managing agresive decoding and ja_JP + utf-8.

[squirrelmail.git] / functions / i18n.php

<?php

/**
 * i18n.php
 *
 * Copyright (c) 1999-2003 The SquirrelMail Project Team
 * Licensed under the GNU GPL. For full terms see the file COPYING.
 *
 * This file contains variuos functions that are needed to do
 * internationalization of SquirrelMail.
 *
 * Internally the output character set is used. Other characters are
 * encoded using Unicode entities according to HTML 4.0.
 *
 * $Id$
 * @package squirrelmail
 */

/** Everything uses global.php... */
require_once(SM_PATH . 'functions/global.php');

/**
 * Converts string from given charset to charset, that can be displayed by user translation.
 *
 * Function by default returns html encoded strings, if translation uses different encoding.
 * If Japanese translation is used - function returns string converted to euc-jp
 * If iconv or recode functions are enabled and translation uses utf-8 - function returns utf-8 encoded string.
 * If $charset is not supported - function returns unconverted string.
 * 
 * sanitizing of html tags is also done by this function.
 *
 * @param string $charset
 * @param string $string Text to be decoded
 * @return string decoded string
 */
function charset_decode ($charset, $string) {
    global $languages, $squirrelmail_language, $default_charset;
    global $use_php_recode, $use_php_iconv, $agresive_decoding;

    if (isset($languages[$squirrelmail_language]['XTRA_CODE']) &&
        function_exists($languages[$squirrelmail_language]['XTRA_CODE'])) {
        $string = $languages[$squirrelmail_language]['XTRA_CODE']('decode', $string);
    }

    $charset = strtolower($charset);

    set_my_charset();

    // Variables that allow to use functions without function_exist() calls
    if (! isset($use_php_recode) || $use_php_recode=="" ) {
	     $use_php_recode=false; }
    if (! isset($use_php_iconv) || $use_php_iconv=="" ) {
         $use_php_iconv=false; }

    // Don't do conversion if charset is the same.
    if ( $charset == strtolower($default_charset) )
          return htmlspecialchars($string);

    // catch iso-8859-8-i thing
    if ( $charset == "iso-8859-8-i" )
              $charset = "iso-8859-8";

    /*
     * Recode converts html special characters automatically if you use 
     * 'charset..html' decoding. There is no documented way to put -d option 
     * into php recode function call.
     */
    if ( $use_php_recode ) {
      if ( $default_charset == "utf-8" ) {
	// other charsets can be converted to utf-8 without loss.
	// and output string is smaller
	$string = recode_string($charset . "..utf-8",$string);
	return htmlspecialchars($string);
      } else {
	$string = recode_string($charset . "..html",$string);
	// recode does not convert single quote, htmlspecialchars does.
	$string = str_replace("'", '&#039;', $string);
	return $string;
      }
    }

    // iconv functions does not have html target and can be used only with utf-8
    if ( $use_php_iconv && $default_charset=='utf-8') {
      $string = iconv($charset,$default_charset,$string);
      return htmlspecialchars($string);
    }

    // If we don't use recode and iconv, we'll do it old way.

    /* All HTML special characters are 7 bit and can be replaced first */
    
    $string = htmlspecialchars ($string);

    /* controls cpu and memory intensive decoding cycles */
    if (! isset($agresive_decoding) || $agresive_decoding=="" ) {
         $agresive_decoding=false; }

    $decode=fixcharset($charset);
    $decodefile=SM_PATH . 'functions/decode/' . $decode . '.php';
    if (file_exists($decodefile)) {
	include_once($decodefile);
	$ret = call_user_func('charset_decode_'.$decode, $string);
    } else {
	$ret = $string;
    }
    return( $ret );
}
		                                                                                                                           
/**
 * Makes charset name suitable for decoding cycles
 *
 * @param string $charset Name of charset
 * @return string $charset Adjusted name of charset
 */
function fixcharset($charset) {
    // minus removed from function names
    $charset=str_replace('-','_',$charset);
    
    // windows-125x and cp125x charsets
    $charset=str_replace('windows_','cp',$charset);

    // ibm > cp
    $charset=str_replace('ibm','cp',$charset);

    // iso-8859-8-i -> iso-8859-8
    // use same cycle until I'll find differences
    $charset=str_replace('iso_8859_8_i','iso_8859_8',$charset);

    return $charset;
}

/**
 * 8bit cleanup functions.
 *
 * Replaces all 8 bit characters from ISO-8859 character sets with '?'
 * Legacy function used for unsupported ISO-8859 charsets
 * 
 * @param string $string string that has to be cleaned
 * @return string cleaned string
 */
function charset_decode_iso_8859_default ($string) {
    return (strtr($string, "\240\241\242\243\244\245\246\247".
                    "\250\251\252\253\254\255\256\257".
                    "\260\261\262\263\264\265\266\267".
                    "\270\271\272\273\274\275\276\277".
                    "\300\301\302\303\304\305\306\307".
                    "\310\311\312\313\314\315\316\317".
                    "\320\321\322\323\324\325\326\327".
                    "\330\331\332\333\334\335\336\337".
                    "\340\341\342\343\344\345\346\347".
                    "\350\351\352\353\354\355\356\357".
                    "\360\361\362\363\364\365\366\367".
                    "\370\371\372\373\374\375\376\377",
                    "????????????????????????????????????????".
                    "????????????????????????????????????????".
                    "????????????????????????????????????????".
                    "????????"));

}

/**
 * ns_4551_1 decoding function
 *
 * This is the same as ISO-646-NO and is used by some
 * Microsoft programs when sending Norwegian characters
 * 
 * @param string $string
 * @return string 
 */
function charset_decode_ns_4551_1 ($string) {
    /*
     * These characters are:
     * Latin capital letter AE
     * Latin capital letter O with stroke
     * Latin capital letter A with ring above
     * and the same as small letters
     */