diff --git a/README.md b/README.md index 9e184cc..8556101 100644 --- a/README.md +++ b/README.md @@ -98,7 +98,7 @@ $( '.uls-trigger' ).uls( { Features -------- -jQuery.uls has an elaborative language information collection. It knows about +jQuery.uls has an elaborative language information collection and it is based on https://github.com/wikimedia/language-data.git. It knows about 1. The script in which a language is written. 2. The script code @@ -151,4 +151,3 @@ Coding style ------------- Please follow [jQuery coding guidelines](http://docs.jquery.com/JQuery_Core_Style_Guidelines) - diff --git a/data/Spyc.php b/data/Spyc.php deleted file mode 100644 index 49e0cbb..0000000 --- a/data/Spyc.php +++ /dev/null @@ -1,1161 +0,0 @@ - - * @author Chris Wanstrath - * @link https://github.com/mustangostang/spyc/ - * @copyright Copyright 2005-2006 Chris Wanstrath, 2006-2011 Vlad Andersen - * @license http://www.opensource.org/licenses/mit-license.php MIT License - * @package Spyc - */ - -if (!function_exists('spyc_load')) { - /** - * Parses YAML to array. - * @param string $string YAML string. - * @return array - */ - function spyc_load ($string) { - return Spyc::YAMLLoadString($string); - } -} - -if (!function_exists('spyc_load_file')) { - /** - * Parses YAML to array. - * @param string $file Path to YAML file. - * @return array - */ - function spyc_load_file ($file) { - return Spyc::YAMLLoad($file); - } -} - -if (!function_exists('spyc_dump')) { - /** - * Dumps array to YAML. - * @param array $data Array. - * @return string - */ - function spyc_dump ($data) { - return Spyc::YAMLDump($data, false, false, true); - } -} - -if (!class_exists('Spyc')) { - -/** - * The Simple PHP YAML Class. - * - * This class can be used to read a YAML file and convert its contents - * into a PHP array. It currently supports a very limited subsection of - * the YAML spec. - * - * Usage: - * - * $Spyc = new Spyc; - * $array = $Spyc->load($file); - * - * or: - * - * $array = Spyc::YAMLLoad($file); - * - * or: - * - * $array = spyc_load_file($file); - * - * @package Spyc - */ -class Spyc { - - // SETTINGS - - const REMPTY = "\0\0\0\0\0"; - - /** - * Setting this to true will force YAMLDump to enclose any string value in - * quotes. False by default. - * - * @var bool - */ - public $setting_dump_force_quotes = false; - - /** - * Setting this to true will forse YAMLLoad to use syck_load function when - * possible. False by default. - * @var bool - */ - public $setting_use_syck_is_possible = false; - - - - /**#@+ - * @access private - * @var mixed - */ - private $_dumpIndent; - private $_dumpWordWrap; - private $_containsGroupAnchor = false; - private $_containsGroupAlias = false; - private $path; - private $result; - private $LiteralPlaceHolder = '___YAML_Literal_Block___'; - private $SavedGroups = array(); - private $indent; - /** - * Path modifier that should be applied after adding current element. - * @var array - */ - private $delayedPath = array(); - - /**#@+ - * @access public - * @var mixed - */ - public $_nodeId; - -/** - * Load a valid YAML string to Spyc. - * @param string $input - * @return array - */ - public function load ($input) { - return $this->_loadString($input); - } - - /** - * Load a valid YAML file to Spyc. - * @param string $file - * @return array - */ - public function loadFile ($file) { - return $this->_load($file); - } - - /** - * Load YAML into a PHP array statically - * - * The load method, when supplied with a YAML stream (string or file), - * will do its best to convert YAML in a file into a PHP array. Pretty - * simple. - * Usage: - * - * $array = Spyc::YAMLLoad('lucky.yaml'); - * print_r($array); - * - * @access public - * @return array - * @param string $input Path of YAML file or string containing YAML - */ - public static function YAMLLoad($input) { - $Spyc = new Spyc; - return $Spyc->_load($input); - } - - /** - * Load a string of YAML into a PHP array statically - * - * The load method, when supplied with a YAML string, will do its best - * to convert YAML in a string into a PHP array. Pretty simple. - * - * Note: use this function if you don't want files from the file system - * loaded and processed as YAML. This is of interest to people concerned - * about security whose input is from a string. - * - * Usage: - * - * $array = Spyc::YAMLLoadString("---\n0: hello world\n"); - * print_r($array); - * - * @access public - * @return array - * @param string $input String containing YAML - */ - public static function YAMLLoadString($input) { - $Spyc = new Spyc; - return $Spyc->_loadString($input); - } - - /** - * Dump YAML from PHP array statically - * - * The dump method, when supplied with an array, will do its best - * to convert the array into friendly YAML. Pretty simple. Feel free to - * save the returned string as nothing.yaml and pass it around. - * - * Oh, and you can decide how big the indent is and what the wordwrap - * for folding is. Pretty cool -- just pass in 'false' for either if - * you want to use the default. - * - * Indent's default is 2 spaces, wordwrap's default is 40 characters. And - * you can turn off wordwrap by passing in 0. - * - * @access public - * @return string - * @param array|\stdClass $array PHP array - * @param int $indent Pass in false to use the default, which is 2 - * @param int $wordwrap Pass in 0 for no wordwrap, false for default (40) - * @param bool $no_opening_dashes Do not start YAML file with "---\n" - */ - public static function YAMLDump($array, $indent = false, $wordwrap = false, $no_opening_dashes = false) { - $spyc = new Spyc; - return $spyc->dump($array, $indent, $wordwrap, $no_opening_dashes); - } - - - /** - * Dump PHP array to YAML - * - * The dump method, when supplied with an array, will do its best - * to convert the array into friendly YAML. Pretty simple. Feel free to - * save the returned string as tasteful.yaml and pass it around. - * - * Oh, and you can decide how big the indent is and what the wordwrap - * for folding is. Pretty cool -- just pass in 'false' for either if - * you want to use the default. - * - * Indent's default is 2 spaces, wordwrap's default is 40 characters. And - * you can turn off wordwrap by passing in 0. - * - * @access public - * @return string - * @param array $array PHP array - * @param int $indent Pass in false to use the default, which is 2 - * @param int $wordwrap Pass in 0 for no wordwrap, false for default (40) - */ - public function dump($array,$indent = false,$wordwrap = false, $no_opening_dashes = false) { - // Dumps to some very clean YAML. We'll have to add some more features - // and options soon. And better support for folding. - - // New features and options. - if ($indent === false or !is_numeric($indent)) { - $this->_dumpIndent = 2; - } else { - $this->_dumpIndent = $indent; - } - - if ($wordwrap === false or !is_numeric($wordwrap)) { - $this->_dumpWordWrap = 40; - } else { - $this->_dumpWordWrap = $wordwrap; - } - - // New YAML document - $string = ""; - if (!$no_opening_dashes) $string = "---\n"; - - // Start at the base of the array and move through it. - if ($array) { - $array = (array)$array; - $previous_key = -1; - foreach ($array as $key => $value) { - if (!isset($first_key)) $first_key = $key; - $string .= $this->_yamlize($key,$value,0,$previous_key, $first_key, $array); - $previous_key = $key; - } - } - return $string; - } - - /** - * Attempts to convert a key / value array item to YAML - * @access private - * @return string - * @param $key The name of the key - * @param $value The value of the item - * @param $indent The indent of the current node - */ - private function _yamlize($key,$value,$indent, $previous_key = -1, $first_key = 0, $source_array = null) { - if(is_object($value)) $value = (array)$value; - if (is_array($value)) { - if (empty ($value)) - return $this->_dumpNode($key, array(), $indent, $previous_key, $first_key, $source_array); - // It has children. What to do? - // Make it the right kind of item - $string = $this->_dumpNode($key, self::REMPTY, $indent, $previous_key, $first_key, $source_array); - // Add the indent - $indent += $this->_dumpIndent; - // Yamlize the array - $string .= $this->_yamlizeArray($value,$indent); - } elseif (!is_array($value)) { - // It doesn't have children. Yip. - $string = $this->_dumpNode($key, $value, $indent, $previous_key, $first_key, $source_array); - } - return $string; - } - - /** - * Attempts to convert an array to YAML - * @access private - * @return string - * @param $array The array you want to convert - * @param $indent The indent of the current level - */ - private function _yamlizeArray($array,$indent) { - if (is_array($array)) { - $string = ''; - $previous_key = -1; - foreach ($array as $key => $value) { - if (!isset($first_key)) $first_key = $key; - $string .= $this->_yamlize($key, $value, $indent, $previous_key, $first_key, $array); - $previous_key = $key; - } - return $string; - } else { - return false; - } - } - - /** - * Returns YAML from a key and a value - * @access private - * @return string - * @param $key The name of the key - * @param $value The value of the item - * @param $indent The indent of the current node - */ - private function _dumpNode($key, $value, $indent, $previous_key = -1, $first_key = 0, $source_array = null) { - // do some folding here, for blocks - if (is_string ($value) && ((strpos($value,"\n") !== false || strpos($value,": ") !== false || strpos($value,"- ") !== false || - strpos($value,"*") !== false || strpos($value,"#") !== false || strpos($value,"<") !== false || strpos($value,">") !== false || strpos ($value, '%') !== false || strpos ($value, ' ') !== false || - strpos($value,"[") !== false || strpos($value,"]") !== false || strpos($value,"{") !== false || strpos($value,"}") !== false) || strpos($value,"&") !== false || strpos($value, "'") !== false || strpos($value, "!") === 0 || - substr ($value, -1, 1) == ':') - ) { - $value = $this->_doLiteralBlock($value,$indent); - } else { - $value = $this->_doFolding($value,$indent); - } - - if ($value === array()) $value = '[ ]'; - if ($value === "") $value = '""'; - if (self::isTranslationWord($value)) { - $value = $this->_doLiteralBlock($value, $indent); - } - if (trim ($value) != $value) - $value = $this->_doLiteralBlock($value,$indent); - - if (is_bool($value)) { - $value = $value ? "true" : "false"; - } - - if ($value === null) $value = 'null'; - if ($value === "'" . self::REMPTY . "'") $value = null; - - $spaces = str_repeat(' ',$indent); - - //if (is_int($key) && $key - 1 == $previous_key && $first_key===0) { - if (is_array ($source_array) && array_keys($source_array) === range(0, count($source_array) - 1)) { - // It's a sequence - $string = $spaces.'- '.$value."\n"; - } else { - // if ($first_key===0) throw new Exception('Keys are all screwy. The first one was zero, now it\'s "'. $key .'"'); - // It's mapped - if (strpos($key, ":") !== false || strpos($key, "#") !== false) { $key = '"' . $key . '"'; } - $string = rtrim ($spaces.$key.': '.$value)."\n"; - } - return $string; - } - - /** - * Creates a literal block for dumping - * @access private - * @return string - * @param $value - * @param $indent int The value of the indent - */ - private function _doLiteralBlock($value,$indent) { - if ($value === "\n") return '\n'; - if (strpos($value, "\n") === false && strpos($value, "'") === false) { - return sprintf ("'%s'", $value); - } - if (strpos($value, "\n") === false && strpos($value, '"') === false) { - return sprintf ('"%s"', $value); - } - $exploded = explode("\n",$value); - $newValue = '|'; - if (isset($exploded[0]) && ($exploded[0] == "|" || $exploded[0] == "|-" || $exploded[0] == ">")) { - $newValue = $exploded[0]; - unset($exploded[0]); - } - $indent += $this->_dumpIndent; - $spaces = str_repeat(' ',$indent); - foreach ($exploded as $line) { - $line = trim($line); - if (strpos($line, '"') === 0 && strrpos($line, '"') == (strlen($line)-1) || strpos($line, "'") === 0 && strrpos($line, "'") == (strlen($line)-1)) { - $line = substr($line, 1, -1); - } - $newValue .= "\n" . $spaces . ($line); - } - return $newValue; - } - - /** - * Folds a string of text, if necessary - * @access private - * @return string - * @param $value The string you wish to fold - */ - private function _doFolding($value,$indent) { - // Don't do anything if wordwrap is set to 0 - - if ($this->_dumpWordWrap !== 0 && is_string ($value) && strlen($value) > $this->_dumpWordWrap) { - $indent += $this->_dumpIndent; - $indent = str_repeat(' ',$indent); - $wrapped = wordwrap($value,$this->_dumpWordWrap,"\n$indent"); - $value = ">\n".$indent.$wrapped; - } else { - if ($this->setting_dump_force_quotes && is_string ($value) && $value !