From 1fd977808b077b015a79a92cad77f3c1e6894de4 Mon Sep 17 00:00:00 2001
From: gustavf <gustavf@7612ce4b-ef26-0410-bec9-ea0150e637f0>
Date: Mon, 28 Feb 2000 14:18:43 +0000
Subject: [PATCH] Added i18n.php and moved som functionality to that file.

git-svn-id: https://svn.code.sf.net/p/squirrelmail/code/trunk/squirrelmail@247 7612ce4b-ef26-0410-bec9-ea0150e637f0
---
 functions/i18n.php | 111 +++++++++++++++++++++++++++++++++++++++++++++
 functions/mime.php |  72 ++++-------------------------
 2 files changed, 120 insertions(+), 63 deletions(-)
 create mode 100644 functions/i18n.php

diff --git a/functions/i18n.php b/functions/i18n.php
new file mode 100644
index 00000000..779513f1
--- /dev/null
+++ b/functions/i18n.php
@@ -0,0 +1,111 @@
+<?
+
+/**
+ ** i18n.php
+ ** 
+ ** This file contains variuos functions that are needed to do
+ ** internationalization of SquirrelMail.
+ **
+ ** Internally iso-8859-1 is used as character set. Other characters
+ ** are encoded using Unicode entities according to HTML 4.0.
+ **/
+
+   $i18n_php = true;
+
+   // Decodes a string to the internal encoding from the given charset
+   function charset_decode ($charset, $string) {
+      // All HTML special characters are 7 bit and can be replaced first
+      $string = htmlspecialchars ($string);
+
+      $charset = strolower($charset);
+
+      if (ereg("iso-8859-(.*)", $charset, $res)) {
+         if ($res[1] == "1")
+            return charset_decode_iso_8859_1 ($string);
+         else if ($res[1] == "15")
+            return charset_decode_iso_8859_15 ($string);
+         else
+            return charset_decode_iso_8859_default ($string);
+      } else if ($charset == "ns_4551-1") {
+         return charset_decode_ns_4551_1 ($string);
+      } else 
+         return $string;
+   }
+
+   // iso-8859-1 is the same as Latin 1 and is normally used
+   // in western europe.
+   function charset_decode_iso_8859_1 ($string) {
+      // This is only debug code as long as the internal
+      // character set is iso-8859-1
+
+      // Latin small letter o with stroke
+      while (ereg("\370", $string))
+         $string = ereg_replace ("\370", "&#248;", $string);
+
+      return ($string);
+   }
+
+   // iso-8859-15 is Latin 15 and has very much the same use as Latin 1
+   // but has the Euro symbol and some characters needed for French.
+   function charset_decode_iso_8859_15 ($string) {
+      // Euro sign
+      while (ereg("\244", $replace))
+         $string = ereg_replace ("\244", "&#8364;", $string);
+      // Latin capital letter S with caron
+      while (ereg("\246", $string))
+         $string = ereg_replace ("\244", "&#352;", $string);
+      // Latin small letter s with caron
+      while (ereg("\250", $string))
+         $string = ereg_replace ("\250", "&#353;", $string);
+      // Latin capital letter Z with caron
+      while (ereg("\264", $string))
+         $string = ereg_replace ("\264", "&#381;", $string);
+      // Latin small letter z with caron
+      while (ereg("\270", $string))
+         $string = ereg_replace ("\270", "&#382;", $string);
+      // Latin capital ligature OE
+      while (ereg("\274", $string))
+         $string = ereg_replace ("\274", "&#338;", $string);
+      // Latin small ligature oe
+      while (ereg("\275", $string))
+         $string = ereg_replace ("\275", "&#339;", $string);
+      // Latin capital letter Y with diaeresis
+      while (ereg("\276", $string))
+         $string = ereg_replace ("\276", "&#376;", $string);
+
+      return ($string);
+   }
+
+   // Remove al 8 bit characters from all other ISO-8859 character sets
+   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", 
+                    "????????????????????????????????????????".
+                    "????????????????????????????????????????".
+                    "????????????????????????????????????????".
+                    "????????"));
+      
+   }
+
+   // This is the same as ISO-646-NO and is used by some
+   // Microsoft programs when sending Norwegian characters
+   function charset_decode_ns_4551_1 ($string) {
+      // These characters are:
+      // Latin capital letter AE
+      // Latin capital letter O with stroke
+      // Latin capital letter A with ring above
+      // and the same as small letters
+      return strtr ($string, "[\\]{|}", "ÆØÅæøå");
+   }
+
+?>
diff --git a/functions/mime.php b/functions/mime.php
index 5c1d39f1..e2cac359 100644
--- a/functions/mime.php
+++ b/functions/mime.php
@@ -5,6 +5,9 @@
     **/
 
