/**
* Detects encoding of xml-formatted text.
* @param string $string The input xml-formatted text.
* @param string $default_encoding This is the default encoding to be returned if there is no way the xml-text's encoding to be detected. If it not spesified, the system encoding is assumed then.
* @return string Returns the detected encoding.
* @todo The second parameter is to be eliminated. See api_detect_encoding_html().
*/
function api_detect_encoding_xml($string, $default_encoding = null)
{
if (preg_match(_PCRE_XML_ENCODING, $string, $matches)) {
return api_refine_encoding_id($matches[1]);
}
if (api_is_valid_utf8($string)) {
return 'UTF-8';
}
if (empty($default_encoding)) {
$default_encoding = _api_mb_internal_encoding();
}
return api_refine_encoding_id($default_encoding);
}
/**
* Sorts an array using natural order algorithm.
* @param array $array The input array.
* @param string $language (optional) The language in which comparison is to be made. If language is omitted, interface language is assumed then.
* @param string $encoding (optional) The used internally by this function character encoding. If it is omitted, the platform character set will be used by default.
* @return bool Returns TRUE on success, FALSE on error.
* This function is aimed at replacing the function natsort() for sorting human-language strings.
* @link http://php.net/manual/en/function.natsort.php
*/
function api_natsort(&$array, $language = null, $encoding = null)
{
if (INTL_INSTALLED) {
if (empty($encoding)) {
$encoding = _api_mb_internal_encoding();
}
$collator = _api_get_alpha_numerical_collator($language);
if (is_object($collator)) {
global $_api_collator, $_api_encoding;
$_api_collator = $collator;
$_api_encoding = $encoding;
return uasort($array, '_api_cmp');
}
}
return natsort($array);
}
/**
* Converts character encoding of a xml-formatted text from UTF-8 into a specified encoding. If inside the text the encoding is declared, it is modified accordingly.
* @param string $string The text being converted.
* @param string $to_encoding (optional) The encoding that text is being converted to. If it is omited, the platform character set is assumed.
* @return string Returns the converted xml-text.
*/
static function api_utf8_decode_xml($string, $to_encoding = null)
{
if (empty($to_encoding)) {
$to_encoding = _api_mb_internal_encoding();
}
return self::_api_convert_encoding_xml($string, $to_encoding, 'UTF-8');
}
/**
* Splits a string by a regular expression, UTF-8 aware when it is applicable.
* @param string $pattern The pattern to search for, as a string.
* @param string $subject The input string.
* @param int $limit (optional) If specified, then only substrings up to $limit are returned with the rest of the string being placed in the last substring. A limit of -1, 0 or null means "no limit" and, as is standard across PHP.
* @param int $flags (optional) $flags can be any combination of the following flags (combined with bitwise | operator):
* PREG_SPLIT_NO_EMPTY - if this flag is set, only non-empty pieces will be returned;
* PREG_SPLIT_DELIM_CAPTURE - if this flag is set, parenthesized expression in the delimiter pattern will be captured and returned as well;
* PREG_SPLIT_OFFSET_CAPTURE - If this flag is set, for every occurring match the appendant string offset will also be returned.
* Note that this changes the return value in an array where every element is an array consisting of the matched string at offset 0 and its string offset into subject at offset 1.
* @param string $encoding (optional) The used internally by this function character encoding. If it is omitted, the platform character set will be used by default.
* @return array Returns an array containing substrings of $subject split along boundaries matched by $pattern.
* @link http://php.net/preg_split
*/
function api_preg_split($pattern, $subject, $limit = -1, $flags = 0, $encoding = null)
{
if (empty($encoding)) {
$encoding = _api_mb_internal_encoding();
}
return preg_split(api_is_utf8($encoding) ? $pattern . 'u' : $pattern, $subject, $limit, $flags);
}
/**
* This function returns the encoding, currently used by the system.
* @return string The system's encoding.
* Note: The value of api_get_setting('platform_charset') is tried to be returned first,
* on the second place the global variable $charset is tried to be returned. If for some
* reason both attempts fail, then the libraly's internal value will be returned.
*/
function api_get_system_encoding()
{
static $system_encoding;
if (!isset($system_encoding)) {
$encoding_setting = api_get_setting('platform_charset');
if (empty($encoding_setting)) {
global $charset;
if (empty($charset)) {
return _api_mb_internal_encoding();
}
return $charset;
}
$system_encoding = $encoding_setting;
}
return $system_encoding;
}