Source for file String.php
Documentation is available at String.php
* Copyright (c) 2006 - 2010 PHPExcel * This library is free software; you can redistribute it and/or * modify it under the terms of the GNU Lesser General Public * License as published by the Free Software Foundation; either * version 2.1 of the License, or (at your option) any later version. * This library is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU * Lesser General Public License for more details. * You should have received a copy of the GNU Lesser General Public * License along with this library; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA * @package PHPExcel_Shared * @copyright Copyright (c) 2006 - 2010 PHPExcel (http://www.codeplex.com/PHPExcel) * @license http://www.gnu.org/licenses/old-licenses/lgpl-2.1.txt LGPL * @version 1.7.3c, 2010-06-01 * @package PHPExcel_Shared * @copyright Copyright (c) 2006 - 2010 PHPExcel (http://www.codeplex.com/PHPExcel) const STRING_REGEXP_FRACTION = '(-?)(\d+)\s+(\d+\/\d+)'; * Control characters array private static $_controlCharacters = array(); private static $_SYLKCharacters = array(); private static $_decimalSeparator; private static $_thousandsSeparator; * Is mbstring extension avalable? private static $_isMbstringEnabled; * Is iconv extension avalable? private static $_isIconvEnabled; * Build control characters array private static function _buildControlCharacters() { for ($i = 0; $i <= 31; ++ $i) { if ($i != 9 && $i != 10 && $i != 13) { self::$_controlCharacters[$find] = $replace; * Build SYLK characters array private static function _buildSYLKCharacters() self::$_SYLKCharacters = array( "\x1B(0" => '€', // 128 in CP1252 "\x1B(2" => '‚', // 130 in CP1252 "\x1B(3" => 'ƒ', // 131 in CP1252 "\x1B(4" => '„', // 132 in CP1252 "\x1B(5" => '…', // 133 in CP1252 "\x1B(6" => '†', // 134 in CP1252 "\x1B(7" => '‡', // 135 in CP1252 "\x1B(8" => 'ˆ', // 136 in CP1252 "\x1B(9" => '‰', // 137 in CP1252 "\x1B(:" => 'Š', // 138 in CP1252 "\x1B(;" => '‹', // 139 in CP1252 "\x1BNj" => 'Œ', // 140 in CP1252 "\x1B(>" => 'Ž', // 142 in CP1252 "\x1B)1" => '‘', // 145 in CP1252 "\x1B)2" => '’', // 146 in CP1252 "\x1B)3" => '“', // 147 in CP1252 "\x1B)4" => '”', // 148 in CP1252 "\x1B)5" => '•', // 149 in CP1252 "\x1B)6" => '–', // 150 in CP1252 "\x1B)7" => '—', // 151 in CP1252 "\x1B)8" => '˜', // 152 in CP1252 "\x1B)9" => '™', // 153 in CP1252 "\x1B):" => 'š', // 154 in CP1252 "\x1B);" => '›', // 155 in CP1252 "\x1BNz" => 'œ', // 156 in CP1252 "\x1B)>" => 'ž', // 158 in CP1252 "\x1B)?" => 'Ÿ', // 159 in CP1252 "\x1B*0" => ' ', // 160 in CP1252 "\x1BN!" => '¡', // 161 in CP1252 "\x1BN\"" => '¢', // 162 in CP1252 "\x1BN#" => '£', // 163 in CP1252 "\x1BN(" => '¤', // 164 in CP1252 "\x1BN%" => '¥', // 165 in CP1252 "\x1B*6" => '¦', // 166 in CP1252 "\x1BN'" => '§', // 167 in CP1252 "\x1BNH " => '¨', // 168 in CP1252 "\x1BNS" => '©', // 169 in CP1252 "\x1BNc" => 'ª', // 170 in CP1252 "\x1BN+" => '«', // 171 in CP1252 "\x1B*<" => '¬', // 172 in CP1252 "\x1B*=" => '', // 173 in CP1252 "\x1BNR" => '®', // 174 in CP1252 "\x1B*?" => '¯', // 175 in CP1252 "\x1BN0" => '°', // 176 in CP1252 "\x1BN1" => '±', // 177 in CP1252 "\x1BN2" => '²', // 178 in CP1252 "\x1BN3" => '³', // 179 in CP1252 "\x1BNB " => '´', // 180 in CP1252 "\x1BN5" => 'µ', // 181 in CP1252 "\x1BN6" => '¶', // 182 in CP1252 "\x1BN7" => '·', // 183 in CP1252 "\x1B+8" => '¸', // 184 in CP1252 "\x1BNQ" => '¹', // 185 in CP1252 "\x1BNk" => 'º', // 