2005-04-08 Sven de Marothy <sven@physto.se>

        * gnu/java/nio/charset/Provider.java: Add new charsets.
        * gnu/java/nio/charset/UTF_16.java: Default to using BOM.
        * gnu/java/nio/charset/UTF_16Decoder.java: Minor fixes.
        * gnu/java/nio/charset/UTF_16Encoder.java,
        Use NIO's built-in byte-ordering instead.
        * gnu/java/nio/charset/UTF_8.java,
        (Decoder): Correct values of maximum chars per byte.
        (decodeLoop): Handle 4-byte surrogates.
        * gnu/java/nio/charset/ByteCharset.java
        * gnu/java/nio/charset/Cp424.java
        * gnu/java/nio/charset/Cp437.java
        * gnu/java/nio/charset/Cp737.java
        * gnu/java/nio/charset/Cp775.java
        * gnu/java/nio/charset/Cp850.java
        * gnu/java/nio/charset/Cp852.java
        * gnu/java/nio/charset/Cp855.java
        * gnu/java/nio/charset/Cp857.java
        * gnu/java/nio/charset/Cp860.java
        * gnu/java/nio/charset/Cp861.java
        * gnu/java/nio/charset/Cp862.java
        * gnu/java/nio/charset/Cp863.java
        * gnu/java/nio/charset/Cp864.java
        * gnu/java/nio/charset/Cp865.java
        * gnu/java/nio/charset/Cp866.java
        * gnu/java/nio/charset/Cp869.java
        * gnu/java/nio/charset/Cp874.java
        * gnu/java/nio/charset/EncodingHelper.java
        * gnu/java/nio/charset/ISO_8859_13.java
        * gnu/java/nio/charset/ISO_8859_15.java
        * gnu/java/nio/charset/ISO_8859_2.java
        * gnu/java/nio/charset/ISO_8859_3.java
        * gnu/java/nio/charset/ISO_8859_4.java
        * gnu/java/nio/charset/ISO_8859_5.java
        * gnu/java/nio/charset/ISO_8859_6.java
        * gnu/java/nio/charset/ISO_8859_7.java
        * gnu/java/nio/charset/ISO_8859_8.java
        * gnu/java/nio/charset/ISO_8859_9.java
        * gnu/java/nio/charset/KOI_8.java
        * gnu/java/nio/charset/MS874.java
        * gnu/java/nio/charset/MacCentralEurope.java
        * gnu/java/nio/charset/MacCroatian.java
        * gnu/java/nio/charset/MacCyrillic.java
        * gnu/java/nio/charset/MacDingbat.java
        * gnu/java/nio/charset/MacGreek.java
        * gnu/java/nio/charset/MacIceland.java
        * gnu/java/nio/charset/MacRoman.java
        * gnu/java/nio/charset/MacRomania.java
        * gnu/java/nio/charset/MacSymbol.java
        * gnu/java/nio/charset/MacThai.java
        * gnu/java/nio/charset/MacTurkish.java
        * gnu/java/nio/charset/Windows1250.java
        * gnu/java/nio/charset/Windows1251.java
        * gnu/java/nio/charset/Windows1252.java
        * gnu/java/nio/charset/Windows1253.java
        * gnu/java/nio/charset/Windows1254.java
        * gnu/java/nio/charset/Windows1255.java
        * gnu/java/nio/charset/Windows1256.java
        * gnu/java/nio/charset/Windows1257.java
        * gnu/java/nio/charset/Windows1258.java
        New files.

1 files changed, 83 insertions, 1 deletions

diff --git a/gnu/java/nio/charset/Provider.java b/gnu/java/nio/charset/Provider.java
index 1a5606813..781c10ec9 100644
--- a/gnu/java/nio/charset/Provider.java
+++ b/gnu/java/nio/charset/Provider.java
@@ -77,8 +77,14 @@ public final class Provider extends CharsetProvider
    */
   private final HashMap charsets;
 
+  /**
+   * We don't load all available charsets at the start
+   */
+  private boolean extendedLoaded;
+
   private Provider ()
   {
+    extendedLoaded = false;
     canonicalNames = new HashMap ();
     charsets = new HashMap ();
 
@@ -99,10 +105,80 @@ public final class Provider extends CharsetProvider
 
     // UTF-16
     addCharset (new UTF_16 ());
+
+    // Windows-1250 aka cp-1250 (East European)
+    addCharset (new Windows1250 ());
+
+    // Windows-1251 (Cyrillic)
+    addCharset (new Windows1251 ());
+
+    // Windows-1252 aka cp-1252 (Latin-1)
+    addCharset (new Windows1252 ());
+
+    // Windows-1253 (Greek)
+    addCharset (new Windows1253 ());
+
+    // Windows-1254 (Turkish)
+    addCharset (new Windows1254 ());
+
+    // Windows-1257 (Baltic)
+    addCharset (new Windows1257 ());
+
+    // ISO-8859-2 aka ISO-LATIN-2
+    addCharset (new ISO_8859_2 ());
+
+    // ISO-8859-4 aka ISO-LATIN-4
+    addCharset (new ISO_8859_4 ());
+
+    // ISO-8859-5 (Cyrillic)
+    addCharset (new ISO_8859_5 ());
+
+    // ISO-8859-7 (Greek)
+    addCharset (new ISO_8859_7 ());
+
+    // ISO-8859-9 aka ISO-LATIN-5
+    addCharset (new ISO_8859_9 ());
+
+    // ISO-8859-13 aka ISO-LATIN-7
+    addCharset (new ISO_8859_13 ());
+
+    // ISO-8859-15 aka ISO-LATIN-9
+    addCharset (new ISO_8859_15 ());
+
+    // KOI8 (Cyrillic)
+    addCharset (new KOI_8 ());
+  }
+
+ /**
+  * Load non-mandatory charsets.
+  */
+  private void loadExtended ()
+  {
+    if(extendedLoaded)
+      return;
+
+    addCharset (new ISO_8859_3 ());    // ISO-8859-3 aka ISO-LATIN-3
+    addCharset (new ISO_8859_6 ());    // ISO-8859-6 (Arabic)
+    addCharset (new ISO_8859_8 ());    // ISO-8859-8 (Hebrew)
+
+    // Some more codepages
+    addCharset (new Cp855()); // IBM Cyrillic
+    addCharset (new Cp857()); // IBM Turkish
+    addCharset (new Cp860()); // MSDOS Portugese
+    addCharset (new Cp861()); // MSDOS Icelandic
+    addCharset (new Cp862()); // PC Hebrew
+    addCharset (new Cp863()); // MSDOS Can. French
+    addCharset (new Cp864()); // PC Arabic
+    addCharset (new Cp865()); // MSDOS Nordic
+    addCharset (new Cp866()); // MSDOS Russian
+    addCharset (new Cp869()); // IBM modern Greek
+    addCharset (new Cp874()); // IBM Thai
+    extendedLoaded = true;
   }
 
   public Iterator charsets ()
   {
+    loadExtended();
     return Collections.unmodifiableCollection (charsets.values ())
                       .iterator ();
   }
@@ -119,7 +195,13 @@ public final class Provider extends CharsetProvider
    */
   public Charset charsetForName (String charsetName)
   {
-    return (Charset) charsets.get(canonicalNames.get(charsetName.toLowerCase()));
+    Charset cs = (Charset) charsets.get(canonicalNames.get(charsetName.toLowerCase()));
+    if(cs == null && !extendedLoaded)
+     {
+       loadExtended();
+       cs = (Charset) charsets.get(canonicalNames.get(charsetName.toLowerCase()));
+     }
+    return cs;
   }
 
   /**