Changeset 109 for devel/www/code.php

Timestamp:

Sep 14, 2008, 9:10:49 PM (16 years ago)

Author:

george

Message:

• Opraveno: Soubor pro převod kódování znaků do a z UTF-8.

File:

• devel/www/code.php (modified) (7 diffs)

devel/www/code.php

@@ -31 +31 @@
 */
 
-$iso2_utf8 = array(
+$CharTable = array(
+  'iso2' => array(
         0x80=>"\xc2\x80",
         0x81=>"\xc2\x81",
@@ -160 +161 @@
         0xFE=>"\xc5\xa3",
         0xFF=>"\xcb\x99"
-);
-
-$win1250_utf8 = array(
+  ),
+  'win1250' => array(
         0x80=>"\xc2\x80",
         0x81=>"\xc2\x81",
-        0x82=>"\x140\x9a",
+        0x82=>"\xe2\x80\x9a",
         0x83=>"\xc2\x83",
-        0x84=>"\x140\x9e",
-        0x85=>"\x140\xa6",
-        0x86=>"\x140\xa0",
-        0x87=>"\x140\xa1",
+        0x84=>"\xe2\x80\x9e",
+        0x85=>"\xe2\x80\xa6",
+        0x86=>"\xe2\x80\xa0",
+        0x87=>"\xe2\x80\xa1",
         0x88=>"\xc2\x88",
-        0x89=>"\x140\xb0",
+        0x89=>"\xe2\x80\xb0",
         0x8a=>"\xc5\xa0",
-        0x8b=>"\x140\xb9",
+        0x8b=>"\xe2\x80\xb9",
         0x8c=>"\xc5\x9a",
         0x8d=>"\xc5\xa4",
@@ -180 +180 @@
         0x8f=>"\xc5\xb9",
         0x90=>"\xc2\x90",
-        0x91=>"\x140\x98",
-        0x92=>"\x140\x99",
-        0x93=>"\x140\x9c",
-        0x94=>"\x140\x9d",
-        0x95=>"\x140\xa2",
-        0x96=>"\x140\x93",
-        0x97=>"\x140\x94",
-        0x98=>"\xc2\x98",
-        0x99=>"\x144\xa2",
+        0x91=>"\xe2\x80\x98",
+        0x92=>"\xe2\x80\x99",
+        0x93=>"\xe2\x80\x9c",
+        0x94=>"\xe2\x80\x9d",
+        0x95=>"\xe2\x80\xa2",
+        0x96=>"\xe2\x80\x93",
+        0x97=>"\xe2\x80\x94",
+        0x98=>"\xe2\x80\x98",
+        0x99=>"\xe2\x84\xa2",
         0x9a=>"\xc5\xa1",
-        0x9b=>"\x140\xba",
+        0x9b=>"\xe2\x80\xba",
         0x9c=>"\xc5\x9b",
         0x9d=>"\xc5\xa5",
@@ -291 +291 @@
         0xfe=>"\xc5\xa3",
         0xff=>"\xcb\x99"
-);
-
-$iso1_utf8 = array(
+  ),
+  'iso1' => array(
         0xA0=>"\xc2\xa0",
         0xA1=>"\xc2\xa1",
@@ -389 +388 @@
         0xFD=>"\xc3\xbd",
         0xFE=>"\xc3\xbe"
-);
-
-$win1257_utf8 = array(
-        0x80=>"\x142\xac",
+  ),
+  'win1257' => array(
+        0x80=>"\xe2\x82\xac",
         0x81=>"\xc0\x4",
-        0x82=>"\x140\x9a",
+        0x82=>"\xe2\x80\x9a",
         0x83=>"\xc0\x4",
-        0x84=>"\x140\x9e",
-        0x85=>"\x140\xa6",
-        0x86=>"\x140\xa0",
-        0x87=>"\x140\xa1",
+        0x84=>"\xe2\x80\x9e",
+        0x85=>"\xe2\x80\xa6",
+        0x86=>"\xe2\x80\xa0",
+        0x87=>"\xe2\x80\xa1",
         0x88=>"\xc0\x4",
-        0x89=>"\x140\xb0",
+        0x89=>"\xe2\x80\xb0",
         0x8A=>"\xc0\x4",
-        0x8B=>"\x140\xb9",
+        0x8B=>"\xe2\x80\xb9",
         0x8C=>"\xc0\x4",
         0x8D=>"\xc2\xa8",
@@ -409 +407 @@
         0x8F=>"\xc2\xb8",
         0x90=>"\xc0\x4",
-        0x91=>"\x140\x98",
-        0x92=>"\x140\x99",
-        0x93=>"\x140\x9c",
-        0x94=>"\x140\x9d",
-        0x95=>"\x140\xa2",
-        0x96=>"\x140\x93",
-        0x97=>"\x140\x94",
+        0x91=>"\xe2\x80\x98",
+        0x92=>"\xe2\x80\x99",
+        0x93=>"\xe2\x80\x9c",
+        0x94=>"\xe2\x80\x9d",
+        0x95=>"\xe2\x80\xa2",
+        0x96=>"\xe2\x80\x93",
+        0x97=>"\xe2\x80\x94",
         0x98=>"\xc0\x4",
-        0x99=>"\x144\xa2",
+        0x99=>"\xe2\x84\xa2",
         0x9A=>"\xc0\x4",
-        0x9B=>"\x140\xba",
+        0x9B=>"\xe2\x80\xba",
         0x9C=>"\xc0\x4",
         0x9D=>"\xc2\xaf",
@@ -520 +518 @@
         0xFE=>"\xc5\xbe",
         0xFF=>"\xcb\x99"
+  ),
 );
 
