PHP mbstring extension for improved Unicode support.', array('@url' => 'http://www.php.net/mbstring')));
}
// Check mbstring configuration
if (ini_get('mbstring.func_overload') != 0) {
return array(UNICODE_ERROR, $t('Multibyte string function overloading in PHP is active and must be disabled. Check the php.ini mbstring.func_overload setting. Please refer to the PHP mbstring documentation for more information.', array('@url' => 'http://www.php.net/mbstring')));
}
if (ini_get('mbstring.encoding_translation') != 0) {
return array(UNICODE_ERROR, $t('Multibyte string input conversion in PHP is active and must be disabled. Check the php.ini mbstring.encoding_translation setting. Please refer to the PHP mbstring documentation for more information.', array('@url' => 'http://www.php.net/mbstring')));
}
if (ini_get('mbstring.http_input') != 'pass') {
return array(UNICODE_ERROR, $t('Multibyte string input conversion in PHP is active and must be disabled. Check the php.ini mbstring.http_input setting. Please refer to the PHP mbstring documentation for more information.', array('@url' => 'http://www.php.net/mbstring')));
}
if (ini_get('mbstring.http_output') != 'pass') {
return array(UNICODE_ERROR, $t('Multibyte string output conversion in PHP is active and must be disabled. Check the php.ini mbstring.http_output setting. Please refer to the PHP mbstring documentation for more information.', array('@url' => 'http://www.php.net/mbstring')));
}
// Set appropriate configuration
mb_internal_encoding('utf-8');
mb_language('uni');
return array(UNICODE_MULTIBYTE, '');
}
/**
* Return Unicode library status and errors.
*/
function unicode_requirements() {
// Ensure translations don't break at install time
$t = get_t();
$libraries = array(
UNICODE_SINGLEBYTE => $t('Standard PHP'),
UNICODE_MULTIBYTE => $t('PHP Mbstring Extension'),
UNICODE_ERROR => $t('Error'),
);
$severities = array(
UNICODE_SINGLEBYTE => REQUIREMENT_WARNING,
UNICODE_MULTIBYTE => REQUIREMENT_OK,
UNICODE_ERROR => REQUIREMENT_ERROR,
);
list($library, $description) = _unicode_check();
$requirements['unicode'] = array(
'title' => $t('Unicode library'),
'value' => $libraries[$library],
);
if ($description) {
$requirements['unicode']['description'] = $description;
}
$requirements['unicode']['severity'] = $severities[$library];
return $requirements;
}
/**
* Prepare a new XML parser.
*
* This is a wrapper around xml_parser_create() which extracts the encoding from
* the XML data first and sets the output encoding to UTF-8. This function should
* be used instead of xml_parser_create(), because PHP 4's XML parser doesn't
* check the input encoding itself. "Starting from PHP 5, the input encoding is
* automatically detected, so that the encoding parameter specifies only the
* output encoding."
*
* This is also where unsupported encodings will be converted. Callers should
* take this into account: $data might have been changed after the call.
*
* @param &$data
* The XML data which will be parsed later.
* @return
* An XML parser object or FALSE on error.
*
* @ingroup php_wrappers
*/
function drupal_xml_parser_create(&$data) {
// Default XML encoding is UTF-8
$encoding = 'utf-8';
$bom = FALSE;
// Check for UTF-8 byte order mark (PHP5's XML parser doesn't handle it).
if (!strncmp($data, "\xEF\xBB\xBF", 3)) {
$bom = TRUE;
$data = substr($data, 3);
}
// Check for an encoding declaration in the XML prolog if no BOM was found.
if (!$bom && preg_match('/^<\?xml[^>]+encoding="(.+?)"/', $data, $match)) {
$encoding = $match[1];
}
// Unsupported encodings are converted here into UTF-8.
$php_supported = array('utf-8', 'iso-8859-1', 'us-ascii');
if (!in_array(strtolower($encoding), $php_supported)) {
$out = drupal_convert_to_utf8($data, $encoding);
if ($out !== FALSE) {
$encoding = 'utf-8';
$data = preg_replace('/^(<\?xml[^>]+encoding)="(.+?)"/', '\\1="utf-8"', $out);
}
else {
watchdog('php', 'Could not convert XML encoding %s to UTF-8.', array('%s' => $encoding), WATCHDOG_WARNING);
return FALSE;
}
}
$xml_parser = xml_parser_create($encoding);
xml_parser_set_option($xml_parser, XML_OPTION_TARGET_ENCODING, 'utf-8');
return $xml_parser;
}
/**
* Convert data to UTF-8
*
* Requires the iconv, GNU recode or mbstring PHP extension.
*
* @param $data
* The data to be converted.
* @param $encoding
* The encoding that the data is in
* @return
* Converted data or FALSE.
