.

From ada3beb0a6c649bd9bfc6a87b2fe69ee8ae563f7 Mon Sep 17 00:00:00 2001 From: Andreas Baumann Date: Sat, 1 Feb 2020 08:57:06 +0100 Subject: initial checkin --- include/utf8/index.html | 1 + include/utf8/mbstring/core.php | 144 +++++++++++++ include/utf8/mbstring/index.html | 1 + include/utf8/native/core.php | 422 +++++++++++++++++++++++++++++++++++++ include/utf8/native/index.html | 1 + include/utf8/ord.php | 78 +++++++ include/utf8/str_ireplace.php | 72 +++++++ include/utf8/str_pad.php | 59 ++++++ include/utf8/str_split.php | 33 +++ include/utf8/strcasecmp.php | 27 +++ include/utf8/strcspn.php | 36 ++++ include/utf8/stristr.php | 34 +++ include/utf8/strrev.php | 22 ++ include/utf8/strspn.php | 32 +++ include/utf8/substr_replace.php | 27 +++ include/utf8/trim.php | 74 +++++++ include/utf8/ucfirst.php | 35 ++++ include/utf8/ucwords.php | 46 ++++ include/utf8/utf8.php | 72 +++++++ include/utf8/utils/ascii.php | 221 ++++++++++++++++++++ include/utf8/utils/bad.php | 430 ++++++++++++++++++++++++++++++++++++++ include/utf8/utils/index.html | 1 + include/utf8/utils/patterns.php | 67 ++++++ include/utf8/utils/position.php | 171 +++++++++++++++ include/utf8/utils/specials.php | 131 ++++++++++++ include/utf8/utils/unicode.php | 241 +++++++++++++++++++++ include/utf8/utils/validation.php | 186 +++++++++++++++++ 27 files changed, 2664 insertions(+) create mode 100644 include/utf8/index.html create mode 100644 include/utf8/mbstring/core.php create mode 100644 include/utf8/mbstring/index.html create mode 100644 include/utf8/native/core.php create mode 100644 include/utf8/native/index.html create mode 100644 include/utf8/ord.php create mode 100644 include/utf8/str_ireplace.php create mode 100644 include/utf8/str_pad.php create mode 100644 include/utf8/str_split.php create mode 100644 include/utf8/strcasecmp.php create mode 100644 include/utf8/strcspn.php create mode 100644 include/utf8/stristr.php create mode 100644 include/utf8/strrev.php create mode 100644 include/utf8/strspn.php create mode 100644 include/utf8/substr_replace.php create mode 100644 include/utf8/trim.php create mode 100644 include/utf8/ucfirst.php create mode 100644 include/utf8/ucwords.php create mode 100644 include/utf8/utf8.php create mode 100644 include/utf8/utils/ascii.php create mode 100644 include/utf8/utils/bad.php create mode 100644 include/utf8/utils/index.html create mode 100644 include/utf8/utils/patterns.php create mode 100644 include/utf8/utils/position.php create mode 100644 include/utf8/utils/specials.php create mode 100644 include/utf8/utils/unicode.php create mode 100644 include/utf8/utils/validation.php (limited to 'include/utf8') diff --git a/include/utf8/index.html b/include/utf8/index.html new file mode 100644 index 0000000..89337b2 --- /dev/null +++ b/include/utf8/index.html @@ -0,0 +1 @@ +.. diff --git a/include/utf8/mbstring/core.php b/include/utf8/mbstring/core.php new file mode 100644 index 0000000..bea1c32 --- /dev/null +++ b/include/utf8/mbstring/core.php @@ -0,0 +1,144 @@ +.. diff --git a/include/utf8/native/core.php b/include/utf8/native/core.php new file mode 100644 index 0000000..58636f5 --- /dev/null +++ b/include/utf8/native/core.php @@ -0,0 +1,422 @@ + +* @link http://www.php.net/manual/en/function.strlen.php +* @link http://www.php.net/manual/en/function.utf8-decode.php +* @param string UTF-8 string +* @return int number of UTF-8 characters in string +* @package utf8 +* @subpackage strings +*/ +function utf8_strlen($str) +{ + return strlen(utf8_decode($str)); +} + +/** +* UTF-8 aware alternative to strpos +* Find position of first occurrence of a string +* Note: This will get alot slower if offset is used +* Note: requires utf8_strlen amd utf8_substr to be loaded +* @param string haystack +* @param string needle (you should validate this with utf8_is_valid) +* @param integer offset in characters (from left) +* @return mixed integer position or FALSE on failure +* @see http://www.php.net/strpos +* @see utf8_strlen +* @see utf8_substr +* @package utf8 +* @subpackage strings +*/ +function utf8_strpos($str, $needle, $offset = false) +{ + if ($offset === false) + { + $ar = explode($needle, $str, 2); + + if (count($ar) > 1) + return utf8_strlen($ar[0]); + + return false; + } + else + { + if (!is_int($offset)) + { + trigger_error('utf8_strpos: Offset must be an integer', E_USER_ERROR); + return false; + } + + $str = utf8_substr($str, $offset); + + if (($pos = utf8_strpos($str, $needle)) !== false) + return $pos + $offset; + + return false; + } +} + +/** +* UTF-8 aware alternative to strrpos +* Find position of last occurrence of a char in a string +* Note: This will get alot slower if offset is used +* Note: requires utf8_substr and utf8_strlen to be loaded +* @param string haystack +* @param string needle (you should validate this with utf8_is_valid) +* @param integer (optional) offset (from left) +* @return mixed integer position or FALSE on failure +* @see http://www.php.net/strrpos +* @see utf8_substr +* @see utf8_strlen +* @package utf8 +* @subpackage strings +*/ +function utf8_strrpos($str, $needle, $offset = false) +{ + if ($offset === false) + { + $ar = explode($needle, $str); + + if (count($ar) > 1) + { + // Pop off the end of the string where the last match was made + array_pop($ar); + $str = join($needle, $ar); + + return utf8_strlen($str); + } + + return false; + } + else + { + if (!is_int($offset)) + { + trigger_error('utf8_strrpos expects parameter 3 to be long', E_USER_WARNING); + return false; + } + + $str = utf8_substr($str, $offset); + + if (($pos = utf8_strrpos($str, $needle)) !== false) + return $pos + $offset; + + return false; + } +} + +/** +* UTF-8 aware alternative to substr +* Return part of a string given character offset (and optionally length) +* +* Note arguments: comparied to substr - if offset or length are +* not integers, this version will not complain but rather massages them +* into an integer. +* +* Note on returned values: substr documentation states false can be +* returned in some cases (e.g. offset > string length) +* mb_substr never returns false, it will return an empty string instead. +* This adopts the mb_substr approach +* +* Note on implementation: PCRE only supports repetitions of less than +* 65536, in order to accept up to MAXINT values for offset and length, +* we'll repeat a group of 65535 characters when needed. +* +* Note on implementation: calculating the number of characters in the +* string is a relatively expensive operation, so we only carry it out when +* necessary. It isn't necessary for +ve offsets and no specified length +* +* @author Chris Smith +* @param string +* @param integer number of UTF-8 characters offset (from left) +* @param integer (optional) length in UTF-8 characters from offset +* @return mixed string or FALSE if failure +* @package utf8 +* @subpackage strings +*/ +function utf8_substr($str, $offset, $length = false) +{ + // Generates E_NOTICE for PHP4 objects, but not PHP5 objects + $str = (string) $str; + $offset = (int) $offset; + + if ($length) + $length = (int) $length; + + // Handle trivial cases + if ($length === 0) + return ''; + if ($offset < 0 && $length < 0 && $length < $offset) + return ''; + + // Normalise negative offsets (we could use a tail + // anchored pattern, but they are horribly slow!) + if ($offset < 0) + { + // See notes + $strlen = utf8_strlen($str); + $offset = $strlen + $offset; + + if ($offset < 0) + $offset = 0; + } + + $Op = ''; + $Lp = ''; + + // Establish a pattern for offset, a + // non-captured group equal in length to offset + if ($offset > 0) + { + $Ox = (int) ($offset / 65535); + $Oy = $offset % 65535; + + if ($Ox) + $Op = '(?:.