diff options
Diffstat (limited to 'core/includes/unicode.inc')
| -rw-r--r-- | core/includes/unicode.inc | 601 |
1 files changed, 601 insertions, 0 deletions
diff --git a/core/includes/unicode.inc b/core/includes/unicode.inc new file mode 100644 index 000000000000..9dde2ca70cca --- /dev/null +++ b/core/includes/unicode.inc @@ -0,0 +1,601 @@ +<?php + +/** + * Indicates an error during check for PHP unicode support. + */ +define('UNICODE_ERROR', -1); + +/** + * Indicates that standard PHP (emulated) unicode support is being used. + */ +define('UNICODE_SINGLEBYTE', 0); + +/** + * Indicates that full unicode support with the PHP mbstring extension is being + * used. + */ +define('UNICODE_MULTIBYTE', 1); + +/** + * Matches Unicode characters that are word boundaries. + * + * @see http://unicode.org/glossary + * + * Characters with the following General_category (gc) property values are used + * as word boundaries. While this does not fully conform to the Word Boundaries + * algorithm described in http://unicode.org/reports/tr29, as PCRE does not + * contain the Word_Break property table, this simpler algorithm has to do. + * - Cc, Cf, Cn, Co, Cs: Other. + * - Pc, Pd, Pe, Pf, Pi, Po, Ps: Punctuation. + * - Sc, Sk, Sm, So: Symbols. + * - Zl, Zp, Zs: Separators. + * + * Non-boundary characters include the following General_category (gc) property + * values: + * - Ll, Lm, Lo, Lt, Lu: Letters. + * - Mc, Me, Mn: Combining Marks. + * - Nd, Nl, No: Numbers. + * + * Note that the PCRE property matcher is not used because we wanted to be + * compatible with Unicode 5.2.0 regardless of the PCRE version used (and any + * bugs in PCRE property tables). + */ +define('PREG_CLASS_UNICODE_WORD_BOUNDARY', + '\x{0}-\x{2F}\x{3A}-\x{40}\x{5B}-\x{60}\x{7B}-\x{A9}\x{AB}-\x{B1}\x{B4}' . + '\x{B6}-\x{B8}\x{BB}\x{BF}\x{D7}\x{F7}\x{2C2}-\x{2C5}\x{2D2}-\x{2DF}' . + '\x{2E5}-\x{2EB}\x{2ED}\x{2EF}-\x{2FF}\x{375}\x{37E}-\x{385}\x{387}\x{3F6}' . + '\x{482}\x{55A}-\x{55F}\x{589}-\x{58A}\x{5BE}\x{5C0}\x{5C3}\x{5C6}' . + '\x{5F3}-\x{60F}\x{61B}-\x{61F}\x{66A}-\x{66D}\x{6D4}\x{6DD}\x{6E9}' . + '\x{6FD}-\x{6FE}\x{700}-\x{70F}\x{7F6}-\x{7F9}\x{830}-\x{83E}' . + '\x{964}-\x{965}\x{970}\x{9F2}-\x{9F3}\x{9FA}-\x{9FB}\x{AF1}\x{B70}' . + '\x{BF3}-\x{BFA}\x{C7F}\x{CF1}-\x{CF2}\x{D79}\x{DF4}\x{E3F}\x{E4F}' . + '\x{E5A}-\x{E5B}\x{F01}-\x{F17}\x{F1A}-\x{F1F}\x{F34}\x{F36}\x{F38}' . + '\x{F3A}-\x{F3D}\x{F85}\x{FBE}-\x{FC5}\x{FC7}-\x{FD8}\x{104A}-\x{104F}' . + '\x{109E}-\x{109F}\x{10FB}\x{1360}-\x{1368}\x{1390}-\x{1399}\x{1400}' . + '\x{166D}-\x{166E}\x{1680}\x{169B}-\x{169C}\x{16EB}-\x{16ED}' . + '\x{1735}-\x{1736}\x{17B4}-\x{17B5}\x{17D4}-\x{17D6}\x{17D8}-\x{17DB}' . + '\x{1800}-\x{180A}\x{180E}\x{1940}-\x{1945}\x{19DE}-\x{19FF}' . + '\x{1A1E}-\x{1A1F}\x{1AA0}-\x{1AA6}\x{1AA8}-\x{1AAD}\x{1B5A}-\x{1B6A}' . + '\x{1B74}-\x{1B7C}\x{1C3B}-\x{1C3F}\x{1C7E}-\x{1C7F}\x{1CD3}\x{1FBD}' . + '\x{1FBF}-\x{1FC1}\x{1FCD}-\x{1FCF}\x{1FDD}-\x{1FDF}\x{1FED}-\x{1FEF}' . + '\x{1FFD}-\x{206F}\x{207A}-\x{207E}\x{208A}-\x{208E}\x{20A0}-\x{20B8}' . + '\x{2100}-\x{2101}\x{2103}-\x{2106}\x{2108}-\x{2109}\x{2114}' . + '\x{2116}-\x{2118}\x{211E}-\x{2123}\x{2125}\x{2127}\x{2129}\x{212E}' . + '\x{213A}-\x{213B}\x{2140}-\x{2144}\x{214A}-\x{214D}\x{214F}' . + '\x{2190}-\x{244A}\x{249C}-\x{24E9}\x{2500}-\x{2775}\x{2794}-\x{2B59}' . + '\x{2CE5}-\x{2CEA}\x{2CF9}-