*/
function drupal_convert_to_utf8($data, $encoding) {
if (function_exists('iconv')) {
$out = @iconv($encoding, 'utf-8', $data);
}
elseif (function_exists('mb_convert_encoding')) {
$out = @mb_convert_encoding($data, 'utf-8', $encoding);
}
elseif (function_exists('recode_string')) {
$out = @recode_string($encoding . '..utf-8', $data);
}
else {
watchdog('php', 'Unsupported encoding %s. Please install iconv, GNU recode or mbstring for PHP.', array('%s' => $encoding), WATCHDOG_ERROR);
return FALSE;
}
return $out;
}
/**
* Truncate a UTF-8-encoded string safely to a number of bytes.
*
* If the end position is in the middle of a UTF-8 sequence, it scans backwards
* until the beginning of the byte sequence.
*
* Use this function whenever you want to chop off a string at an unsure
* location. On the other hand, if you're sure that you're splitting on a
* character boundary (e.g. after using strpos() or similar), you can safely use
* substr() instead.
*
* @param $string
* The string to truncate.
* @param $len
* An upper limit on the returned string length.
* @return
* The truncated string.
*/
function drupal_truncate_bytes($string, $len) {
if (strlen($string) <= $len) {
return $string;
}
if ((ord($string[$len]) < 0x80) || (ord($string[$len]) >= 0xC0)) {
return substr($string, 0, $len);
}
// Scan backwards to beginning of the byte sequence.
while (--$len >= 0 && ord($string[$len]) >= 0x80 && ord($string[$len]) < 0xC0);
return substr($string, 0, $len);
}
/**
* Truncates a UTF-8-encoded string safely to a number of characters.
*
* @param $string
* The string to truncate.
* @param $max_length
* An upper limit on the returned string length, including trailing ellipsis
* if $add_ellipsis is TRUE.
* @param $wordsafe
* If TRUE, attempt to truncate on a word boundary. Word boundaries are
* spaces, punctuation, and Unicode characters used as word boundaries in
* non-Latin languages; see PREG_CLASS_UNICODE_WORD_BOUNDARY for more
* information. If a word boundary cannot be found that would make the length
* of the returned string fall within length guidelines (see parameters
* $max_return_length and $min_wordsafe_length), word boundaries are ignored.
* @param $add_ellipsis
* If TRUE, add t('...') to the end of the truncated string (defaults to
* FALSE). The string length will still fall within $max_return_length.
* @param $min_wordsafe_length
* If $wordsafe is TRUE, the minimum acceptable length for truncation (before
* adding an ellipsis, if $add_ellipsis is TRUE). Has no effect if $wordsafe
* is FALSE. This can be used to prevent having a very short resulting string
* that will not be understandable. For instance, if you are truncating the
* string "See myverylongurlexample.com for more information" to a word-safe
* return length of 20, the only available word boundary within 20 characters
* is after the word "See", which wouldn't leave a very informative string. If
* you had set $min_wordsafe_length to 10, though, the function would realise
* that "See" alone is too short, and would then just truncate ignoring word
* boundaries, giving you "See myverylongurl..." (assuming you had set
* $add_ellipses to TRUE).
*
* @return
* The truncated string.
*/
function truncate_utf8($string, $max_length, $wordsafe = FALSE, $add_ellipsis = FALSE, $min_wordsafe_length = 1) {
$ellipsis = '';
$max_length = max($max_length, 0);
$min_wordsafe_length = max($min_wordsafe_length, 0);
if (drupal_strlen($string) <= $max_length) {
// No truncation needed, so don't add ellipsis, just return.
return $string;
}
if ($add_ellipsis) {
// Truncate ellipsis in case $max_length is small.
$ellipsis = drupal_substr(t('...'), 0, $max_length);
$max_length -= drupal_strlen($ellipsis);
$max_length = max($max_length, 0);
}
if ($max_length <= $min_wordsafe_length) {
// Do not attempt word-safe if lengths are bad.
$wordsafe = FALSE;
}
if ($wordsafe) {
$matches = array();
// Find the last word boundary, if there is one within $min_wordsafe_length
// to $max_length characters. preg_match() is always greedy, so it will
// find the longest string possible.
$found = preg_match('/^(.{' . $min_wordsafe_length . ',' . $max_length . '})[' . PREG_CLASS_UNICODE_WORD_BOUNDARY . ']/u', $string, $matches);
if ($found) {
$string = $matches[1];
}
else {
$string = drupal_substr($string, 0, $max_length);
}
}
else {
$string = drupal_substr($string, 0, $max_length);
}
if ($add_ellipsis) {
$string .= $ellipsis;
}
return $string;
}
/**
* Encodes MIME/HTTP header values that contain non-ASCII, UTF-8 encoded
* characters.