{65535}){'.$Ox.'}'; + + $Op = '^(?:'.$Op.'.{'.$Oy.'})'; + } + else + $Op = '^'; + + + // Establish a pattern for length + if (!$length) + { + // The rest of the string + $Lp = '(.*)$'; + } + else + { + // See notes + if (!isset($strlen)) + $strlen = strlen(utf8_decode($str)); + + // Another trivial case + if ($offset > $strlen) + return ''; + + if ($length > 0) + { + // Reduce any length that would go passed the end of the string + $length = min($strlen-$offset, $length); + + $Lx = (int)( $length / 65535 ); + $Ly = $length % 65535; + + // Negative length requires a captured group of length characters + if ($Lx) $Lp = '(?:.{65535}){'.$Lx.'}'; + $Lp = '('.$Lp.'.{'.$Ly.'})'; + } + else if ($length < 0) + { + + if ($length < ($offset - $strlen)) + return ''; + + $Lx = (int)((-$length)/65535); + $Ly = (-$length)%65535; + + // Negative length requires ... capture everything except a group of + // -length characters anchored at the tail-end of the string + if ($Lx) + $Lp = '(?:.{65535}){'.$Lx.'}'; + + $Lp = '(.*)(?:'.$Lp.'.{'.$Ly.'})$'; + } + } + + if (!preg_match('#'.$Op.$Lp.'#us', $str, $match)) + return ''; + + return $match[1]; +} + +/** +* UTF-8 aware alternative to strtolower +* Make a string lowercase +* Note: The concept of a characters "case" only exists is some alphabets +* such as Latin, Greek, Cyrillic, Armenian and archaic Georgian - it does +* not exist in the Chinese alphabet, for example. See Unicode Standard +* Annex #21: Case Mappings +* Note: requires utf8_to_unicode and utf8_from_unicode +* @author Andreas Gohr +* @param string +* @return mixed either string in lowercase or FALSE is UTF-8 invalid +* @see http://www.php.net/strtolower +* @see utf8_to_unicode +* @see utf8_from_unicode +* @see http://www.unicode.org/reports/tr21/tr21-5.html +* @see http://dev.splitbrain.org/view/darcs/dokuwiki/inc/utf8.php +* @package utf8 +* @subpackage strings +*/ +function utf8_strtolower($string) +{ + static $UTF8_UPPER_TO_LOWER = false; + + if (!$UTF8_UPPER_TO_LOWER) + { + $UTF8_UPPER_TO_LOWER = array( + 0x0041=>0x0061, 0x03A6=>0x03C6, 0x0162=>0x0163, 0x00C5=>0x00E5, 0x0042=>0x0062, + 0x0139=>0x013A, 0x00C1=>0x00E1, 0x0141=>0x0142, 0x038E=>0x03CD, 0x0100=>0x0101, + 0x0490=>0x0491, 0x0394=>0x03B4, 0x015A=>0x015B, 0x0044=>0x0064, 0x0393=>0x03B3, + 0x00D4=>0x00F4, 0x042A=>0x044A, 0x0419=>0x0439, 0x0112=>0x0113, 0x041C=>0x043C, + 0x015E=>0x015F, 0x0143=>0x0144, 0x00CE=>0x00EE, 0x040E=>0x045E, 0x042F=>0x044F, + 0x039A=>0x03BA, 0x0154=>0x0155, 0x0049=>0x0069, 0x0053=>0x0073, 0x1E1E=>0x1E1F, + 0x0134=>0x0135, 0x0427=>0x0447, 0x03A0=>0x03C0, 0x0418=>0x0438, 0x00D3=>0x00F3, + 0x0420=>0x0440, 0x0404=>0x0454, 0x0415=>0x0435, 0x0429=>0x0449, 0x014A=>0x014B, + 0x0411=>0x0431, 0x0409=>0x0459, 0x1E02=>0x1E03, 0x00D6=>0x00F6, 0x00D9=>0x00F9, + 0x004E=>0x006E, 0x0401=>0x0451, 0x03A4=>0x03C4, 0x0423=>0x0443, 0x015C=>0x015D, + 0x0403=>0x0453, 0x03A8=>0x03C8, 0x0158=>0x0159, 0x0047=>0x0067, 0x00C4=>0x00E4, + 0x0386=>0x03AC, 0x0389=>0x03AE, 0x0166=>0x0167, 0x039E=>0x03BE, 0x0164=>0x0165, + 0x0116=>0x0117, 0x0108=>0x0109, 0x0056=>0x0076, 0x00DE=>0x00FE, 0x0156=>0x0157, + 0x00DA=>0x00FA, 0x1E60=>0x1E61, 0x1E82=>0x1E83, 0x00C2=>0x00E2, 0x0118=>0x0119, + 0x0145=>0x0146, 0x0050=>0x0070, 0x0150=>0x0151, 0x042E=>0x044E, 0x0128=>0x0129, + 0x03A7=>0x03C7, 0x013D=>0x013E, 0x0422=>0x0442, 0x005A=>0x007A, 0x0428=>0x0448, + 0x03A1=>0x03C1, 0x1E80=>0x1E81, 0x016C=>0x016D, 0x00D5=>0x00F5, 0x0055=>0x0075, + 0x0176=>0x0177, 0x00DC=>0x00FC, 0x1E56=>0x1E57, 0x03A3=>0x03C3, 0x041A=>0x043A, + 0x004D=>0x006D, 0x016A=>0x016B, 0x0170=>0x0171, 0x0424=>0x0444, 0x00CC=>0x00EC, + 0x0168=>0x0169, 0x039F=>0x03BF, 0x004B=>0x006B, 0x00D2=>0x00F2, 0x00C0=>0x00E0, + 0x0414=>0x0434, 0x03A9=>0x03C9, 0x1E6A=>0x1E6B, 0x00C3=>0x00E3, 0x042D=>0x044D, + 0x0416=>0x0436, 0x01A0=>0x01A1, 0x010C=>0x010D, 0x011C=>0x011D, 0x00D0=>0x00F0, + 0x013B=>0x013C, 0x040F=>0x045F, 0x040A=>0x045A, 0x00C8=>0x00E8, 0x03A5=>0x03C5, + 0x0046=>0x0066, 0x00DD=>0x00FD, 0x0043=>0x0063, 0x021A=>0x021B, 0x00CA=>0x00EA, + 0x0399=>0x03B9, 0x0179=>0x017A, 0x00CF=>0x00EF, 0x01AF=>0x01B0, 0x0045=>0x0065, + 0x039B=>0x03BB, 0x0398=>0x03B8, 0x039C=>0x03BC, 0x040C=>0x045C, 0x041F=>0x043F, + 0x042C=>0x044C, 0x00DE=>0x00FE, 0x00D0=>0x00F0, 0x1EF2=>0x1EF3, 0x0048=>0x0068, + 0x00CB=>0x00EB, 0x0110=>0x0111, 0x0413=>0x0433, 0x012E=>0x012F, 0x00C6=>0x00E6, + 0x0058=>0x0078, 0x0160=>0x0161, 0x016E=>0x016F, 0x0391=>0x03B1, 0x0407=>0x0457, + 0x0172=>0x0173, 0x0178=>0x00FF, 0x004F=>0x006F, 0x041B=>0x043B, 0x0395=>0x03B5, + 0x0425=>0x0445, 0x0120=>0x0121, 0x017D=>0x017E, 0x017B=>0x017C, 0x0396=>0x03B6, + 0x0392=>0x03B2, 0x0388=>0x03AD, 0x1E84=>0x1E85, 0x0174=>0x0175, 0x0051=>0x0071, + 0x0417=>0x0437, 0x1E0A=>0x1E0B, 0x0147=>0x0148, 0x0104=>0x0105, 0x0408=>0x0458, + 0x014C=>0x014D, 0x00CD=>0x00ED, 0x0059=>0x0079, 0x010A=>0x010B, 0x038F=>0x03CE, + 0x0052=>0x0072, 0x0410=>0x0430, 0x0405=>0x0455, 0x0402=>0x0452, 0x0126=>0x0127, + 0x0136=>0x0137, 0x012A=>0x012B, 0x038A=>0x03AF, 0x042B=>0x044B, 0x004C=>0x006C, + 0x0397=>0x03B7, 0x0124=>0x0125, 0x0218=>0x0219, 0x00DB=>0x00FB, 0x011E=>0x011F, + 0x041E=>0x043E, 0x1E40=>0x1E41, 0x039D=>0x03BD, 0x0106=>0x0107, 0x03AB=>0x03CB, + 0x0426=>0x0446, 0x00DE=>0x00FE, 0x00C7=>0x00E7, 0x03AA=>0x03CA, 0x0421=>0x0441, + 0x0412=>0x0432, 0x010E=>0x010F, 0x00D8=>0x00F8, 0x0057=>0x0077, 0x011A=>0x011B, + 0x0054=>0x0074, 0x004A=>0x006A, 0x040B=>0x045B, 0x0406=>0x0456, 0x0102=>0x0103, + 0x039B=>0x03BB, 0x00D1=>0x00F1, 0x041D=>0x043D, 0x038C=>0x03CC, 0x00C9=>0x00E9, + 0x00D0=>0x00F0, 0x0407=>0x0457, 0x0122=>0x0123); + } + + $uni = utf8_to_unicode($string); + + if (!$uni) + return false; + + $cnt = count($uni); + + for ($i=0; $i < $cnt; $i++) + if (isset($UTF8_UPPER_TO_LOWER[$uni[$i]])) + $uni[$i] = $UTF8_UPPER_TO_LOWER[$uni[$i]]; + + return utf8_from_unicode($uni); +} + +/** +* UTF-8 aware alternative to strtoupper +* Make a string uppercase +* Note: The concept of a characters "case" only exists is some alphabets +* such as Latin, Greek, Cyrillic, Armenian and archaic Georgian - it does +* not exist in the Chinese alphabet, for example. See Unicode Standard +* Annex #21: Case Mappings +* Note: requires utf8_to_unicode and utf8_from_unicode +* @author Andreas Gohr +* @param string +* @return mixed either string in lowercase or FALSE is UTF-8 invalid +* @see http://www.php.net/strtoupper +* @see utf8_to_unicode +* @see utf8_from_unicode +* @see http://www.unicode.org/reports/tr21/tr21-5.html +* @see http://dev.splitbrain.org/view/darcs/dokuwiki/inc/utf8.php +* @package utf8 +* @subpackage strings +*/ +function utf8_strtoupper($string) +{ + static $UTF8_LOWER_TO_UPPER = false; + + if (!