/**
* This is a php-implementation of a function that is similar to mb_convert_encoding() from mbstring extension.
* The function converts a given string from one to another character encoding.
* @param string $string The string being converted.
* @param string $to_encoding The encoding that $string is being converted to.
* @param string $from_encoding The encoding that $string is being converted from.
* @return string Returns the converted string.
*/
function _api_convert_encoding(&$string, $to_encoding, $from_encoding)
{
$str = (string) $string;
static $character_map = array();
static $utf8_compatible = array('UTF-8', 'US-ASCII');
if (empty($str)) {
return $str;
}
$to_encoding = api_refine_encoding_id($to_encoding);
$from_encoding = api_refine_encoding_id($from_encoding);
if (api_equal_encodings($to_encoding, $from_encoding)) {
return $str;
}
if ($to_encoding == 'HTML-ENTITIES') {
return api_htmlentities($str, ENT_QUOTES, $from_encoding);
}
if ($from_encoding == 'HTML-ENTITIES') {
return api_html_entity_decode($str, ENT_QUOTES, $to_encoding);
}
$to = _api_get_character_map_name($to_encoding);
$from = _api_get_character_map_name($from_encoding);
if (empty($to) || empty($from) || $to == $from || in_array($to, $utf8_compatible) && in_array($from, $utf8_compatible)) {
return $str;
}
if (!isset($character_map[$to])) {
$character_map[$to] =& _api_parse_character_map($to);
}
if ($character_map[$to] === false) {
return $str;
}
if (!isset($character_map[$from])) {
$character_map[$from] =& _api_parse_character_map($from);
}
if ($character_map[$from] === false) {
return $str;
}
if ($from != 'UTF-8') {
$len = api_byte_count($str);
$codepoints = array();
for ($i = 0; $i < $len; $i++) {
$ord = ord($str[$i]);
if ($ord > 127) {
if (isset($character_map[$from]['local'][$ord])) {
$codepoints[] = $character_map[$from]['local'][$ord];
} else {
$codepoints[] = 0xfffd;
// U+FFFD REPLACEMENT CHARACTER is the general substitute character in the Unicode Standard.
}
} else {
$codepoints[] = $ord;
}
}
} else {
$codepoints = _api_utf8_to_unicode($str);
}
if ($to != 'UTF-8') {
foreach ($codepoints as $i => &$codepoint) {
if ($codepoint > 127) {
if (isset($character_map[$to]['unicode'][$codepoint])) {
$codepoint = chr($character_map[$to]['unicode'][$codepoint]);
} else {
$codepoint = '?';
// Unknown character.
}
} else {
$codepoint = chr($codepoint);
}
}
$str = implode($codepoints);
} else {
$str = _api_utf8_from_unicode($codepoints);
}
return $str;
}
/**
* Replaces text within a portion of a string.
* @param string $string The input string.
* @param string $replacement The replacement string.
* @param int $start The position from which replacing will begin.
* Notes:
* If $start is positive, the replacing will begin at the $start'th offset into the string.
* If $start is negative, the replacing will begin at the $start'th character from the end of the string.
* @param int $length (optional) The position where replacing will end.
* Notes:
* If given and is positive, it represents the length of the portion of the string which is to be replaced.
* If it is negative, it represents the number of characters from the end of string at which to stop replacing.
* If it is not given, then it will default to api_strlen($string); i.e. end the replacing at the end of string.
* If $length is zero, then this function will have the effect of inserting replacement into the string at the given start offset.
* @param string $encoding (optional) The used internally by this function character encoding. If it is omitted, the platform character set will be used by default.
* @return string The result string is returned.
* This function is aimed at replacing the function substr_replace() for human-language strings.
* @link http://php.net/manual/function.substr-replace
*/
function api_substr_replace($string, $replacement, $start, $length = null, $encoding = null)
{
if (empty($encoding)) {
$encoding = _api_mb_internal_encoding();
}
if (_api_is_single_byte_encoding($encoding)) {
if (is_null($length)) {
return substr_replace($string, $replacement, $start);
}
return substr_replace($string, $replacement, $start, $length);
}
if (api_is_encoding_supported($encoding)) {
if (is_null($length)) {
$length = api_strlen($string);
}
if (!api_is_utf8($encoding)) {
$string = api_utf8_encode($string, $encoding);
$replacement = api_utf8_encode($replacement, $encoding);
}
$string = _api_utf8_to_unicode($string);
array_splice($string, $start, $length, _api_utf8_to_unicode($replacement));
$string = _api_utf8_from_unicode($string);
if (!api_is_utf8($encoding)) {
$string = api_utf8_decode($string, $encoding);
}
return $string;
}
if (is_null($length)) {
return substr_replace($string, $replacement, $start);
}
return substr_replace($string, $replacement, $start, $length);
}