== self::REMPTY) - $value = '"' . $value . '"'; - if (is_numeric($value) && is_string($value)) - $value = '"' . $value . '"'; - } - - - return $value; - } - - private function isTrueWord($value) { - $words = self::getTranslations(array('true', 'on', 'yes', 'y')); - return in_array($value, $words, true); - } - - private function isFalseWord($value) { - $words = self::getTranslations(array('false', 'off', 'no', 'n')); - return in_array($value, $words, true); - } - - private function isNullWord($value) { - $words = self::getTranslations(array('null', '~')); - return in_array($value, $words, true); - } - - private function isTranslationWord($value) { - return ( - self::isTrueWord($value) || - self::isFalseWord($value) || - self::isNullWord($value) - ); - } - - /** - * Coerce a string into a native type - * Reference: http://yaml.org/type/bool.html - * TODO: Use only words from the YAML spec. - * @access private - * @param $value The value to coerce - */ - private function coerceValue(&$value) { - if (self::isTrueWord($value)) { - $value = true; - } else if (self::isFalseWord($value)) { - $value = false; - } else if (self::isNullWord($value)) { - $value = null; - } - } - - /** - * Given a set of words, perform the appropriate translations on them to - * match the YAML 1.1 specification for type coercing. - * @param $words The words to translate - * @access private - */ - private static function getTranslations(array $words) { - $result = array(); - foreach ($words as $i) { - $result = array_merge($result, array(ucfirst($i), strtoupper($i), strtolower($i))); - } - return $result; - } - -// LOADING FUNCTIONS - - private function _load($input) { - $Source = $this->loadFromSource($input); - return $this->loadWithSource($Source); - } - - private function _loadString($input) { - $Source = $this->loadFromString($input); - return $this->loadWithSource($Source); - } - - private function loadWithSource($Source) { - if (empty ($Source)) return array(); - if ($this->setting_use_syck_is_possible && function_exists ('syck_load')) { - $array = syck_load (implode ("\n", $Source)); - return is_array($array) ? $array : array(); - } - - $this->path = array(); - $this->result = array(); - - $cnt = count($Source); - for ($i = 0; $i < $cnt; $i++) { - $line = $Source[$i]; - - $this->indent = strlen($line) - strlen(ltrim($line)); - $tempPath = $this->getParentPathByIndent($this->indent); - $line = self::stripIndent($line, $this->indent); - if (self::isComment($line)) continue; - if (self::isEmpty($line)) continue; - $this->path = $tempPath; - - $literalBlockStyle = self::startsLiteralBlock($line); - if ($literalBlockStyle) { - $line = rtrim ($line, $literalBlockStyle . " \n"); - $literalBlock = ''; - $line .= ' '.$this->LiteralPlaceHolder; - $literal_block_indent = strlen($Source[$i+1]) - strlen(ltrim($Source[$i+1])); - while (++$i < $cnt && $this->literalBlockContinues($Source[$i], $this->indent)) { - $literalBlock = $this->addLiteralLine($literalBlock, $Source[$i], $literalBlockStyle, $literal_block_indent); - } - $i--; - } - - // Strip out comments - if (strpos ($line, '#')) { - $line = preg_replace('/\s*#([^"\']+)$/','',$line); - } - - while (++$i < $cnt && self::greedilyNeedNextLine($line)) { - $line = rtrim ($line, " \n\t\r") . ' ' . ltrim ($Source[$i], " \t"); - } - $i--; - - $lineArray = $this->_parseLine($line); - - if ($literalBlockStyle) - $lineArray = $this->revertLiteralPlaceHolder ($lineArray, $literalBlock); - - $this->addArray($lineArray, $this->indent); - - foreach ($this->delayedPath as $indent => $delayedPath) - $this->path[$indent] = $delayedPath; - - $this->delayedPath = array(); - - } - return $this->result; - } - - private function loadFromSource ($input) { - if (!empty($input) && strpos($input, "\n") === false && file_exists($input)) - $input = file_get_contents($input); - - return $this->loadFromString($input); - } - - private function loadFromString ($input) { - $lines = explode("\n",$input); - foreach ($lines as $k => $_) { - $lines[$k] = rtrim ($_, "\r"); - } - return $lines; - } - - /** - * Parses YAML code and returns an array for a node - * @access private - * @return array - * @param string $line A line from the YAML file - */ - private function _parseLine($line) { - if (!$line) return array(); - $line = trim($line); - if (!$line) return array(); - - $array = array(); - - $group = $this->nodeContainsGroup($line); - if ($group) { - $this->addGroup($line, $group); - $line = $this->stripGroup ($line, $group); - } - - if ($this->startsMappedSequence($line)) - return $this->returnMappedSequence($line); - - if ($this->startsMappedValue($line)) - return $this->returnMappedValue($line); - - if ($this->isArrayElement($line)) - return $this->returnArrayElement($line); - - if ($this->isPlainArray($line)) - return $this->returnPlainArray($line); - - - return $this->returnKeyValuePair($line); - - } - - /** - * Finds the type of the passed value, returns the value as the new type. - * @access private - * @param string $value - * @return mixed - */ - private function _toType($value) { - if ($value === '') return ""; - $first_character = $value[0]; - $last_character = substr($value, -1, 1); - - $is_quoted = false; - do { - if (!$value) break; - if ($first_character != '"' && $first_character != "'") break; - if ($last_character != '"' && $last_character != "'") break; - $is_quoted = true; - } while (0); - - if ($is_quoted) { - $value = str_replace('\n', "\n", $value); - if ($first_character == "'") - return strtr(substr ($value, 1, -1), array ('\'\'' => '\'', '\\\''=> '\'')); - return strtr(substr ($value, 1, -1), array ('\\"' => '"', '\\\''=> '\'')); - } - - if (strpos($value, ' #') !== false && !$is_quoted) - $value = preg_replace('/\s+#(.+)$/','',$value); - - if ($first_character == '[' && $last_character == ']') { - // Take out strings sequences and mappings - $innerValue = trim(substr ($value, 1, -1)); - if ($innerValue === '') return array(); - $explode = $this->_inlineEscape($innerValue); - // Propagate value array - $value = array(); - foreach ($explode as $v) { - $value[] = $this->_toType($v); - } - return $value; - } - - if (strpos($value,': ')!==false && $first_character != '{') { - $array = explode(': ',$value); - $key = trim($array[0]); - array_shift($array); - $value = trim(implode(': ',$array)); - $value = $this->_toType($value); - return array($key => $value); - } - - if ($first_character == '{' && $last_character == '}') { - $innerValue = trim(substr ($value, 1, -1)); - if ($innerValue === '') return array(); - // Inline Mapping - // Take out strings sequences and mappings - $explode = $this->_inlineEscape($innerValue); - // Propagate value array - $array = array(); - foreach ($explode as $v) { - $SubArr = $this->_toType($v); - if (empty($SubArr)) continue; - if (is_array ($SubArr)) { - $array[key($SubArr)] = $SubArr[key($SubArr)]; continue; - } - $array[] = $SubArr; - } - return $array; - } - - if ($value == 'null' || $value == 'NULL' || $value == 'Null' || $value == '' || $value == '~') { - return null; - } - - if ( is_numeric($value) && preg_match ('/^(-|)[1-9]+[0-9]*$/', $value) ){ - $intvalue = (int)$value; - if ($intvalue != PHP_INT_MAX && $intvalue != ~PHP_INT_MAX) - $value = $intvalue; - return $value; - } - - if ( is_string($value) && preg_match('/^0[xX][0-9a-fA-F]+$/', $value)) { - // Hexadecimal value. - return hexdec($value); - } - - $this->coerceValue($value); - - if (is_numeric($value)) { - if ($value === '0') return 0; - if (rtrim ($value, 0) === $value) - $value = (float)$value; - return $value; - } - - return $value; - } - - /** - * Used in inlines to check for more inlines or quoted strings - * @access private - * @return array - */ - private function _inlineEscape($inline) { - // There's gotta be a cleaner way to do this... - // While pure sequences seem to be nesting just fine, - // pure mappings and mappings with sequences inside can't go very - // deep. This needs to be fixed. - - $seqs = array(); - $maps = array(); - $saved_strings = array(); - $saved_empties = array(); - - // Check for empty strings - $regex = '/("")|(\'\')/'; - if (preg_match_all($regex,$inline,$strings)) { - $saved_empties = $strings[0]; - $inline = preg_replace($regex,'YAMLEmpty',$inline); - } - unset($regex); - - // Check for strings - $regex = '/(?:(")|(?:\'))((?(1)[^"]+|[^\']+))(?(1)"|\')/'; - if (preg_match_all($regex,$inline,$strings)) { - $saved_strings = $strings[0]; - $inline = preg_replace($regex,'YAMLString',$inline); - } - unset($regex); - - // echo $inline; - - $i = 0; - do { - - // Check for sequences - while (preg_match('/\[([^{}\[\]]+)\]/U',$inline,$matchseqs)) { - $seqs[] = $matchseqs[0]; - $inline = preg_replace('/\[([^{}\[\]]+)\]/U', ('YAMLSeq' . (count($seqs) - 1) . 's'), $inline, 1); - } - - // Check for mappings - while (preg_match('/{([^\[\]{}]+)}/U',$inline,$matchmaps)) { - $maps[] = $matchmaps[0]; - $inline = preg_replace('/{([^\[\]{}]+)}/U', ('YAMLMap' . (count($maps) - 1) . 's'), $inline, 1); - } - - if ($i++ >= 10) break; - - } while (strpos ($inline, '[') !== false || strpos ($inline, '{') !== false); - - $explode = explode(',',$inline); - $explode = array_map('trim', $explode); - $stringi = 0; $i = 0; - - while (1) { - - // Re-add the sequences - if (!empty($seqs)) { - foreach ($explode as $key => $value) { - if (strpos($value,'YAMLSeq') !== false) { - foreach ($seqs as $seqk => $seq) { - $explode[$key] = str_replace(('YAMLSeq'.$seqk.'s'),$seq,$value); - $value = $explode[$key]; - } - } - } - } - - // Re-add the mappings - if (!empty($maps)) { - foreach ($explode as $key => $value) { - if (strpos($value,'YAMLMap') !== false) { - foreach ($maps as $mapk => $map) { - $explode[$key] = str_replace(('YAMLMap'.$mapk.'s'), $map, $value); - $value = $explode[$key]; - } - } - } - } - - - // Re-add the strings - if (!empty($saved_strings)) { - foreach ($explode as $key => $value) { - while (strpos($value,'YAMLString') !== false) { - $explode[$key] = preg_replace('/YAMLString/',$saved_strings[$stringi],$value, 1); - unset($saved_strings[$stringi]); - ++$stringi; - $value = $explode[$key]; - } - } - } - - - // Re-add the empties - if (!empty($saved_empties)) { - foreach ($explode as $key => $value) { - while (strpos($value,'YAMLEmpty') !== false) { - $explode[$key] = preg_replace('/YAMLEmpty/', '', $value, 1); - $value = $explode[$key]; - } - } - } - - $finished = true; - foreach ($explode as $key => $value) { - if (strpos($value,'YAMLSeq') !== false) { - $finished = false; break; - } - if (strpos($value,'YAMLMap') !== false) { - $finished = false; break; - } - if (strpos($value,'YAMLString') !== false) { - $finished = false; break; - } - if (strpos($value,'YAMLEmpty') !== false) { - $finished = false; break; - } - } - if ($finished) break; - - $i++; - if ($i > 10) - break; // Prevent infinite loops. - } - - - return $explode; - } - - private function literalBlockContinues ($line, $lineIndent) { - if (!trim($line)) return true; - if (strlen($line) - strlen(ltrim($line)) > $lineIndent) return true; - return false; - } - - private function referenceContentsByAlias ($alias) { - do { - if (!isset($this->SavedGroups[$alias])) { echo "Bad group name: $alias."; break; } - $groupPath = $this->SavedGroups[$alias]; - $value = $this->result; - foreach ($groupPath as $k) { - $value = $value[$k]; - } - } while (false); - return $value; - } - - private function addArrayInline ($array, $indent) { - $CommonGroupPath = $this->path; - if (empty ($array)) return false; - - foreach ($array as $k => $_) { - $this->addArray(array($k => $_), $indent); - $this->path = $CommonGroupPath; - } - return true; - } - - private function addArray ($incoming_data, $incoming_indent) { - - // print_r ($incoming_data); - - if (count ($incoming_data) > 1) - return $this->addArrayInline ($incoming_data, $incoming_indent); - - $key = key ($incoming_data); - $value = isset($incoming_data[$key]) ? $incoming_data[$key] : null; - if ($key === '__!YAMLZero') $key = '0'; - - if ($incoming_indent == 0 && !$this->_containsGroupAlias && !$this->_containsGroupAnchor) { // Shortcut for root-level values. - if ($key || $key === '' || $key === '0') { - $this->result[$key] = $value; - } else { - $this->result[] = $value; end ($this->result); $key = key ($this->result); - } - $this->path[$incoming_indent] = $key; - return; - } - - - - $history = array(); - // Unfolding inner array tree. - $history[] = $_arr = $this->result; - foreach ($this->path as $k) { - $history[] = $_arr = $_arr[$k]; - } - - if ($this->_containsGroupAlias) { - $value = $this->referenceContentsByAlias($this->_containsGroupAlias); - $this->_containsGroupAlias = false; - } - - - // Adding string or numeric key to the innermost level or $this->arr. - if (is_string($key) && $key == '<<') { - if (!is_array ($_arr)) { $_arr = array (); } - - $_arr = array_merge ($_arr, $value); - } else if ($key || $key === '' || $key === '0') { - if (!is_array ($_arr)) - $_arr = array ($key=>$value); - else - $_arr[$key] = $value; - } else { - if (!is_array ($_arr)) { $_arr = array ($value); $key = 0; } - else { $_arr[] = $value; end ($_arr); $key = key ($_arr); } - } - - $reverse_path = array_reverse($this->path); - $reverse_history = array_reverse ($history); - $reverse_history[0] = $_arr; - $cnt = count($reverse_history) - 1; - for ($i = 0; $i < $cnt; $i++) { - $reverse_history[$i+1][$reverse_path[$i]] = $reverse_history[$i]; - } - $this->result = $reverse_history[$cnt]; - - $this->path[$incoming_indent] = $key; - - if ($this->_containsGroupAnchor) { - $this->SavedGroups[$this->_containsGroupAnchor] = $this->path; - if (is_array ($value)) { - $k = key ($value); - if (!is_int ($k)) { - $this->SavedGroups[$this->_containsGroupAnchor][$incoming_indent + 2] = $k; - } - } - $this->_containsGroupAnchor = false; - } - - } - - private static function startsLiteralBlock ($line) { - $lastChar = substr (trim($line), -1); - if ($lastChar != '>' && $lastChar != '|') return false; - if ($lastChar == '|') return $lastChar; - // HTML tags should not be counted as literal blocks. - if (preg_match ('#<.