/**
* Tries to determine the language of the document by looking at the
* $sample_text and $url provided
* the language
* @param string $sample_text sample text to try guess the language from
* @param string $url url of web-page as a fallback look at the country
* to figure out language
*
* @return string language tag for guessed language
*/
static function calculateLang($sample_text = NULL, $url = NULL)
{
if ($url != NULL) {
$lang = UrlParser::getLang($url);
if ($lang != NULL) {
return $lang;
}
}
if ($sample_text != NULL) {
$words = mb_split("[[:space:]]|" . PUNCT, $sample_text);
$num_words = count($words);
$ascii_count = 0;
foreach ($words as $word) {
if (strlen($word) == mb_strlen($word)) {
$ascii_count++;
}
}
// crude, but let's guess ASCII == english
if ($ascii_count / $num_words > EN_RATIO) {
$lang = 'en';
} else {
$lang = NULL;
}
} else {
$lang = NULL;
}
return $lang;
}
