Hi, I'm writing a search engine for my site and need to extract chunks of text with given keyword and few words around for the search result list. I ended with something like that:
/**
* This function return part of the original text with
* the searched term and few words around the searched term
* @param string $text Original text
* @param string $word Searched term
* @param int $maxChunks Number of chunks returned
* @param int $wordsAround Number of words before and after searched term
*/
public static function searchTerm($text, $word=null, $maxChunks=3, $wordsAround=3) {
$word = trim($word);
if(empty($word)) {
return NULL;
}
$words = explode(' ', $word); // extract single words from searched phrase
$text = strip_tags($text); // clean up the text
$whack = array(); // chunk buffer
$cycle = 0; // successful matches counter
foreach($words as $word) {
$match = array();
// there are named parameters 'pre', 'term' and 'pos'
if(preg_match("/(?P\w+){0,$wordsAround} (?P$word) (?P\w+){0,$wordsAround}/", $text, $match)) {
$cycle++;
$whack[] = $match['pre'] . ' ' . $word . ' ' . $match['pos'];
if($cycle == $maxChunks) break;
}
}
return implode(' | ', $whack);
}