$UTF8_LOWER_TO_UPPER) + { + $UTF8_LOWER_TO_UPPER = array( + 0x0061=>0x0041, 0x03C6=>0x03A6, 0x0163=>0x0162, 0x00E5=>0x00C5, 0x0062=>0x0042, + 0x013A=>0x0139, 0x00E1=>0x00C1, 0x0142=>0x0141, 0x03CD=>0x038E, 0x0101=>0x0100, + 0x0491=>0x0490, 0x03B4=>0x0394, 0x015B=>0x015A, 0x0064=>0x0044, 0x03B3=>0x0393, + 0x00F4=>0x00D4, 0x044A=>0x042A, 0x0439=>0x0419, 0x0113=>0x0112, 0x043C=>0x041C, + 0x015F=>0x015E, 0x0144=>0x0143, 0x00EE=>0x00CE, 0x045E=>0x040E, 0x044F=>0x042F, + 0x03BA=>0x039A, 0x0155=>0x0154, 0x0069=>0x0049, 0x0073=>0x0053, 0x1E1F=>0x1E1E, + 0x0135=>0x0134, 0x0447=>0x0427, 0x03C0=>0x03A0, 0x0438=>0x0418, 0x00F3=>0x00D3, + 0x0440=>0x0420, 0x0454=>0x0404, 0x0435=>0x0415, 0x0449=>0x0429, 0x014B=>0x014A, + 0x0431=>0x0411, 0x0459=>0x0409, 0x1E03=>0x1E02, 0x00F6=>0x00D6, 0x00F9=>0x00D9, + 0x006E=>0x004E, 0x0451=>0x0401, 0x03C4=>0x03A4, 0x0443=>0x0423, 0x015D=>0x015C, + 0x0453=>0x0403, 0x03C8=>0x03A8, 0x0159=>0x0158, 0x0067=>0x0047, 0x00E4=>0x00C4, + 0x03AC=>0x0386, 0x03AE=>0x0389, 0x0167=>0x0166, 0x03BE=>0x039E, 0x0165=>0x0164, + 0x0117=>0x0116, 0x0109=>0x0108, 0x0076=>0x0056, 0x00FE=>0x00DE, 0x0157=>0x0156, + 0x00FA=>0x00DA, 0x1E61=>0x1E60, 0x1E83=>0x1E82, 0x00E2=>0x00C2, 0x0119=>0x0118, + 0x0146=>0x0145, 0x0070=>0x0050, 0x0151=>0x0150, 0x044E=>0x042E, 0x0129=>0x0128, + 0x03C7=>0x03A7, 0x013E=>0x013D, 0x0442=>0x0422, 0x007A=>0x005A, 0x0448=>0x0428, + 0x03C1=>0x03A1, 0x1E81=>0x1E80, 0x016D=>0x016C, 0x00F5=>0x00D5, 0x0075=>0x0055, + 0x0177=>0x0176, 0x00FC=>0x00DC, 0x1E57=>0x1E56, 0x03C3=>0x03A3, 0x043A=>0x041A, + 0x006D=>0x004D, 0x016B=>0x016A, 0x0171=>0x0170, 0x0444=>0x0424, 0x00EC=>0x00CC, + 0x0169=>0x0168, 0x03BF=>0x039F, 0x006B=>0x004B, 0x00F2=>0x00D2, 0x00E0=>0x00C0, + 0x0434=>0x0414, 0x03C9=>0x03A9, 0x1E6B=>0x1E6A, 0x00E3=>0x00C3, 0x044D=>0x042D, + 0x0436=>0x0416, 0x01A1=>0x01A0, 0x010D=>0x010C, 0x011D=>0x011C, 0x00F0=>0x00D0, + 0x013C=>0x013B, 0x045F=>0x040F, 0x045A=>0x040A, 0x00E8=>0x00C8, 0x03C5=>0x03A5, + 0x0066=>0x0046, 0x00FD=>0x00DD, 0x0063=>0x0043, 0x021B=>0x021A, 0x00EA=>0x00CA, + 0x03B9=>0x0399, 0x017A=>0x0179, 0x00EF=>0x00CF, 0x01B0=>0x01AF, 0x0065=>0x0045, + 0x03BB=>0x039B, 0x03B8=>0x0398, 0x03BC=>0x039C, 0x045C=>0x040C, 0x043F=>0x041F, + 0x044C=>0x042C, 0x00FE=>0x00DE, 0x00F0=>0x00D0, 0x1EF3=>0x1EF2, 0x0068=>0x0048, + 0x00EB=>0x00CB, 0x0111=>0x0110, 0x0433=>0x0413, 0x012F=>0x012E, 0x00E6=>0x00C6, + 0x0078=>0x0058, 0x0161=>0x0160, 0x016F=>0x016E, 0x03B1=>0x0391, 0x0457=>0x0407, + 0x0173=>0x0172, 0x00FF=>0x0178, 0x006F=>0x004F, 0x043B=>0x041B, 0x03B5=>0x0395, + 0x0445=>0x0425, 0x0121=>0x0120, 0x017E=>0x017D, 0x017C=>0x017B, 0x03B6=>0x0396, + 0x03B2=>0x0392, 0x03AD=>0x0388, 0x1E85=>0x1E84, 0x0175=>0x0174, 0x0071=>0x0051, + 0x0437=>0x0417, 0x1E0B=>0x1E0A, 0x0148=>0x0147, 0x0105=>0x0104, 0x0458=>0x0408, + 0x014D=>0x014C, 0x00ED=>0x00CD, 0x0079=>0x0059, 0x010B=>0x010A, 0x03CE=>0x038F, + 0x0072=>0x0052, 0x0430=>0x0410, 0x0455=>0x0405, 0x0452=>0x0402, 0x0127=>0x0126, + 0x0137=>0x0136, 0x012B=>0x012A, 0x03AF=>0x038A, 0x044B=>0x042B, 0x006C=>0x004C, + 0x03B7=>0x0397, 0x0125=>0x0124, 0x0219=>0x0218, 0x00FB=>0x00DB, 0x011F=>0x011E, + 0x043E=>0x041E, 0x1E41=>0x1E40, 0x03BD=>0x039D, 0x0107=>0x0106, 0x03CB=>0x03AB, + 0x0446=>0x0426, 0x00FE=>0x00DE, 0x00E7=>0x00C7, 0x03CA=>0x03AA, 0x0441=>0x0421, + 0x0432=>0x0412, 0x010F=>0x010E, 0x00F8=>0x00D8, 0x0077=>0x0057, 0x011B=>0x011A, + 0x0074=>0x0054, 0x006A=>0x004A, 0x045B=>0x040B, 0x0456=>0x0406, 0x0103=>0x0102, + 0x03BB=>0x039B, 0x00F1=>0x00D1, 0x043D=>0x041D, 0x03CC=>0x038C, 0x00E9=>0x00C9, + 0x00F0=>0x00D0, 0x0457=>0x0407, 0x0123=>0x0122); + } + + $uni = utf8_to_unicode($string); + + if (!$uni) + return false; + + $cnt = count($uni); + + for ($i=0; $i < $cnt; $i++) + if(isset($UTF8_LOWER_TO_UPPER[$uni[$i]])) + $uni[$i] = $UTF8_LOWER_TO_UPPER[$uni[$i]]; + + return utf8_from_unicode($uni); +} diff --git a/include/utf8/native/index.html b/include/utf8/native/index.html new file mode 100644 index 0000000..89337b2 --- /dev/null +++ b/include/utf8/native/index.html @@ -0,0 +1 @@ +.. diff --git a/include/utf8/ord.php b/include/utf8/ord.php new file mode 100644 index 0000000..a333f96 --- /dev/null +++ b/include/utf8/ord.php @@ -0,0 +1,78 @@ += 0 && $ord0 <= 127) + return $ord0; + + if (!isset($chr{1})) + { + trigger_error('Short sequence - at least 2 bytes expected, only 1 seen'); + return false; + } + + $ord1 = ord($chr{1}); + if ($ord0 >= 192 && $ord0 <= 223) + return ($ord0 - 192) * 64 + ($ord1 - 128); + + if (!isset($chr{2})) + { + trigger_error('Short sequence - at least 3 bytes expected, only 2 seen'); + return false; + } + + $ord2 = ord($chr{2}); + if ($ord0 >= 224 && $ord0 <= 239) + return ($ord0-224)*4096 + ($ord1-128)*64 + ($ord2-128); + + if (!isset($chr{3})) + { + trigger_error('Short sequence - at least 4 bytes expected, only 3 seen'); + return false; + } + + $ord3 = ord($chr{3}); + if ($ord0>=240 && $ord0<=247) + return ($ord0-240)*262144 + ($ord1-128)*4096 + ($ord2-128)*64 + ($ord3-128); + + if (!isset($chr{4})) + { + trigger_error('Short sequence - at least 5 bytes expected, only 4 seen'); + return false; + } + + $ord4 = ord($chr{4}); + if ($ord0>=248 && $ord0<=251) + return ($ord0-248)*16777216 + ($ord1-128)*262144 + ($ord2-128)*4096 + ($ord3-128)*64 + ($ord4-128); + + if (!isset($chr{5})) + { + trigger_error('Short sequence - at least 6 bytes expected, only 5 seen'); + return false; + } + + if ($ord0>=252 && $ord0<=253) + return ($ord0-252) * 1073741824 + ($ord1-128)*16777216 + ($ord2-128)*262144 + ($ord3-128)*4096 + ($ord4-128)*64 + (ord($c{5})-128); + + if ($ord0 >= 254 && $ord0 <= 255) + { + trigger_error('Invalid UTF-8 with surrogate ordinal '.$ord0); + return false; + } +} diff --git a/include/utf8/str_ireplace.php b/include/utf8/str_ireplace.php new file mode 100644 index 0000000..7257b0a --- /dev/null +++ b/include/utf8/str_ireplace.php @@ -0,0 +1,72 @@ + +* @param string $input +* @param int $length +* @param string $padStr +* @param int $type ( same constants as str_pad ) +* @return string +* @see http://www.php.net/str_pad +* @see utf8_substr +* @package utf8 +* @subpackage strings +*/ +function utf8_str_pad($input, $length, $padStr=' ', $type=STR_PAD_RIGHT) +{ + $inputLen = utf8_strlen($input); + if ($length <= $inputLen) + return $input; + + $padStrLen = utf8_strlen($padStr); + $padLen = $length - $inputLen; + + if ($type == STR_PAD_RIGHT) + { + $repeatTimes = ceil($padLen / $padStrLen); + return utf8_substr($input.str_repeat($padStr, $repeatTimes), 0, $length); + } + + if ($type == STR_PAD_LEFT) + { + $repeatTimes = ceil($padLen / $padStrLen); + return utf8_substr(str_repeat($padStr, $repeatTimes), 0, floor($padLen)).