*?>$#', $line)) return false; - return $lastChar; - } - - private static function greedilyNeedNextLine($line) { - $line = trim ($line); - if (!strlen($line)) return false; - if (substr ($line, -1, 1) == ']') return false; - if ($line[0] == '[') return true; - if (preg_match ('#^[^:]+?:\s*\[#', $line)) return true; - return false; - } - - private function addLiteralLine ($literalBlock, $line, $literalBlockStyle, $indent = -1) { - $line = self::stripIndent($line, $indent); - if ($literalBlockStyle !== '|') { - $line = self::stripIndent($line); - } - $line = rtrim ($line, "\r\n\t ") . "\n"; - if ($literalBlockStyle == '|') { - return $literalBlock . $line; - } - if (strlen($line) == 0) - return rtrim($literalBlock, ' ') . "\n"; - if ($line == "\n" && $literalBlockStyle == '>') { - return rtrim ($literalBlock, " \t") . "\n"; - } - if ($line != "\n") - $line = trim ($line, "\r\n ") . " "; - return $literalBlock . $line; - } - - function revertLiteralPlaceHolder ($lineArray, $literalBlock) { - foreach ($lineArray as $k => $_) { - if (is_array($_)) - $lineArray[$k] = $this->revertLiteralPlaceHolder ($_, $literalBlock); - else if (substr($_, -1 * strlen ($this->LiteralPlaceHolder)) == $this->LiteralPlaceHolder) - $lineArray[$k] = rtrim ($literalBlock, " \r\n"); - } - return $lineArray; - } - - private static function stripIndent ($line, $indent = -1) { - if ($indent == -1) $indent = strlen($line) - strlen(ltrim($line)); - return substr ($line, $indent); - } - - private function getParentPathByIndent ($indent) { - if ($indent == 0) return array(); - $linePath = $this->path; - do { - end($linePath); $lastIndentInParentPath = key($linePath); - if ($indent <= $lastIndentInParentPath) array_pop ($linePath); - } while ($indent <= $lastIndentInParentPath); - return $linePath; - } - - - private function clearBiggerPathValues ($indent) { - - - if ($indent == 0) $this->path = array(); - if (empty ($this->path)) return true; - - foreach ($this->path as $k => $_) { - if ($k > $indent) unset ($this->path[$k]); - } - - return true; - } - - - private static function isComment ($line) { - if (!$line) return false; - if ($line[0] == '#') return true; - if (trim($line, " \r\n\t") == '---') return true; - return false; - } - - private static function isEmpty ($line) { - return (trim ($line) === ''); - } - - - private function isArrayElement ($line) { - if (!$line || !is_scalar($line)) return false; - if (substr($line, 0, 2) != '- ') return false; - if (strlen ($line) > 3) - if (substr($line,0,3) == '---') return false; - - return true; - } - - private function isHashElement ($line) { - return strpos($line, ':'); - } - - private function isLiteral ($line) { - if ($this->isArrayElement($line)) return false; - if ($this->isHashElement($line)) return false; - return true; - } - - - private static function unquote ($value) { - if (!$value) return $value; - if (!is_string($value)) return $value; - if ($value[0] == '\'') return trim ($value, '\''); - if ($value[0] == '"') return trim ($value, '"'); - return $value; - } - - private function startsMappedSequence ($line) { - return (substr($line, 0, 2) == '- ' && substr ($line, -1, 1) == ':'); - } - - private function returnMappedSequence ($line) { - $array = array(); - $key = self::unquote(trim(substr($line,1,-1))); - $array[$key] = array(); - $this->delayedPath = array(strpos ($line, $key) + $this->indent => $key); - return array($array); - } - - private function checkKeysInValue($value) { - if (strchr('[{"\'', $value[0]) === false) { - if (strchr($value, ': ') !== false) { - throw new Exception('Too many keys: '.$value); - } - } - } - - private function returnMappedValue ($line) { - $this->checkKeysInValue($line); - $array = array(); - $key = self::unquote (trim(substr($line,0,-1))); - $array[$key] = ''; - return $array; - } - - private function startsMappedValue ($line) { - return (substr ($line, -1, 1) == ':'); - } - - private function isPlainArray ($line) { - return ($line[0] == '[' && substr ($line, -1, 1) == ']'); - } - - private function returnPlainArray ($line) { - return $this->_toType($line); - } - - private function returnKeyValuePair ($line) { - $array = array(); - $key = ''; - if (strpos ($line, ': ')) { - // It's a key/value pair most likely - // If the key is in double quotes pull it out - if (($line[0] == '"' || $line[0] == "'") && preg_match('/^(["\'](.*)["\'](\s)*:)/',$line,$matches)) { - $value = trim(str_replace($matches[1],'',$line)); - $key = $matches[2]; - } else { - // Do some guesswork as to the key and the value - $explode = explode(': ', $line); - $key = trim(array_shift($explode)); - $value = trim(implode(': ', $explode)); - $this->checkKeysInValue($value); - } - // Set the type of the value. Int, string, etc - $value = $this->_toType($value); - if ($key === '0') $key = '__!YAMLZero'; - $array[$key] = $value; - } else { - $array = array ($line); - } - return $array; - - } - - - private function returnArrayElement ($line) { - if (strlen($line) <= 1) return array(array()); // Weird %) - $array = array(); - $value = trim(substr($line,1)); - $value = $this->_toType($value); - if ($this->isArrayElement($value)) { - $value = $this->returnArrayElement($value); - } - $array[] = $value; - return $array; - } - - - private function nodeContainsGroup ($line) { - $symbolsForReference = 'A-z0-9_\-'; - if (strpos($line, '&') === false && strpos($line, '*') === false) return false; // Please die fast ;-) - if ($line[0] == '&' && preg_match('/^(&['.$symbolsForReference.']+)/', $line, $matches)) return $matches[1]; - if ($line[0] == '*' && preg_match('/^(\*['.$symbolsForReference.']+)/', $line, $matches)) return $matches[1]; - if (preg_match('/(&['.$symbolsForReference.']+)$/', $line, $matches)) return $matches[1]; - if (preg_match('/(\*['.$symbolsForReference.']+$)/', $line, $matches)) return $matches[1]; - if (preg_match ('#^\s*<<\s*:\s*(\*[^\s]+).*$#', $line, $matches)) return $matches[1]; - return false; - - } - - private function addGroup ($line, $group) { - if ($group[0] == '&') $this->_containsGroupAnchor = substr ($group, 1); - if ($group[0] == '*') $this->_containsGroupAlias = substr ($group, 1); - //print_r ($this->path); - } - - private function stripGroup ($line, $group) { - $line = trim(str_replace($group, '', $line)); - return $line; - } -} -} - -// Enable use of Spyc from command line -// The syntax is the following: php Spyc.php spyc.yaml - -do { - if (PHP_SAPI != 'cli') break; - if (empty ($_SERVER['argc']) || $_SERVER['argc'] < 2) break; - if (empty ($_SERVER['PHP_SELF']) || FALSE === strpos ($_SERVER['PHP_SELF'], 'Spyc.php') ) break; - $file = $argv[1]; - echo json_encode (spyc_load_file ($file)); -} while (0); diff --git a/data/generated-langdb.json b/data/generated-langdb.json deleted file mode 100644 index f7d88ab..0000000 --- a/data/generated-langdb.json +++ /dev/null @@ -1,5448 +0,0 @@ -{ - "languages": { - "aa": [ - "Latn", - [ - "AF" - ], - "Qafár af" - ], - "ab": [ - "Cyrl", - [ - "EU" - ], - "Аҧсшәа" - ], - "abs": [ - "Latn", - [ - "AS" - ], - "Bahasa Ambon" - ], - "ace": [ - "Latn", - [ - "AS", - "PA" - ], - "Acèh" - ], - "acf": [ - "Latn", - [ - "AM" - ], - "kwéyòl" - ], - "ady": [ - "Cyrl", - [ - "EU", - "ME" - ], - "Адыгабзэ" - ], - "ady-cyrl": [ - "ady" - ], - "ady-latn": [ - "Latn", - [ - "EU", - "ME" - ], - "Adygabze" - ], - "aeb": [ - "aeb-arab" - ], - "aeb-arab": [ - "Arab", - [ - "AF" - ], - "تونسي" - ], - "aeb-latn": [ - "Latn", - [ - "AF" - ], - "Tûnsî" - ], - "af": [ - "Latn", - [ - "AF" - ], - "Afrikaans" - ], - "ahr": [ - "Deva", - [ - "AS" - ], - "अहिराणी" - ], - "ais": [ - "Latn", - [ - "AS" - ], - "Sakizaya" - ], - "ak": [ - "Latn", - [ - "AF" - ], - "Akan" - ], - "akz": [ - "Latn", - [ - "AM" - ], - "Albaamo innaaɬiilka" - ], - "aln": [ - "Latn", - [ - "EU" - ], - "Gegë" - ], - "am": [ - "Ethi", - [ - "AF" - ], - "አማርኛ" - ], - "ami": [ - "Latn", - [ - "AS" - ], - "Pangcah" - ], - "an": [ - "Latn", - [ - "EU" - ], - "aragonés" - ], - "ang": [ - "Latn", - [ - "EU" - ], - "Ænglisc" - ], - "anp": [ - "Deva", - [ - "AS" - ], - "अङ्गिका" - ], - "ar": [ - "Arab", - [ - "ME" - ], - "العربية" - ], - "arc": [ - "Syrc", - [ - "ME" - ], - "ܐܪܡܝܐ" - ], - "arn": [ - "Latn", - [ - "AM" - ], - "mapudungun" - ], - "aro": [ - "Latn", - [ - "AM" - ], - "Araona" - ], - "arq": [ - "Arab", - [ - "AF" - ], - "جازايرية" - ], - "ary": [ - "Latn", - [ - "ME" - ], - "Maġribi" - ], - "arz": [ - "Arab", - [ - "ME" - ], - "مصرى" - ], - "as": [ - "Beng", - [ - "AS" - ], - "অসমীয়া" - ], - "ase": [ - "Sgnw", - [ - "AM" - ], - "American sign language" - ], - "ast": [ - "Latn", - [ - "EU" - ], - "asturianu" - ], - "atj": [ - "Latn", - [ - "AM" - ], - "atikamekw" - ], - "av": [ - "Cyrl", - [ - "EU" - ], - "авар" - ], - "avk": [ - "Latn", - [ - "WW" - ], - "Kotava" - ], - "ay": [ - "Latn", - [ - "AM" - ], - "Aymar aru" - ], - "az": [ - "az-latn" - ], - "az-arab": [ - "Arab", - [ - "AS", - "ME" - ], - "تۆرکجه" - ], - "az-latn": [ - "Latn", - [ - "EU", - "ME" - ], - "azərbaycanca" - ], - "az-cyrl": [ - "Cyrl", - [ - "EU", - "ME" - ], - "азәрбајҹанҹа" - ], - "azb": [ - "az-arab" - ], - "azj": [ - "az-latn" - ], - "ba": [ - "Cyrl", - [ - "EU" - ], - "башҡортса" - ], - "ban": [ - "Bali", - [ - "AS" - ], - "ᬩᬲᬩᬮᬶ" - ], - "bar": [ - "Latn", - [ - "EU" - ], - "Boarisch" - ], - "bat-smg": [ - "sgs" - ], - "bbc-latn": [ - "Latn", - [ - "AS" - ], - "Batak Toba" - ], - "bbc-batk": [ - "Batk", - [ - "AS" - ], - "ᯅᯖᯂ᯲ ᯖᯬᯅ" - ], - "bbc": [ - "bbc-latn" - ], - "bcc": [ - "Arab", - [ - "AS", - "ME" - ], - "جهلسری بلوچی" - ], - "bcl": [ - "Latn", - [ - "AS" - ], - "Bikol Central" - ], - "be-tarask": [ - "Cyrl", - [ - "EU" - ], - "беларуская (тарашкевіца)" - ], - "be-x-old": [ - "be-tarask" - ], - "be": [ - "Cyrl", - [ - "EU" - ], - "беларуская" - ], - "bew": [ - "Latn", - [ - "AS" - ], - "Bahasa Betawi" - ], - "bfa": [ - "Latn", - [ - "AF" - ], - "Bari" - ], - "bft": [ - "Arab", - [ - "AS" - ], - "بلتی" - ], - "bfq": [ - "Taml", - [ - "AS" - ], - "படகா" - ], - "bg": [ - "Cyrl", - [ - "EU" - ], - "български" - ], - "bgn": [ - "Arab", - [ - "AS", - "ME" - ], - "روچ کپتین بلوچی" - ], - "bh": [ - "bho" - ], - "bho": [ - "Deva", - [ - "AS" - ], - "भोजपुरी" - ], - "bi": [ - "Latn", - [ - "PA" - ], - "Bislama" - ], - "bjn": [ - "Latn", - [ - "AS" - ], - "Bahasa Banjar" - ], - "bm": [ - "Latn", - [ - "AF" - ], - "bamanankan" - ], - "bn": [ - "Beng", - [ - "AS" - ], - "বাংলা" - ], - "bo": [ - "Tibt", - [ - "AS" - ], - "བོད་ཡིག" - ], - "bpy": [ - "Beng", - [ - "AS" - ], - "বিষ্ণুপ্রিয়া মণিপুরী" - ], - "bqi": [ - "Arab", - [ - "AS", - "ME" - ], - "بختیاری" - ], - "br": [ - "Latn", - [ - "EU" - ], - "brezhoneg" - ], - "brh": [ - "Latn", - [ - "ME", - "AS" - ], - "Bráhuí" - ], - "brx": [ - "Deva", - [ - "AS" - ], - "बड़ो" - ], - "bs": [ - "Latn", - [ - "EU" - ], - "bosanski" - ], - "bto": [ - "Latn", - [ - "AS" - ], - "Iriga Bicolano" - ], - "bug": [ - "Bugi", - [ - "AS" - ], - "ᨅᨔ ᨕᨘᨁᨗ" - ], - "bxr": [ - "Cyrl", - [ - "AS" - ], - "буряад" - ], - "byn": [ - "Ethi", - [ - "AF" - ], - "ብሊን" - ], - "ca": [ - "Latn", - [ - "EU" - ], - "català" - ], - "cbk-zam": [ - "Latn", - [ - "AS" - ], - "Chavacano de Zamboanga" - ], - "cdo": [ - "Latn", - [ - "AS" - ], - "Mìng-dĕ̤ng-ngṳ̄" - ], - "ce": [ - "Cyrl", - [ - "EU" - ], - "нохчийн" - ], - "ceb": [ - "Latn", - [ - "AS" - ], - "Cebuano" - ], - "ch": [ - "Latn", - [ - "PA" - ], - "Chamoru" - ], - "chm": [ - "mhr" - ], - "cho": [ - "Latn", - [ - "AM" - ], - "Choctaw" - ], - "chr": [ - "Cher", - [ - "AM" - ], - "ᏣᎳᎩ" - ], - "chy": [ - "Latn", - [ - "AM" - ], - "Tsetsêhestâhese" - ], - "ciw": [ - "Latn", - [ - "AM" - ], - "Ojibwemowin" - ], - "cjy": [ - "cjy-hant" - ], - "cjy-hans": [ - "Hans", - [ - "AS" - ], - "晋语（简化字)" - ], - "cjy-hant": [ - "Hant", - [ - "AS" - ], - "晉語" - ], - "ckb": [ - "Arab", - [ - "ME" - ], - "کوردی" - ], - "cnh": [ - "Latn", - [ - "AS" - ], - "Lai holh" - ], - "co": [ - "Latn", - [ - "EU" - ], - "corsu" - ], - "cop": [ - "Copt", - [ - "AF", - "ME" - ], - "ϯⲙⲉⲧⲣⲉⲙⲛ̀ⲭⲏⲙⲓ" - ], - "cps": [ - "Latn", - [ - "AS" - ], - "Capiceño" - ], - "cr": [ - "Cans", - [ - "AM" - ], - "ᓀᐦᐃᔭᐍᐏᐣ" - ], - "cr-cans": [ - "cr" - ], - "cr-latn": [ - "Latn", - [ - "AM" - ], - "Nēhiyawēwin" - ], - "crh": [ - "Latn", - [ - "EU" - ], - "qırımtatarca" - ], - "crh-cyrl": [ - "Cyrl", - [ - "EU" - ], - "къырымтатарджа" - ], - "crh-latn": [ - "crh" - ], - "cs": [ - "Latn", - [ - "EU" - ], - "čeština" - ], - "csb": [ - "Latn", - [ - "EU" - ], - "kaszëbsczi" - ], - "cu": [ - "Cyrl", - [ - "EU" - ], - "словѣньскъ \/ ⰔⰎⰑⰂⰡⰐⰠⰔⰍⰟ" - ], - "cv": [ - "Cyrl", - [ - "EU" - ], - "Чӑвашла" - ], - "cy": [ - "Latn", - [ - "EU" - ], - "Cymraeg" - ], - "da": [ - "Latn", - [ - "EU" - ], - "dansk" - ], - "dag": [ - "Latn", - [ - "AF" - ], - "dagbanli" - ], - "de-at": [ - "Latn", - [ - "EU" - ], - "Österreichisches Deutsch" - ], - "de-ch": [ - "Latn", - [ - "EU" - ], - "Schweizer Hochdeutsch" - ], - "de-formal": [ - "Latn", - [ - "EU" - ], - "Deutsch (Sie-Form)" - ], - "de": [ - "Latn", - [ - "EU" - ], - "Deutsch" - ], - "din": [ - "Latn", - [ - "AF" - ], - "Thuɔŋjäŋ" - ], - "diq": [ - "Latn", - [ - "EU", - "AS" - ], - "Zazaki" - ], - "doi": [ - "Deva", - [ - "AS" - ], - "डोगरी" - ], - "dsb": [ - "Latn", - [ - "EU" - ], - "dolnoserbski" - ], - "dtp": [ - "Latn", - [ - "AS" - ], - "Dusun Bundu-liwan" - ], - "dty": [ - "Deva", - [ - "AS" - ], - "डोटेली" - ], - "dv": [ - "Thaa", - [ - "AS" - ], - "ދިވެހިބަސް" - ], - "dz": [ - "Tibt", - [ - "AS" - ], - "ཇོང་ཁ" - ], - "ee": [ - "Latn", - [ - "AF" - ], - "eʋegbe" - ], - "egl": [ - "Latn", - [ - "EU" - ], - "Emiliàn" - ], - "el": [ - "Grek", - [ - "EU" - ], - "Ελληνικά" - ], - "eml": [ - "Latn", - [ - "EU" - ], - "emiliàn e rumagnòl" - ], - "en-ca": [ - "Latn", - [ - "AM" - ], - "Canadian English" - ], - "en-gb": [ - "Latn", - [ - "EU", - "AS", - "PA" - ], - "British English" - ], - "en": [ - "Latn", - [ - "EU", - "AM", - "AF", - "ME", - "AS", - "PA", - "WW" - ], - "English" - ], - "eo": [ - "Latn", - [ - "WW" - ], - "Esperanto" - ], - "es-419": [ - "Latn", - [ - "AM" - ], - "español de America Latina" - ], - "es-formal": [ - "Latn", - [ - "EU", - "AM", - "AF", - "WW" - ], - "español (formal)" - ], - "es": [ - "Latn", - [ - "EU", - "AM", - "AF", - "WW" - ], - "español" - ], - "es-ni": [ - "Latn", - [ - "AM" - ], - "español nicaragüense" - ], - "esu": [ - "Latn", - [ - "AM" - ], - "Yup'ik" - ], - "et": [ - "Latn", - [ - "EU" - ], - "eesti" - ], - "eu": [ - "Latn", - [ - "EU" - ], - "euskara" - ], - "ext": [ - "Latn", - [ - "EU" - ], - "estremeñu" - ], - "fa": [ - "Arab", - [ - "AS", - "ME" - ], - "فارسی" - ], - "fax": [ - "Latn", - [ - "EU" - ], - "Fala" - ], - "ff": [ - "Latn", - [ - "AF" - ], - "Fulfulde" - ], - "fi": [ - "Latn", - [ - "EU" - ], - "suomi" - ], - "fil": [ - "tl" - ], - "fit": [ - "Latn", - [ - "EU" - ], - "meänkieli" - ], - "fiu-vro": [ - "vro" - ], - "fj": [ - "Latn", - [ - "PA" - ], - "Na Vosa Vakaviti" - ], - "fo": [ - "Latn", - [ - "EU" - ], - "føroyskt" - ], - "fr": [ - "Latn", - [ - "EU", - "AM", - "WW" - ], - "français" - ], - "frc": [ - "Latn", - [ - "AM" - ], - "français cadien" - ], - "frp": [ - "Latn", - [ - "EU" - ], - "arpetan" - ], - "frr": [ - "Latn", - [ - "EU" - ], - "Nordfriisk" - ], - "fur": [ - "Latn", - [ - "EU" - ], - "furlan" - ], - "fy": [ - "Latn", - [ - "EU" - ], - "Frysk" - ], - "ga": [ - "Latn", - [ - "EU" - ], - "Gaeilge" - ], - "gaa": [ - "Latn", - [ - "AF" - ], - "Ga" - ], - "gag": [ - "Latn", - [ - "EU" - ], - "Gagauz" - ], - "gah": [ - "Latn", - [ - "AS" - ], - "Alekano" - ], - "gan-hans": [ - "Hans", - [ - "AS" - ], - "赣语（简体）" - ], - "gan-hant": [ - "gan" - ], - "gan": [ - "Hant", - [ - "AS" - ], - "贛語" - ], - "gbz": [ - "Latn", - [ - "AS" - ], - "Dari-e Mazdeyasnā" - ], - "gcf": [ - "Latn", - [ - "AM" - ], - "Guadeloupean Creole French" - ], - "gd": [ - "Latn", - [ - "EU" - ], - "Gàidhlig" - ], - "gl": [ - "Latn", - [ - "EU" - ], - "galego" - ], - "glk": [ - "Arab", - [ - "AS", - "ME" - ], - "گیلکی" - ], - "gn": [ - "Latn", - [ - "AM" - ], - "Avañe'ẽ" - ], - "gom": [ - "gom-deva" - ], - "gom-deva": [ - "Deva", - [ - "AS" - ], - "गोंयची कोंकणी" - ], - "gom-latn": [ - "Latn", - [ - "AS" - ], - "Gõychi Konknni" - ], - "got": [ - "Goth", - [ - "EU" - ], - "𐌲𐌿𐍄𐌹𐍃𐌺" - ], - "grc": [ - "Grek", - [ - "EU" - ], - "Ἀρχαία ἑλληνικὴ" - ], - "gsw": [ - "Latn", - [ - "EU" - ], - "Alemannisch" - ], - "gu": [ - "Gujr", - [ - "AS" - ], - "ગુજરાતી" - ], - "guc": [ - "Latn", - [ - "AM" - ], - "Wayúu" - ], - "gum": [ - "Latn", - [ - "AM" - ], - "Namtrik" - ], - "gur": [ - "Latn", - [ - "AF" - ], - "Gurenɛ" - ], - "gv": [ - "Latn", - [ - "EU" - ], - "Gaelg" - ], - "ha-arab": [ - "Arab", - [ - "AF" - ], - "هَوُسَ" - ], - "ha-latn": [ - "Latn", - [ - "AF" - ], - "Hausa" - ], - "ha": [ - "ha-latn" - ], - "hak": [ - "Latn", - [ - "AS" - ], - "Hak-kâ-fa" - ], - "haw": [ - "Latn", - [ - "AM", - "PA" - ], - "Hawai`i" - ], - "he": [ - "Hebr", - [ - "ME" - ], - "עברית" - ], - "hak-hans": [ - "Hans", - [ - "AS" - ], - "客家语（简体）" - ], - "hak-hant": [ - "Hant", - [ - "AS" - ], - "客家語（繁體）" - ], - "hi": [ - "Deva", - [ - "AS" - ], - "हिन्दी" - ], - "hif": [ - "Latn", - [ - "PA", - "AS" - ], - "Fiji Hindi" - ], - "hif-deva": [ - "Deva", - [ - "AS" - ], - "फ़ीजी हिन्दी" - ], - "hif-latn": [ - "hif" - ], - "hil": [ - "Latn", - [ - "AS" - ], - "Ilonggo" - ], - "hne": [ - "Deva", - [ - "AS" - ], - "छत्तीसगढ़ी" - ], - "ho": [ - "Latn", - [ - "PA" - ], - "Hiri Motu" - ], - "hoc": [ - "Wara", - [ - "AS" - ], - "𑢹𑣉𑣉" - ], - "hr": [ - "Latn", - [ - "EU" - ], - "hrvatski" - ], - "hrx": [ - "Latn", - [ - "AM" - ], - "Hunsrik" - ], - "hsb": [ - "Latn", - [ - "EU" - ], - "hornjoserbsce" - ], - "hsn": [ - "Hans", - [ - "AS" - ], - "湘语" - ], - "ht": [ - "Latn", - [ - "AM" - ], - "Kreyòl ayisyen" - ], - "hu-formal": [ - "Latn", - [ - "EU" - ], - "Magyar (magázó)" - ], - "hu": [ - "Latn", - [ - "EU" - ], - "magyar" - ], - "hy": [ - "Armn", - [ - "EU", - "ME" - ], - "Հայերեն" - ], - "hz": [ - "Latn", - [ - "AF" - ], - "Otsiherero" - ], - "ia": [ - "Latn", - [ - "WW" - ], - "interlingua" - ], - "id": [ - "Latn", - [ - "AS" - ], - "Bahasa Indonesia" - ], - "ie": [ - "Latn", - [ - "WW" - ], - "Interlingue" - ], - "ig": [ - "Latn", - [ - "AF" - ], - "Igbo" - ], - "ii": [ - "Yiii", - [ - "AS" - ], - "ꆇꉙ" - ], - "ik": [ - "Latn", - [ - "AM" - ], - "Iñupiak" - ], - "ike-cans": [ - "Cans", - [ - "AM" - ], - "ᐃᓄᒃᑎᑐᑦ" - ], - "ike-latn": [ - "Latn", - [ - "AM" - ], - "inuktitut" - ], - "ilo": [ - "Latn", - [ - "AS" - ], - "Ilokano" - ], - "inh": [ - "Cyrl", - [ - "EU" - ], - "ГӀалгӀай" - ], - "io": [ - "Latn", - [ - "WW" - ], - "Ido" - ], - "is": [ - "Latn", - [ - "EU" - ], - "íslenska" - ], - "it": [ - "Latn", - [ - "EU" - ], - "italiano" - ], - "iu": [ - "ike-cans" - ], - "ja": [ - "Jpan", - [ - "AS" - ], - "日本語" - ], - "jam": [ - "Latn", - [ - "AM" - ], - "Patois" - ], - "jbo": [ - "Latn", - [ - "WW" - ], - "lojban" - ], - "jdt": [ - "jdt-cyrl" - ], - "jdt-cyrl": [ - "Cyrl", - [ - "EU", - "AS" - ], - "жугьури" - ], - "jut": [ - "Latn", - [ - "EU" - ], - "jysk" - ], - "jv": [ - "Latn", - [ - "AS", - "PA" - ], - "Basa Jawa" - ], - "jv-java": [ - "Java", - [ - "AS", - "PA" - ], - "ꦧꦱꦗꦮ" - ], - "ka": [ - "Geor", - [ - "EU" - ], - "ქართული" - ], - "kaa": [ - "Latn", - [ - "AS" - ], - "Qaraqalpaqsha" - ], - "kab": [ - "Latn", - [ - "AF", - "EU" - ], - "Taqbaylit" - ], - "kac": [ - "Latn", - [ - "AS" - ], - "Jinghpaw" - ], - "kbd-cyrl": [ - "kbd" - ], - "kbd-latn": [ - "Latn", - [ - "EU" - ], - "Qabardjajəbza" - ], - "kbd": [ - "Cyrl", - [ - "EU", - "ME" - ], - "Адыгэбзэ" - ], - "kbp": [ - "Latn", - [ - "AF" - ], - "Kabɩyɛ" - ], - "kea": [ - "Latn", - [ - "AF" - ], - "Kabuverdianu" - ], - "kg": [ - "Latn", - [ - "AF" - ], - "Kongo" - ], - "kgp": [ - "Latn", - [ - "AM" - ], - "Kaingáng" - ], - "khw": [ - "Arab", - [ - "ME", - "AS" - ], - "کھوار" - ], - "ki": [ - "Latn", - [ - "AF" - ], - "Gĩkũyũ" - ], - "kiu": [ - "Latn", - [ - "EU", - "ME" - ], - "Kırmancki" - ], - "kj": [ - "Latn", - [ - "AF" - ], - "Kwanyama" - ], - "kjh": [ - "Cyrl", - [ - "AS" - ], - "хакас" - ], - "kk": [ - "kk-cyrl" - ], - "kk-arab": [ - "Arab", - [ - "EU", - "AS" - ], - "قازاقشا (تٶتە)" - ], - "kk-cn": [ - "kk-arab" - ], - "kk-cyrl": [ - "Cyrl", - [ - "EU", - "AS" - ], - "қазақша" - ], - "kk-kz": [ - "kk-cyrl" - ], - "kk-latn": [ - "Latn", - [ - "EU", - "AS", - "ME" - ], - "qazaqşa" - ], - "kk-tr": [ - "kk-latn" - ], - "kl": [ - "Latn", - [ - "AM", - "EU" - ], - "kalaallisut" - ], - "km": [ - "Khmr", - [ - "AS" - ], - "ភាសាខ្មែរ" - ], - "kn": [ - "Knda", - [ - "AS" - ], - "ಕನ್ನಡ" - ], - "knn": [ - "Deva", - [ - "AS" - ], - "महाराष्ट्रीय कोंकणी" - ], - "ko-kp": [ - "Kore", - [ - "AS" - ], - "한국어 (조선)" - ], - "ko": [ - "Kore", - [ - "AS" - ], - "한국어" - ], - "koi": [ - "Cyrl", - [ - "EU" - ], - "Перем Коми" - ], - "kr": [ - "Latn", - [ - "AF" - ], - "Kanuri" - ], - "krc": [ - "Cyrl", - [ - "EU" - ], - "къарачай-малкъар" - ], - "kri": [ - "Latn", - [ - "AF" - ], - "Krio" - ], - "krj": [ - "Latn", - [ - "ME", - "EU" - ], - "Kinaray-a" - ], - "krl": [ - "Latn", - [ - "EU" - ], - "Karjala" - ], - "ks-arab": [ - "Arab", - [ - "AS" - ], - "کٲشُر" - ], - "ks-deva": [ - "Deva", - [ - "AS" - ], - "कॉशुर" - ], - "ks": [ - "ks-arab" - ], - "ksf": [ - "Latn", - [ - "AF" - ], - "Bafia" - ], - "ksh": [ - "Latn", - [ - "EU" - ], - "Ripoarisch" - ], - "ku": [ - "ku-latn" - ], - "ku-arab": [ - "Arab", - [ - "EU", - "ME" - ], - "كوردي" - ], - "ku-latn": [ - "Latn", - [ - "EU", - "ME" - ], - "Kurdî" - ], - "kv": [ - "Cyrl", - [ - "EU" - ], - "коми" - ], - "kw": [ - "Latn", - [ - "EU" - ], - "kernowek" - ], - "ky": [ - "Cyrl", - [ - "AS" - ], - "Кыргызча" - ], - "la": [ - "Latn", - [ - "EU" - ], - "Latina" - ], - "lad": [ - "lad-latn" - ], - "lad-latn": [ - "Latn", - [ - "ME", - "EU", - "AM" - ], - "Ladino" - ], - "lad-hebr": [ - "Hebr", - [ - "ME", - "EU", - "AM" - ], - "לאדינו" - ], - "lag": [ - "Latn", - [ - "AF" - ], - "Kilaangi" - ], - "lb": [ - "Latn", - [ - "EU" - ], - "Lëtzebuergesch" - ], - "lbe": [ - "Cyrl", - [ - "EU" - ], - "лакку" - ], - "lez": [ - "Cyrl", - [ - "EU" - ], - "лезги" - ], - "lfn": [ - "Latn", - [ - "WW" - ], - "Lingua Franca Nova" - ], - "lg": [ - "Latn", - [ - "AF" - ], - "Luganda" - ], - "li": [ - "Latn", - [ - "EU" - ], - "Limburgs" - ], - "lij": [ - "Latn", - [ - "EU" - ], - "Ligure" - ], - "liv": [ - "Latn", - [ - "EU" - ], - "Līvõ kēļ" - ], - "lki": [ - "Arab", - [ - "AS", - "ME" - ], - "لەکی" - ], - "lkt": [ - "Latn", - [ - "AM" - ], - "Lakȟótiyapi" - ], - "lld": [ - "Latn", - [ - "EU" - ], - "Ladin" - ], - "lmo": [ - "Latn", - [ - "EU" - ], - "lumbaart" - ], - "ln": [ - "Latn", - [ - "AF" - ], - "lingála" - ], - "lo": [ - "Laoo", - [ - "AS" - ], - "ລາວ" - ], - "loz": [ - "Latn", - [ - "AF" - ], - "Silozi" - ], - "lt": [ - "Latn", - [ - "EU" - ], - "lietuvių" - ], - "lrc": [ - "Arab", - [ - "AS", - "ME" - ], - "لۊری شومالی" - ], - "ltg": [ - "Latn", - [ - "EU" - ], - "latgaļu" - ], - "lud": [ - "Latn", - [ - "EU" - ], - "lüüdi" - ], - "lus": [ - "Latn", - [ - "AS" - ], - "Mizo ţawng" - ], - "lut": [ - "Latn", - [ - "AM" - ], - "dxʷləšucid" - ], - "luz": [ - "Arab", - [ - "ME" - ], - "لئری دوٙمینی" - ], - "lv": [ - "Latn", - [ - "EU" - ], - "latviešu" - ], - "lzh": [ - "Hant", - [ - "AS" - ], - "文言" - ], - "lzz": [ - "Latn", - [ - "EU", - "ME" - ], - "Lazuri" - ], - "mai": [ - "Deva", - [ - "AS" - ], - "मैथिली" - ], - "map-bms": [ - "Latn", - [ - "AS" - ], - "Basa Banyumasan" - ], - "mdf": [ - "Cyrl", - [ - "EU" - ], - "мокшень" - ], - "mfe": [ - "Latn", - [ - "AM" - ], - "Morisyen" - ], - "mg": [ - "Latn", - [ - "AF" - ], - "Malagasy" - ], - "mh": [ - "Latn", - [ - "PA" - ], - "Ebon" - ], - "mhr": [ - "Cyrl", - [ - "EU" - ], - "олык марий" - ], - "mi": [ - "Latn", - [ - "PA" - ], - "Māori" - ], - "mic": [ - "Latn", - [ - "AM" - ], - "Mi'kmaq" - ], - "min": [ - "Latn", - [ - "AS" - ], - "Baso Minangkabau" - ], - "miq": [ - "Latn", - [ - "AM" - ], - "Mískitu" - ], - "mk": [ - "Cyrl", - [ - "EU" - ], - "македонски" - ], - "ml": [ - "Mlym", - [ - "AS", - "ME" - ], - "മലയാളം" - ], - "mn": [ - "Cyrl", - [ - "AS" - ], - "монгол" - ], - "mnc": [ - "Mong", - [ - "AS" - ], - "ᠮᠠᠨᠵᡠ ᡤᡳᠰᡠᠨ" - ], - "mni": [ - "Beng", - [ - "AS" - ], - "মেইতেই লোন্" - ], - "mnw": [ - "Mymr", - [ - "AS" - ], - "ဘာသာ မန်" - ], - "mo": [ - "Cyrl", - [ - "EU" - ], - "молдовеняскэ" - ], - "mr": [ - "Deva", - [ - "AS", - "ME" - ], - "मराठी" - ], - "mrj": [ - "Cyrl", - [ - "EU" - ], - "кырык мары" - ], - "ms": [ - "Latn", - [ - "AS" - ], - "Bahasa Melayu" - ], - "mt": [ - "Latn", - [ - "EU" - ], - "Malti" - ], - "mui": [ - "Latn", - [ - "AS" - ], - "Musi" - ], - "mus": [ - "Latn", - [ - "AM" - ], - "Mvskoke" - ], - "mwl": [ - "Latn", - [ - "EU" - ], - "Mirandés" - ], - "mwv": [ - "Latn", - [ - "AS" - ], - "Behase Mentawei" - ], - "mww": [ - "mww-latn" - ], - "mww-latn": [ - "Latn", - [ - "AS" - ], - "Hmoob Dawb" - ], - "my": [ - "Mymr", - [ - "AS" - ], - "မြန်မာဘာသာ" - ], - "myv": [ - "Cyrl", - [ - "EU" - ], - "эрзянь" - ], - "mzn": [ - "Arab", - [ - "ME", - "AS" - ], - "مازِرونی" - ], - "na": [ - "Latn", - [ - "PA" - ], - "Dorerin Naoero" - ], - "nah": [ - "Latn", - [ - "AM" - ], - "Nāhuatl" - ], - "nan": [ - "Latn", - [ - "AS" - ], - "Bân-lâm-gú" - ], - "nap": [ - "Latn", - [ - "EU" - ], - "Napulitano" - ], - "nb": [ - "Latn", - [ - "EU" - ], - "norsk (bokmål)" - ], - "nds-nl": [ - "Latn", - [ - "EU" - ], - "Nedersaksisch" - ], - "nds": [ - "Latn", - [ - "EU" - ], - "Plattdüütsch" - ], - "ne": [ - "Deva", - [ - "AS" - ], - "नेपाली" - ], - "new": [ - "Deva", - [ - "AS" - ], - "नेपाल भाषा" - ], - "ng": [ - "Latn", - [ - "AF" - ], - "Oshiwambo" - ], - "niu": [ - "Latn", - [ - "PA" - ], - "ko e vagahau Niuē" - ], - "njo": [ - "Latn", - [ - "AS" - ], - "Ao" - ], - "nl-informal": [ - "Latn", - [ - "EU", - "AM" - ], - "Nederlands (informeel)" - ], - "nl": [ - "Latn", - [ - "EU", - "AM" - ], - "Nederlands" - ], - "nn": [ - "Latn", - [ - "EU" - ], - "norsk (nynorsk)" - ], - "no": [ - "Latn", - [ - "EU" - ], - "norsk" - ], - "nod": [ - "Thai", - [ - "AS" - ], - "คำเมือง" - ], - "nov": [ - "Latn", - [ - "WW" - ], - "Novial" - ], - "nqo": [ - "Nkoo", - [ - "AF" - ], - "ߒߞߏ" - ], - "nrm": [ - "Latn", - [ - "EU" - ], - "Nouormand" - ], - "nso": [ - "Latn", - [ - "AF" - ], - "Sesotho sa Leboa" - ], - "nv": [ - "Latn", - [ - "AM" - ], - "Diné bizaad" - ], - "ny": [ - "Latn", - [ - "AF" - ], - "Chi-Chewa" - ], - "nys": [ - "Latn", - [ - "PA" - ], - "Nyungar" - ], - "oc": [ - "Latn", - [ - "EU" - ], - "occitan" - ], - "olo": [ - "Latn", - [ - "AS", - "EU" - ], - "Livvinkarjala" - ], - "om": [ - "Latn", - [ - "AF" - ], - "Oromoo" - ], - "or": [ - "Orya", - [ - "AS" - ], - "ଓଡ଼ିଆ" - ], - "os": [ - "Cyrl", - [ - "EU" - ], - "Ирон" - ], - "ota": [ - "Arab", - [ - "AS", - "EU" - ], - "لسان