Examples of com.ibm.icu.charset.CharsetProviderICU

com.ibm.icu.charset.CharsetProviderICU
A concrete subclass of CharsetProvider for loading and providing charset converters in ICU. @stable ICU 3.6

    
    // provide better code coverage for Charset Callbacks
    /* Different aspects of callbacks are being tested including using different context available */
    public void TestCharsetCallbacks() {
        CoderResult result = CoderResult.UNDERFLOW;
        CharsetProvider provider = new CharsetProviderICU();       
        CharsetEncoder encoder = provider.charsetForName("iso-2022-jp").newEncoder();
        CharsetDecoder decoder = provider.charsetForName("iso-2022-jp").newDecoder();
        
        String context3[] = {
                "i",
                "J"
        };

View Full Code Here

        }
    }
    
    // Testing invalid input exceptions
    public void TestInvalidInput() {
        CharsetProvider provider = new CharsetProviderICU();
        Charset charset = provider.charsetForName("iso-2022-jp");
        CharsetEncoder encoder = charset.newEncoder();
        CharsetDecoder decoder = charset.newDecoder();
        
        try {
            encoder.encode(CharBuffer.allocate(10), null, true);

View Full Code Here

    // Port over from ICU4C for test conversion tables (mbcs version 5.x)
    // Provide better code coverage in CharsetMBCS, CharsetDecoderICU, and CharsetEncoderICU.
    public void TestCharsetTestData() {
        CoderResult result = CoderResult.UNDERFLOW;
        String charsetName = "test4";
        CharsetProvider provider = new CharsetProviderICU();
        Charset charset = ((CharsetProviderICU)provider).charsetForName(charsetName, "com/ibm/icu/dev/data/testdata",
                            this.getClass().getClassLoader());
        CharsetEncoder encoder = charset.newEncoder();
        CharsetDecoder decoder = charset.newDecoder();

View Full Code Here

            0x02, 0x08, 0x0c, (byte)0xe2, 0x16, (byte)0xa3, (byte)0xb7, (byte)0xcb, 0x0f, 0x4f,(byte) 0xe1,(byte) 0x80, 0x05,(byte) 0xec, 0x60, (byte)0x8d,
            (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};

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);

View Full Code Here


    
    private void FromUnicodeCase(ConversionCase cc) {


        // create charset encoder for conversion test
        CharsetProviderICU provider = new CharsetProviderICU();
        CharsetEncoder encoder = null;
        Charset charset = null;
        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) == '*')
                    ? (Charset) provider.charsetForName(cc.charset.substring(1),
                        "com/ibm/icu/dev/data/testdata", this.getClass().getClassLoader())
                    : (Charset) provider.charsetForName(cc.charset);
            encoder = (CharsetEncoder) charset.newEncoder();
            encoder.onMalformedInput(CodingErrorAction.REPLACE);
            encoder.onUnmappableCharacter(CodingErrorAction.REPLACE);
            if (encoder instanceof CharsetEncoderICU) {
                ((CharsetEncoderICU)encoder).setFallbackUsed(cc.fallbacks);

View Full Code Here

    }


    private void ToUnicodeCase(ConversionCase cc) {


        // create converter for charset and decoder for each test case
        CharsetProviderICU provider = new CharsetProviderICU();
        CharsetDecoder decoder = null;
        Charset charset = null;


        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) == '*')
                    ? (Charset) provider.charsetForName(cc.charset.substring(1),
                        "com/ibm/icu/dev/data/testdata", this.getClass().getClassLoader())
                    : (Charset) provider.charsetForName(cc.charset);
            decoder = (CharsetDecoder) charset.newDecoder();
            decoder.onMalformedInput(CodingErrorAction.REPLACE);
            decoder.onUnmappableCharacter(CodingErrorAction.REPLACE);


        } catch (Exception 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" ||

View Full Code Here

        
        /* Create an encoder to get the bytes.
         * Using String.getBytes("IBM420") can produce inconsistent results
         * between different versions of the JDK.
         */
        CharsetEncoder encoder = new CharsetProviderICU().charsetForName("IBM420").newEncoder();
        
        m = _testIBM420_ar_rtl(s, encoder);
        charsetMatch = m.getName();
        CheckAssert(charsetMatch.equals("IBM420_rtl"));

View Full Code Here


    PerfTest.Function TestCharsetDecoderICU() {
        try{
            return new PerfTest.Function() {
                CharBuffer outBuf = CharBuffer.allocate(unicodeBuffer.length);
                Charset myCharset = new CharsetProviderICU().charsetForName(testName);
                ByteBuffer srcBuf = ByteBuffer.wrap(encBuffer,0,encBuffer.length);
                CharsetDecoder decoder = myCharset.newDecoder();


                public void call() {
                    try{

View Full Code Here

0 1 2 3 4 5

TOP

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

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

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

com.ibm.icu.dev.test.charsetdet.TestCharsetDetector

com.ibm.icu.dev.test.perf.ConverterPerformanceTest

java.nio.charset.UnsupportedCharsetException

java.nio.charset.Charset

java.util.HashMap

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.