chosen or
// a range is missing, please contact me
-define(IDX_ASIAN,'['.
- '\x{0E00}-\x{0E7F}'. // Thai
- '\x{2E80}-\x{D7AF}'. // CJK -> Hangul
- '\x{F900}-\x{FAFF}'. // CJK Compatibility Ideographs
- '\x{FE30}-\x{FE4F}'. // CJK Compatibility Forms
- ']');
+define('IDX_ASIAN','['.
+ '\x{0E00}-\x{0E7F}'. // Thai
+ '\x{2E80}-\x{D7AF}'. // CJK -> Hangul
+ '\x{F900}-\x{FAFF}'. // CJK Compatibility Ideographs
+ '\x{FE30}-\x{FE4F}'. // CJK Compatibility Forms
+ ']');
/**
@@ -52,8 +52,9 @@ function idx_getPageWords($page){
foreach ($tokens as $word => $count) {
// simple filter to restrict use of utf8_stripspecials
if (preg_match('/[^0-9A-Za-z]/u', $word)) {
- // handle asian chars as single words
- $word = preg_replace('/('.IDX_ASIAN.')/u','\1 ',$word);
+ // handle asian chars as single words (may fail on older PHP version)
+ $asia = @preg_replace('/('.IDX_ASIAN.')/u','\1 ',$word);
+ if(!is_null($asia)) $word = $asia; //recover from regexp failure
$arr = explode(' ', utf8_stripspecials($word,' ','._\-:'));
$arr = array_count_values($arr);
@@ -326,8 +327,9 @@ function idx_tokenizer($string,&$stopwords){
$words = array();
if(preg_match('/[^0-9A-Za-z]/u', $string)){
- #handle asian chars as single words
- $string = preg_replace('/('.IDX_ASIAN.')/u','\1 ',$string);
+ // handle asian chars as single words (may fail on older PHP version)
+ $asia = @preg_replace('/('.IDX_ASIAN.')/u','\1 ',$string);
+ if(!is_null($asia)) $string = $asia; //recover from regexp failure
$arr = explode(' ', utf8_stripspecials($string,' ','._\-:'));
foreach ($arr as $w) {
--
GitLab