$input; + } + + if ($type == STR_PAD_BOTH) + { + $padLen /= 2; + $padAmountLeft = floor($padLen); + $padAmountRight = ceil($padLen); + $repeatTimesLeft = ceil($padAmountLeft / $padStrLen); + $repeatTimesRight = ceil($padAmountRight / $padStrLen); + + $paddingLeft = utf8_substr(str_repeat($padStr, $repeatTimesLeft), 0, $padAmountLeft); + $paddingRight = utf8_substr(str_repeat($padStr, $repeatTimesRight), 0, $padAmountLeft); + + return $paddingLeft.$input.$paddingRight; + } + + trigger_error('utf8_str_pad: Unknown padding type ('.$type.')', E_USER_ERROR); +} diff --git a/include/utf8/str_split.php b/include/utf8/str_split.php new file mode 100644 index 0000000..15bc215 --- /dev/null +++ b/include/utf8/str_split.php @@ -0,0 +1,33 @@ + +* @see http://www.php.net/ltrim +* @see http://dev.splitbrain.org/view/darcs/dokuwiki/inc/utf8.php +* @return string +* @package utf8 +* @subpackage strings +*/ +function utf8_ltrim( $str, $charlist=false) +{ + if($charlist === false) + return ltrim($str); + + // Quote charlist for use in a characterclass + $charlist = preg_replace('!([\\\\\\-\\]\\[/^])!', '\\\${1}', $charlist); + + return preg_replace('/^['.$charlist.']+/u', '', $str); +} + +/** +* UTF-8 aware replacement for rtrim() +* Note: you only need to use this if you are supplying the charlist +* optional arg and it contains UTF-8 characters. Otherwise rtrim will +* work normally on a UTF-8 string +* @author Andreas Gohr +* @see http://www.php.net/rtrim +* @see http://dev.splitbrain.org/view/darcs/dokuwiki/inc/utf8.php +* @return string +* @package utf8 +* @subpackage strings +*/ +function utf8_rtrim($str, $charlist=false) +{ + if($charlist === false) + return rtrim($str); + + // Quote charlist for use in a characterclass + $charlist = preg_replace('!([\\\\\\-\\]\\[/^])!', '\\\${1}', $charlist); + + return preg_replace('/['.$charlist.']+$/u', '', $str); +} + +//--------------------------------------------------------------- +/** +* UTF-8 aware replacement for trim() +* Note: you only need to use this if you are supplying the charlist +* optional arg and it contains UTF-8 characters. Otherwise trim will +* work normally on a UTF-8 string +* @author Andreas Gohr +* @see http://www.php.net/trim +* @see http://dev.splitbrain.org/view/darcs/dokuwiki/inc/utf8.php +* @return string +* @package utf8 +* @subpackage strings +*/ +function utf8_trim( $str, $charlist=false) +{ + if($charlist === false) + return trim($str); + + return utf8_ltrim(utf8_rtrim($str, $charlist), $charlist); +} diff --git a/include/utf8/ucfirst.php b/include/utf8/ucfirst.php new file mode 100644 index 0000000..efee55d --- /dev/null +++ b/include/utf8/ucfirst.php @@ -0,0 +1,35 @@ + +* if ( utf8_is_ascii($someString) ) { +* // It's just ASCII - use the native PHP version +* $someString = strtolower($someString); +* } else { +* $someString = utf8_strtolower($someString); +* } +* +* +* @param string +* @return boolean TRUE if it's all ASCII +* @package utf8 +* @subpackage ascii +* @see utf8_is_ascii_ctrl +*/ +function utf8_is_ascii($str) +{ + // Search for any bytes which are outside the ASCII range... + return (preg_match('/(?:[^\x00-\x7F])/', $str) !== 1); +} + +/** +* Tests whether a string contains only 7bit ASCII bytes with device +* control codes omitted. The device control codes can be found on the +* second table here: http://www.w3schools.com/tags/ref_ascii.asp +* +* @param string +* @return boolean TRUE if it's all ASCII without device control codes +* @package utf8 +* @subpackage ascii +* @see utf8_is_ascii +*/ +function utf8_is_ascii_ctrl($str) +{ + // Search for any bytes which are outside the ASCII range, or are device control codes + if (strlen($str) > 0) + return (preg_match('/[^\x09\x0A\x0D\x20-\x7E]/', $str) !== 1); + + return false; +} + +/** +* Strip out all non-7bit ASCII bytes +* If you need to transmit a string to system which you know can only +* support 7bit ASCII, you could use this function. +* @param string +* @return string with non ASCII bytes removed +* @package utf8 +* @subpackage ascii +* @see utf8_strip_non_ascii_ctrl +*/ +function utf8_strip_non_ascii($str) +{ + ob_start(); + + while (preg_match('/^([\x00-\x7F]+)|([^\x00-\x7F]+)/S', $str, $matches)) + { + if (!isset($matches[2])) + echo $matches[0]; + + $str = substr($str, strlen($matches[0])); + } + + $result = ob_get_contents(); + ob_end_clean(); + + return $result; +} + +/** +* Strip out device control codes in the ASCII range +* which are not permitted in XML. Note that this leaves +* multi-byte characters untouched - it only removes device +* control codes +* @see http://hsivonen.iki.fi/producing-xml/#controlchar +* @param string +* @return string control codes removed +*/ +function utf8_strip_ascii_ctrl($str) +{ + ob_start(); + + while (preg_match('/^([^\x00-\x08\x0B\x0C\x0E-\x1F\x7F]+)|([\x00-\x08\x0B\x0C\x0E-\x1F\x7F]+)/S', $str, $matches)) + { + if (!isset($matches[2])) + echo $matches[0]; + + $str = substr($str, strlen($matches[0])); + } + + $result = ob_get_contents(); + ob_end_clean(); + + return $result; +} + +/** +* Strip out all non 7bit ASCII bytes and ASCII device control codes. +* For a list of ASCII device control codes see the 2nd table here: +* http://www.w3schools.com/tags/ref_ascii.asp +* +* @param string +* @return boolean TRUE if it's all ASCII +* @package utf8 +* @subpackage ascii +*/ +function utf8_strip_non_ascii_ctrl($str) +{ + ob_start(); + + while (preg_match( '/^([\x09\x0A\x0D\x20-\x7E]+)|([^\x09\x0A\x0D\x20-\x7E]+)/S', $str, $matches)) + { + if (!isset($matches[2])) + echo $matches[0]; + + $str = substr($str, strlen($matches[0])); + } + + $result = ob_get_contents(); + ob_end_clean(); + + return $result; +} + +/** +* Replace accented UTF-8 characters by unaccented ASCII-7 "equivalents". +* The purpose of this function is to replace characters commonly found in Latin +* alphabets with something more or less equivalent from the ASCII range. This can +* be useful for converting a UTF-8 to something ready for a filename, for example. +* Following the use of this function, you would probably also pass the string +* through utf8_strip_non_ascii to clean out any other non-ASCII chars +* Use the optional parameter to just deaccent lower ($case = -1) or upper ($case = 1) +* letters. Default is to deaccent both cases ($case = 0) +* +* For a more complete implementation of transliteration, see the utf8_to_ascii package +* available from the phputf8 project downloads: +* http://prdownloads.sourceforge.net/phputf8 +* +* @param string UTF-8 string +* @param int (optional) -1 lowercase only, +1 uppercase only, 1 both cases +* @param string UTF-8 with accented characters