*
* For example, mime_header_encode('tést.txt') returns "=?UTF-8?B?dMOpc3QudHh0?=".
*
* See http://www.rfc-editor.org/rfc/rfc2047.txt for more information.
*
* Notes:
* - Only encode strings that contain non-ASCII characters.
* - We progressively cut-off a chunk with truncate_utf8(). This is to ensure
* each chunk starts and ends on a character boundary.
* - Using \n as the chunk separator may cause problems on some systems and may
* have to be changed to \r\n or \r.
*/
function mime_header_encode($string) {
if (preg_match('/[^\x20-\x7E]/', $string)) {
$chunk_size = 47; // floor((75 - strlen("=?UTF-8?B??=")) * 0.75);
$len = strlen($string);
$output = '';
while ($len > 0) {
$chunk = drupal_truncate_bytes($string, $chunk_size);
$output .= ' =?UTF-8?B?' . base64_encode($chunk) . "?=\n";
$c = strlen($chunk);
$string = substr($string, $c);
$len -= $c;
}
return trim($output);
}
return $string;
}
/**
* Complement to mime_header_encode
*/
function mime_header_decode($header) {
// First step: encoded chunks followed by other encoded chunks (need to collapse whitespace)
$header = preg_replace_callback('/=\?([^?]+)\?(Q|B)\?([^?]+|\?(?!=))\?=\s+(?==\?)/', '_mime_header_decode', $header);
// Second step: remaining chunks (do not collapse whitespace)
return preg_replace_callback('/=\?([^?]+)\?(Q|B)\?([^?]+|\?(?!=))\?=/', '_mime_header_decode', $header);
}
/**
* Helper function to mime_header_decode
*/
function _mime_header_decode($matches) {
// Regexp groups:
// 1: Character set name
// 2: Escaping method (Q or B)
// 3: Encoded data
$data = ($matches[2] == 'B') ? base64_decode($matches[3]) : str_replace('_', ' ', quoted_printable_decode($matches[3]));
if (strtolower($matches[1]) != 'utf-8') {
$data = drupal_convert_to_utf8($data, $matches[1]);
}
return $data;
}
/**
* Decode all HTML entities (including numerical ones) to regular UTF-8 bytes.
* Double-escaped entities will only be decoded once ("<" becomes "<", not "<").
*
* @param $text
* The text to decode entities in.
* @param $exclude
* An array of characters which should not be decoded. For example,
* array('<', '&', '"'). This affects both named and numerical entities.
*/
function decode_entities($text, $exclude = array()) {
static $html_entities;
if (!isset($html_entities)) {
include DRUPAL_ROOT . '/includes/unicode.entities.inc';
}
// Flip the exclude list so that we can do quick lookups later.
$exclude = array_flip($exclude);
// Use a regexp to select all entities in one pass, to avoid decoding
// double-escaped entities twice. The PREG_REPLACE_EVAL modifier 'e' is
// being used to allow for a callback (see
// http://php.net/manual/en/reference.pcre.pattern.modifiers).
return preg_replace('/&(#x?)?([A-Za-z0-9]+);/e', '_decode_entities("$1", "$2", "$0", $html_entities, $exclude)', $text);
}
/**
* Helper function for decode_entities
*/
function _decode_entities($prefix, $codepoint, $original, &$html_entities, &$exclude) {
// Named entity
if (!$prefix) {
// A named entity not in the exclude list.
if (isset($html_entities[$original]) && !isset($exclude[$html_entities[$original]])) {
return $html_entities[$original];
}
else {
return $original;
}
}
// Hexadecimal numerical entity
if ($prefix == '#x') {
$codepoint = base_convert($codepoint, 16, 10);
}
// Decimal numerical entity (strip leading zeros to avoid PHP octal notation)
else {
$codepoint = preg_replace('/^0+/', '', $codepoint);
}
// Encode codepoint as UTF-8 bytes
if ($codepoint < 0x80) {
$str = chr($codepoint);
}
elseif ($codepoint < 0x800) {
$str = chr(0xC0 | ($codepoint >> 6))
. chr(0x80 | ($codepoint & 0x3F));
}
elseif ($codepoint < 0x10000) {
$str = chr(0xE0 | ( $codepoint >> 12))
. chr(0x80 | (($codepoint >> 6) & 0x3F))
. chr(0x80 | ( $codepoint & 0x3F));
}
elseif ($codepoint < 0x200000) {
$str = chr(0xF0 | ( $codepoint >> 18))
. chr(0x80 | (($codepoint >> 12) & 0x3F))
. chr(0x80 | (($codepoint >> 6) & 0x3F))
. chr(0x80 | ( $codepoint & 0x3F));
}
// Check for excluded characters
if (isset($exclude[$str])) {
return $original;
}
else {
return $str;
}
}
/**
* Count the amount of characters in a UTF-8 string. This is less than or
* equal to the byte count.