 
+   if (!isset($i18n_php))
+      include "../functions/i18n.php";
+
    /** This is the first function called.  It decides if this is a multipart
        message or if it should be handled as a single entity
     **/
@@ -202,77 +205,20 @@
    // This functions decode strings that is encoded according to 
    // RFC1522 (MIME Part Two: Message Header Extensions for Non-ASCII Text).
    function decodeHeader ($string) {
-      // Recognizing only US-ASCII and ISO-8859. Other charsets should
-      // probably be recognized as well.
-      if (eregi('=\?(us-ascii|iso-8859-([0-9])+)\?(q|b)\?([^?]+)\?=', 
+      if (eregi('=\?([^?]+)\?(q|b)\?([^?]+)\?=', 
                 $string, $res)) {
-         if (ucfirst($res[3]) == "B") {
-            $replace = base64_decode($res[4]);
+         if (ucfirst($res[2]) == "B") {
+            $replace = base64_decode($res[3]);
          } else {
-            $replace = ereg_replace("_", " ", $res[4]);
+            $replace = ereg_replace("_", " ", $res[3]);
             $replace = quoted_printable_decode($replace);
          }
 
-         // All HTML characters are in the 7-bit ASCII range and can
-         // be replaced before doing anything with the 8-bi
-         // characters.
-         $replace = htmlspecialchars($replace);
-
-         if ($res[2] == 1) {
-            // This if clause is debug code. -- gustavf
-            // Latin small letter o with stroke
-            while (ereg("\370", $replace))
-               $replace = ereg_replace ("\370", "&#248;", $replace);
-         } else if ($res[2] == "15") {
-            // Euro sign
-            while (ereg("\244", $replace))
-               $replace = ereg_replace ("\244", "&#8364;", $replace);
-            // Latin capital letter S with caron
-            while (ereg("\246", $replace))
-               $replace = ereg_replace ("\244", "&#352;", $replace);
-            // Latin small letter s with caron
-            while (ereg("\250", $replace))
-               $replace = ereg_replace ("\250", "&#353;", $replace);
-            // Latin capital letter Z with caron
-            while (ereg("\264", $replace))
-               $replace = ereg_replace ("\264", "&#381;", $replace);
-            // Latin small letter z with caron
-            while (ereg("\270", $replace))
-               $replace = ereg_replace ("\270", "&#382;", $replace);
-            // Latin capital ligature OE
-            while (ereg("\274", $replace))
-               $replace = ereg_replace ("\274", "&#338;", $replace);
-            // Latin small ligature oe
-            while (ereg("\275", $replace))
-               $replace = ereg_replace ("\275", "&#339;", $replace);
-            // Latin capital letter Y with diaeresis
-            while (ereg("\276", $replace))
-               $replace = ereg_replace ("\276", "&#376;", $replace);
-         } else if ($res[2] != "") {
-            // This gets rid of all characters over 0x9F for other
-            // iso-8859 charsets.
-            $replace = strtr($replace, "\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", 
-                             "????????????????????????????????????????".
-                             "????????????????????????????????????????".
-                             "????????????????????????????????????????".
-                             "????????");
-         }
+         $replace = charset_decode ($res[1], $replace);
 
          $string = eregi_replace
-            ('=\?(us-ascii|iso-8859-([0-9])+)\?(q|b)\?([^?]+)\?=',
+            ('=\?([^?]+)\?(q|b)\?([^?]+)\?=',
              $replace, $string);
-
          // In case there should be more encoding in the string: recurse
          return (decodeHeader($string));
       } else         
-- 
2.25.1