replaced by ASCII chars +* @return string accented chars replaced with ascii equivalents +* @author Andreas Gohr +* @package utf8 +* @subpackage ascii +*/ +function utf8_accents_to_ascii($str, $case=0) +{ + static $UTF8_LOWER_ACCENTS = null; + static $UTF8_UPPER_ACCENTS = null; + + if($case <= 0) + { + + if (is_null($UTF8_LOWER_ACCENTS)) + { + $UTF8_LOWER_ACCENTS = array( + 'à' => 'a', 'ô' => 'o', 'ď' => 'd', 'ḟ' => 'f', 'ë' => 'e', 'š' => 's', 'ơ' => 'o', + 'ß' => 'ss', 'ă' => 'a', 'ř' => 'r', 'ț' => 't', 'ň' => 'n', 'ā' => 'a', 'ķ' => 'k', + 'ŝ' => 's', 'ỳ' => 'y', 'ņ' => 'n', 'ĺ' => 'l', 'ħ' => 'h', 'ṗ' => 'p', 'ó' => 'o', + 'ú' => 'u', 'ě' => 'e', 'é' => 'e', 'ç' => 'c', 'ẁ' => 'w', 'ċ' => 'c', 'õ' => 'o', + 'ṡ' => 's', 'ø' => 'o', 'ģ' => 'g', 'ŧ' => 't', 'ș' => 's', 'ė' => 'e', 'ĉ' => 'c', + 'ś' => 's', 'î' => 'i', 'ű' => 'u', 'ć' => 'c', 'ę' => 'e', 'ŵ' => 'w', 'ṫ' => 't', + 'ū' => 'u', 'č' => 'c', 'ö' => 'oe', 'è' => 'e', 'ŷ' => 'y', 'ą' => 'a', 'ł' => 'l', + 'ų' => 'u', 'ů' => 'u', 'ş' => 's', 'ğ' => 'g', 'ļ' => 'l', 'ƒ' => 'f', 'ž' => 'z', + 'ẃ' => 'w', 'ḃ' => 'b', 'å' => 'a', 'ì' => 'i', 'ï' => 'i', 'ḋ' => 'd', 'ť' => 't', + 'ŗ' => 'r', 'ä' => 'ae', 'í' => 'i', 'ŕ' => 'r', 'ê' => 'e', 'ü' => 'ue', 'ò' => 'o', + 'ē' => 'e', 'ñ' => 'n', 'ń' => 'n', 'ĥ' => 'h', 'ĝ' => 'g', 'đ' => 'd', 'ĵ' => 'j', + 'ÿ' => 'y', 'ũ' => 'u', 'ŭ' => 'u', 'ư' => 'u', 'ţ' => 't', 'ý' => 'y', 'ő' => 'o', + 'â' => 'a', 'ľ' => 'l', 'ẅ' => 'w', 'ż' => 'z', 'ī' => 'i', 'ã' => 'a', 'ġ' => 'g', + 'ṁ' => 'm', 'ō' => 'o', 'ĩ' => 'i', 'ù' => 'u', 'į' => 'i', 'ź' => 'z', 'á' => 'a', + 'û' => 'u', 'þ' => 'th', 'ð' => 'dh', 'æ' => 'ae', 'µ' => 'u', 'ĕ' => 'e', + ); + } + + $str = str_replace(array_keys($UTF8_LOWER_ACCENTS), array_values($UTF8_LOWER_ACCENTS), $str); + } + + if($case >= 0) + { + if (is_null($UTF8_UPPER_ACCENTS)) + { + $UTF8_UPPER_ACCENTS = array( + 'À' => 'A', 'Ô' => 'O', 'Ď' => 'D', 'Ḟ' => 'F', 'Ë' => 'E', 'Š' => 'S', 'Ơ' => 'O', + 'Ă' => 'A', 'Ř' => 'R', 'Ț' => 'T', 'Ň' => 'N', 'Ā' => 'A', 'Ķ' => 'K', + 'Ŝ' => 'S', 'Ỳ' => 'Y', 'Ņ' => 'N', 'Ĺ' => 'L', 'Ħ' => 'H', 'Ṗ' => 'P', 'Ó' => 'O', + 'Ú' => 'U', 'Ě' => 'E', 'É' => 'E', 'Ç' => 'C', 'Ẁ' => 'W', 'Ċ' => 'C', 'Õ' => 'O', + 'Ṡ' => 'S', 'Ø' => 'O', 'Ģ' => 'G', 'Ŧ' => 'T', 'Ș' => 'S', 'Ė' => 'E', 'Ĉ' => 'C', + 'Ś' => 'S', 'Î' => 'I', 'Ű' => 'U', 'Ć' => 'C', 'Ę' => 'E', 'Ŵ' => 'W', 'Ṫ' => 'T', + 'Ū' => 'U', 'Č' => 'C', 'Ö' => 'Oe', 'È' => 'E', 'Ŷ' => 'Y', 'Ą' => 'A', 'Ł' => 'L', + 'Ų' => 'U', 'Ů' => 'U', 'Ş' => 'S', 'Ğ' => 'G', 'Ļ' => 'L', 'Ƒ' => 'F', 'Ž' => 'Z', + 'Ẃ' => 'W', 'Ḃ' => 'B', 'Å' => 'A', 'Ì' => 'I', 'Ï' => 'I', 'Ḋ' => 'D', 'Ť' => 'T', + 'Ŗ' => 'R', 'Ä' => 'Ae', 'Í' => 'I', 'Ŕ' => 'R', 'Ê' => 'E', 'Ü' => 'Ue', 'Ò' => 'O', + 'Ē' => 'E', 'Ñ' => 'N', 'Ń' => 'N', 'Ĥ' => 'H', 'Ĝ' => 'G', 'Đ' => 'D', 'Ĵ' => 'J', + 'Ÿ' => 'Y', 'Ũ' => 'U', 'Ŭ' => 'U', 'Ư' => 'U', 'Ţ' => 'T', 'Ý' => 'Y', 'Ő' => 'O', + 'Â' => 'A', 'Ľ' => 'L', 'Ẅ' => 'W', 'Ż' => 'Z', 'Ī' => 'I', 'Ã' => 'A', 'Ġ' => 'G', + 'Ṁ' => 'M', 'Ō' => 'O', 'Ĩ' => 'I', 'Ù' => 'U', 'Į' => 'I', 'Ź' => 'Z', 'Á' => 'A', + 'Û' => 'U', 'Þ' => 'Th', 'Ð' => 'Dh', 'Æ' => 'Ae', 'Ĕ' => 'E', + ); + } + + $str = str_replace(array_keys($UTF8_UPPER_ACCENTS), array_values($UTF8_UPPER_ACCENTS), $str); + } + + return $str; +} diff --git a/include/utf8/utils/bad.php b/include/utf8/utils/bad.php new file mode 100644 index 0000000..2704294 --- /dev/null +++ b/include/utf8/utils/bad.php @@ -0,0 +1,430 @@ + 0) + return $badList; + + return false; +} + +/** +* Strips out any bad bytes from a UTF-8 string and returns the rest +* PCRE Pattern to locate bad bytes in a UTF-8 string +* Comes from W3 FAQ: Multilingual Forms +* Note: modified to include full ASCII range including control chars +* @see http://www.w3.org/International/questions/qa-forms-utf-8 +* @param string +* @return string +* @package utf8 +* @subpackage bad +*/ +function utf8_bad_strip($original) +{ + return utf8_bad_replace($original, ''); +} + +/** +* Replace bad bytes with an alternative character - ASCII character +* recommended is replacement char +* PCRE Pattern to locate bad bytes in a UTF-8 string +* Comes from W3 FAQ: Multilingual Forms +* Note: modified to include full ASCII range including control chars +* @see http://www.w3.org/International/questions/qa-forms-utf-8 +* @param string to search +* @param string to replace bad bytes with (defaults to '?') - use ASCII +* @return string +* @package utf8 +* @subpackage bad +*/ +function utf8_bad_replace($original, $replace = '?') { + $result = ''; + + $strlen = strlen($original); + for ($i = 0; $i < $strlen;) { + $char = $original[$i++]; + $byte = ord($char); + + if ($byte < 0x80) $bytes = 0; // 1-bytes (00000000 - 01111111) + else if ($byte < 0xC0) { // 1-bytes (10000000 - 10111111) + $result .= $replace; + continue; + } + else if ($byte < 0xE0) $bytes = 1; // 2-bytes (11000000 - 11011111) + else if ($byte < 0xF0) $bytes = 2; // 3-bytes (11100000 - 11101111) + else if ($byte < 0xF8) $bytes = 3; // 4-bytes (11110000 - 11110111) + else if ($byte < 0xFC) $bytes = 4; // 5-bytes (11111000 - 11111011) + else if ($byte < 0xFE) $bytes = 5; // 6-bytes (11111100 - 11111101) + else { // Otherwise it's something invalid + $result .= $replace; + continue; + } + + // Check our input actually has enough data + if ($i + $bytes > $strlen) { + $result .= $replace; + continue; + } + + // If we've got this far then we have a multiple-byte character + for ($j = 0; $j < $bytes; $j++) { + $byte = $original[$i + $j]; + + $char .= $byte; + $byte = ord($byte); + + // Every following byte must be 10000000 - 10111111 + if ($byte < 0x80 || $byte > 0xBF) { + $result .= $replace; + continue 2; + } + } + + $i += $bytes; + $result .= $char; + } + + return $result; +} + +/** +* Return code from utf8_bad_identify() when a five octet sequence is detected. +* Note: 5 octets sequences are valid UTF-8 but are not supported by Unicode so +* do not represent a useful character +* @see utf8_bad_identify +* @package utf8 +* @subpackage bad +*/ +define('UTF8_BAD_5OCTET', 1); + +/** +* Return code from utf8_bad_identify() when a six octet sequence is detected. +* Note: 6 octets sequences are valid UTF-8 but are not supported by Unicode so +* do not represent a useful character +* @see utf8_bad_identify +* @package utf8 +* @subpackage bad +*/ +define('UTF8_BAD_6OCTET', 2); + +/** +* Return code from utf8_bad_identify(). +* Invalid octet for use as start of multi-byte UTF-8 sequence +* @see utf8_bad_identify +* @package utf8 +* @subpackage bad +*/ +define('UTF8_BAD_SEQID', 3); + +/** +* Return code from utf8_bad_identify(). +* From Unicode 3.1, non-shortest form is illegal +* @see utf8_bad_identify +* @package utf8 +* @subpackage bad +*/ +define('UTF8_BAD_NONSHORT', 4); + +/** +* Return code from utf8_bad_identify(). +* From Unicode 3.2, surrogate characters are illegal +* @see utf8_bad_identify +* @package utf8 +* @subpackage bad +*/ +define('UTF8_BAD_SURROGATE', 5); + +/** +* Return code from utf8_bad_identify(). +* Codepoints outside the Unicode range are illegal +* @see utf8_bad_identify +* @package utf8 +* @subpackage bad +*/ +define('UTF8_BAD_UNIOUTRANGE', 6); + +/** +* Return code from utf8_bad_identify(). +* Incomplete multi-octet sequence +* Note: this is kind of a "catch-all" +* @see utf8_bad_identify +* @package utf8 +* @subpackage bad +*/ +define('UTF8_BAD_SEQINCOMPLETE', 7); + +/** +* Reports on the type of bad byte found in a UTF-8 string. Returns a +* status code on the first bad byte found +* @author +* @param string UTF-8 encoded string +* @return mixed integer constant describing problem or FALSE if valid UTF-8 +* @see utf8_bad_explain +* @see http://hsivonen.iki.fi/php-utf8/ +* @package utf8 +* @subpackage bad +*/ +function utf8_bad_identify($str, &$i) +{ + $mState = 0; // Cached expected number of octets after the current octet + // until the beginning of the next UTF8 character sequence + $mUcs4 = 0; // Cached Unicode character + $mBytes = 1; // Cached expected number of octets in the current sequence + + $len = strlen($str); + + for($i=0; $i < $len; $i++) + { + $in = ord($str{$i}); + + if ( $mState == 0) + { + // When mState is zero we expect either a US-ASCII character or a multi-octet sequence. + if (0 == (0x80 & ($in))) + { + // US-ASCII, pass straight through. + $mBytes = 1; + } + else if (0xC0 == (0xE0 & ($in))) + { + // First octet of 2 octet sequence + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x1F) << 6; + $mState = 1; + $mBytes = 2; + } + else if (0xE0 == (0xF0 & ($in))) + { + // First octet of 3 octet sequence + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x0F) << 12; + $mState = 2; + $mBytes = 3; + } + else if (0xF0 == (0xF8 & ($in))) + { + // First octet of 4 octet sequence + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x07) << 18; + $mState = 3; + $mBytes = 4; + } + else if (0xF8 == (0xFC & ($in))) + { + /* First octet of 5 octet sequence. + * + * This is illegal because the encoded codepoint must be either + * (a) not the shortest form or + * (b) outside the Unicode range of 0-0x10FFFF. + */ + return UTF8_BAD_5OCTET; + } + else if (0xFC == (0xFE & ($in))) + { + // First octet of 6 octet sequence, see comments for 5 octet sequence. + return UTF8_BAD_6OCTET; + } + else + { + // Current octet is neither in the US-ASCII range nor a legal first + // octet of a multi-octet sequence. + return UTF8_BAD_SEQID; + } + } + else + { + // When mState is non-zero, we expect a continuation of the multi-octet sequence + if (0x80 == (0xC0 & ($in))) + { + // Legal continuation. + $shift = ($mState - 1) * 6; + $tmp = $in; + $tmp = ($tmp & 0x0000003F) << $shift; + $mUcs4 |= $tmp; + + /** + * End of the multi-octet sequence. mUcs4 now contains the final + * Unicode codepoint to be output + */ + if (0 == --$mState) + { + // From Unicode 3.1, non-shortest form is illegal + if (((2 == $mBytes) && ($mUcs4 < 0x0080)) || + ((3 == $mBytes) && ($mUcs4 < 0x0800)) || + ((4 == $mBytes) && ($mUcs4 < 0x10000)) ) + return UTF8_BAD_NONSHORT; + else if (($mUcs4 & 0xFFFFF800) == 0xD800) // From Unicode 3.2, surrogate characters are illegal + return UTF8_BAD_SURROGATE; + else if ($mUcs4 > 0x10FFFF) // Codepoints outside the Unicode range are illegal + return UTF8_BAD_UNIOUTRANGE; + + // Initialize UTF8 cache + $mState = 0; + $mUcs4 = 0; + $mBytes = 1; + } + + } + else + { + // ((0xC0 & (*in) != 0x80) && (mState != 0)) + // Incomplete multi-octet sequence. + $i--; + return UTF8_BAD_SEQINCOMPLETE; + } + } + } + + // Incomplete multi-octet sequence + if ($mState != 0) + { + $i--; + return UTF8_BAD_SEQINCOMPLETE; + } + + // No bad octets found + $i = null; + return false; +} + +/** +* Takes a return code from utf8_bad_identify() are returns a message +* (in English) explaining what the problem is. +* @param int return code from utf8_bad_identify +* @return mixed string message or FALSE if return code unknown +* @see utf8_bad_identify +* @package utf8 +* @subpackage bad +*/ +function utf8_bad_explain($code) +{ + switch ($code) + { + case UTF8_BAD_5OCTET: + return 'Five octet sequences are valid UTF-8 but are not supported by Unicode'; + break; + + case UTF8_BAD_6OCTET: + return 'Six octet sequences are valid UTF-8 but are not supported by Unicode'; + break; + + case UTF8_BAD_SEQID: + return 'Invalid octet for use as start of multi-byte UTF-8 sequence'; + break; + + case UTF8_BAD_NONSHORT: + return 'From Unicode 3.1, non-shortest form is illegal'; + break; + + case UTF8_BAD_SURROGATE: + return 'From Unicode 3.2, surrogate characters are illegal'; + break; + + case UTF8_BAD_UNIOUTRANGE: + return 'Codepoints outside the Unicode range are illegal'; + break; + + case UTF8_BAD_SEQINCOMPLETE: + return 'Incomplete multi-octet sequence'; + break; + } + + trigger_error('Unknown error code: '.$code, E_USER_WARNING); + + return false; +} diff --git a/include/utf8/utils/index.html b/include/utf8/utils/index.html new file mode 100644 index 0000000..89337b2 --- /dev/null +++ b/include/utf8/utils/index.html @@ -0,0 +1 @@ +.. diff --git a/include/utf8/utils/patterns.php b/include/utf8/utils/patterns.php new file mode 100644 index 0000000..5a85a4f --- /dev/null +++ b/include/utf8/utils/patterns.php @@ -0,0 +1,67 @@ + +* @param string string to locate index in +* @param int (n times) +* @return mixed - int if only one input int, array if more +* @return boolean TRUE if it's all ASCII +* @package utf8 +* @subpackage position +*/ +function utf8_byte_position() +{ + $args = func_get_args(); + $str =& array_shift($args); + + if (!is_string($str)) + return false; + + $result = array(); + $prev = array(0, 0); // Trivial byte index, character offset pair + $i = utf8_locate_next_chr($str, 300); // Use a short piece of str to estimate bytes per character. $i (& $j) -> byte indexes into $str + $c = strlen(utf8_decode(substr($str, 0, $i))); // $c -> character offset into $str + + // Deal with arguments from lowest to highest + sort($args); + + foreach ($args as $offset) + { + // Sanity checks FIXME + + // 0 is an easy check + if ($offset == 0) + { + $result[] = 0; continue; + } + + // Ensure no endless looping + $safety_valve = 50; + + do + { + if (($c - $prev[1]) == 0) + { + // Hack: gone past end of string + $error = 0; + $i = strlen($str); + break; + } + + $j = $i + (int)(($offset-$c) * ($i - $prev[0]) / ($c - $prev[1])); + $j = utf8_locate_next_chr($str, $j); // Correct to utf8 character boundary + $prev = array($i,$c); // Save the index, offset for use next iteration + + if ($j > $i) + $c += strlen(utf8_decode(substr($str, $i, $j-$i))); // Determine new character offset + else + $c -= strlen(utf8_decode(substr($str, $j, $i-$j))); // Ditto + + $error = abs($c-$offset); + $i = $j; // Ready for next time around + } + while (($error > 7) && --$safety_valve); // From 7 it is faster