Lossless (character-wise) conversion of HTML to ASCII
| public static convertToASCIIDumbLossless ( string $str ) : string | ||
| $str | string | UTF-8 string to be converted to ASCII |
| return | string | ASCII encoded string with non-ASCII character entity-ized |
/**
* Converts a string from UTF-8 based on configuration.
* @note Currently, this is a lossy conversion, with unexpressable
* characters being omitted.
*/
public static function convertFromUTF8($str, $config, $context)
{
static $iconv = null;
if ($iconv === null) {
$iconv = function_exists('iconv');
}
$encoding = $config->get('Core', 'Encoding');
if ($encoding === 'utf-8') {
return $str;
}
if ($config->get('Core', 'EscapeNonASCIICharacters')) {
$str = HTMLPurifier_Encoder::convertToASCIIDumbLossless($str);
}
if ($iconv && !$config->get('Test', 'ForceNoIconv')) {
return @iconv('utf-8', $encoding . '//IGNORE', $str);
} elseif ($encoding === 'iso-8859-1') {
return @utf8_decode($str);
}
trigger_error('Encoding not supported', E_USER_ERROR);
}
/**
* Converts a string from UTF-8 based on configuration.
* @note Currently, this is a lossy conversion, with unexpressable
* characters being omitted.
*/
public static function convertFromUTF8($str, $config, $context)
{
$encoding = $config->get('Core.Encoding');
if ($encoding === 'utf-8') {
return $str;
}
static $iconv = null;
if ($iconv === null) {
$iconv = function_exists('iconv');
}
if ($escape = $config->get('Core.EscapeNonASCIICharacters')) {
$str = HTMLPurifier_Encoder::convertToASCIIDumbLossless($str);
}
set_error_handler(array('HTMLPurifier_Encoder', 'muteErrorHandler'));
if ($iconv && !$config->get('Test.ForceNoIconv')) {
// Undo our previous fix in convertToUTF8, otherwise iconv will barf
$ascii_fix = HTMLPurifier_Encoder::testEncodingSupportsASCII($encoding);
if (!$escape && !empty($ascii_fix)) {
$clear_fix = array();
foreach ($ascii_fix as $utf8 => $native) {
$clear_fix[$utf8] = '';
}
$str = strtr($str, $clear_fix);
}
$str = strtr($str, array_flip($ascii_fix));
// Normal stuff
$str = iconv('utf-8', $encoding . '//IGNORE', $str);
restore_error_handler();
return $str;
} elseif ($encoding === 'iso-8859-1') {
$str = utf8_decode($str);
restore_error_handler();
return $str;
}
trigger_error('Encoding not supported', E_USER_ERROR);
}
public function test_convertToASCIIDumbLossless()
{
// Uppercase thorn letter
$this->assertIdentical(HTMLPurifier_Encoder::convertToASCIIDumbLossless("Þorn"), "Þorn");
$this->assertIdentical(HTMLPurifier_Encoder::convertToASCIIDumbLossless("an"), "an");
// test up to four bytes
$this->assertIdentical(HTMLPurifier_Encoder::convertToASCIIDumbLossless("ó € "), "󠀠");
}