186 in CP1252 "\x1BN;" => '»', // 187 in CP1252 "\x1BN<" => '¼', // 188 in CP1252 "\x1BN=" => '½', // 189 in CP1252 "\x1BN>" => '¾', // 190 in CP1252 "\x1BN?" => '¿', // 191 in CP1252 "\x1BNAA" => 'À', // 192 in CP1252 "\x1BNBA" => 'Á', // 193 in CP1252 "\x1BNCA" => 'Â', // 194 in CP1252 "\x1BNDA" => 'Ã', // 195 in CP1252 "\x1BNHA" => 'Ä', // 196 in CP1252 "\x1BNJA" => 'Å', // 197 in CP1252 "\x1BNa" => 'Æ', // 198 in CP1252 "\x1BNKC" => 'Ç', // 199 in CP1252 "\x1BNAE" => 'È', // 200 in CP1252 "\x1BNBE" => 'É', // 201 in CP1252 "\x1BNCE" => 'Ê', // 202 in CP1252 "\x1BNHE" => 'Ë', // 203 in CP1252 "\x1BNAI" => 'Ì', // 204 in CP1252 "\x1BNBI" => 'Í', // 205 in CP1252 "\x1BNCI" => 'Î', // 206 in CP1252 "\x1BNHI" => 'Ï', // 207 in CP1252 "\x1BNb" => 'Ð', // 208 in CP1252 "\x1BNDN" => 'Ñ', // 209 in CP1252 "\x1BNAO" => 'Ò', // 210 in CP1252 "\x1BNBO" => 'Ó', // 211 in CP1252 "\x1BNCO" => 'Ô', // 212 in CP1252 "\x1BNDO" => 'Õ', // 213 in CP1252 "\x1BNHO" => 'Ö', // 214 in CP1252 "\x1B-7" => '×', // 215 in CP1252 "\x1BNi" => 'Ø', // 216 in CP1252 "\x1BNAU" => 'Ù', // 217 in CP1252 "\x1BNBU" => 'Ú', // 218 in CP1252 "\x1BNCU" => 'Û', // 219 in CP1252 "\x1BNHU" => 'Ü', // 220 in CP1252 "\x1B-=" => 'Ý', // 221 in CP1252 "\x1BNl" => 'Þ', // 222 in CP1252 "\x1BN{" => 'ß', // 223 in CP1252 "\x1BNAa" => 'à', // 224 in CP1252 "\x1BNBa" => 'á', // 225 in CP1252 "\x1BNCa" => 'â', // 226 in CP1252 "\x1BNDa" => 'ã', // 227 in CP1252 "\x1BNHa" => 'ä', // 228 in CP1252 "\x1BNJa" => 'å', // 229 in CP1252 "\x1BNq" => 'æ', // 230 in CP1252 "\x1BNKc" => 'ç', // 231 in CP1252 "\x1BNAe" => 'è', // 232 in CP1252 "\x1BNBe" => 'é', // 233 in CP1252 "\x1BNCe" => 'ê', // 234 in CP1252 "\x1BNHe" => 'ë', // 235 in CP1252 "\x1BNAi" => 'ì', // 236 in CP1252 "\x1BNBi" => 'í', // 237 in CP1252 "\x1BNCi" => 'î', // 238 in CP1252 "\x1BNHi" => 'ï', // 239 in CP1252 "\x1BNs" => 'ð', // 240 in CP1252 "\x1BNDn" => 'ñ', // 241 in CP1252 "\x1BNAo" => 'ò', // 242 in CP1252 "\x1BNBo" => 'ó', // 243 in CP1252 "\x1BNCo" => 'ô', // 244 in CP1252 "\x1BNDo" => 'õ', // 245 in CP1252 "\x1BNHo" => 'ö', // 246 in CP1252 "\x1B/7" => '÷', // 247 in CP1252 "\x1BNy" => 'ø', // 248 in CP1252 "\x1BNAu" => 'ù', // 249 in CP1252 "\x1BNBu" => 'ú', // 250 in CP1252 "\x1BNCu" => 'û', // 251 in CP1252 "\x1BNHu" => 'ü', // 252 in CP1252 "\x1B/=" => 'ý', // 253 in CP1252 "\x1BN|" => 'þ', // 254 in CP1252 "\x1BNHy" => 'ÿ', // 255 in CP1252 * Get whether mbstring extension is available if (isset (self::$_isMbstringEnabled)) { return self::$_isMbstringEnabled; self::$_isMbstringEnabled = function_exists('mb_convert_encoding') ? return self::$_isMbstringEnabled; * Get whether iconv extension is available if (isset (self::$_isIconvEnabled)) { return self::$_isIconvEnabled; // Fail if iconv doesn't exist if (!function_exists('iconv')) { self::$_isIconvEnabled = false; // Sometimes iconv is not working, and e.g. iconv('UTF-8', 'UTF-16LE', 'x') just returns false, if (!@iconv('UTF-8', 'UTF-16LE', 'x')) { self::$_isIconvEnabled = false; // Sometimes iconv_substr('A', 0, 1, 'UTF-8') just returns false in PHP 5.2.0 // we cannot use iconv in that case either (http://bugs.php.net/bug.php?id=37773) if (!