Generator of a UTF-8 character decoder that repairs coding defects.

src/altk/common/engine/util/UTF8BenevolentDecoder.java

@@ -0,0 +1,27 @@
+package altk.common.engine.util;
+
+import java.nio.charset.Charset;
+import java.nio.charset.CharsetDecoder;
+import java.nio.charset.CodingErrorAction;
+
+/**
+ * The only method returns a UTF-8 CharsetDecoder object that repairs malformed or
+ * unmappable UTF-8 characters as it decodes an input byte stream.
+ * @author Yuk-Ming
+ *
+ */
+public class UTF8BenevolentDecoder
+{
+    /**
+     * @return a UTF-8 CharsetDecoder object that repairs malformed or
+     * unmappable UTF-8 characters as it decodes an input byte stream
+     */
+    public static CharsetDecoder getDecoder()
+    {
+        Charset utf8Charset = Charset.forName("UTF-8");
+        CharsetDecoder utf8Decoder = utf8Charset.newDecoder();
+        // Clean content off bad UTF-8 characters.
+        utf8Decoder.onMalformedInput(CodingErrorAction.REPLACE).onUnmappableCharacter(CodingErrorAction.REPLACE);
+        return utf8Decoder;
+    }
+}