Examples of com.ibm.icu.text.UCharacterIterator

com.ibm.icu.text.UCharacterIterator
Abstract class that defines an API for iteration on text objects.This is an interface for forward and backward iteration and random access into a text object. Forward iteration is done with post-increment and backward iteration is done with pre-decrement semantics, while the java.text.CharacterIterator interface methods provided forward iteration with "pre-increment" and backward iteration with pre-decrement semantics. This API is more efficient for forward iteration over code points. The other major difference is that this API can do both code unit and code point iteration, java.text.CharacterIterator can only iterate over code units and is limited to BMP (0 - 0xFFFF) @author Ram @stable ICU 2.4

        }
    }
    private void doTestIDNToASCII(String src, String expected, int options, Object expectedException) 
                throws Exception{
        StringBuffer inBuf = new StringBuffer(src);
        UCharacterIterator inIter = UCharacterIterator.getInstance(src);
        try{
            
            StringBuffer out = IDNA.convertIDNToASCII(src,options);
            if(expected!=null && out != null && !out.toString().equals(expected)){
                errln("convertToIDNASCII did not return expected result with options : "+ options +

View Full Code Here

    }
    public void TestNamePrepConformance() throws Exception{
        StringPrep namePrep = StringPrep.getInstance(StringPrep.RFC3491_NAMEPREP);
        for(int i=0; i<TestData.conformanceTestCases.length;i++){
            TestData.ConformanceTestCase testCase = TestData.conformanceTestCases[i];
            UCharacterIterator iter = UCharacterIterator.getInstance(testCase.input);
            try{
                StringBuffer output = namePrep.prepare(iter,StringPrep.DEFAULT);
                if(testCase.output !=null && output!=null && !testCase.output.equals(output.toString())){
                    errln("Did not get the expected output. Expected: " + prettify(testCase.output)+
                          " Got: "+ prettify(output) );
                }
                if(testCase.expected!=null && !unassignedException.equals(testCase.expected)){
                    errln("Did not get the expected exception. The operation succeeded!");
                }
            }catch(StringPrepParseException ex){
                if(testCase.expected == null || !ex.equals(testCase.expected)){
                    errln("Did not get the expected exception for source: " +testCase.input +" Got:  "+ ex.toString());
                }
            }
            
            try{
                iter.setToStart();
                StringBuffer output = namePrep.prepare(iter,StringPrep.ALLOW_UNASSIGNED);
                if(testCase.output !=null && output!=null && !testCase.output.equals(output.toString())){
                    errln("Did not get the expected output. Expected: " + prettify(testCase.output)+
                          " Got: "+ prettify(output) );
                }

View Full Code Here

        String expected = Utility.unescape("\\U0001d15e\\U0001d157\\U0001d165\\U0001d15e");
        Normalizer iter = new Normalizer(new StringCharacterIterator(Utility.unescape(src)),
                                                Normalizer.NONE,0);
        int index = 0;
        int ch;
        UCharacterIterator cIter =  UCharacterIterator.getInstance(expected);
        
        while ((ch=iter.next())!= Normalizer.DONE){
            if (index >= expected.length()) {
                errln("FAIL: " +  "Unexpected character '" + (char)ch
                        + "' (" + hex(ch) + ")"
                        + " at index " + index);
                break;
            }
            int want = UTF16.charAt(expected,index);
            if (ch != want) {
                errln("FAIL: " +  "got '" + (char)ch
                        + "' (" + hex(ch) + ")"
                        + " but expected '" + want + "' (" + hex(want)+ ")"
                        + " at index " + index);
            }
            index+=  UTF16.getCharCount(ch);
        }
        if (index < expected.length()) {
            errln("FAIL: " +  "Only got " + index + " chars, expected "
            + expected.length());
        }
        
        cIter.setToLimit();
        while((ch=iter.previous())!=Normalizer.DONE){
            int want = cIter.previousCodePoint();
            if (ch != want ) {
                errln("FAIL: " + "got '" + (char)ch
                        + "' (" + hex(ch) + ")"
                        + " but expected '" + want + "' (" + hex(want) + ")"
                        + " at index " + index);

View Full Code Here

    public void TestNormalizerAPI() throws Exception {
        try{
            // instantiate a Normalizer from a CharacterIterator
            String s=Utility.unescape("a\u0308\uac00\\U0002f800");
            // make s a bit longer and more interesting
            UCharacterIterator iter = UCharacterIterator.getInstance(s+s);
            Normalizer norm = new Normalizer(iter, Normalizer.NFC,0);
            if(norm.next()!=0xe4) {
                errln("error in Normalizer(CharacterIterator).next()");
            }   
    