@iconv('UTF-8', 'UTF-16LE', 'x')) { self::$_isIconvEnabled = false; // CUSTOM: IBM AIX iconv() does not work self::$_isIconvEnabled = false; // If we reach here no problems were detected with iconv self::$_isIconvEnabled = true; * Convert from OpenXML escaped control character to PHP control character * That's correct, control characters are stored directly in the shared-strings table. * We do encode characters that cannot be represented in XML using the following escape sequence: * _xHHHH_ where H represents a hexadecimal character in the character's value... * So you could end up with something like _x0008_ in a string (either in a cell value (<v>) * element or in the shared string <t> element. * @param string $value Value to unescape if(empty(self::$_controlCharacters)) { self::_buildControlCharacters(); return str_replace( array_keys(self::$_controlCharacters), array_values(self::$_controlCharacters), $value ); * Convert from PHP control character to OpenXML escaped control character * That's correct, control characters are stored directly in the shared-strings table. * We do encode characters that cannot be represented in XML using the following escape sequence: * _xHHHH_ where H represents a hexadecimal character in the character's value... * So you could end up with something like _x0008_ in a string (either in a cell value (<v>) * element or in the shared string <t> element. * @param string $value Value to escape if(empty(self::$_controlCharacters)) { self::_buildControlCharacters(); * Try to sanitize UTF8, stripping invalid byte sequences. Not perfect. Does not surrogate characters. if (self::getIsIconvEnabled()) { $value = @iconv('UTF-8', 'UTF-8', $value); if (self::getIsMbstringEnabled()) { * Check if a string contains UTF8 data public static function IsUTF8($value = '') { * Formats a numeric value as a string for output in various output writers forcing * point as decimal separator in case locale is other than English. * Converts a UTF-8 string into BIFF8 Unicode string data (8-bit string length) * Writes the string using uncompressed notation, no rich text, no Asian phonetics * If mbstring extension is not available, ASCII is assumed, and compressed notation is used * although this will give wrong results for non-ASCII strings * see OpenOffice.org's Documentation of the Microsoft Excel File Format, sect. 2.5.3 * @param string $value UTF-8 encoded string $ln = self::CountCharacters($value, 'UTF-8'); $opt = (self::getIsIconvEnabled() || self::getIsMbstringEnabled()) ? $chars = self::ConvertEncoding($value, 'UTF-16LE', 'UTF-8'); $data = pack('CC', $ln, $opt) . $chars; * Converts a UTF-8 string into BIFF8 Unicode string data (16-bit string length) * Writes the string using uncompressed notation, no rich text, no Asian phonetics * If mbstring extension is not available, ASCII is assumed, and compressed notation is used * although this will give wrong results for non-ASCII strings * see OpenOffice.org's Documentation of the Microsoft Excel File Format, sect. 2.5.3 * @param string $value UTF-8 encoded string $ln = self::CountCharacters($value, 'UTF-8'); $opt = (self::getIsIconvEnabled() || self::getIsMbstringEnabled()) ? $chars = self::ConvertEncoding($value, 'UTF-16LE', 'UTF-8'); $data = pack('vC', $ln, $opt) . $chars; * Convert string from one encoding to another. First try iconv, then mbstring, or no convertion * @param string $to Encoding to convert to, e.g. 'UTF-8' * @param string $from Encoding to convert from, e.g. 