-/*
-  function to convert to UTF-8
-  because characters numbered 0-127 are standard ASCII characters and are same in Unicode,
-  we have to recode only higher characters
-  function pass through the string and when it finds such character, it is replaced with
-  UTF-8 two byte representation
-*/
-function to_utf8($string,$charset="iso2")
+
+function ToUTF8($String, $Charset = 'iso2')
 {
-  eval("global \$".$charset."_utf8;");
-  eval("\$coding=\$".$charset."_utf8;");
-
-  for ($i = 0; $i < strlen($string); $i++) 
+  global $CharTable;
+
+  $Result = '';
+  for($I = 0; $I < strlen($String); $I++) 
   {
-     if(ord($string[$i]) > 127) 
+     if(ord($String[$I]) < 128) $Result .= $String[$I];
+     else if(ord($String[$I]) > 127)
      {
-       $string = substr($string, 0, $i).$coding[ord($string[$i])].substr($string, ++$i);
+       $Result .= $CharTable[$Charset][ord($String[$I])];
      }
   }
-  return($string);
+  return($Result);
 }
 
-/*
-  reverse function to convert from UTF-8
-  and again it pass through the string and when the two following bytes correspond to
-  two byte combination given in translation array, these two characters are replaced with
-  one character from given coding
-    it takes the key returned by array_search() and since the key is the number of specific
-    character, we can use chr()
-*/
-function from_utf8($string,$charset="iso2")
+function FromUTF8($String, $Charset = 'iso2')
 {
-  eval("global \$".$charset."_utf8;");
-  eval("\$coding=\$".$charset."_utf8;");
-
-  for($i = 0; $i < strlen($string) - 1; $i++) 
+  global $CharTable;
+
+  $Result = '';
+  $UTFPrefix = '';
+  for($I = 0; $I < strlen($String); $I++)
   {
-    if($code = array_search($string[$i].$string[($i + 1)], $coding))
-      $string = substr($string, 0, $i).chr($code).substr($string, $i + 2);
+    if(ord($String{$I}) & 0x80) // UTF control character
+    {
+      if(ord($String{$I}) & 0x40) // First
+      {
+       if($UTFPrefix != '') $Result .= chr(array_search($UTFPrefix, $CharTable[$Charset]));
+        $UTFPrefix = $String{$I};
+      }
+      else $UTFPrefix .= $String{$I}; // Next
+    } else
+    {
+      if($UTFPrefix != '') $Result .= chr(array_search($UTFPrefix, $CharTable[$Charset]));
+      $UTFPrefix = '';
+      $Result .= $String{$I};
+    }
   }
-  return $string;
+  return($Result);
 }
+
 ?>