*
* @ingroup php_wrappers
*/
function drupal_strlen($text) {
global $multibyte;
if ($multibyte == UNICODE_MULTIBYTE) {
return mb_strlen($text);
}
else {
// Do not count UTF-8 continuation bytes.
return strlen(preg_replace("/[\x80-\xBF]/", '', $text));
}
}
/**
* Uppercase a UTF-8 string.
*
* @ingroup php_wrappers
*/
function drupal_strtoupper($text) {
global $multibyte;
if ($multibyte == UNICODE_MULTIBYTE) {
return mb_strtoupper($text);
}
else {
// Use C-locale for ASCII-only uppercase
$text = strtoupper($text);
// Case flip Latin-1 accented letters
$text = preg_replace_callback('/\xC3[\xA0-\xB6\xB8-\xBE]/', '_unicode_caseflip', $text);
return $text;
}
}
/**
* Lowercase a UTF-8 string.
*
* @ingroup php_wrappers
*/
function drupal_strtolower($text) {
global $multibyte;
if ($multibyte == UNICODE_MULTIBYTE) {
return mb_strtolower($text);
}
else {
// Use C-locale for ASCII-only lowercase
$text = strtolower($text);
// Case flip Latin-1 accented letters
$text = preg_replace_callback('/\xC3[\x80-\x96\x98-\x9E]/', '_unicode_caseflip', $text);
return $text;
}
}
/**
* Helper function for case conversion of Latin-1.
* Used for flipping U+C0-U+DE to U+E0-U+FD and back.
*/
function _unicode_caseflip($matches) {
return $matches[0][0] . chr(ord($matches[0][1]) ^ 32);
}
/**
* Capitalize the first letter of a UTF-8 string.
*
* @ingroup php_wrappers
*/
function drupal_ucfirst($text) {
// Note: no mbstring equivalent!
return drupal_strtoupper(drupal_substr($text, 0, 1)) . drupal_substr($text, 1);
}
/**
* Cut off a piece of a string based on character indices and counts. Follows
* the same behavior as PHP's own substr() function.
*
* Note that for cutting off a string at a known character/substring
* location, the usage of PHP's normal strpos/substr is safe and
* much faster.
*
* @ingroup php_wrappers
*/
function drupal_substr($text, $start, $length = NULL) {
global $multibyte;
if ($multibyte == UNICODE_MULTIBYTE) {
return $length === NULL ? mb_substr($text, $start) : mb_substr($text, $start, $length);
}
else {
$strlen = strlen($text);
// Find the starting byte offset.
$bytes = 0;
if ($start > 0) {
// Count all the continuation bytes from the start until we have found
// $start characters or the end of the string.
$bytes = -1; $chars = -1;
while ($bytes < $strlen - 1 && $chars < $start) {
$bytes++;
$c = ord($text[$bytes]);
if ($c < 0x80 || $c >= 0xC0) {
$chars++;
}
}
}
elseif ($start < 0) {
// Count all the continuation bytes from the end until we have found
// abs($start) characters.
$start = abs($start);
$bytes = $strlen; $chars = 0;
while ($bytes > 0 && $chars < $start) {
$bytes--;
$c = ord($text[$bytes]);
if ($c < 0x80 || $c >= 0xC0) {
$chars++;
}
}
}
$istart = $bytes;
// Find the ending byte offset.
if ($length === NULL) {
$iend = $strlen;
}
elseif ($length > 0) {
// Count all the continuation bytes from the starting index until we have
// found $length characters or reached the end of the string, then
// backtrace one byte.
$iend = $istart - 1;
$chars = -1;
$last_real = FALSE;
while ($iend < $strlen - 1 && $chars < $length) {
$iend++;
$c = ord($text[$iend]);
$last_real = FALSE;
if ($c < 0x80 || $c >= 0xC0) {
$chars++;
$last_real = TRUE;
}
}
// Backtrace one byte if the last character we found was a real character
// and we don't need it.
if ($last_real && $chars >= $length) {
$iend--;
}
}
elseif ($length < 0) {
// Count all the continuation bytes from the end until we have found
// abs($start) characters, then backtrace one byte.
$length = abs($length);
$iend = $strlen; $chars = 0;
while ($iend > 0 && $chars < $length) {
$iend--;
$c = ord($text[$iend]);
if ($c < 0x80 || $c >= 0xC0) {
$chars++;
}
}
// Backtrace one byte if we are not at the beginning of the string.
if ($iend > 0) {
$iend--;
}
}
else {
// $length == 0, return an empty string.
return '';
}
return substr($text, $istart, max(0, $iend - $istart + 1));
}
}