'UTF-16LE' if (self::getIsIconvEnabled()) { $value = iconv($from, $to, $value); if (self::getIsMbstringEnabled()) { return self::utf16_decode($value, false); }else if($from == 'UTF-16BE'){ return self::utf16_decode($value); * Decode UTF-16 encoded strings. * Can handle both BOM'ed data and un-BOM'ed data. * Assumes Big-Endian byte order if no BOM is available. * This function was taken from http://php.net/manual/en/function.utf8-decode.php * and $bom_be parameter added. * @param string $str UTF-16 encoded data to decode. * @return string UTF-8 / ISO encoded data. * @version 0.2 / 2010-05-13 * @author Rasmus Andersson {@link http://rasmusandersson.se/} if( strlen($str) < 2 ) return $str; if( $c0 == 0xfe && $c1 == 0xff ) { $str = substr($str,2); } elseif( $c0 == 0xff && $c1 == 0xfe ) { $str = substr($str,2); $bom_be = false; } for($i= 0;$i< $len;$i+= 2) { if( $bom_be ) { $val = ord($str{$i}) << 4; $val += ord($str{$i+ 1}); } else { $val = ord($str{$i+ 1}) << 4; $val += ord($str{$i}); } $newstr .= ($val == 0x228) ? "\n" : chr($val); * Get character count. First try mbstring, then iconv, finally strlen * @param string $enc Encoding * @return int Character count if (self::getIsIconvEnabled()) { if (self::getIsMbstringEnabled()) { * Get a substring of a UTF-8 encoded string * @param string $pValue UTF-8 encoded string * @param int $start Start offset * @param int $length Maximum number of characters in substring public static function Substring($pValue = '', $pStart = 0, $pLength = 0) if (self::getIsIconvEnabled()) { $string = iconv_substr($pValue, $pStart, $pLength, 'UTF-8'); if (self::getIsMbstringEnabled()) { $string = mb_substr($pValue, $pStart, $pLength, 'UTF-8'); $string = substr($pValue, $pStart, $pLength); * Identify whether a string contains a fractional numeric value, * and convert it to a numeric if it is * @param string &$operand string value to test if (preg_match('/^'. self::STRING_REGEXP_FRACTION. '$/i', $operand, $match)) { $sign = ($match[1] == '-') ? '-' : '+'; $fractionFormula = '='. $sign. $match[2]. $sign. $match[3]; } // function convertToNumberIfFraction() * Get the decimal separator. If it has not yet been set explicitly, try to obtain number * formatting information from locale. if (!isset (self::$_decimalSeparator)) { $localeconv = localeconv(); self::$_decimalSeparator = $localeconv['decimal_point'] != '' ? $localeconv['decimal_point'] : $localeconv['mon_decimal_point']; if (self::$_decimalSeparator == '') self::$_decimalSeparator = '.'; return self::$_decimalSeparator; * Set the decimal separator. Only used by PHPExcel_Style_NumberFormat::toFormattedString() * to format output by PHPExcel_Writer_HTML and PHPExcel_Writer_PDF * @param string $pValue Character for decimal separator self::$_decimalSeparator = $pValue; * Get the thousands separator. If it has not yet been set explicitly, try to obtain number * formatting information from locale. if (!isset (self::$_thousandsSeparator)) { $localeconv = localeconv(); self::$_thousandsSeparator = $localeconv['thousands_sep'] != '' ? $localeconv['thousands_sep'] : $localeconv['mon_thousands_sep']; return self::$_thousandsSeparator; * Set the thousands separator. Only used by PHPExcel_Style_NumberFormat::toFormattedString() * to format output by PHPExcel_Writer_HTML and PHPExcel_Writer_PDF * @param string $pValue Character for thousands separator self::$_thousandsSeparator = $pValue; * Convert SYLK encoded string to UTF-8 * @return string UTF-8 encoded string // If there is no escape character in the string there is nothing to do if (strpos($pValue, '') === false) { if(empty(self::$_SYLKCharacters)) { self::_buildSYLKCharacters(); foreach (self::$_SYLKCharacters as $k => $v) { $pValue = str_replace($k, $v, $pValue);
|
