public function utf8_to_ascii_test()
{
$this->assert_equal("Te glossa mou edosan ellenike", UTF8::transliterate_to_ascii("Τη γλώσσα μου έδωσαν ελληνική"));
$this->assert_equal("Na bierieghu pustynnykh voln", UTF8::transliterate_to_ascii("На берегу пустынных волн"));
$this->assert_equal("vepxis tqaosani shot`a rust`aveli", UTF8::transliterate_to_ascii("ვეპხის ტყაოსანი შოთა რუსთაველი"));
$this->assert_equal("WoNengTunXiaBoLiErBuShangShenTi", UTF8::transliterate_to_ascii("我能吞下玻璃而不伤身体"));
}
/**
* Replaces special/accented UTF-8 characters by ASCII-7 'equivalents'.
*
* @param string string to transliterate
* @param integer -1 lowercase only, +1 uppercase only, 0 both cases
* @return string
*/
public static function transliterate_to_ascii($str, $case = 0)
{
static $UTF8_SPECIAL_CHARS = NULL;
if ($UTF8_SPECIAL_CHARS === null) {
$UTF8_SPECIAL_CHARS = array('⁰' => '0', '₀' => '0', '¹' => '1', 'ˡ' => 'l', '₁' => '1', '²' => '2', '₂' => '2', '³' => '3', '₃' => '3', '⁴' => '4', '₄' => '4', '⁵' => '5', '₅' => '5', '⁶' => '6', '₆' => '6', '⁷' => '7', '₇' => '7', '⁸' => '8', '₈' => '8', '⁹' => '9', '₉' => '9', '¼' => '1/4', '½' => '1/2', '¾' => '3/4', '⅓' => '1/3', '⅔' => '2/3', '⅕' => '1/5', '⅖' => '2/5', '⅗' => '3/5', '⅘' => '4/5', '⅙' => '1/6', '⅚' => '5/6', '⅛' => '1/8', '⅜' => '3/8', '⅝' => '5/8', '⅞' => '7/8', '⅟' => '1/', '⁺' => '+', '₊' => '+', '⁻' => '-', '₋' => '-', '⁼' => '=', '₌' => '=', '⁽' => '(', '₍' => '(', '⁾' => ')', '₎' => ')', 'ª' => 'a', '@' => 'a', '€' => 'e', 'ⁿ' => 'n', '°' => 'o', 'º' => 'o', '¤' => 'o', 'ˣ' => 'x', 'ʸ' => 'y', '$' => 'S', '©' => '(c)', '℠' => 'SM', '℡' => 'TEL', '™' => 'TM', 'ä' => 'ae', 'Ä' => 'Ae', 'ö' => 'oe', 'Ö' => 'Oe', 'ü' => 'ue', 'Ü' => 'eE', 'å' => 'aa', 'Å' => 'Aa');
}
$str = str_replace(array_keys($UTF8_SPECIAL_CHARS), array_values($UTF8_SPECIAL_CHARS), $str);
return UTF8::transliterate_to_ascii($str, $case);
}
/**
* Converts a slug to value valid for a URL.
*
* We could validate it by setting a rule, but for the most part, who cares?
*
* @param mixed $value
* @return mixed
*/
public static function slug($value)
{
$value = UTF8::transliterate_to_ascii($value);
// Only allow slashes, dashes, and lowercase letters
$value = preg_replace('/[^a-z0-9-\\/]/', '-', strtolower($value));
// Strip multiple dashes
$value = preg_replace('/-{2,}/', '-', $value);
// Trim an ending or starting dashes
$value = trim($value, '-');
return $value;
}
public static function title($title, $separator = '-', $ascii_only = FALSE)
{
if ($ascii_only === TRUE) {
$title = UTF8::transliterate_to_ascii($title);
$title = preg_replace('![^' . preg_quote($separator) . 'a-z0-9\\s]+!', '', strtolower($title));
} else {
$title = preg_replace('![^' . preg_quote($separator) . '\\pL\\pN\\s]+!u', '', UTF8::strtolower($title));
}
$title = preg_replace('![' . preg_quote($separator) . '\\s]+!u', $separator, $title);
return trim($title, $separator);
}
/**
* Generate safe name for file
*
* @param string filename
* @param integer max filename length
* @return string safe filename
* @return boolean FALSE, if filename can not be safed
*/
public static function safe_name($filename, $remove_spaces = TRUE, $max_length = NULL)
{
if ($filename) {
$info = pathinfo($filename);
$fname = trim($info['filename']);
if ($remove_spaces === TRUE) {
// Remove spaces and other separators from the filename
$fname = preg_replace('/[\\pZ]+/uD', '_', $fname);
}
// Remove any punctuation from filename
$fname = preg_replace('/[\\p{Po}]+/uD', '', $fname);
$fname = trim($fname);
// Get the extension from the filename
$extension = Arr::get($info, 'extension', '');
$ext_length = strlen($extension);
$ext_length and ++$ext_length;
// Extension length with dot
if ($max_length !== NULL and $ext_length > $max_length) {
return FALSE;
}
if ($ext_length and preg_match('/[^a-zA-Z0-9]/', $extension)) {
// Extension is invalid
return FALSE;
}
// Transliterate filename
$fname = UTF8::transliterate_to_ascii($fname);
// Remove any special characters from filename
$fname = preg_replace('/[^-a-zA-Z0-9_]+/', '', $fname);
if ($fname == '') {
// Use sha1 hash as safe name
$fname = sha1($info['basename']);
}
if ($max_length !== NULL and strlen($fname) + $ext_length > $max_length) {
$fname = substr($fname, 0, $max_length - $ext_length);
if (!strlen($fname)) {
// Can not truncate filename
return FALSE;
}
}
$filename = $info['dirname'] !== '.' ? $info['dirname'] . DIRECTORY_SEPARATOR : '';
$filename .= $fname . ($ext_length ? '.' . $extension : '');
}
return $filename;
}
/**
* Converts a slug to value valid for a URL.