            // test clone(), ==, and hashCode()
            Normalizer clone=(Normalizer)norm.clone();
            if(clone.equals(norm)) {
                errln("error in Normalizer(Normalizer(CharacterIterator)).clone()!=norm");
            }
    
            
            if(clone.getLength()!= norm.getLength()){
               errln("error in Normalizer.getBeginIndex()");
            } 
            // clone must have the same hashCode()
            //if(clone.hashCode()!=norm.hashCode()) {
            //    errln("error in Normalizer(Normalizer(CharacterIterator)).clone().hashCode()!=copy.hashCode()");
            //}
            if(clone.next()!=0xac00) {
                errln("error in Normalizer(Normalizer(CharacterIterator)).next()");
            }
            int ch = clone.next();
            if(ch!=0x4e3d) {
                errln("error in Normalizer(Normalizer(CharacterIterator)).clone().next()");
            }
            // position changed, must change hashCode()
            if(clone.hashCode()==norm.hashCode()) {
                errln("error in Normalizer(Normalizer(CharacterIterator)).clone().next().hashCode()==copy.hashCode()");
            }
    
            // test compose() and decompose()
            StringBuffer tel;
            String nfkc, nfkd;
            tel=new StringBuffer("\u2121\u2121\u2121\u2121\u2121\u2121\u2121\u2121\u2121\u2121");
            tel.insert(1,(char)0x0301);
    
            nfkc=Normalizer.compose(tel.toString(), true);
            nfkd=Normalizer.decompose(tel.toString(), true);
            if(
                !nfkc.equals(Utility.unescape("TE\u0139TELTELTELTELTELTELTELTELTEL"))||
                !nfkd.equals(Utility.unescape("TEL\u0301TELTELTELTELTELTELTELTELTEL"))
            ) {
                errln("error in Normalizer::(de)compose(): wrong result(s)");
            }
    
            // test setIndex()
//            ch=norm.setIndex(3);
//            if(ch!=0x4e3d) {
//                errln("error in Normalizer(CharacterIterator).setIndex(3)");
//            }
    
            // test setText(CharacterIterator) and getText()
            String out, out2;
            clone.setText(iter);
    
            out = clone.getText();
            out2 = iter.getText();
            if( !out.equals(out2) ||
                clone.startIndex()!=0||
                clone.endIndex()!=iter.getLength()
            ) {
                errln("error in Normalizer::setText() or Normalizer::getText()");
            }
     
            char[] fillIn1 = new char[clone.getLength()];
            char[] fillIn2 = new char[iter.getLength()];
            int len = clone.getText(fillIn1);
            iter.getText(fillIn2,0);
            if(!Utility.arrayRegionMatches(fillIn1,0,fillIn2,0,len)){
                errln("error in Normalizer.getText(). Normalizer: "+
                                Utility.hex(new String(fillIn1))+ 
                                " Iter: " + Utility.hex(new String(fillIn2)));
            }

View Full Code Here

       }
     }
     
     public void TestBugJ2068(){
        String sample = "The quick brown fox jumped over the lazy dog";
        UCharacterIterator text = UCharacterIterator.getInstance(sample);
        Normalizer norm = new Normalizer(text,Normalizer.NFC,0);
        text.setIndex(4);
        if(text.current() == norm.current()){
            errln("Normalizer is not cloning the UCharacterIterator");
        }
     }

View Full Code Here

                               throws StringPrepParseException{
        int[] in = new int[input.length()];
        int inLen = 0;
        int ch;
        StringBuffer result = new StringBuffer();
        UCharacterIterator iter = UCharacterIterator.getInstance(input);
        while((ch=iter.nextCodePoint())!= UCharacterIterator.DONE){
            in[inLen++]=ch;
        }


        int[] outLen =  new int[1];
        outLen[0] = input.length()*4;

View Full Code Here

    }
    
    private static byte[] prepare(byte[] src, StringPrep strprep)
                throws StringPrepParseException, UnsupportedEncodingException{
        String s = new String(src, "UTF-8");
        UCharacterIterator iter =  UCharacterIterator.getInstance(s);
        StringBuffer out = strprep.prepare(iter,StringPrep.DEFAULT);
        return out.toString().getBytes("UTF-8");
    }

