]*?>(.*?)'si";
preg_match($title, $content, $matches);
if(isset($matches[1])) {
return $matches[1];
}
return "";
}
// Выбираем основу слова
function clean ($word)
{
return Stemmer::russian(strtolower($word));
}
function process ($base, $files)
{
$path = new Path($base);
// Список документов
foreach ($path->getContentRec($files) as $file) {
$content = file_get_contents ($file);
$text = stripText($content);
// $title = self::getTitle ($content);
$title = pathinfo($file, PATHINFO_BASENAME);
// echo $file, "\n";
// Список слов в документе
$list = tokenize($text);
foreach ($list as $word) {
$preword = self::clean($word);
if (isset($this->index[$preword])) {
$index = $this->index[$preword];
if ( ! in_array ($this->count, $index)) $this->index[$preword] [] = $this->count;
} else {
// Не записываем слова длинна которых меньше 2
if (strlen($preword) > 1) {
$this->index[$preword] = array ($this->count);
}
}
}
$this->text [] = array ($title, $path->relPath ($file), $text);
$this->count ++;
}
ksort($this->index);
}
/**
* Сохранение результата поиска
*/
function saveData ($file)
{
$file = fopen($file, "w");
// Количество слов и текстов
fwrite ($file, pack("SS", count($this->index), count($this->text)));
foreach ($this->index as $word => $value) {
$length = strlen($word);
array_unshift ($value, "SSa*S*", $length, count($value), $word);
fwrite($file, call_user_func_array ('pack', $value));
}
foreach ($this->text as $text) {
fwrite($file, pack("SSSa*a*a*",
strlen($text[0]), strlen($text[1]), strlen($text[2])
, $text[0], $text[1], $text[2]));
}
}
}