*
* @param mixed $value
* @return mixed
* @uses UTF8::transliterate_to_ascii
* @credits Kohana-Team
*/
public function set(Jam_Validated $model, $value, $is_changed)
{
list($value, $return) = $this->_default($model, $value);
if (!$return) {
if ($this->ascii_only === TRUE) {
// Transliterate value to ASCII
$value = UTF8::transliterate_to_ascii($value);
}
// Set preserved characters
$preserved_characters = preg_quote($this->separator);
// Add hierarchy separator to preserved characters if set
if ($this->hierarchy_separator) {
$preserved_characters .= preg_quote($this->hierarchy_separator);
}
// Remove all characters that are not in preserved characters, a-z, 0-9, or whitespace
$value = preg_replace('![^' . $preserved_characters . 'a-z0-9\\s]+!', '', strtolower($value));
// Remove whitespace around hierarchy separators if hierarchy separator is set
if ($this->hierarchy_separator) {
$value = preg_replace('/\\s*([' . preg_quote($this->hierarchy_separator, '/') . '])\\s*/', '$1', $value);
}
// Replace all separator characters and whitespace by a single separator
$value = preg_replace('![' . preg_quote($this->separator) . '\\s]+!u', $this->separator, $value);
// Trim separators from the beginning and end
$value = trim($value, $this->separator);
// Check if hierarchy separator is set
if ($this->hierarchy_separator) {
// Replace all hierarchy separators by a single hierarchy separator
$value = preg_replace('![' . preg_quote($this->hierarchy_separator) . ']+!u', $this->hierarchy_separator, $value);
// Trim hierarchy separators from the beginning and end
$value = trim($value, $this->hierarchy_separator);
// Look for separators again at the beginning and end just in case
$value = trim($value, $this->separator);
}
}
return $value;
}
/**
* Tests UTF8::transliterate_to_ascii
*
* @test
* @dataProvider provider_transliterate_to_ascii
*/
public function test_transliterate_to_ascii($input, $case, $expected)
{
$this->assertSame($expected, UTF8::transliterate_to_ascii($input, $case));
}
/**
* Convert a phrase to a URL-safe title.
*
* echo URL::title('My Blog Post'); // "my-blog-post"
*
* @param string $title Phrase to convert
* @param string $separator Word separator (any single character)
* @param boolean $ascii_only Transliterate to ASCII?
* @return string
* @uses UTF8::transliterate_to_ascii
*/
public static function title($title, $separator = '-', $ascii_only = FALSE)
{
if ($ascii_only === TRUE) {
// Transliterate non-ASCII characters
$title = UTF8::transliterate_to_ascii($title);
// Remove all characters that are not the separator, a-z, 0-9, or whitespace
$title = preg_replace('![^' . preg_quote($separator) . 'a-z0-9\\s]+!', $separator, strtolower($title));
} else {
// Remove all characters that are not the separator, letters, numbers, or whitespace
$title = preg_replace('![^' . preg_quote($separator) . '\\pL\\pN\\s]+!u', '', UTF8::strtolower($title));
}
// Replace all separator characters and whitespace by a single separator
$title = preg_replace('![' . preg_quote($separator) . '\\s]+!u', $separator, $title);
// Trim separators from the beginning and end
return trim($title, $separator);
}
/**
* Convert a phrase to a URL-safe title.
*
* echo URL::title('Мой блог пост'); // "moi-blog-post"
*
* @param string $title Phrase to convert
* @param string $separator Word separator (any single character)
* @return string
* @uses UTF8::ru_translit
* @uses UTF8::transliterate_to_ascii
*/
public static function to_slug($text, $separator = '-')
{
$value = UTF8::ru_translit($text);
// Transliterate value to ASCII
$value = UTF8::transliterate_to_ascii($value);
// Set preserved characters
$preserved_characters = preg_quote($separator);
// Remove all characters that are not in preserved characters, a-z, 0-9, point or whitespace
$value = preg_replace('![^' . $preserved_characters . 'a-z0-9.\\s]+!', '', strtolower($value));
// Replace all separator characters and whitespace by a single separator
$value = preg_replace('![' . preg_quote($separator) . '\\s]+!u', $separator, $value);
// Trim separators from the beginning and end
return trim($value, $separator);
}
public function bench_utf8($subject)
{
return UTF8::transliterate_to_ascii($subject);
}
/**
* Method to make a filename safe for writing on the filesystem, removing all strange characters
* @param string $filename
* @return string
*/
public static function sanitize($filename, $separator = '-')
{
// Transliterate strange chars
$filename = UTF8::transliterate_to_ascii($filename);
// Sanitize the filename
$filename = preg_replace('/[^a-z0-9-\\.]/', $separator, strtolower($filename));
// Remove spaces
$filename = preg_replace('/\\s+/u', $separator, $filename);
// Strip multiple dashes
$filename = preg_replace('/-{2,}/', $separator, $filename);
return $filename;
}
