This expensive function tests whether or not a given character
encoding supports ASCII. 7/8-bit encodings like Shift_JIS will
fail this test, and require special processing. Variable width
encodings shouldn't ever fail.
| public static testEncodingSupportsASCII ( string $encoding, boolean $bypass = false ) : Array | ||
| $encoding | string | Encoding name to test, as per iconv format |
| $bypass | boolean | Whether or not to bypass the precompiled arrays. |
| return | Array | of UTF-8 characters to their corresponding ASCII, which can be used to "undo" any overzealous iconv action. |
/**
* Converts a string from UTF-8 based on configuration.
* @note Currently, this is a lossy conversion, with unexpressable
* characters being omitted.
*/
public static function convertFromUTF8($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 $str;
}
trigger_error('Encoding not supported', E_USER_ERROR);
}
public function assertASCIISupportCheck($enc, $ret)
{
$test = HTMLPurifier_Encoder::testEncodingSupportsASCII($enc, true);
if ($test === false) {
return;
}
$this->assertIdentical(HTMLPurifier_Encoder::testEncodingSupportsASCII($enc), $ret);
$this->assertIdentical(HTMLPurifier_Encoder::testEncodingSupportsASCII($enc, true), $ret);
}