\x{2CFC}\x{2CFE}-\x{2CFF}\x{2E00}-\x{2E2E}' . + '\x{2E30}-\x{3004}\x{3008}-\x{3020}\x{3030}\x{3036}-\x{3037}' . + '\x{303D}-\x{303F}\x{309B}-\x{309C}\x{30A0}\x{30FB}\x{3190}-\x{3191}' . + '\x{3196}-\x{319F}\x{31C0}-\x{31E3}\x{3200}-\x{321E}\x{322A}-\x{3250}' . + '\x{3260}-\x{327F}\x{328A}-\x{32B0}\x{32C0}-\x{33FF}\x{4DC0}-\x{4DFF}' . + '\x{A490}-\x{A4C6}\x{A4FE}-\x{A4FF}\x{A60D}-\x{A60F}\x{A673}\x{A67E}' . + '\x{A6F2}-\x{A716}\x{A720}-\x{A721}\x{A789}-\x{A78A}\x{A828}-\x{A82B}' . + '\x{A836}-\x{A839}\x{A874}-\x{A877}\x{A8CE}-\x{A8CF}\x{A8F8}-\x{A8FA}' . + '\x{A92E}-\x{A92F}\x{A95F}\x{A9C1}-\x{A9CD}\x{A9DE}-\x{A9DF}' . + '\x{AA5C}-\x{AA5F}\x{AA77}-\x{AA79}\x{AADE}-\x{AADF}\x{ABEB}' . + '\x{D800}-\x{F8FF}\x{FB29}\x{FD3E}-\x{FD3F}\x{FDFC}-\x{FDFD}' . + '\x{FE10}-\x{FE19}\x{FE30}-\x{FE6B}\x{FEFF}-\x{FF0F}\x{FF1A}-\x{FF20}' . + '\x{FF3B}-\x{FF40}\x{FF5B}-\x{FF65}\x{FFE0}-\x{FFFD}'); + +/** + * Wrapper around _unicode_check(). + */ +function unicode_check() { + list($GLOBALS['multibyte']) = _unicode_check(); +} + +/** + * Perform checks about Unicode support in PHP, and set the right settings if + * needed. + * + * Because Drupal needs to be able to handle text in various encodings, we do + * not support mbstring function overloading. HTTP input/output conversion must + * be disabled for similar reasons. + * + * @param $errors + * Whether to report any fatal errors with form_set_error(). + */ +function _unicode_check() { + // Ensure translations don't break at install time + $t = get_t(); + + // Check for mbstring extension + if (!function_exists('mb_strlen')) { + return array(UNICODE_SINGLEBYTE, $t('Operations on Unicode strings are emulated on a best-effort basis. Install the <a href="@url">PHP mbstring extension</a> 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 <em>mbstring.func_overload</em> setting. Please refer to the <a href="@url">PHP mbstring documentation</a> 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 <em>mbstring.encoding_translation</em> setting. Please refer to the <a href="@url">PHP mbstring documentation</a> 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 <em>mbstring.http_input</em> setting. Please refer to the <a href="@url">PHP mbstring documentation</a> 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 <em>mbstring.http_output</em> setting. Please refer to the <a href="@url">PHP mbstring documentation</a> 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_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_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; +} + +/** + * Decodes all HTML entities (including numerical ones) to regular UTF-8 bytes. + * + * Double-escaped entities will only be decoded once ("&lt;" becomes "<", + * not "<"). Be careful when using this function, as decode_entities can revert + * previous sanitization efforts (<script> will become <script>). + * + * @param $text + * The text to decode entities in. + * + * @return + * The input $text, with all HTML entities decoded once. + */ +function decode_entities($text) { + return html_entity_decode($text, ENT_QUOTES, 'UTF-8'); +} + +/** + * Count the amount of characters in a UTF-8 string. This is less than or + * equal to the byte count. + * + * @ingroup php_wrappers + */ +function drupal_strlen($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)); + } +} |