这是一个从字符串中提取常用词的函数。它需要三个参数;字符串、停用词数组和关键字计数。您必须使用将 txt 文件放入数组的 php 函数从 txt 文件中获取 stop_words
$stop_words = file('stop_words.txt', FILE_IGNORE_NEW_LINES | FILE_SKIP_EMPTY_LINES);
$this->extract_common_words($text, $stop_words)
您可以使用此文件stop_words.txt作为您的主要停用词文件,或创建您自己的文件。
function extract_common_words($string, $stop_words, $max_count = 5) {
$string = preg_replace('/ss+/i', '', $string);
$string = trim($string); // trim the string
$string = preg_replace('/[^a-zA-Z -]/', '', $string); // only take alphabet characters, but keep the spaces and dashes too…
$string = strtolower($string); // make it lowercase
preg_match_all('/\b.*?\b/i', $string, $match_words);
$match_words = $match_words[0];
foreach ( $match_words as $key => $item ) {
if ( $item == '' || in_array(strtolower($item), $stop_words) || strlen($item) <= 3 ) {
unset($match_words[$key]);
}
}
$word_count = str_word_count( implode(" ", $match_words) , 1);
$frequency = array_count_values($word_count);
arsort($frequency);
//arsort($word_count_arr);
$keywords = array_slice($frequency, 0, $max_count);
return $keywords;
}