| commit | author | age | ||
| 4e17e6 | 1 | <?php |
| T | 2 | ///////////////////////////// |
| 3 | // utf8.inc | |
| 4 | // (C)2002 Ryo Chijiiwa <Ryo@IlohaMail.org> | |
| 5 | // | |
| 6 | // Description: | |
| 7 | // UTF-8 handling functions | |
| 8 | // | |
| 9 | // This file is part of IlohaMail. IlohaMail is free software released | |
| 10 | // under the GPL license. See enclosed file COPYING for details, or | |
| 11 | // see http://www.fsf.org/copyleft/gpl.html | |
| 12 | //////////////////////////// | |
| 13 | ||
| 14 | /** | |
| 15 | * takes a string of utf-8 encoded characters and converts it to a string of unicode entities | |
| 16 | * each unicode entitiy has the form &#nnnnn; n={0..9} and can be displayed by utf-8 supporting | |
| 17 | * browsers | |
| 18 | * @param $source string encoded using utf-8 [STRING] | |
| 19 | * @return string of unicode entities [STRING] | |
| 20 | * @access public | |
| 21 | */ | |
| 22 | /** | |
| 23 | * Author: ronen at greyzone dot com | |
| 24 | * Taken from php.net comment: | |
| 25 | * http://www.php.net/manual/en/function.utf8-decode.php | |
| 26 | **/ | |
| 27 | function utf8ToUnicodeEntities ($source) { | |
| 28 | // array used to figure what number to decrement from character order value | |
| 29 | // according to number of characters used to map unicode to ascii by utf-8 | |
| 30 | $decrement[4] = 240; | |
| 31 | $decrement[3] = 224; | |
| 32 | $decrement[2] = 192; | |
| 33 | $decrement[1] = 0; | |
| 34 | ||
| 35 | // the number of bits to shift each charNum by | |
| 36 | $shift[1][0] = 0; | |
| 37 | $shift[2][0] = 6; | |
| 38 | $shift[2][1] = 0; | |
| 39 | $shift[3][0] = 12; | |
| 40 | $shift[3][1] = 6; | |
| 41 | $shift[3][2] = 0; | |
| 42 | $shift[4][0] = 18; | |
| 43 | $shift[4][1] = 12; | |
| 44 | $shift[4][2] = 6; | |
| 45 | $shift[4][3] = 0; | |
| 46 | ||
| 47 | $pos = 0; | |
| 48 | $len = strlen ($source); | |
| 49 | $encodedString = ''; | |
| 50 | while ($pos < $len) { | |
| 51 | $asciiPos = ord (substr ($source, $pos, 1)); | |
| 52 | if (($asciiPos >= 240) && ($asciiPos <= 255)) { | |
| 53 | // 4 chars representing one unicode character | |
| 54 | $thisLetter = substr ($source, $pos, 4); | |
| 55 | $pos += 4; | |
| 56 | } | |
| 57 | else if (($asciiPos >= 224) && ($asciiPos <= 239)) { | |
| 58 | // 3 chars representing one unicode character | |
| 59 | $thisLetter = substr ($source, $pos, 3); | |
| 60 | $pos += 3; | |
| 61 | } | |
| 62 | else if (($asciiPos >= 192) && ($asciiPos <= 223)) { | |
| 63 | // 2 chars representing one unicode character | |
| 64 | $thisLetter = substr ($source, $pos, 2); | |
| 65 | $pos += 2; | |
| 66 | } | |
| 67 | else { | |
| 68 | // 1 char (lower ascii) | |
| 69 | $thisLetter = substr ($source, $pos, 1); | |
| 70 | $pos += 1; | |
| 71 | } | |
| 72 | ||
| 73 | // process the string representing the letter to a unicode entity | |
| 74 | $thisLen = strlen ($thisLetter); | |
| 75 | $thisPos = 0; | |
| 76 | $decimalCode = 0; | |
| 77 | while ($thisPos < $thisLen) { | |
| 78 | $thisCharOrd = ord (substr ($thisLetter, $thisPos, 1)); | |
| 79 | if ($thisPos == 0) { | |
| 80 | $charNum = intval ($thisCharOrd - $decrement[$thisLen]); | |
| 81 | $decimalCode += ($charNum << $shift[$thisLen][$thisPos]); | |
| 82 | } | |
| 83 | else { | |
| 84 | $charNum = intval ($thisCharOrd - 128); | |
| 85 | $decimalCode += ($charNum << $shift[$thisLen][$thisPos]); | |
| 86 | } | |
| 87 | ||
| 88 | $thisPos++; | |
| 89 | } | |
| 90 | ||
| a95e0e | 91 | if ($decimalCode<128) |
| T | 92 | $encodedLetter = chr($decimalCode); |
| 93 | else if ($thisLen == 1) | |
| 4e17e6 | 94 | $encodedLetter = "&#". str_pad($decimalCode, 3, "0", STR_PAD_LEFT) . ';'; |
| T | 95 | else |
| 96 | $encodedLetter = "&#". str_pad($decimalCode, 5, "0", STR_PAD_LEFT) . ';'; | |
| 97 | ||
| 98 | $encodedString .= $encodedLetter; | |
| 99 | } | |
| 100 | ||
| 101 | return $encodedString; | |
| 102 | } | |
| 103 | ||
| 104 | ?> | |
