diff --git a/inc/fulltext.php b/inc/fulltext.php index 89fa5b25917ab613d31e0bf32455f9c8d3fc1070..4d4b8138c5e46a4986edf33245784b88391ed96b 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'],$matches[1]); } diff --git a/inc/indexer.php b/inc/indexer.php index a8511b1ee113ac765d0ef14b9e27c2144b8f1116..22bd8566bbc6192b9c8745e93812594f0f442cef 100644 --- a/inc/indexer.php +++ b/inc/indexer.php @@ -17,12 +17,12 @@ // Ranges taken from http://en.wikipedia.org/wiki/Unicode_block // I'm no language expert. If you think some ranges are wrongly chosen or // a range is missing, please contact me -define(IDX_ASIAN,'['. - '\x{0E00}-\x{0E7F}'. // Thai - '\x{2E80}-\x{D7AF}'. // CJK -> Hangul - '\x{F900}-\x{FAFF}'. // CJK Compatibility Ideographs - '\x{FE30}-\x{FE4F}'. // CJK Compatibility Forms - ']'); +define('IDX_ASIAN','['. + '\x{0E00}-\x{0E7F}'. // Thai + '\x{2E80}-\x{D7AF}'. // CJK -> Hangul + '\x{F900}-\x{FAFF}'. // CJK Compatibility Ideographs + '\x{FE30}-\x{FE4F}'. // CJK Compatibility Forms + ']'); /** @@ -52,8 +52,9 @@ function idx_getPageWords($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) {