to iterate over the string + + if ($error && $error <= 7) + { + if ($c < $offset) + { + // Move up + while ($error--) + $i = utf8_locate_next_chr($str, ++$i); + } + else + { + // Move down + while ($error--) + $i = utf8_locate_current_chr($str, --$i); + } + + // Ready for next arg + $c = $offset; + } + + $result[] = $i; + } + + if (count($result) == 1) + return $result[0]; + + return $result; +} + +/** +* Given a string and any byte index, returns the byte index +* of the start of the current UTF-8 character, relative to supplied +* position. If the current character begins at the same place as the +* supplied byte index, that byte index will be returned. Otherwise +* this function will step backwards, looking for the index where +* curent UTF-8 character begins +* @author Chris Smith +* @param string +* @param int byte index in the string +* @return int byte index of start of next UTF-8 character +* @package utf8 +* @subpackage position +*/ +function utf8_locate_current_chr( &$str, $idx ) +{ + if ($idx <= 0) + return 0; + + $limit = strlen($str); + if ($idx >= $limit) + return $limit; + + // Binary value for any byte after the first in a multi-byte UTF-8 character + // will be like 10xxxxxx so & 0xC0 can be used to detect this kind + // of byte - assuming well formed UTF-8 + while ($idx && ((ord($str[$idx]) & 0xC0) == 0x80)) + $idx--; + + return $idx; +} + +/** +* Given a string and any byte index, returns the byte index +* of the start of the next UTF-8 character, relative to supplied +* position. If the next character begins at the same place as the +* supplied byte index, that byte index will be returned. +* @author Chris Smith +* @param string +* @param int byte index in the string +* @return int byte index of start of next UTF-8 character +* @package utf8 +* @subpackage position +*/ +function utf8_locate_next_chr(&$str, $idx) +{ + if ($idx <= 0) + return 0; + + $limit = strlen($str); + if ($idx >= $limit) + return $limit; + + // Binary value for any byte after the first in a multi-byte UTF-8 character + // will be like 10xxxxxx so & 0xC0 can be used to detect this kind + // of byte - assuming well formed UTF-8 + while (($idx < $limit) && ((ord($str[$idx]) & 0xC0) == 0x80)) + $idx++; + + return $idx; +} diff --git a/include/utf8/utils/specials.php b/include/utf8/utils/specials.php new file mode 100644 index 0000000..69219dc --- /dev/null +++ b/include/utf8/utils/specials.php @@ -0,0 +1,131 @@ + +* @param string $string The UTF8 string to strip of special chars +* @param string (optional) $repl Replace special with this string +* @return string with common non-alphanumeric characters removed +* @see utf8_specials_pattern +*/ +function utf8_strip_specials($string, $repl='') +{ + return preg_replace(utf8_specials_pattern(), $repl, $string); +} diff --git a/include/utf8/utils/unicode.php b/include/utf8/utils/unicode.php new file mode 100644 index 0000000..f0e86cb --- /dev/null +++ b/include/utf8/utils/unicode.php @@ -0,0 +1,241 @@ + 0xFFFF. Occurrances of the BOM are ignored. Surrogates +* are not allowed. +* Returns false if the input string isn't a valid UTF-8 octet sequence +* and raises a PHP error at level E_USER_WARNING +* Note: this function has been modified slightly in this library to +* trigger errors on encountering bad bytes +* @author +* @param string UTF-8 encoded string +* @return mixed array of unicode code points or FALSE if UTF-8 invalid +* @see utf8_from_unicode +* @see http://hsivonen.iki.fi/php-utf8/ +* @package utf8 +* @subpackage unicode +*/ +function utf8_to_unicode($str) +{ + $mState = 0; // Cached expected number of octets after the current octet + // until the beginning of the next UTF8 character sequence + $mUcs4 = 0; // Cached Unicode character + $mBytes = 1; // Cached expected number of octets in the current sequence + + $out = array(); + $len = strlen($str); + + for($i = 0; $i < $len; $i++) + { + $in = ord($str[$i]); + + if ($mState == 0) + { + // When mState is zero we expect either a US-ASCII character or a multi-octet sequence. + if (0 == (0x80 & ($in))) + { + // US-ASCII, pass straight through. + $out[] = $in; + $mBytes = 1; + } + else if (0xC0 == (0xE0 & ($in))) + { + // First octet of 2 octet sequence + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x1F) << 6; + $mState = 1; + $mBytes = 2; + } + else if (0xE0 == (0xF0 & ($in))) + { + // First octet of 3 octet sequence + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x0F) << 12; + $mState = 2; + $mBytes = 3; + } + else if (0xF0 == (0xF8 & ($in))) + { + // First octet of 4 octet sequence + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x07) << 18; + $mState = 3; + $mBytes = 4; + } + else if (0xF8 == (0xFC & ($in))) + { + /* First octet of 5 octet sequence. + * + * This is illegal because the encoded codepoint must be either + * (a) not the shortest form or + * (b) outside the Unicode range of 0-0x10FFFF. + * Rather than trying to resynchronize, we will carry on until the end + * of the sequence and let the later error handling code catch it. + */ + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x03) << 24; + $mState = 4; + $mBytes = 5; + } + else if (0xFC == (0xFE & ($in))) + { + // First octet of 6 octet sequence, see comments for 5 octet sequence. + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 1) << 30; + $mState = 5; + $mBytes = 6; + } + else + { + // Current octet is neither in the US-ASCII range nor a legal first octet of a multi-octet sequence + trigger_error('utf8_to_unicode: Illegal sequence identifier in UTF-8 at byte '.$i, E_USER_WARNING); + return false; + } + } + else + { + // When mState is non-zero, we expect a continuation of the multi-octet sequence + if (0x80 == (0xC0 & ($in))) + { + // Legal continuation. + $shift = ($mState - 1) * 6; + $tmp = $in; + $tmp = ($tmp & 0x0000003F) << $shift; + $mUcs4 |= $tmp; + + /** + * End of the multi-octet sequence. mUcs4 now contains the final + * Unicode codepoint to be output + */ + if (0 == --$mState) + { + /* + * Check for illegal sequences and codepoints. + */ + // From Unicode 3.1, non-shortest form is illegal + if (((2 == $mBytes) && ($mUcs4 < 0x0080)) || ((3 == $mBytes) && ($mUcs4 < 0x0800)) || + ((4 == $mBytes) && ($mUcs4 < 0x10000)) || (4 < $mBytes) || + // From Unicode 3.2, surrogate characters are illegal + (($mUcs4 & 0xFFFFF800) == 0xD800) || + // Codepoints outside the Unicode range are illegal + ($mUcs4 > 0x10FFFF)) + { + trigger_error('utf8_to_unicode: Illegal sequence or codepoint in UTF-8 at byte '.$i, E_USER_WARNING); + return false; + } + + // BOM is legal but we don't want to output it + if (0xFEFF != $mUcs4) + $out[] = $mUcs4; + + // Initialize UTF8 cache + $mState = 0; + $mUcs4 = 0; + $mBytes = 1; + } + + } + else + { + /* ((0xC0 & (*in) != 0x80) && (mState != 0)) + Incomplete multi-octet sequence. */ + trigger_error('utf8_to_unicode: Incomplete multi-octet sequence in UTF-8 at byte '.