عثمانى" - ], - "ovd": [ - "Latn", - [ - "EU" - ], - "övdalsk" - ], - "pa": [ - "pa-guru" - ], - "pa-guru": [ - "Guru", - [ - "AS" - ], - "ਪੰਜਾਬੀ" - ], - "pag": [ - "Latn", - [ - "AS" - ], - "Pangasinan" - ], - "pam": [ - "Latn", - [ - "AS" - ], - "Kapampangan" - ], - "pap": [ - "Latn", - [ - "AM" - ], - "Papiamentu" - ], - "pbb": [ - "Latn", - [ - "AM" - ], - "Nasa Yuwe" - ], - "pcd": [ - "Latn", - [ - "EU" - ], - "Picard" - ], - "pdc": [ - "Latn", - [ - "EU", - "AM" - ], - "Deitsch" - ], - "pdt": [ - "Latn", - [ - "EU", - "AM" - ], - "Plautdietsch" - ], - "pfl": [ - "Latn", - [ - "EU" - ], - "Pälzisch" - ], - "pi": [ - "Deva", - [ - "AS" - ], - "पालि" - ], - "pih": [ - "Latn", - [ - "PA" - ], - "Norfuk \/ Pitkern" - ], - "pis": [ - "Latn", - [ - "PA" - ], - "Pijin" - ], - "pko": [ - "Latn", - [ - "AF" - ], - "Pökoot" - ], - "pl": [ - "Latn", - [ - "EU" - ], - "polski" - ], - "pms": [ - "Latn", - [ - "EU" - ], - "Piemontèis" - ], - "pnb": [ - "Arab", - [ - "AS", - "ME" - ], - "پنجابی" - ], - "pnt": [ - "Grek", - [ - "EU" - ], - "Ποντιακά" - ], - "ppl": [ - "Latn", - [ - "AM" - ], - "Nawat" - ], - "prg": [ - "Latn", - [ - "EU" - ], - "Prūsiskan" - ], - "prs": [ - "Arab", - [ - "AS", - "ME" - ], - "دری" - ], - "ps": [ - "Arab", - [ - "AS", - "ME" - ], - "پښتو" - ], - "pt-br": [ - "Latn", - [ - "AM" - ], - "português do Brasil" - ], - "pt": [ - "Latn", - [ - "EU", - "AM", - "AS", - "PA", - "AF", - "WW" - ], - "português" - ], - "qu": [ - "Latn", - [ - "AM" - ], - "Runa Simi" - ], - "qug": [ - "Latn", - [ - "AM" - ], - "Runa shimi" - ], - "rap": [ - "Latn", - [ - "AM" - ], - "arero rapa nui" - ], - "rcf": [ - "Latn", - [ - "AF" - ], - "Kreol Réyoné" - ], - "rgn": [ - "Latn", - [ - "EU" - ], - "Rumagnôl" - ], - "rif": [ - "Latn", - [ - "AF" - ], - "Tarifit" - ], - "rki": [ - "Mymr", - [ - "AS" - ], - "ရခိုင်" - ], - "rm": [ - "Latn", - [ - "EU" - ], - "rumantsch" - ], - "rmf": [ - "Latn", - [ - "EU" - ], - "kaalengo tšimb" - ], - "rmy": [ - "Latn", - [ - "EU" - ], - "Romani" - ], - "rn": [ - "Latn", - [ - "AF" - ], - "Kirundi" - ], - "ro": [ - "Latn", - [ - "EU" - ], - "română" - ], - "roa-rup": [ - "rup" - ], - "roa-tara": [ - "Latn", - [ - "EU" - ], - "tarandíne" - ], - "rtm": [ - "Latn", - [ - "PA" - ], - "Faeag Rotuma" - ], - "ru": [ - "Cyrl", - [ - "EU", - "AS", - "ME" - ], - "русский" - ], - "rue": [ - "Cyrl", - [ - "EU" - ], - "русиньскый" - ], - "rup": [ - "Latn", - [ - "EU" - ], - "armãneashti" - ], - "ruq": [ - "Cyrl", - [ - "EU" - ], - "Влахесте" - ], - "ruq-cyrl": [ - "ruq" - ], - "ruq-grek": [ - "Grek", - [ - "EU" - ], - "Megleno-Romanian (Greek script)" - ], - "ruq-latn": [ - "Latn", - [ - "EU" - ], - "Vlăheşte" - ], - "rut": [ - "Cyrl", - [ - "EU" - ], - "мыхаӀбишды" - ], - "rw": [ - "Latn", - [ - "AF" - ], - "Kinyarwanda" - ], - "rwr": [ - "Deva", - [ - "AS" - ], - "मारवाड़ी" - ], - "ryu": [ - "Kana", - [ - "AS" - ], - "ʔucināguci" - ], - "sa": [ - "Deva", - [ - "AS" - ], - "संस्कृतम्" - ], - "sah": [ - "Cyrl", - [ - "EU", - "AS" - ], - "саха тыла" - ], - "sat": [ - "Latn", - [ - "AS" - ], - "Santali" - ], - "saz": [ - "Saur", - [ - "AS" - ], - "ꢱꣃꢬꢵꢯ꣄ꢡ꣄ꢬꢵ" - ], - "sc": [ - "Latn", - [ - "EU" - ], - "sardu" - ], - "scn": [ - "Latn", - [ - "EU" - ], - "sicilianu" - ], - "sco": [ - "Latn", - [ - "EU" - ], - "Scots" - ], - "sd": [ - "Arab", - [ - "AS" - ], - "سنڌي" - ], - "sdc": [ - "Latn", - [ - "EU" - ], - "Sassaresu" - ], - "sdh": [ - "Arab", - [ - "ME" - ], - "کوردی خوارگ" - ], - "se": [ - "Latn", - [ - "EU" - ], - "sámegiella" - ], - "ses": [ - "Latn", - [ - "AF" - ], - "Koyraboro Senni" - ], - "sei": [ - "Latn", - [ - "AM" - ], - "Cmique Itom" - ], - "sg": [ - "Latn", - [ - "AF" - ], - "Sängö" - ], - "sgs": [ - "Latn", - [ - "EU" - ], - "žemaitėška" - ], - "sh": [ - "Latn", - [ - "EU" - ], - "srpskohrvatski" - ], - "shi-latn": [ - "Latn", - [ - "AF" - ], - "Tašlḥiyt" - ], - "shi-tfng": [ - "Tfng", - [ - "AF" - ], - "ⵜⴰⵛⵍⵃⵉⵜ" - ], - "shi": [ - "shi-latn" - ], - "shn": [ - "Mymr", - [ - "AS" - ], - "လိၵ်ႈတႆး" - ], - "si": [ - "Sinh", - [ - "AS" - ], - "සිංහල" - ], - "simple": [ - "Latn", - [ - "WW" - ], - "Simple English" - ], - "sjo": [ - "Mong", - [ - "AS" - ], - "ᠰᡞᠪᡝ ᡤᡞᠰᡠᠨ" - ], - "sk": [ - "Latn", - [ - "EU" - ], - "slovenčina" - ], - "sl": [ - "Latn", - [ - "EU" - ], - "slovenščina" - ], - "sli": [ - "Latn", - [ - "EU" - ], - "Schläsch" - ], - "slr": [ - "Latn", - [ - "AS" - ], - "Salırça" - ], - "sly": [ - "Latn", - [ - "AS" - ], - "Bahasa Selayar" - ], - "skr-arab": [ - "Arab", - [ - "AS" - ], - "سرائیکی" - ], - "skr": [ - "skr-arab" - ], - "syc": [ - "Syrc", - [ - "ME" - ], - "ܣܘܪܝܝܐ" - ], - "sm": [ - "Latn", - [ - "PA" - ], - "Gagana Samoa" - ], - "sma": [ - "Latn", - [ - "EU" - ], - "åarjelsaemien" - ], - "smj": [ - "Latn", - [ - "EU" - ], - "julevsámegiella" - ], - "smn": [ - "Latn", - [ - "EU" - ], - "anarâškielâ" - ], - "sms": [ - "Latn", - [ - "EU" - ], - "sää´mǩiõll" - ], - "sn": [ - "Latn", - [ - "AF" - ], - "chiShona" - ], - "so": [ - "Latn", - [ - "AF" - ], - "Soomaaliga" - ], - "son": [ - "Latn", - [ - "AF" - ], - "soŋay" - ], - "sq": [ - "Latn", - [ - "EU" - ], - "shqip" - ], - "sr": [ - "sr-cyrl" - ], - "sr-ec": [ - "sr-cyrl" - ], - "sr-cyrl": [ - "Cyrl", - [ - "EU" - ], - "српски" - ], - "sr-el": [ - "sr-latn" - ], - "sr-latn": [ - "Latn", - [ - "EU" - ], - "srpski" - ], - "srn": [ - "Latn", - [ - "AM", - "EU" - ], - "Sranantongo" - ], - "ss": [ - "Latn", - [ - "AF" - ], - "SiSwati" - ], - "st": [ - "Latn", - [ - "AF" - ], - "Sesotho" - ], - "stq": [ - "Latn", - [ - "EU" - ], - "Seeltersk" - ], - "sty": [ - "Cyrl", - [ - "EU", - "AS" - ], - "себертатар" - ], - "su": [ - "Latn", - [ - "AS" - ], - "Basa Sunda" - ], - "sv": [ - "Latn", - [ - "EU" - ], - "svenska" - ], - "sw": [ - "Latn", - [ - "AF" - ], - "Kiswahili" - ], - "swb": [ - "Latn", - [ - "AF" - ], - "Shikomoro" - ], - "sxu": [ - "Latn", - [ - "EU" - ], - "Säggssch" - ], - "szl": [ - "Latn", - [ - "EU" - ], - "ślůnski" - ], - "ta": [ - "Taml", - [ - "AS" - ], - "தமிழ்" - ], - "tay": [ - "Latn", - [ - "AS" - ], - "Tayal" - ], - "tcy": [ - "Knda", - [ - "AS" - ], - "ತುಳು" - ], - "te": [ - "Telu", - [ - "AS" - ], - "తెలుగు" - ], - "tet": [ - "Latn", - [ - "AS", - "PA" - ], - "tetun" - ], - "tg-cyrl": [ - "Cyrl", - [ - "AS" - ], - "тоҷикӣ" - ], - "tg-latn": [ - "Latn", - [ - "AS" - ], - "tojikī" - ], - "tg": [ - "tg-cyrl" - ], - "th": [ - "Thai", - [ - "AS" - ], - "ไทย" - ], - "ti": [ - "Ethi", - [ - "AF" - ], - "ትግርኛ" - ], - "tig": [ - "Ethi", - [ - "AF" - ], - "ትግረ" - ], - "tk": [ - "Latn", - [ - "AS" - ], - "Türkmençe" - ], - "tkr": [ - "Cyrl", - [ - "AS" - ], - "ЦӀаӀхна миз" - ], - "tl": [ - "Latn", - [ - "AS" - ], - "Tagalog" - ], - "tly": [ - "Cyrl", - [ - "EU", - "AS", - "ME" - ], - "толышә зывон" - ], - "tmr": [ - "Hebr", - [ - "ME", - "EU", - "AM" - ], - "ארמית בבלית" - ], - "tn": [ - "Latn", - [ - "AF" - ], - "Setswana" - ], - "to": [ - "Latn", - [ - "PA" - ], - "lea faka-Tonga" - ], - "tokipona": [ - "Latn", - [ - "WW" - ], - "Toki Pona" - ], - "tpi": [ - "Latn", - [ - "PA", - "AS" - ], - "Tok Pisin" - ], - "tr": [ - "Latn", - [ - "EU", - "ME" - ], - "Türkçe" - ], - "trp": [ - "Latn", - [ - "AS" - ], - "Kokborok (Tripuri)" - ], - "tru": [ - "Latn", - [ - "AS" - ], - "Ṫuroyo" - ], - "trv": [ - "Latn", - [ - "AS" - ], - "Sediq Taroko" - ], - "ts": [ - "Latn", - [ - "AF" - ], - "Xitsonga" - ], - "tsd": [ - "Grek", - [ - "EU" - ], - "Τσακωνικά" - ], - "tt": [ - "Cyrl", - [ - "EU" - ], - "татарча" - ], - "tt-cyrl": [ - "tt" - ], - "tt-latn": [ - "Latn", - [ - "EU" - ], - "tatarça" - ], - "ttt": [ - "Cyrl", - [ - "AS" - ], - "Tati" - ], - "tum": [ - "Latn", - [ - "AF" - ], - "chiTumbuka" - ], - "tw": [ - "Latn", - [ - "AF" - ], - "Twi" - ], - "twd": [ - "Latn", - [ - "EU" - ], - "Tweants" - ], - "ty": [ - "Latn", - [ - "PA" - ], - "reo tahiti" - ], - "tyv": [ - "Cyrl", - [ - "AS" - ], - "тыва дыл" - ], - "tzl": [ - "Latn", - [ - "WW" - ], - "Talossan" - ], - "tzm": [ - "Tfng", - [ - "AF" - ], - "ⵜⴰⵎⴰⵣⵉⵖⵜ" - ], - "udm": [ - "Cyrl", - [ - "EU" - ], - "удмурт" - ], - "ug": [ - "ug-arab" - ], - "ug-arab": [ - "Arab", - [ - "AS" - ], - "ئۇيغۇرچە" - ], - "ug-latn": [ - "Latn", - [ - "AS" - ], - "uyghurche" - ], - "ug-cyrl": [ - "Cyrl", - [ - "AS" - ], - "уйғурчә" - ], - "uk": [ - "Cyrl", - [ - "EU" - ], - "українська" - ], - "ur": [ - "Arab", - [ - "AS", - "ME" - ], - "اردو" - ], - "uz": [ - "Latn", - [ - "AS" - ], - "oʻzbekcha" - ], - "ve": [ - "Latn", - [ - "AF" - ], - "Tshivenda" - ], - "vec": [ - "Latn", - [ - "EU" - ], - "vèneto" - ], - "vep": [ - "Latn", - [ - "EU" - ], - "vepsän kel’" - ], - "vi": [ - "Latn", - [ - "AS" - ], - "Tiếng Việt" - ], - "vls": [ - "Latn", - [ - "EU" - ], - "West-Vlams" - ], - "vmf": [ - "Latn", - [ - "EU" - ], - "Mainfränkisch" - ], - "vo": [ - "Latn", - [ - "WW" - ], - "Volapük" - ], - "vot": [ - "Latn", - [ - "EU" - ], - "Vaďďa" - ], - "vro": [ - "Latn", - [ - "EU" - ], - "Võro" - ], - "wa": [ - "Latn", - [ - "EU" - ], - "walon" - ], - "war": [ - "Latn", - [ - "AS" - ], - "Winaray" - ], - "wls": [ - "Latn", - [ - "PA" - ], - "Faka'uvea" - ], - "wo": [ - "Latn", - [ - "AF" - ], - "Wolof" - ], - "wuu": [ - "Hans", - [ - "AS" - ], - "吴语" - ], - "xal": [ - "Cyrl", - [ - "EU" - ], - "хальмг" - ], - "xh": [ - "Latn", - [ - "AF" - ], - "isiXhosa" - ], - "xmf": [ - "Geor", - [ - "EU" - ], - "მარგალური" - ], - "xsy": [ - "Latn", - [ - "AS" - ], - "SaiSiyat" - ], - "ydd": [ - "Hebr", - [ - "AS", - "EU" - ], - "Eastern Yiddish" - ], - "yi": [ - "Hebr", - [ - "ME", - "EU", - "AM" - ], - "ייִדיש" - ], - "yo": [ - "Latn", - [ - "AF" - ], - "Yorùbá" - ], - "yrk": [ - "Cyrl", - [ - "AS" - ], - "Ненэцяʼ вада" - ], - "yrl": [ - "Latn", - [ - "AM" - ], - "ñe'engatú" - ], - "yua": [ - "Latn", - [ - "AM" - ], - "Maaya T'aan" - ], - "yue": [ - "Hant", - [ - "AS" - ], - "粵語" - ], - "za": [ - "Latn", - [ - "AS" - ], - "Vahcuengh" - ], - "zea": [ - "Latn", - [ - "EU" - ], - "Zeêuws" - ], - "zgh": [ - "Tfng", - [ - "AF" - ], - "ⵜⴰⵎⴰⵣⵉⵖⵜ ⵜⴰⵏⴰⵡⴰⵢⵜ" - ], - "zh": [ - "Hans", - [ - "AS" - ], - "中文" - ], - "zh-classical": [ - "lzh" - ], - "zh-cn": [ - "Hans", - [ - "AS" - ], - "中文（中国大陆）" - ], - "zh-hans": [ - "Hans", - [ - "AS" - ], - "中文（简体）" - ], - "zh-hant": [ - "Hant", - [ - "AS" - ], - "中文（繁體）" - ], - "zh-hk": [ - "Hant", - [ - "AS" - ], - "中文（香港）" - ], - "zh-min-nan": [ - "nan" - ], - "zh-mo": [ - "Hant", - [ - "AS" - ], - "中文（澳門）" - ], - "zh-my": [ - "Hans", - [ - "AS" - ], - "中文（马来西亚）" - ], - "zh-sg": [ - "Hans", - [ - "AS" - ], - "中文（新加坡）" - ], - "zh-tw": [ - "Hant", - [ - "AS" - ], - "中文（台灣）" - ], - "zh-yue": [ - "yue" - ], - "zu": [ - "Latn", - [ - "AF" - ], - "isiZulu" - ] - }, - "scriptgroups": { - "Latin": [ - "Latn", - "Goth" - ], - "Greek": [ - "Grek" - ], - "WestCaucasian": [ - "Armn", - "Geor" - ], - "Arabic": [ - "Arab" - ], - "MiddleEastern": [ - "Hebr", - "Syrc" - ], - "African": [ - "Ethi", - "Nkoo", - "Tfng", - "Copt" - ], - "SouthAsian": [ - "Beng", - "Deva", - "Gujr", - "Guru", - "Knda", - "Mlym", - "Orya", - "Saur", - "Sinh", - "Taml", - "Telu", - "Tibt", - "Thaa", - "Wara" - ], - "Cyrillic": [ - "Cyrl" - ], - "CJK": [ - "Hans", - "Hant", - "Kana", - "Kore", - "Jpan", - "Yiii" - ], - "SouthEastAsian": [ - "Bali", - "Batk", - "Bugi", - "Java", - "Khmr", - "Laoo", - "Mymr", - "Thai" - ], - "Mongolian": [ - "Mong" - ], - "SignWriting": [ - "Sgnw" - ], - "NativeAmerican": [ - "Cher", - "Cans" - ], - "Special": [ - "Zyyy" - ] - }, - "rtlscripts": [ - "Arab", - "Hebr", - "Syrc", - "Nkoo", - "Thaa" - ], - "regiongroups": { - "WW": 1, - "SP": 1, - "AM": 2, - "EU": 3, - "ME": 3, - "AF": 3, - "AS": 4, - "PA": 4 - }, - "territories": { - "AC": [ - "en" - ], - "AD": [ - "ca", - "es", - "fr" - ], - "AE": [ - "ar", - "ml", - "ps", - "fa" - ], - "AF": [ - "fa", - "ps", - "uz", - "tk", - "bgn", - "ug-arab", - "kk-arab", - "kk-cyrl" - ], - "AG": [ - "en", - "pt" - ], - "AI": [ - "en" - ], - "AL": [ - "sq", - "el", - "mk" - ], - "AM": [ - "hy", - "ku-latn", - "az-latn" - ], - "AO": [ - "pt", - "ln" - ], - "AR": [ - "es", - "en", - "cy", - "gn" - ], - "AS": [ - "sm", - "en" - ], - "AT": [ - "de", - "bar", - "en", - "fr", - "it", - "hr", - "sl", - "hu" - ], - "AU": [ - "en", - "zh-hant", - "zh", - "it" - ], - "AW": [ - "nl", - "pap", - "en" - ], - "AX": [ - "sv" - ], - "AZ": [ - "az-latn", - "az-cyrl", - "tly", - "ku-latn", - "ttt", - "tkr" - ], - "BA": [ - "bs", - "en", - "hr", - "sr-cyrl", - "sr-latn" - ], - "BB": [ - "en" - ], - "BD": [ - "bn", - "en", - "my", - "mni" - ], - "BE": [ - "en", - "nl", - "fr", - "de", - "vls", - "wa" - ], - "BF": [ - "fr" - ], - "BG": [ - "bg", - "en", - "ru", - "tr", - "de" - ], - "BH": [ - "ar", - "ml" - ], - "BI": [ - "rn", - "fr", - "sw", - "en" - ], - "BJ": [ - "fr", - "yo" - ], - "BL": [ - "fr" - ], - "BM": [ - "en" - ], - "BN": [ - "ms", - "zh-hant", - "zh", - "en" - ], - "BO": [ - "es", - "qu", - "ay", - "gn", - "aro" - ], - "BQ": [ - "pap", - "nl" - ], - "BR": [ - "pt", - "en", - "de", - "it", - "ja", - "es", - "ko", - "kgp", - "yrl" - ], - "BS": [ - "en" - ], - "BT": [ - "dz", - "ne", - "en" - ], - "BW": [ - "en", - "tn", - "af" - ], - "BY": [ - "be", - "ru" - ], - "BZ": [ - "en", - "es" - ], - "CA": [ - "en", - "fr", - "it", - "de", - "pdt", - "cr", - "yi", - "ike-cans", - "atj" - ], - "CC": [ - "ms", - "en" - ], - "CD": [ - "sw", - "fr", - "ln", - "kg", - "rw" - ], - "CF": [ - "fr", - "sg", - "ln" - ], - "CG": [ - "fr", - "ln" - ], - "CH": [ - "de", - "gsw", - "en", - "fr", - "it", - "lmo", - "pt", - "rm" - ], - "CI": [ - "fr" - ], - "CK": [ - "en" - ], - "CL": [ - "es", - "en", - "arn" - ], - "CM": [ - "fr", - "en", - "ff", - "ar", - "ksf", - "ha-arab", - "ha-latn" - ], - "CN": [ - "zh", - "wuu", - "yue", - "hsn", - "hak", - "nan", - "gan", - "ii", - "ug-arab", - "za", - "mn", - "bo", - "ko", - "kk-arab", - "kk-cyrl", - "ky", - "en", - "ru", - "vi", - "uz", - "lzh" - ], - "CO": [ - "es", - "guc" - ], - "CR": [ - "es" - ], - "CU": [ - "es" - ], - "CV": [ - "kea", - "pt" - ], - "CW": [ - "pap", - "nl", - "es" - ], - "CX": [ - "en" - ], - "CY": [ - "el", - "en", - "tr", - "fr", - "hy", - "ar" - ], - "CZ": [ - "cs", - "en", - "sk", - "de", - "pl" - ], - "DE": [ - "de", - "en", - "fr", - "bar", - "nds", - "nl", - "it", - "es", - "ru", - "vmf", - "tr", - "gsw", - "da", - "hr", - "ku-latn", - "el", - "ksh", - "pl", - "hsb", - "frr", - "dsb", - "stq", - "pfl" - ], - "DG": [ - "en" - ], - "DJ": [ - "aa", - "so", - "ar", - "fr" - ], - "DK": [ - "da", - "en", - "de", - "sv", - "fo", - "kl", - "jut" - ], - "DM": [ - "en" - ], - "DO": [ - "es", - "en" - ], - "DZ": [ - "arq", - "ar", - "fr", - "kab", - "en" - ], - "EA": [ - "es" - ], - "EC": [ - "es", - "qu", - "qug" - ], - "EE": [ - "et", - "ru", - "en", - "fi", - "vro" - ], - "EG": [ - "ar", - "arz", - "en", - "el" - ], - "EH": [ - "ar" - ], - "ER": [ - "ti", - "en", - "tig", - "ar", - "aa", - "byn" - ], - "ES": [ - "es", - "en", - "ca", - "gl", - "eu", - "ast", - "ext" - ], - "ET": [ - "en", - "am", - "om", - "so", - "ti", - "aa" - ], - "FI": [ - "fi", - "en", - "sv", - "de", - "ru", - "et", - "rmf", - "se", - "smn", - "sms" - ], - "FJ": [ - "en", - "hi", - "hif", - "fj", - "rtm" - ], - "FK": [ - "en" - ], - "FM": [ - "en" - ], - "FO": [ - "fo" - ], - "FR": [ - "fr", - "en", - "es", - "de", - "oc", - "it", - "pt", - "pcd", - "gsw", - "br", - "co", - "ca", - "nl", - "eu", - "frp", - "ia" - ], - "GA": [ - "fr" - ], - "GB": [ - "en", - "fr", - "de", - "sco", - "pa-guru", - "cy", - "bn", - "zh-hant", - "zh", - "el", - "it", - "ks-arab", - "gd", - "yi", - "ml", - "ga", - "kw" - ], - "GD": [ - "en" - ], - "GE": [ - "ka", - "xmf", - "ru", - "hy", - "ab", - "os", - "ku-latn" - ], - "GF": [ - "fr", - "zh-hant", - "zh" - ], - "GG": [ - "en" - ], - "GH": [ - "ak", - "en", - "ee", - "gur", - "gaa", - "ha-latn" - ], - "GI": [ - "en", - "es" - ], - "GL": [ - "kl", - "da" - ], - "GM": [ - "en" - ], - "GN": [ - "fr", - "ff", - "nqo" - ], - "GP": [ - "fr" - ], - "GQ": [ - "es", - "fr", - "pt" - ], - "GR": [ - "el", - "en", - "fr", - "de", - "pnt", - "mk", - "tr", - "bg", - "sq", - "tsd" - ], - "GT": [ - "es" - ], - "GU": [ - "en", - "ch" - ], - "GW": [ - "pt" - ], - "GY": [ - "en" - ], - "HK": [ - "zh-hant", - "zh", - "yue", - "en" - ], - "HN": [ - "es", - "en" - ], - "HR": [ - "hr", - "en", - "it" - ], - "HT": [ - "ht", - "fr" - ], - "HU": [ - "hu", - "en", - "de", - "fr", - "ro", - "hr", - "sk", - "sl" - ], - "IC": [ - "es" - ], - "ID": [ - "id", - "jv", - "su", - "ms", - "min", - "bew", - "ban", - "bug", - "bjn", - "ace", - "bbc-latn", - "zh-hant", - "zh", - "sly", - "mwv" - ], - "IE": [ - "en", - "ga", - "fr" - ], - "IL": [ - "he", - "en", - "ar", - "ru", - "ro", - "yi", - "pl", - "lad-latn", - "hu", - "am", - "ti", - "ml" - ], - "IM": [ - "en", - "gv" - ], - "IN": [ - "hi", - "en", - "bn", - "te", - "mr", - "ta", - "ur", - "gu", - "kn", - "ml", - "or", - "pa-guru", - "bho", - "as", - "mai", - "hne", - "ne", - "sat", - "ks-arab", - "gom-deva", - "sd", - "doi", - "tcy", - "brx", - "mni", - "hoc", - "saz", - "bfq", - "njo", - "bo", - "bpy", - "bft", - "sa", - "dv", - "dz" - ], - "IO": [ - "en" - ], - "IQ": [ - "ar", - "en", - "ckb", - "az-arab", - "az-latn", - "fa", - "lrc" - ], - "IR": [ - "fa", - "az-arab", - "az-latn", - "mzn", - "glk", - "ckb", - "sdh", - "tk", - "lrc", - "ar", - "bqi", - "luz", - "lki", - "bgn", - "hy", - "ps", - "ka", - "gbz", - "kk-arab", - "kk-cyrl" - ], - "IS": [ - "is", - "da" - ], - "IT": [ - "it", - "en", - "fr", - "sc", - "de", - "vec", - "nap", - "lij", - "scn", - "sl", - "sdc", - "fur", - "egl", - "ca", - "el", - "lmo", - "pms", - "hr", - "rgn" - ], - "JE": [ - "en" - ], - "JM": [ - "en", - "jam" - ], - "JO": [ - "ar", - "en" - ], - "JP": [ - "ja", - "ryu", - "ko" - ], - "KE": [ - "sw", - "en", - "ki", - "so", - "pko", - "om", - "ar", - "pa-guru", - "gu" - ], - "KG": [ - "ky", - "ru" - ], - "KH": [ - "km" - ], - "KI": [ - "en" - ], - "KM": [ - "ar", - "fr" - ], - "KN": [ - "en" - ], - "KP": [ - "ko" - ], - "KR": [ - "ko" - ], - "KW": [ - "ar" - ], - "KY": [ - "en" - ], - "KZ": [ - "ru", - "kk-cyrl", - "en", - "de", - "ug-cyrl", - "ug-arab" - ], - "LA": [ - "lo" - ], - "LB": [ - "ar", - "en", - "hy", - "ku-arab", - "ku-latn", - "fr" - ], - "LC": [ - "en" - ], - "LI": [ - "de", - "gsw" - ], - "LK": [ - "si", - "ta", - "en" - ], - "LR": [ - "en" - ], - "LS": [ - "st", - "en", - "zu", - "ss", - "xh" - ], - "LT": [ - "lt", - "ru", - "en", - "de", - "sgs" - ], - "LU": [ - "fr", - "lb", - "de", - "en", - "pt" - ], - "LV": [ - "lv", - "en", - "ru", - "ltg" - ], - "LY": [ - "ar" - ], - "MA": [ - "ary", - "ar", - "zgh", - "fr", - "en", - "tzm", - "shi-latn", - "rif", - "es" - ], - "MC": [ - "fr" - ], - "MD": [ - "ro", - "uk", - "bg", - "gag", - "ru" - ], - "ME": [ - "sr-latn", - "sr-cyrl", - "sq" - ], - "MF": [ - "fr" - ], - "MG": [ - "mg", - "fr", - "en" - ], - "MH": [ - "en", - "mh" - ], - "MK": [ - "mk", - "sq", - "tr" - ], - "ML": [ - "bm", - "fr", - "ses", - "ar" - ], - "MM": [ - "my", - "shn", - "kac", - "mnw" - ], - "MN": [ - "mn", - "kk-arab", - "kk-cyrl", - "zh", - "ru", - "ug-cyrl", - "ug-arab" - ], - "MO": [ - "zh-hant", - "zh", - "pt", - "en" - ], - "MP": [ - "en", - "ch" - ], - "MQ": [ - "fr" - ], - "MR": [ - "ar", - "fr", - "ff", - "wo" - ], - "MS": [ - "en" - ], - "MT": [ - "mt", - "en", - "it", - "fr" - ], - "MU": [ - "mfe", - "en", - "bho", - "ur", - "fr", - "ta" - ], - "MV": [ - "dv" - ], - "MW": [ - "en", - "ny", - "tum", - "zu" - ], - "MX": [ - "es", - "en", - "yua", - "sei" - ], - "MY": [ - "ms", - "en", - "zh-hant", - "zh", - "ta", - "jv", - "dtp", - "ml", - "bug", - "bjn" - ], - "MZ": [ - "pt", - "ts", - "ny", - "sw", - "zu" - ], - "NA": [ - "af", - "kj", - "ng", - "hz", - "en", - "de", - "tn" - ], - "NC": [ - "fr" - ], - "NE": [ - "ha-latn", - "fr", - "ar" - ], - "NF": [ - "en" - ], - "NG": [ - "en", - "ha-latn", - "ig", - "yo", - "ha-arab", - "ar" - ], - "NI": [ - "es" - ], - "NL": [ - "nl", - "en", - "de", - "fr", - "nds", - "li", - "fy", - "id", - "zea", - "rif", - "tr" - ], - "NO": [ - "nb", - "nn", - "se" - ], - "NP": [ - "ne", - "mai", - "bho", - "new", - "en", - "dty", - "hi", - "bo", - "bn" - ], - "NR": [ - "en", - "na" - ], - "NU": [ - "en", - "niu" - ], - "NZ": [ - "en", - "mi" - ], - "OM": [ - "ar", - "fa" - ], - "PA": [ - "es", - "en", - "zh-hant", - "zh" - ], - "PE": [ - "es", - "qu", - "ay" - ], - "PF": [ - "fr", - "ty", - "zh-hant", - "zh" - ], - "PG": [ - "tpi", - "en", - "ho" - ], - "PH": [ - "en", - "tl", - "es", - "ceb", - "ilo", - "hil", - "war", - "pam", - "pag", - "zh-hant", - "zh", - "cps", - "krj", - "bto" - ], - "PK": [ - "ur", - "pa-guru", - "en", - "ps", - "sd", - "skr-arab", - "brh", - "fa", - "bgn", - "tg-cyrl", - "bft", - "khw", - "ks-arab" - ], - "PL": [ - "pl", - "en", - "de", - "ru", - "szl", - "be", - "uk", - "csb", - "sli", - "lt" - ], - "PM": [ - "fr", - "en" - ], - "PN": [ - "en" - ], - "PR": [ - "es", - "en" - ], - "PS": [ - "ar" - ], - "PT": [ - "pt", - "en", - "fr", - "es", - "gl" - ], - "PW": [ - "en" - ], - "PY": [ - "gn", - "es", - "de" - ], - "QA": [ - "ar", - "fa", - "ml" - ], - "RE": [ - "fr", - "rcf", - "ta" - ], - "RO": [ - "ro", - "en", - "fr", - "es", - "hu", - "de", - "tr", - "sr-latn", - "sr-cyrl", - "bg", - "el", - "pl" - ], - "RS": [ - "sr-cyrl", - "sr-latn", - "sq", - "hu", - "ro", - "hr", - "sk", - "uk" - ], - "RU": [ - "ru", - "tt", - "ba", - "cv", - "hy", - "ce", - "av", - "udm", - "mhr", - "sah", - "os", - "kbd", - "myv", - "mdf", - "kv", - "lez", - "krc", - "inh", - "tyv", - "az-cyrl", - "az-latn", - "ady", - "krl", - "lbe", - "koi", - "mrj", - "fi", - "sr-latn", - "sr-cyrl", - "vep", - "mn", - "vot", - "cu" - ], - "RW": [ - "rw", - "en", - "fr" - ], - "SA": [ - "ar" - ], - "SB": [ - "en" - ], - "SC": [ - "fr", - "en" - ], - "SD": [ - "ar", - "en", - "ha-arab", - "ha-latn" - ], - "SE": [ - "sv", - "en", - "fi", - "fit", - "se", - "yi", - "smj", - "sma", - "ia" - ], - "SG": [ - "en", - "zh", - "ms", - "ta", - "ml", - "pa-guru" - ], - "SH": [ - "en" - ], - "SI": [ - "sl", - "hr", - "en", - "de", - "hu", - "it" - ], - "SJ": [ - "nb", - "ru" - ], - "SK": [ - "sk", - "cs", - "en", - "de", - "hu", - "uk", - "pl" - ], - "SL": [ - "kri", - "en" - ], - "SM": [ - "it", - "eo" - ], - "SN": [ - "wo", - "fr", - "ff" - ], - "SO": [ - "so", - "ar", - "sw", - "om" - ], - "SR": [ - "nl", - "srn", - "zh-hant", - "zh" - ], - "SS": [ - "ar", - "en" - ], - "ST": [ - "pt" - ], - "SV": [ - "es" - ], - "SX": [ - "en", - "es", - "nl" - ], - "SY": [ - "ar", - "ku-latn", - "fr", - "hy" - ], - "SZ": [ - "en", - "ss", - "zu", - "ts" - ], - "TA": [ - "en" - ], - "TC": [ - "en" - ], - "TD": [ - "fr", - "ar" - ], - "TF": [ - "fr" - ], - "TG": [ - "fr", - "ee" - ], - "TH": [ - "th", - "en", - "nod", - "zh-hant", - "zh", - "mnw", - "shn" - ], - "TJ": [ - "tg-cyrl", - "ru", - "fa", - "ar" - ], - "TK": [ - "en" - ], - "TL": [ - "pt", - "tet" - ], - "TM": [ - "tk", - "ru", - "uz", - "ku-latn" - ], - "TN": [ - "aeb-arab", - "ar", - "fr" - ], - "TO": [ - "to", - "en" - ], - "TR": [ - "tr", - "en", - "ku-latn", - "kbd", - "az-latn", - "az-arab", - "ar", - "bg", - "ady", - "kiu", - "hy", - "ka", - "sr-latn", - "sr-cyrl", - "lzz", - "sq", - "ab", - "el", - "tru", - "uz", - "ky", - "kk-cyrl" - ], - "TT": [ - "en", - "es" - ], - "TV": [ - "en" - ], - "TW": [ - "zh-hant", - "zh", - "trv" - ], - "TZ": [ - "sw", - "en", - "lag" - ], - "UA": [ - "uk", - "ru", - "pl", - "yi", - "rue", - "be", - "crh", - "ro", - "bg", - "tr", - "hu", - "el" - ], - "UG": [ - "sw", - "lg", - "en", - "rw", - "hi" - ], - "UM": [ - "en" - ], - "US": [ - "en", - "es", - "zh-hant", - "zh", - "fr", - "de", - "tl", - "it", - "vi", - "ko", - "ru", - "nv", - "yi", - "pdc", - "haw", - "frc", - "chr", - "esu", - "cho", - "lkt", - "ik", - "mus" - ], - "UY": [ - "es" - ], - "UZ": [ - "uz", - "ru", - "kaa", - "tr" - ], - "VA": [ - "it", - "la" - ], - "VC": [ - "en" - ], - "VE": [ - "es" - ], - "VG": [ - "en" - ], - "VI": [ - "en" - ], - "VN": [ - "vi", - "zh-hant", - "zh" - ], - "VU": [ - "bi", - "en", - "fr" - ], - "WF": [ - "wls", - "fr" - ], - "WS": [ - "sm", - "en" - ], - "XK": [ - "sq", - "aln", - "sr-cyrl", - "sr-latn" - ], - "YE": [ - "ar", - "en" - ], - "YT": [ - "swb", - "fr", - "sw" - ], - "ZA": [ - "en", - "zu", - "xh", - "af", - "nso", - "tn", - "st", - "ts", - "ss", - "ve", - "hi", - "sw" - ], - "ZM": [ - "en", - "ny", - "loz" - ], - "ZW": [ - "sn", - "en", - "ny", - "ve", - "tn" - ] - } -} \ No newline at end of file diff --git a/data/langdb.yaml b/data/langdb.yaml deleted file mode 100644 index d7074ac..0000000 --- a/data/langdb.yaml +++ /dev/null @@ -1,654 +0,0 @@ -languages: - aa: [Latn, [AF], Qafár af] - ab: [Cyrl, [EU], Аҧсшәа] - abs: [Latn, [AS], Bahasa Ambon] - ace: [Latn, [AS, PA], Acèh] - acf: [Latn, [AM], kwéyòl] - ady: [Cyrl, [EU, ME], Адыгабзэ] - ady-cyrl: [ady] - ady-latn: [Latn, [EU, ME], Adygabze] - aeb: [aeb-arab] - aeb-arab: [Arab, [AF], تونسي] - aeb-latn: [Latn, [AF], Tûnsî] - af: [Latn, [AF], Afrikaans] - ahr: [Deva, [AS], अहिराणी] - ais: [Latn, [AS], Sakizaya] - ak: [Latn, [AF], Akan] - akz: [Latn, [AM], Albaamo innaaɬiilka] - aln: [Latn, [EU], Gegë] - am: [Ethi, [AF], አማርኛ] - ami: [Latn, [AS], Pangcah] - an: [Latn, [EU], aragonés] - ang: [Latn, [EU], Ænglisc] - anp: [Deva, [AS], अङ्गिका] - ar: [Arab, [ME], العربية] - arc: [Syrc, [ME], ܐܪܡܝܐ] - arn: [Latn, [AM], mapudungun] - aro: [Latn, [AM], Araona] - arq: [Arab, [AF], جازايرية] - ary: [Latn, [ME], Maġribi] - arz: [Arab, [ME], مصرى] - as: [Beng, [AS], অসমীয়া] - ase: [Sgnw, [AM], American sign language] - ast: [Latn, [EU], asturianu] - atj: [Latn, [AM], atikamekw] - av: [Cyrl, [EU], авар] - avk: [Latn, [WW], Kotava] - ay: [Latn, [AM], Aymar aru] - # The Latin script is the default in the North Azerbaijani Wikipedia, - # which uses the macro code 'az'. Its own standard code is 'azj'. - # The Arabic script is the default in the South Azerbaijani Wikipedia, - # which correctly uses the code 'azb'. - # CLDR uses az-latn and az-arab. - az: [az-latn] - az-arab: [Arab, [AS, ME], تۆرکجه] - az-latn: [Latn, [EU, ME], azərbaycanca] - az-cyrl: [Cyrl, [EU, ME], азәрбајҹанҹа] - azb: [az-arab] - azj: [az-latn] - ba: [Cyrl, [EU], башҡортса] - ban: [Bali, [AS], ᬩᬲᬩᬮᬶ] - bar: [Latn, [EU], Boarisch] - bat-smg: [sgs] - bbc-latn: [Latn, [AS], Batak Toba] - bbc-batk: [Batk, [AS], ᯅᯖᯂ᯲ ᯖᯬᯅ] - bbc: [bbc-latn] - bcc: [Arab, [AS, ME], جهلسری بلوچی] - bcl: [Latn, [AS], Bikol Central] - be-tarask: [Cyrl, [EU], беларуская (тарашкевіца)] - be-x-old: [be-tarask] - be: [Cyrl, [EU], беларуская] - bew: [Latn, [AS], Bahasa Betawi] - bfa: [Latn, [AF], Bari] - bft: [Arab, [AS], بلتی] - bfq: [Taml, [AS], படகா] - bg: [Cyrl, [EU], български] - bgn: [Arab, [AS, ME], روچ کپتین بلوچی] - # FIXME - currently says Bhojpuri, but it's a macrolanguage. - bh: [bho] - bho: [Deva, [AS], भोजपुरी] - bi: [Latn, [PA], Bislama] - bjn: [Latn, [AS], Bahasa Banjar] - bm: [Latn, [AF], bamanankan] - bn: [Beng, [AS], বাংলা] - bo: [Tibt, [AS], བོད་ཡིག] - bpy: [Beng, [AS], বিষ্ণুপ্রিয়া মণিপুরী] - bqi: [Arab, [AS, ME], بختیاری] - br: [Latn, [EU], brezhoneg] - brh: [Latn, [ME, AS], Bráhuí] - brx: [Deva, [AS], बड़ो] - bs: [Latn, [EU], bosanski] - bto: [Latn, [AS], Iriga Bicolano] - bug: [Bugi, [AS], ᨅᨔ ᨕᨘᨁᨗ] - bxr: [Cyrl, [AS], буряад] - byn: [Ethi, [AF], ብሊን] - ca: [Latn, [EU], català] - cbk-zam: [Latn, [AS], Chavacano de Zamboanga] - cdo: [Latn, [AS], Mìng-dĕ̤ng-ngṳ̄] - ce: [Cyrl, [EU], нохчийн] - ceb: [Latn, [AS], Cebuano] - ch: [Latn, [PA], Chamoru] - # FIXME chm is actually a macro language that includes - # mhr and mrj, but CLDR Territory-Language information - # uses chm instead of mhr, so for practical reasons - # it should redirect there. - # A better fix would be this: - # https://phabricator.wikimedia.org/T136164 - chm: [mhr] - cho: [Latn, [AM], Choctaw] - chr: [Cher, [AM], ᏣᎳᎩ] - chy: [Latn, [AM], Tsetsêhestâhese] - ciw: [Latn, [AM], Ojibwemowin] - cjy: [cjy-hant] - cjy-hans: [Hans, [AS], 晋语（简化字)] - cjy-hant: [Hant, [AS], 晉語] - ckb: [Arab, [ME], کوردی] - cnh: [Latn, [AS], Lai holh] - co: [Latn, [EU], corsu] - cop: [Copt, [AF, ME], ϯⲙⲉⲧⲣⲉⲙⲛ̀ⲭⲏⲙⲓ] - cps: [Latn, [AS], Capiceño] - cr: [Cans, [AM], ᓀᐦᐃᔭᐍᐏᐣ] - cr-cans: [cr] - cr-latn: [Latn, [AM], Nēhiyawēwin] - crh: [Latn, [EU], qırımtatarca] - crh-cyrl: [Cyrl, [EU], къырымтатарджа] - crh-latn: [crh] - cs: [Latn, [EU], čeština] - csb: [Latn, [EU], kaszëbsczi] - # FIXME: which script to prefer?.. - cu: [Cyrl, [EU], словѣньскъ / ⰔⰎⰑⰂⰡⰐⰠⰔⰍⰟ] - cv: [Cyrl, [EU], Чӑвашла] - cy: [Latn, [EU], Cymraeg] - da: [Latn, [EU], dansk] - dag: [Latn, [AF], dagbanli] - de-at: [Latn, [EU], Österreichisches Deutsch] - de-ch: [Latn, [EU], Schweizer Hochdeutsch] - de-formal: [Latn, [EU], Deutsch (Sie-Form)] - de: [Latn, [EU], Deutsch] - din: [Latn, [AF], Thuɔŋjäŋ] - diq: [Latn, [EU, AS], Zazaki] - doi: [Deva, [AS], डोगरी] - dsb: [Latn, [EU], dolnoserbski] - dtp: [Latn, [AS], Dusun Bundu-liwan] - dty: [Deva, [AS], डोटेली] - dv: [Thaa, [AS], ދިވެހިބަސް] - dz: [Tibt, [AS], ཇོང་ཁ] - ee: [Latn, [AF], eʋegbe] - egl: [Latn, [EU], Emiliàn] - el: [Grek, [EU], Ελληνικά] - eml: [Latn, [EU], emiliàn e rumagnòl] - en-ca: [Latn, [AM], Canadian English] - en-gb: [Latn, [EU, AS, PA], British English] - en: [Latn, [EU, AM, AF, ME, AS, PA, WW], English] - eo: [Latn, [WW], Esperanto] - es-419: [Latn, [AM], español de America Latina] - # world? - es-formal: [Latn, [EU, AM, AF, WW], español (formal)] - # world? - es: [Latn, [EU, AM, AF, WW], español] - es-ni: [Latn, [AM], español nicaragüense] - esu: [Latn, [AM], "Yup'ik"] - et: [Latn, [EU], eesti] - eu: [Latn, [EU], euskara] - ext: [Latn, [EU], estremeñu] - fa: [Arab, [AS, ME], فارسی] - fax: [Latn, [EU], Fala] - ff: [Latn, [AF], Fulfulde] - fi: [Latn, [EU], suomi] - fil: [tl] - fit: [Latn, [EU], meänkieli] - fiu-vro: [vro] - fj: [Latn, [PA], Na Vosa Vakaviti] - fo: [Latn, [EU], føroyskt] - fr: [Latn, [EU, AM, WW], français] - frc: [Latn, [AM], français cadien] - frp: [Latn, [EU], arpetan] - frr: [Latn, [EU], Nordfriisk] - fur: [Latn, [EU], furlan] - fy: [Latn, [EU], Frysk] - ga: [Latn, [EU], Gaeilge] - gaa: [Latn, [AF], Ga] - gag: [Latn, [EU], Gagauz] - gah: [Latn, [AS], Alekano] - gan-hans: [Hans, [AS], 赣语（简体）] - gan-hant: [gan] - gan: [Hant, [AS], 贛語] - gbz: [Latn, [AS], Dari-e Mazdeyasnā] - gcf: [Latn, [AM], Guadeloupean Creole French] - gd: [Latn, [EU], Gàidhlig] - gl: [Latn, [EU], galego] - glk: [Arab, [AS, ME], گیلکی] - gn: [Latn, [AM], "Avañe'ẽ"] - gom: [gom-deva] - gom-deva: [Deva, [AS], गोंयची कोंकणी] - gom-latn: [Latn, [AS], Gõychi Konknni] - got: [Goth, [EU], 𐌲𐌿𐍄𐌹𐍃𐌺] - grc: [Grek, [EU], Ἀρχαία ἑλληνικὴ] - gsw: [Latn, [EU], Alemannisch] - gu: [Gujr, [AS], ગુજરાતી] - guc: [Latn, [AM], Wayúu] - gum: [Latn, [AM], Namtrik] - gur: [Latn, [AF], Gurenɛ] - gv: [Latn, [EU], Gaelg] - # CLDR uses ha-latn and ha-arab. Latin is more common and is used in Wikipedia. - ha-arab: [Arab, [AF], هَوُسَ] - ha-latn: [Latn, [AF], Hausa] - ha: [ha-latn] - hak: [Latn, [AS], Hak-kâ-fa] - haw: [Latn, [AM, PA], Hawai`i] - he: [Hebr, [ME], עברית] - hak-hans: [Hans, [AS], 客家语（简体）] - hak-hant: [Hant, [AS], 客家語（繁體）] - hi: [Deva, [AS], हिन्दी] - hif: [Latn, [PA, AS], Fiji Hindi] - hif-deva: [Deva, [AS], फ़ीजी हिन्दी] - hif-latn: [hif] - hil: [Latn, [AS], Ilonggo] - hne: [Deva, [AS], छत्तीसगढ़ी] - ho: [Latn, [PA], Hiri Motu] - hoc: [Wara, [AS], 𑢹𑣉𑣉] - hr: [Latn, [EU], hrvatski] - hrx: [Latn, [AM], Hunsrik] - hsb: [Latn, [EU], hornjoserbsce] - hsn: [Hans, [AS], 湘语] - ht: [Latn, [AM], Kreyòl ayisyen] - hu-formal: [Latn, [EU], Magyar (magázó)] - hu: [Latn, [EU], magyar] - hy: [Armn, [EU, ME], Հայերեն] - hz: [Latn, [AF], Otsiherero] - ia: [Latn, [WW], interlingua] - id: [Latn, [AS], Bahasa Indonesia] - ie: [Latn, [WW], Interlingue] - ig: [Latn, [AF], Igbo] - ii: [Yiii, [AS], ꆇꉙ] - ik: [Latn, [AM], Iñupiak] - ike-cans: [Cans, [AM], ᐃᓄᒃᑎᑐᑦ] - ike-latn: [Latn, [AM], inuktitut] - ilo: [Latn, [AS], Ilokano] - inh: [Cyrl, [EU], ГӀалгӀай] - io: [Latn, [WW], Ido] - is: [Latn, [EU], íslenska] - it: [Latn, [EU], italiano] - iu: [ike-cans] - ja: [Jpan, [AS], 日本語] - jam: [Latn, [AM], Patois] - jbo: [Latn, [WW], lojban] - jdt: [jdt-cyrl] - jdt-cyrl: [Cyrl, [EU, AS], жугьури] - jut: [Latn, [EU], jysk] - jv: [Latn, [AS, PA], Basa Jawa] - # For support in webfonts. - jv-java: [Java, [AS, PA], ꦧꦱꦗꦮ] - ka: [Geor, [EU], ქართული] - kaa: [Latn, [AS], Qaraqalpaqsha] - # Can also be Tfng, but the Wikipedia is mostly Latn - kab: [Latn, [AF, EU], Taqbaylit] - kac: [Latn, [AS], Jinghpaw] - kbd-cyrl: [kbd] - kbd-latn: [Latn, [EU], Qabardjajəbza] - kbd: [Cyrl, [EU, ME], Адыгэбзэ] - kbp: [Latn, [AF], Kabɩyɛ] - kea: [Latn, [AF], Kabuverdianu] - kg: [Latn, [AF], Kongo] - kgp: [Latn, [AM], Kaingáng] - khw: [Arab, [ME, AS], کھوار] - ki: [Latn, [AF], Gĩkũyũ] - kiu: [Latn, [EU, ME], Kırmancki] - kj: [Latn, [AF], Kwanyama] - kjh: [Cyrl, [AS], хакас] - kk: [kk-cyrl] - kk-arab: [Arab, [EU, AS], قازاقشا (تٶتە)] - kk-cn: [kk-arab] - kk-cyrl: [Cyrl, [EU, AS], қазақша] - kk-kz: [kk-cyrl] - kk-latn: [Latn, [EU, AS, ME], qazaqşa] - kk-tr: [kk-latn] - kl: [Latn, [AM, EU], kalaallisut] - km: [Khmr, [AS], ភាសាខ្មែរ] - kn: [Knda, [AS], ಕನ್ನಡ] - knn: [Deva, [AS], महाराष्ट्रीय कोंकणी] - # Here Hang may be even more appropriate, because kp has more resistance to Han - ko-kp: [Kore, [AS], 한국어 (조선)] - # Kore is an alias for Hangul+Han. Maybe Hang is more appropriate? - ko: [Kore, [AS], 한국어] - koi: [Cyrl, [EU], Перем Коми] - kr: [Latn, [AF], Kanuri] - krc: [Cyrl, [EU], къарачай-малкъар] - kri: [Latn, [AF], Krio] - krj: [Latn, [ME, EU], Kinaray-a] - krl: [Latn, [EU], Karjala] - ks-arab: [Arab, [AS], کٲشُر] - ks-deva: [Deva, [AS], कॉशुर] - ks: [ks-arab] - ksf: [Latn, [AF], Bafia] - ksh: [Latn, [EU], Ripoarisch] - # CLDR uses ku-latn and ku-arab. Latin is more common and is used in Wikipedia. - ku: [ku-latn] - ku-arab: [Arab, [EU, ME], كوردي] - ku-latn: [Latn, [EU, ME], Kurdî] - kv: [Cyrl, [EU], коми] - kw: [Latn, [EU], kernowek] - ky: [Cyrl, [AS], Кыргызча] - la: [Latn, [EU], Latina] - lad: [lad-latn] - lad-latn: [Latn, [ME, EU, AM], Ladino] - lad-hebr: [Hebr, [ME, EU, AM], לאדינו] - lag: [Latn, [AF], Kilaangi] - lb: [Latn, [EU], Lëtzebuergesch] - lbe: [Cyrl, [EU], лакку] - lez: [Cyrl, [EU], лезги] - lfn: [Latn, [WW], Lingua Franca Nova] - lg: [Latn, [AF], Luganda] - li: [Latn, [EU], Limburgs] - lij: [Latn, [EU], Ligure] - liv: [Latn, [EU], Līvõ kēļ] - lki: [Arab, [AS, ME], لەکی] - lkt: [Latn, [AM], Lakȟótiyapi] - lld: [Latn, [EU], Ladin] - lmo: [Latn, [EU], lumbaart] - ln: [Latn, [AF], lingála] - lo: [Laoo, [AS], ລາວ] - loz: [Latn, [AF], Silozi] - lt: [Latn, [EU], lietuvių] - lrc: [Arab, [AS, ME], لۊری شومالی] - ltg: [Latn, [EU], latgaļu] - lud: [Latn, [EU], lüüdi] - lus: [Latn, [AS], Mizo ţawng] - lut: [Latn, [AM], dxʷləšucid] - luz: [Arab, [ME], لئری دوٙمینی] - lv: [Latn, [EU], latviešu] - lzh: [Hant, [AS], 文言] - # Also Geor, but the incubator is in Latn - lzz: [Latn, [EU, ME], Lazuri] - mai: [Deva, [AS], मैथिली] - map-bms: [Latn, [AS], Basa Banyumasan] - mdf: [Cyrl, [EU], мокшень] - mfe: [Latn, [AM], Morisyen] - mg: [Latn, [AF], Malagasy] - mh: [Latn, [PA], Ebon] - mhr: [Cyrl, [EU], олык марий] - mi: [Latn, [PA], Māori] - mic: [Latn, [AM], "Mi'kmaq"] - min: [Latn, [AS], Baso Minangkabau] - miq: [Latn, [AM], Mískitu] - mk: [Cyrl, [EU], македонски] - ml: [Mlym, [AS, ME], മലയാളം] - # Hmm, can also have Mong some day in some way - mn: [Cyrl, [AS], монгол] - mnc: [Mong, [AS], ᠮᠠᠨᠵᡠ ᡤᡳᠰᡠᠨ] - mni: [Beng, [AS], মেইতেই লোন্] - mnw: [Mymr, [AS], ဘာသာ မန်] - mo: [Cyrl, [EU], молдовеняскэ] - mr: [Deva, [AS, ME], मराठी] - mrj: [Cyrl, [EU], кырык мары] - ms: [Latn, [AS], Bahasa Melayu] - mt: [Latn, [EU], Malti] - mui: [Latn, [AS], Musi] - mus: [Latn, [AM], Mvskoke] - mwl: [Latn, [EU], Mirandés] - mwv: [Latn, [AS], Behase Mentawei] - mww: [mww-latn] - mww-latn: [Latn, [AS], Hmoob Dawb] - my: [Mymr, [AS], မြန်မာဘာသာ] - myv: [Cyrl, [EU], эрзянь] - mzn: [Arab, [ME, AS], مازِرونی] - na: [Latn, [PA], Dorerin Naoero] - nah: [Latn, [AM], Nāhuatl] - nan: [Latn, [AS], Bân-lâm-gú] - nap: [Latn, [EU], Napulitano] - nb: [Latn, [EU], norsk (bokmål)] - nds-nl: [Latn, [EU], Nedersaksisch] - nds: [Latn, [EU], Plattdüütsch] - ne: [Deva, [AS], नेपाली] - new: [Deva, [AS], नेपाल भाषा] - ng: [Latn, [AF], Oshiwambo] - niu: [Latn, [PA], ko e vagahau Niuē] - njo: [Latn, [AS], Ao] - nl-informal: [Latn, [EU, AM], Nederlands (informeel)] - nl: [Latn, [EU, AM], Nederlands] - nn: [Latn, [EU], norsk (nynorsk)] - # There's also nb for Bokmål and nn for Nynorsk - "no": [Latn, [EU], norsk] - nod: [Thai, [AS], คำเมือง] - nov: [Latn, [WW], Novial] - nqo: [Nkoo, [AF], ߒߞߏ] - nrm: [Latn, [EU], Nouormand] - nso: [Latn, [AF], Sesotho sa Leboa] - nv: [Latn, [AM], Diné bizaad] - ny: [Latn, [AF], Chi-Chewa] - nys: [Latn, [PA], Nyungar] - oc: [Latn, [EU], occitan] - olo: [Latn, [AS, EU], Livvinkarjala] - om: [Latn, [AF], Oromoo] - or: [Orya, [AS], ଓଡ଼ିଆ] - os: [Cyrl, [EU], Ирон] - # Bug: 60815 - ota: [Arab, [AS, EU], لسان عثمانى] - ovd: [Latn, [EU], övdalsk] - pa: [pa-guru] - pa-guru: [Guru, [AS], ਪੰਜਾਬੀ] - pag: [Latn, [AS], Pangasinan] - pam: [Latn, [AS], Kapampangan] - pap: [Latn, [AM], Papiamentu] - pbb: [Latn, [AM], Nasa Yuwe] - pcd: [Latn, [EU], Picard] - pdc: [Latn, [EU, AM], Deitsch] - pdt: [Latn, [EU, AM], Plautdietsch] - pfl: [Latn, [EU], Pälzisch] - pi: [Deva, [AS], पालि] - pih: [Latn, [PA], Norfuk / Pitkern] - pis: [Latn, [PA], Pijin] - pko: [Latn, [AF], Pökoot] - pl: [Latn, [EU], polski] - pms: [Latn, [EU], Piemontèis] - pnb: [Arab, [AS, ME], پنجابی] - pnt: [Grek, [EU], Ποντιακά] - ppl: [Latn, [AM], Nawat] - prg: [Latn, [EU], Prūsiskan] - prs: [Arab, [AS, ME], دری] - ps: [Arab, [AS, ME], پښتو] - pt-br: [Latn, [AM], português do Brasil] - pt: [Latn, [EU, AM, AS, PA, AF, WW], português] - qu: [Latn, [AM], Runa Simi] - qug: [Latn, [AM], Runa shimi] - rap: [Latn, [AM], arero rapa nui] - rcf: [Latn, [AF], Kreol Réyoné] - rgn: [Latn, [EU], Rumagnôl] - rif: [Latn, [AF], Tarifit] - rki: [Mymr, [AS], ရခိုင်] - rm: [Latn, [EU], rumantsch] - # Also known as Fíntika Rómma - rmf: [Latn, [EU], kaalengo tšimb] - rmy: [Latn, [EU], Romani] - rn: [Latn, [AF], Kirundi] - ro: [Latn, [EU], română] - roa-rup: [rup] - roa-tara: [Latn, [EU], tarandíne] - rtm: [Latn, [PA], Faeag Rotuma] - # world? - ru: [Cyrl, [EU, AS, ME], русский] - rue: [Cyrl, [EU], русиньскый] - rup: [Latn, [EU], armãneashti] - ruq: [Cyrl, [EU], Влахесте] - ruq-cyrl: [ruq] - # FIXME: broken autonym - ruq-grek: [Grek, [EU], Megleno-Romanian (Greek script)] - ruq-latn: [Latn, [EU], Vlăheşte] - rut: [Cyrl, [EU], мыхаӀбишды] - rw: [Latn, [AF], Kinyarwanda] - # Bug: 60815 - rwr: [Deva, [AS], मारवाड़ी] - ryu: [Kana, [AS], ʔucināguci] - sa: [Deva, [AS], संस्कृतम्] - sah: [Cyrl, [EU, AS], саха тыла] - # Currently Latn, potentially Olck - sat: [Latn, [AS], Santali] - saz: [Saur, [AS], ꢱꣃꢬꢵꢯ꣄ꢡ꣄ꢬꢵ] - sc: [Latn, [EU], sardu] - scn: [Latn, [EU], sicilianu] - sco: [Latn, [EU], Scots] - sd: [Arab, [AS], سنڌي] - sdc: [Latn, [EU], Sassaresu] - sdh: [Arab, [ME], کوردی خوارگ] - se: [Latn, [EU], sámegiella] - ses: [Latn, [AF], Koyraboro Senni] - sei: [Latn, [AM], Cmique Itom] - sg: [Latn, [AF], Sängö] - sgs: [Latn, [EU], žemaitėška] - sh: [Latn, [EU], srpskohrvatski] - shi-latn: [Latn, [AF], Tašlḥiyt] - shi-tfng: [Tfng, [AF], ⵜⴰⵛⵍⵃⵉⵜ] - shi: [shi-latn] - shn: [Mymr, [AS], လိၵ်ႈတႆး] - si: [Sinh, [AS], සිංහල] - simple: [Latn, [WW], Simple English] - sjo: [Mong, [AS], ᠰᡞᠪᡝ ᡤᡞᠰᡠᠨ] - sk: [Latn, [EU], slovenčina] - sl: [Latn, [EU], slovenščina] - sli: [Latn, [EU], Schläsch] - slr: [Latn, [AS], Salırça] - sly: [Latn, [AS], Bahasa Selayar] - skr-arab: [Arab, [AS], سرائیکی] - skr: [skr-arab] - syc: [Syrc, [ME], ܣܘܪܝܝܐ] - sm: [Latn, [PA], Gagana Samoa] - sma: [Latn, [EU], åarjelsaemien] - smj: [Latn, [EU], julevsámegiella] - smn: [Latn, [EU], anarâškielâ] - sms: [Latn, [EU], sää´mǩiõll] - sn: [Latn, [AF], chiShona] - so: [Latn, [AF], Soomaaliga] - son: [Latn, [AF], soŋay] - sq: [Latn, [EU], shqip] - sr: [sr-cyrl] - sr-ec: [sr-cyrl] - sr-cyrl: [Cyrl, [EU], српски] - sr-el: [sr-latn] - sr-latn: [Latn, [EU], srpski] - srn: [Latn, [AM, EU], Sranantongo] - ss: [Latn, [AF], SiSwati] - st: [Latn, [AF], Sesotho] - stq: [Latn, [EU], Seeltersk] - sty: [Cyrl, [EU, AS], себертатар] - su: [Latn, [AS], Basa Sunda] - sv: [Latn, [EU], svenska] - sw: [Latn, [AF], Kiswahili] - swb: [Latn, [AF], Shikomoro] - sxu: [Latn, [EU], Säggssch] - szl: [Latn, [EU], ślůnski] - ta: [Taml, [AS], தமிழ்] - tay: [Latn, [AS], Tayal] - tcy: [Knda, [AS], ತುಳು] - te: [Telu, [AS], తెలుగు] - tet: [Latn, [AS, PA], tetun] - tg-cyrl: [Cyrl, [AS], тоҷикӣ] - tg-latn: [Latn, [AS], tojikī] - tg: [tg-cyrl] - th: [Thai, [AS], ไทย] - ti: [Ethi, [AF], ትግርኛ] - tig: [Ethi, [AF], ትግረ] - tk: [Latn, [AS], Türkmençe] - tkr: [Cyrl, [AS], ЦӀаӀхна миз] - tl: [Latn, [AS], Tagalog] - # A very complicated case. Names.php is Cyrl. In TWN they argue about Cyrl, Latn, and Arab. I can't find reliable external sources. --Amir - tly: [Cyrl, [EU, AS, ME], толышә зывон] - tmr: [Hebr, [ME, EU, AM], ארמית בבלית] - tn: [Latn, [AF], Setswana] - to: [Latn, [PA], lea faka-Tonga] - tokipona: [Latn, [WW], Toki Pona] - tpi: [Latn, [PA, AS], Tok Pisin] - tr: [Latn, [EU, ME], Türkçe] - trp: [Latn, [AS], Kokborok (Tripuri)] - tru: [Latn, [AS], Ṫuroyo] - trv: [Latn, [AS], Sediq Taroko] - ts: [Latn, [AF], Xitsonga] - tsd: [Grek, [EU], Τσακωνικά] - tt: [Cyrl, [EU], татарча] - tt-cyrl: [tt] - tt-latn: [Latn, [EU], tatarça] - ttt: [Cyrl, [AS], Tati] - tum: [Latn, [AF], chiTumbuka] - tw: [Latn, [AF], Twi] - twd: [Latn, [EU], Tweants] - ty: [Latn, [PA], reo tahiti] - tyv: [Cyrl, [AS], тыва дыл] - tzl: [Latn, [WW], Talossan] - tzm: [Tfng, [AF], ⵜⴰⵎⴰⵣⵉⵖⵜ] - udm: [Cyrl, [EU], удмурт] - # CLDR uses ug-arab, ug-latn and ug-cyrl. - # Arabic seems to have the largest number of users and is the main script in the Wikipedia. - ug: [ug-arab] - ug-arab: [Arab, [AS], ئۇيغۇرچە] - ug-latn: [Latn, [AS], uyghurche] - ug-cyrl: [Cyrl, [AS], уйғурчә] - uk: [Cyrl, [EU], українська] - ur: [Arab, [AS, ME], اردو] - uz: [Latn, [AS], oʻzbekcha] - ve: [Latn, [AF], Tshivenda] - vec: [Latn, [EU], vèneto] - vep: [Latn, [EU], vepsän kel’] - vi: [Latn, [AS], Tiếng Việt] - vls: [Latn, [EU], West-Vlams] - vmf: [Latn, [EU], Mainfränkisch] - vo: [Latn, [WW], Volapük] - vot: [Latn, [EU], Vaďďa] - vro: [Latn, [EU], Võro] - wa: [Latn, [EU], walon] - war: [Latn, [AS], Winaray] - wls: [Latn, [PA], "Faka'uvea"] - wo: [Latn, [AF], Wolof] - wuu: [Hans, [AS], 吴语] - xal: [Cyrl, [EU], хальмг] - xh: [Latn, [AF], isiXhosa] - xmf: [Geor, [EU], მარგალური] - xsy: [Latn, [AS], SaiSiyat] - ydd: [Hebr, [AS, EU], Eastern Yiddish] - yi: [Hebr, [ME, EU, AM], ייִדיש] - yo: [Latn, [AF], Yorùbá] - yrk: [Cyrl, [AS], Ненэцяʼ вада] - yrl: [Latn, [AM], "ñe'engatú"] - yua: [Latn, [AM], "Maaya T'aan"] - yue: [Hant, [AS], 粵語] - za: [Latn, [AS], Vahcuengh] - zea: [Latn, [EU], Zeêuws] - zgh: [Tfng, [AF], ⵜⴰⵎⴰⵣⵉⵖⵜ ⵜⴰⵏⴰⵡⴰⵢⵜ] - # world? (may apply to many varieties of Chinese) - zh: [Hans, [AS], 中文] - zh-classical: [lzh] - zh-cn: [Hans, [AS], 中文（中国大陆）] - zh-hans: [Hans, [AS], 中文（简体）] - zh-hant: [Hant, [AS], 中文（繁體）] - zh-hk: [Hant, [AS], 中文（香港）] - zh-min-nan: [nan] - zh-mo: [Hant, [AS], 中文（澳門）] - zh-my: [Hans, [AS], 中文（马来西亚）] - zh-sg: [Hans, [AS], 中文（新加坡）] - zh-tw: [Hant, [AS], 中文（台灣）] - zh-yue: [yue] - zu: [Latn, [AF], isiZulu] - - # All the supported scripts, grouped logically. - # - # The codes are taken from http://unicode.org/iso15924/iso15924-codes.html . - # - # The classification is roughly based on http://www.unicode.org/charts/ - # with some practical corrections. - # - # The order of the groups affects display. Pau Giner suggested the order; - # the rationale of the order is to distance the largest groups from - # one another to improve discoverability. - # - # The group name "Other" is reserved. -scriptgroups: - # It's hard to find a better place for Goth except the Latin group. - Latin: [Latn, Goth] - # Greek is probably different enough from Latin and Cyrillic, but user testing - # may prove otherwise. - Greek: [Grek] - WestCaucasian: [Armn, Geor] - Arabic: [Arab] - # Maybe MiddleEastern can be unified with Arabic. - # Maybe Thaana can be moved here from SouthAsian. - # Maybe it can be unified with African. - MiddleEastern: [Hebr, Syrc] - African: [Ethi, Nkoo, Tfng, Copt] - # India, Nepal, Bangladesh, Sri-Lanka, Bhutan, Maldives. - # - # Thaana (Thaa, the script of Maldives) is here, even though it's RTL, - # because it's closer geographically to India. Maybe it should be moved - # to MiddleEastern or to Arabic, if that would be easier to users. - # - # Tibetan (Tibt) is here, even though it's classified as "Central Asian" by - # Unicode, because linguistically and geographically it's closely related to - # the Brahmic family. - SouthAsian: [Beng, Deva, Gujr, Guru, Knda, Mlym, Orya, Saur, Sinh, Taml, Telu, Tibt, Thaa, Wara] - Cyrillic: [Cyrl] - CJK: [Hans, Hant, Kana, Kore, Jpan, Yiii] - SouthEastAsian: [Bali, Batk, Bugi, Java, Khmr, Laoo, Mymr, Thai] - Mongolian: [Mong] - SignWriting: [Sgnw] - NativeAmerican: [Cher, Cans] - # Undetermined script - Special: [Zyyy] - -rtlscripts: - [Arab, Hebr, Syrc, Nkoo, Thaa] - - # The numbers are also used in HTML id attributes -regiongroups: - # Worldwide, international - WW: 1 - # Special languages. To be shown near Worldwide when relevant. - SP: 1 - # America - AM: 2 - # Europe - EU: 3 - # Middle East - ME: 3 - # Africa - AF: 3 - # Asia - AS: 4 - # Pacific - PA: 4 diff --git a/data/ulsdata2json.php b/data/ulsdata2json.php deleted file mode 100644 index 1ba7cf3..0000000 --- a/data/ulsdata2json.php +++ /dev/null @@ -1,130 +0,0 @@ -territoryInfo->territory as $territoryRecord ) { - $territoryAtributes = $territoryRecord->attributes(); - $territoryCodeAttr = $territoryAtributes['type']; - $territoryCode = (string) $territoryCodeAttr[0]; - $parsedLangdb['territories'][$territoryCode] = array(); - - foreach ( $territoryRecord->languagePopulation as $languageRecord ) { - $languageAttributes = $languageRecord->attributes(); - $languageCodeAttr = $languageAttributes['type']; - // Lower case is a convention for language codes in ULS. - // '_' is used in CLDR for compound codes and it's replaced with '-' here. - - $normalisedCode = strtr( strtolower( (string) $languageCodeAttr[0] ), '_', '-' ); - - $parsedLangdb['territories'][$territoryCode][] = $normalisedCode; - - // In case of codes with variants, also add the base because ULS might consider - // them as separate languages, e.g. zh, zh-hant and zh-hans. - if ( strpos( $normalisedCode, '-' ) !== false ) { - $parts = explode( '-', $normalisedCode ); - $parsedLangdb['territories'][$territoryCode][] = $parts[0]; - } - } -} - -foreach ( $parsedLangdb['territories'] as $territoryCode => $languages ) { - foreach ( $languages as $index => $language ) { - if ( !isset( $parsedLangdb['languages'][$language] ) ) { - echo "Unknown language $language for territory $territoryCode\n"; - unset( $parsedLangdb['territories'][$territoryCode][$index] ); - continue; - } - - $data = $parsedLangdb['languages'][$language]; - if ( count( $data ) === 1 ) { - echo "Redirect for language $language to {$data[0]} territory $territoryCode\n"; - $parsedLangdb['territories'][$territoryCode][$index] = $data[0]; - continue; - } - } - - // Clean-up to save space - if ( count( $parsedLangdb['territories'][$territoryCode] ) === 0 ) { - unset( $parsedLangdb['territories'][$territoryCode] ); - continue; - } - - // Remove duplicates we might have created - $parsedLangdb['territories'][$territoryCode] = - array_unique( $parsedLangdb['territories'][$territoryCode] ); - - - // We need to renumber or json conversion thinks these are objects - $parsedLangdb['territories'][$territoryCode] = - array_values( $parsedLangdb['territories'][$territoryCode] ); -} - -print "Writing JSON langdb...\n"; -$jsonVerbose = json_encode( $parsedLangdb, JSON_PRETTY_PRINT | JSON_UNESCAPED_UNICODE ); -$jsonSlim = json_encode( $parsedLangdb, JSON_UNESCAPED_UNICODE ); -$js = << -1 ) { - duplicateAutonyms.push( language ); - } - - autonyms.push( autonym ); - } - - return duplicateAutonyms; - }; - - /* - * Runs over all languages and checks that all redirects point to a language. - * There's no reason to have double redirects. - */ - doubleRedirects = function () { - var language, target, - result = []; - - for ( language in $.uls.data.languages ) { - target = $.uls.data.isRedirect( language ); - - if ( target && $.uls.data.isRedirect( target ) ) { - result.push( language ); - } - } - - return result; - }; - - /* - * Runs over all script codes mentioned in langdb and checks whether - * they have something that looks like an autonym. - */ - languagesWithoutAutonym = function () { - var language, - result = []; - - for ( language in $.uls.data.languages ) { - if ( typeof $.uls.data.getAutonym( language ) !== 'string' ) { - result.push( language ); - } - } - - return result; - }; - test( '-- Initial check', 1, function ( assert ) { assert.ok( $.fn.uls, '$.fn.uls is defined' ); } ); - test( '-- $.uls.data testing', 31, function ( assert ) { - var autonyms, - languagesToGroup, groupedLanguages; - - // Add a language in run time. - // This is done early to make sure that it doesn't break other functions. - $.uls.data.addLanguage( 'qqq', { - script: 'Latn', - regions: ['SP'], - autonym: 'Language documentation' - } ); - - assert.ok( $.uls.data.getAutonym( 'qqq' ), 'Language documentation', 'Language qqq was added with the correct autonym' ); - - assert.strictEqual( $.uls.data.isRedirect( 'sr-ec' ), 'sr-cyrl', '"sr-ec" is a redirect to "sr-cyrl"' ); - autonyms = $.uls.data.getAutonyms(); - assert.strictEqual( autonyms['zu'], 'isiZulu', 'Correct autonym is returned for Zulu using getAutonyms().' ); - assert.strictEqual( autonyms['pa'], undefined, 'Language "pa" is not listed in autonyms, because it is a redirect' ); - assert.strictEqual( autonyms['pa-guru'], 'ਪੰਜਾਬੀ', 'Language "pa-guru" has the correct autonym' ); - - // This test assumes that we don't want any scripts to be in the 'Other' - // group. Actually, this may become wrong some day. - assert.deepEqual( orphanScripts(), [], 'All scripts belong to script groups.' ); - - assert.deepEqual( badRedirects(), [], 'All redirects have valid targets.' ); - assert.deepEqual( doubleRedirects(), [], 'There are no double redirects.' ); - assert.deepEqual( languagesWithoutAutonym(), [], 'All languages have autonyms.' ); - assert.deepEqual( doubleAutonyms(), [], 'All languages have distinct autonyms.' ); - - assert.strictEqual( - $.uls.data.getGroupOfScript( 'Beng' ), - 'SouthAsian', - 'Bengali script belongs to the SouthAsian group.' - ); - assert.strictEqual( - $.uls.data.getScriptGroupOfLanguage( 'iu' ), - 'NativeAmerican', - 'The script of the Inupiaq language belongs to the NativeAmerican group.' - ); - - assert.strictEqual( $.uls.data.getScript( 'no-such-language' ), 'Zyyy', 'A script for an unknown language is Zyyy - undetermined' ); - assert.strictEqual( $.uls.data.getScript( 'ii' ), 'Yiii', 'Correct script of the Yi language was selected' ); - assert.deepEqual( $.uls.data.getRegions( 'lzz' ), [ - 'EU', 'ME' - ], 'Correct regions of the Laz language were selected' ); - assert.strictEqual( $.uls.data.getRegions( 'no-such-language' ), 'UNKNOWN', 'The region of an invalid language is "UNKNOWN"' ); - - assert.deepEqual( $.uls.data.getLanguagesInScript( 'Knda' ), [ - 'kn', 'tcy' - ], 'languages in script Knda are selected correctly' ); - assert.deepEqual( $.uls.data.getLanguagesInScript( 'Guru' ), - ['pa-guru'], - '"pa-guru" is written in script Guru, and "pa" is skipped as a redirect' - ); - assert.deepEqual( $.uls.data.getLanguagesInScripts( ['Geor', 'Armn'] ), - ['hy', 'ka', 'xmf'], - 'languages in scripts Geor and Armn are selected correctly' - ); - - assert.strictEqual( $.uls.data.getAutonym( 'pa' ), 'ਪੰਜਾਬੀ', 'Correct autonym of the Punjabi language was selected using code pa.' ); - assert.strictEqual( $.uls.data.getAutonym( 'pa-guru' ), 'ਪੰਜਾਬੀ', 'Correct autonym of the Punjabi language was selected using code pa-guru.' ); - - languagesToGroup = { - 'en': 'English', - 'fiu-vro': 'Võro', // Alias before target - 'ru': 'русский', - 'sr': 'српски', // Alias before target - 'sr-cyrl': 'српски', // Target before alias - 'sr-latn': 'srpski', // Target before alias - 'sr-el': 'srpski', // Alias after target - 'vro': 'Võro' // Target after alias - }; - groupedLanguages = { - Latin: [ 'en', 'fiu-vro', 'sr-latn', 'sr-el', 'vro' ], - Cyrillic: [ 'ru', 'sr', 'sr-cyrl' ] - }; - - assert.deepEqual( $.uls.data.getLanguagesByScriptGroup( languagesToGroup ), groupedLanguages, - 'A custom list of languages is grouped correctly using getLanguagesByScriptGroup.' ); - - // autonyms: gn: avañe'ẽ, de: deutsch, hu: magyar, fi: suomi - assert.deepEqual( ['de', 'fi', 'gn', 'hu'].sort( $.uls.data.sortByAutonym ), [ - 'gn', 'de', 'hu', 'fi' - ], 'Languages are correctly sorted by autonym' ); - - assert.strictEqual( $.uls.data.isRtl( 'te' ), false, 'Telugu language is not RTL' ); - assert.strictEqual( $.uls.data.isRtl( 'dv' ), true, 'Divehi language is RTL' ); - assert.strictEqual( $.uls.data.getDir( 'mzn' ), 'rtl', 'Mazandarani language is RTL' ); - assert.strictEqual( $.uls.data.getDir( 'uk' ), 'ltr', 'Ukrainian language is LTR' ); - - assert.ok( - $.inArray( 'sah', $.uls.data.getLanguagesInTerritory( 'RU' ) ) > -1, - 'Sakha language is spoken in Russia' - ); - - assert.ok( $.uls.data.deleteLanguage( 'qqq' ), 'Deleting language qqq, which was added earlier, returns true.' ); - assert.strictEqual( $.uls.data.languages['qqq'], undefined, 'Data about qqq is undefined after being deleted.' ); - assert.ok( !$.uls.data.deleteLanguage( 'qqr' ), 'Deleting language qqr, which was never added, returns false.' ); - } ); }( jQuery ) );