View Full Code Here

            int i= findStringIndex(special_prefixes, prefixString);
            String suffixString = s.substring(index+1, s.length());
            if(i>-1 && !suffixString.equals("")){
                throw new StringPrepParseException("Suffix following a special index", StringPrepParseException.INVALID_CHAR_FOUND);
            }
            UCharacterIterator prefix = UCharacterIterator.getInstance(prefixString);
            UCharacterIterator suffix = UCharacterIterator.getInstance(suffixString);
            out.append(prep.nfsmxp.prepare(prefix,StringPrep.DEFAULT));
            out.append(AT_SIGN); // add the delimiter
            out.append(prep.nfsmxs.prepare(suffix, StringPrep.DEFAULT));
        }else{
            UCharacterIterator iter = UCharacterIterator.getInstance(s);
            out.append(prep.nfsmxp.prepare(iter,StringPrep.DEFAULT));
            
        }
       return out.toString().getBytes("UTF-8");
    }

View Full Code Here

    private String map ( String src, int options)
                                throws StringPrepParseException{
        // map 
        boolean allowUnassigned =  ((options & ALLOW_UNASSIGNED)>0);
        String caseMapOut = transform.mapTransform.transliterate(src);    
        UCharacterIterator iter = UCharacterIterator.getInstance(caseMapOut);
        int ch;
        while((ch=iter.nextCodePoint())!=UCharacterIterator.DONE){                          
            if(transform.unassignedSet.contains(ch)==true && allowUnassigned ==false){
                throw new StringPrepParseException("An unassigned code point was found in the input",
                                         StringPrepParseException.UNASSIGNED_ERROR);
            }
        }

View Full Code Here

    public StringBuffer prepare(String src,int options)
                                   throws StringPrepParseException{
 
        int ch;
        String mapOut = map(src,options);
        UCharacterIterator iter = UCharacterIterator.getInstance(mapOut);


        int direction=UCharacterDirection.CHAR_DIRECTION_COUNT,
            firstCharDir=UCharacterDirection.CHAR_DIRECTION_COUNT;    
        int rtlPos=-1, ltrPos=-1;
        boolean rightToLeft=false, leftToRight=false;
           
        while((ch=iter.nextCodePoint())!= UCharacterIterator.DONE){




            if(transform.prohibitedSet.contains(ch)==true && ch!=0x0020){
                throw new StringPrepParseException("A prohibited code point was found in the input",
                                         StringPrepParseException.PROHIBITED_ERROR,
                                         iter.getText(),iter.getIndex());
            }


            direction = UCharacter.getDirection(ch);
            if(firstCharDir == UCharacterDirection.CHAR_DIRECTION_COUNT){
                firstCharDir = direction;
            }
            if(direction == UCharacterDirection.LEFT_TO_RIGHT){
                leftToRight = true;
                ltrPos = iter.getIndex()-1;
            }
            if(direction == UCharacterDirection.RIGHT_TO_LEFT || direction == UCharacterDirection.RIGHT_TO_LEFT_ARABIC){
                rightToLeft = true;
                rtlPos = iter.getIndex()-1;
            }
        }           


        // satisfy 2
        if( leftToRight == true && rightToLeft == true){
            throw new StringPrepParseException("The input does not conform to the rules for BiDi code points.",
                                     StringPrepParseException.CHECK_BIDI_ERROR,iter.getText(),(rtlPos>ltrPos) ? rtlPos : ltrPos);
        }


        //satisfy 3
        if( rightToLeft == true && 
            !((firstCharDir == UCharacterDirection.RIGHT_TO_LEFT || firstCharDir == UCharacterDirection.RIGHT_TO_LEFT_ARABIC) &&
            (direction == UCharacterDirection.RIGHT_TO_LEFT || direction == UCharacterDirection.RIGHT_TO_LEFT_ARABIC))
           ){
            throw new StringPrepParseException("The input does not conform to the rules for BiDi code points.",
                                      StringPrepParseException.CHECK_BIDI_ERROR,iter.getText(),(rtlPos>ltrPos) ? rtlPos : ltrPos);
        }
        
        return new StringBuffer(mapOut);


      }

View Full Code Here

0 1 2 3

TOP

Related Classes of com.ibm.icu.text.UCharacterIterator

com.ibm.icu.dev.test.iterator.TestUCharacterIterator

com.ibm.icu.dev.test.normalizer.BasicTest

com.ibm.icu.dev.test.stringprep.IDNAReference

com.ibm.icu.dev.test.stringprep.NamePrepTransform

com.ibm.icu.dev.test.stringprep.NFS4StringPrep

com.ibm.icu.dev.test.stringprep.PunycodeReference

com.ibm.icu.dev.test.stringprep.TestIDNA

com.ibm.icu.dev.test.stringprep.TestIDNARef

com.ibm.icu.impl.BOCU

com.ibm.icu.impl.CharacterIteratorWrapper

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.