$i, E_USER_WARNING); + return false; + } + } + } + + return $out; +} + +/** +* Takes an array of ints representing the Unicode characters and returns +* a UTF-8 string. Astral planes are supported ie. the ints in the +* input can be > 0xFFFF. Occurrances of the BOM are ignored. Surrogates +* are not allowed. +* Returns false if the input array contains ints that represent +* surrogates or are outside the Unicode range +* and raises a PHP error at level E_USER_WARNING +* Note: this function has been modified slightly in this library to use +* output buffering to concatenate the UTF-8 string (faster) as well as +* reference the array by it's keys +* @param array of unicode code points representing a string +* @return mixed UTF-8 string or FALSE if array contains invalid code points +* @author +* @see utf8_to_unicode +* @see http://hsivonen.iki.fi/php-utf8/ +* @package utf8 +* @subpackage unicode +*/ +function utf8_from_unicode($arr) +{ + ob_start(); + + foreach (array_keys($arr) as $k) + { + if ( ($arr[$k] >= 0) && ($arr[$k] <= 0x007f) ) // ASCII range (including control chars) + { + echo chr($arr[$k]); + } + else if ($arr[$k] <= 0x07ff) //2 byte sequence + { + echo chr(0xc0 | ($arr[$k] >> 6)); + echo chr(0x80 | ($arr[$k] & 0x003f)); + } + else if($arr[$k] == 0xFEFF) // Byte order mark (skip) + { + // Nop -- zap the BOM + } + else if ($arr[$k] >= 0xD800 && $arr[$k] <= 0xDFFF) // Test for illegal surrogates + { + // Found a surrogate + trigger_error('utf8_from_unicode: Illegal surrogate at index: '.$k.', value: '.$arr[$k], E_USER_WARNING); + + return false; + } + else if ($arr[$k] <= 0xffff) // 3 byte sequence + { + echo chr(0xe0 | ($arr[$k] >> 12)); + echo chr(0x80 | (($arr[$k] >> 6) & 0x003f)); + echo chr(0x80 | ($arr[$k] & 0x003f)); + } + else if ($arr[$k] <= 0x10ffff) // 4 byte sequence + { + echo chr(0xf0 | ($arr[$k] >> 18)); + echo chr(0x80 | (($arr[$k] >> 12) & 0x3f)); + echo chr(0x80 | (($arr[$k] >> 6) & 0x3f)); + echo chr(0x80 | ($arr[$k] & 0x3f)); + } + else + { + trigger_error('utf8_from_unicode: Codepoint out of Unicode range at index: '.$k.', value: '.$arr[$k], E_USER_WARNING); + + // Out of range + return false; + } + } + + $result = ob_get_contents(); + ob_end_clean(); + + return $result; +} diff --git a/include/utf8/utils/validation.php b/include/utf8/utils/validation.php new file mode 100644 index 0000000..90dce8e --- /dev/null +++ b/include/utf8/utils/validation.php @@ -0,0 +1,186 @@ + +* @param string UTF-8 encoded string +* @return boolean true if valid +* @see http://hsivonen.iki.fi/php-utf8/ +* @see utf8_compliant +* @package utf8 +* @subpackage validation +*/ +function utf8_is_valid($str) +{ + $mState = 0; // Cached expected number of octets after the current octet + // until the beginning of the next UTF8 character sequence + $mUcs4 = 0; // Cached Unicode character + $mBytes = 1; // Cached expected number of octets in the current sequence + + $len = strlen($str); + + for($i = 0; $i < $len; $i++) + { + $in = ord($str{$i}); + + if ( $mState == 0) + { + // When mState is zero we expect either a US-ASCII character or a multi-octet sequence. + if (0 == (0x80 & ($in))) + { + $mBytes = 1; // US-ASCII, pass straight through + } + else if (0xC0 == (0xE0 & ($in))) + { + // First octet of 2 octet sequence + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x1F) << 6; + $mState = 1; + $mBytes = 2; + } + else if (0xE0 == (0xF0 & ($in))) + { + // First octet of 3 octet sequence + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x0F) << 12; + $mState = 2; + $mBytes = 3; + } + else if (0xF0 == (0xF8 & ($in))) + { + // First octet of 4 octet sequence + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x07) << 18; + $mState = 3; + $mBytes = 4; + } + else if (0xF8 == (0xFC & ($in))) + { + /* First octet of 5 octet sequence. + * + * This is illegal because the encoded codepoint must be either + * (a) not the shortest form or + * (b) outside the Unicode range of 0-0x10FFFF. + * Rather than trying to resynchronize, we will carry on until the end + * of the sequence and let the later error handling code catch it. + */ + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 0x03) << 24; + $mState = 4; + $mBytes = 5; + } + else if (0xFC == (0xFE & ($in))) + { + // First octet of 6 octet sequence, see comments for 5 octet sequence. + $mUcs4 = ($in); + $mUcs4 = ($mUcs4 & 1) << 30; + $mState = 5; + $mBytes = 6; + } + else + { + // Current octet is neither in the US-ASCII range nor a legal first octet of a multi-octet sequence. + return false; + } + } + else + { + // When mState is non-zero, we expect a continuation of the multi-octet sequence + if (0x80 == (0xC0 & ($in))) + { + // Legal continuation. + $shift = ($mState - 1) * 6; + $tmp = $in; + $tmp = ($tmp & 0x0000003F) << $shift; + $mUcs4 |= $tmp; + + /** + * End of the multi-octet sequence. mUcs4 now contains the final + * Unicode codepoint to be output + */ + if (0 == --$mState) + { + /* + * Check for illegal sequences and codepoints. + */ + // From Unicode 3.1, non-shortest form is illegal + if (((2 == $mBytes) && ($mUcs4 < 0x0080)) || ((3 == $mBytes) && ($mUcs4 < 0x0800)) || + ((4 == $mBytes) && ($mUcs4 < 0x10000)) || (4 < $mBytes) || + // From Unicode 3.2, surrogate characters are illegal + (($mUcs4 & 0xFFFFF800) == 0xD800) || + // Codepoints outside the Unicode range are illegal + ($mUcs4 > 0x10FFFF)) + { + return FALSE; + } + + // Initialize UTF8 cache + $mState = 0; + $mUcs4 = 0; + $mBytes = 1; + } + } + else + { + /** + *((0xC0 & (*in) != 0x80) && (mState != 0)) + * Incomplete multi-octet sequence. + */ + + return false; + } + } + } + + return true; +} + +/** +* Tests whether a string complies as UTF-8. This will be much +* faster than utf8_is_valid, but will pass five and six octet +* UTF-8 sequences, which are not supported by Unicode and +* so cannot be displayed correctly in a browser. In other words +* it is not as strict as utf8_is_valid but it's faster. If you use +* is to validate user input, you place yourself at the risk that +* attackers will be able to inject 5 and 6 byte sequences (which +* may or may not be a significant risk, depending on what you are +* are doing) +* Note: Does not pass five and six octet UTF-8 sequences anymore in +* in the unit tests. +* @see utf8_is_valid +* @see http://www.php.net/manual/en/reference.pcre.pattern.modifiers.php#54805 +* @param string UTF-8 string to check +* @return boolean TRUE if string is valid UTF-8 +* @package utf8 +* @subpackage validation +*/ +function utf8_compliant($str) +{ + if (strlen($str) == 0) + return true; + + // If even just the first character can be matched, when the /u + // modifier is used, then it's valid UTF-8. If the UTF-8 is somehow + // invalid, nothing at all will match, even if the string contains + // some valid sequences + return (preg_match('/^.{1}/us', $str, $ar) == 1); +} -- cgit v1.2.3-70-g09d2