/**
* Function to check if a filetype is allowed
* @see HTML_QuickForm_Rule
* @param array $file Uploaded file
* @param array $extensions Allowed extensions
* @return boolean True if filetype is allowed
*/
function validate($file, $extensions = array())
{
$parts = explode('.', $file['name']);
if (count($parts) < 2) {
return false;
}
$ext = $parts[count($parts) - 1];
return api_in_array_nocase($ext, $extensions);
}
function get_directory_content($path)
{
$exceptions = array('.', '..', 'CVS', '.htaccess', '.svn', '_svn', 'index.html');
$result = array();
$path = realpath($path);
if (!is_dir($path)) {
return $result;
}
if (!($handle = opendir($path))) {
return $result;
}
while (($dir_entry = readdir($handle)) !== false) {
if (api_in_array_nocase($dir_entry, $exceptions)) {
continue;
}
$dir_entry_full_path = $path . '/' . $dir_entry;
if (filetype($dir_entry_full_path) != 'dir') {
$result[] = str_replace("\\", '/', $dir_entry_full_path);
}
}
closedir($handle);
asort($result);
return $result;
}
/**
*
* The value $max_delta = 80000 is good enough for speed and detection accuracy.
* If you set the value of $max_delta too low, no language will be recognized.
* $max_delta = 400 * 350 = 140000 is the best detection with lowest speed.
*/
function &_api_compare_n_grams(&$n_grams, $encoding, $max_delta = LANGUAGE_DETECT_MAX_DELTA)
{
static $language_profiles;
if (!isset($language_profiles)) {
// Reading the language profile files from the internationalization database.
$exceptions = array('.', '..', 'CVS', '.htaccess', '.svn', '_svn', 'index.html');
$path = str_replace("\\", '/', dirname(__FILE__) . '/internationalization_database/language_detection/language_profiles/');
$non_utf8_encodings =& _api_non_utf8_encodings();
if (is_dir($path)) {
if ($handle = @opendir($path)) {
while (($dir_entry = @readdir($handle)) !== false) {
if (api_in_array_nocase($dir_entry, $exceptions)) {
continue;
}
if (strpos($dir_entry, '.txt') === false) {
continue;
}
$dir_entry_full_path = $path . '/' . $dir_entry;
if (@filetype($dir_entry_full_path) != 'dir') {
if (false !== ($data = @file_get_contents($dir_entry_full_path))) {
$language = basename($dir_entry_full_path, '.txt');
$encodings = array('UTF-8');
if (!empty($non_utf8_encodings[$language])) {
$encodings = array_merge($encodings, $non_utf8_encodings[$language]);
}
foreach ($encodings as $enc) {
$data_enc = api_utf8_decode($data, $enc);
if (empty($data_enc)) {
continue;
}
$key = $language . ':' . $enc;
$language_profiles[$key]['data'] = array_flip(explode("\n", $data_enc));
$language_profiles[$key]['language'] = $language;
$language_profiles[$key]['encoding'] = $enc;
}
}
}
}
}
}
@closedir($handle);
ksort($language_profiles);
}
if (!is_array($n_grams) || empty($n_grams)) {
return array();
}
// Comparison between the input n-grams and the lanuage profiles.
foreach ($language_profiles as $key => &$language_profile) {
if (!api_is_language_supported($language_profile['language']) || !api_equal_encodings($encoding, $language_profile['encoding'])) {
continue;
}
$delta = 0;
// This is a summary measurment for matching between the input text and the current language profile.
// Searching each n-gram from the input text into the language profile.
foreach ($n_grams as $rank => &$n_gram) {
if (isset($language_profile['data'][$n_gram])) {
// The n-gram has been found, the difference between places in both
// arrays is calculated (so called delta-points are adopted for
// measuring distances between n-gram ranks.
$delta += abs($rank - $language_profile['data'][$n_gram]);
} else {
// The n-gram has not been found in the profile. We add then
// a large enough "distance" in delta-points.
$delta += 400;
}
// Abort: This language already differs too much.
if ($delta > $max_delta) {
break;
}
}
// Include only non-aborted languages in result array.
if ($delta < $max_delta - 400) {
$result[$key] = $delta;
}
}
if (!isset($result)) {
return array();
}
asort($result);
return $result;
}
/**
* Checks if a value exists in an array, a case insensitive version of in_array() function with extended multibyte support.
* @param mixed $needle The searched value. If needle is a string, the comparison is done in a case-insensitive manner.
* @param array $haystack The array.
* @param bool $strict (optional) If is set to TRUE then the function will also check the types of the $needle in the $haystack. The default value if FALSE.
* @param string $encoding (optional) The used internally by this function character encoding. If it is omitted, the platform character set will be used by default.
* @return bool Returns TRUE if $needle is found in the array, FALSE otherwise.
* @link http://php.net/manual/en/function.in-array.php
*/
function api_in_array_nocase($needle, $haystack, $strict = false, $encoding = null)
{
if (is_array($needle)) {
foreach ($needle as $item) {
if (api_in_array_nocase($item, $haystack, $strict, $encoding)) {
return true;
}
}
return false;
}
if (!is_string($needle)) {
return in_array($needle, $haystack, $strict);
}
$needle = api_strtolower($needle, $encoding);
if (!is_array($haystack)) {
return false;
}
foreach ($haystack as $item) {
if ($strict && !is_string($item)) {
continue;
}
if (api_strtolower($item, $encoding) == $needle) {
return true;
}
}
return false;
}
