Examples of com.ibm.icu.charset.CharsetICU

com.ibm.icu.charset.CharsetICU

A subclass of java.nio.Charset for providing implementation of ICU's charset converters. This API is used to convert codepage or character encoded data to and from UTF-16. You can open a converter with {@link Charset#forName } and {@link #forNameICU }. With that converter, you can get its properties, set options, convert your data.

Since many software programs recogize different converter names for different types of converters, there are other functions in this API to iterate over the converter aliases. @stable ICU 3.6

            (byte)0xea, 0x06,(byte) 0xd3,(byte) 0xe6, 0x0f,(byte) 0x8a, 0x00, 0x30, 0x44, 0x65,(byte) 0xb9, (byte)0xe4, (byte)0xfe,(byte) 0xe7,(byte) 0xc2, 0x06,
            (byte)0xcb, (byte)0x82
        };
        
        CharsetProviderICU cs = new CharsetProviderICU();
        CharsetICU charset = (CharsetICU)cs.charsetForName("scsu");
        CharsetDecoder decode = charset.newDecoder();
        CharsetEncoder encode = charset.newEncoder();
        
        //String[] codePoints = {"allFeatures", "german","russian","japanese"};
        byte[][] fromUnicode={allFeaturesSCSU,germanSCSU,russianSCSU,japaneseSCSU};
        char[][] toUnicode = {allFeaturesUTF16, germanUTF16,russianUTF16,japaneseUTF16};
        
        for(int i=0;i<4;i++){
            ByteBuffer decoderBuffer = ByteBuffer.wrap(fromUnicode[i]);
            CharBuffer encoderBuffer = CharBuffer.wrap(toUnicode[i]);
                           
            try{
                // Decoding 
                CharBuffer decoderResult = decode.decode(decoderBuffer);
                encoderBuffer.position(0);
                if(!decoderResult.equals(encoderBuffer)){
                    errln("Error occured while decoding "+ charset.name());
                }
                // Encoding 
                ByteBuffer encoderResult = encode.encode(encoderBuffer);
                // RoundTrip Test
                ByteBuffer roundTrip = encoderResult;
                CharBuffer roundTripResult = decode.decode(roundTrip);
                encoderBuffer.position(0);
                if(!roundTripResult.equals(encoderBuffer)){
                    errln("Error occured while encoding "+ charset.name());
                }
            }catch(Exception e){
                errln("Exception while converting SCSU thrown: " + e);
            }
        }

View Full Code Here

            0x01, /// from 41 
            (byte) 0xDE, (byte) 0x83, 0x20, 0x09 
        };
        
        CharsetProviderICU cs = new CharsetProviderICU();
        CharsetICU charset = (CharsetICU)cs.charsetForName("BOCU-1");
        CharsetDecoder decode = charset.newDecoder();
        CharsetEncoder encode = charset.newEncoder();
       
        ByteBuffer decoderBuffer = ByteBuffer.wrap(sampleText);
        CharBuffer encoderBuffer = CharBuffer.wrap(expected);
        try{
            // Decoding 
            CharBuffer decoderResult = decode.decode(decoderBuffer);
            
            encoderBuffer.position(0);
            if(!decoderResult.equals(encoderBuffer)){
                errln("Error occured while decoding "+ charset.name());
            }
            // Encoding 
            ByteBuffer encoderResult = encode.encode(encoderBuffer);
            // RoundTrip Test
            ByteBuffer roundTrip = encoderResult;
            CharBuffer roundTripResult = decode.decode(roundTrip);
            
            encoderBuffer.position(0);
            if(!roundTripResult.equals(encoderBuffer)){
                errln("Error occured while encoding "+ charset.name());
            }
        }catch(Exception e){
            errln("Exception while converting BOCU-1 thrown: " + e);
        }
    }

View Full Code Here

       
        
        // retrieve test case data
        ConversionCase cc = new ConversionCase();
        CharsetProviderICU provider = new CharsetProviderICU();
        CharsetICU charset  ;
       
             
        UnicodeSet mapset = new UnicodeSet();
        UnicodeSet mapnotset = new UnicodeSet();
        UnicodeSet unicodeset = new UnicodeSet();
        String ellipsis = "0x2e";
        cc.charset = ((ICUResourceBundle) testcase.getObject("charset"))
                .getString();
        cc.map = ((ICUResourceBundle) testcase.getObject("map")).getString();
        cc.mapnot = ((ICUResourceBundle) testcase.getObject("mapnot"))
                .getString();
        
     
        int which = ((ICUResourceBundle) testcase.getObject("which")).getInt(); // only checking for ROUNDTRIP_SET
        
        // ----for debugging only
        logln("");
        logln("TestGetUnicodeSet[" + cc.charset + "] ");
        logln("...............................................");
        
        try{
           // if cc.charset starts with '*', obtain it from com/ibm/icu/dev/data/testdata
           charset = (cc.charset != null && cc.charset.length() > 0 && cc.charset.charAt(0) == '*')
                    ? (CharsetICU) provider.charsetForName(cc.charset.substring(1),
                        "com/ibm/icu/dev/data/testdata", this.getClass().getClassLoader())
                    : (CharsetICU) provider.charsetForName(cc.charset);
           
           //checking for converter that are not supported at this point        
           try{
               if(charset.name()=="BOCU-1" ||charset.name()== "SCSU"|| charset.name()=="lmbcs1" || charset.name()== "lmbcs2" ||
                      charset.name()== "lmbcs3" || charset.name()== "lmbcs4" || charset.name()=="lmbcs5" || charset.name()=="lmbcs6" ||
                      charset.name()== "lmbcs8" || charset.name()=="lmbcs11" || charset.name()=="lmbcs16" || charset.name()=="lmbcs17" || 
                      charset.name()=="lmbcs18"|| charset.name()=="lmbcs19"){
                   
                   logln("Converter not supported at this point :" +charset.displayName());
                   return;
               }
                             
               if(which==1){
                   logln("Fallback set not supported at this point for converter : "+charset.displayName());
                  return;
               }
               
           }catch(Exception e){
               return;
           }
           
           mapset.clear();
           mapnotset.clear();
                   
           mapset.applyPattern(cc.map,false);
           mapnotset.applyPattern(cc.mapnot,false);
           
           charset.getUnicodeSet(unicodeset, which);
           UnicodeSet diffset = new UnicodeSet();
           
           //are there items that must be in unicodeset but are not?           
           (diffset = mapset).removeAll(unicodeset);
           if(!diffset.isEmpty()){

View Full Code Here

TOP

Related Classes of com.ibm.icu.charset.CharsetICU

com.ibm.icu.dev.test.charset.TestCharset

com.ibm.icu.dev.test.charset.TestConversion

java.lang.reflect.Constructor

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.