Examples of com.ibm.icu.text.CharsetDetector.detect()

com.ibm.icu.text.CharsetDetector.detect()
Return the charset that best matches the supplied input data. Note though, that because the detection only looks at the start of the input data, there is a possibility that the returned charset will fail to handle the full set of input data.
Raise an exception if
- no charset appears to match the data.
- no input text has been provided
@return a CharsetMatch object representing the best matching charset, ornull if there are no matches. @stable ICU 3.4

        if (! m.getName().equals("UTF-16BE")) {
            errln("Encoding detection failure: expected UTF-16BE, got " + m.getName());
        }
        
        det.setText(leBytes);
        m = det.detect();
        
        if (! m.getName().equals("UTF-16LE")) {
            errln("Encoding detection failure: expected UTF-16LE, got " + m.getName());
        }

View Full Code Here

        
        CharsetDetector det = new CharsetDetector();
        CharsetMatch m;
        
        det.setText(bWindows);
        m = det.detect();
        
        if (m.getName() != "windows-1252") {
            errln("Text with C1 bytes not correctly detected as windows-1252.");
            return;
        }

View Full Code Here

            errln("Text with C1 bytes not correctly detected as windows-1252.");
            return;
        }
        
        det.setText(bISO);
        m = det.detect();
        
        if (m.getName() != "ISO-8859-1") {
            errln("Text without C1 bytes not correctly detected as ISO-8859-1.");
        }
    }

View Full Code Here

        
        CharsetDetector det = new CharsetDetector();
        CharsetMatch m;
        for (int i=0; i<shortBytes.length; i++) {
            det.setText(shortBytes[i]);
            m = det.detect();
            logln("i=" + i + " -> " + m.getName());
        }
    }
    
    public void TestBufferOverflow()

View Full Code Here


        det.setDeclaredEncoding("ISO-2022-JP");


        for (int idx = 0; idx < testStrings.length; idx += 1) {
            det.setText(testStrings[idx]);
            match = det.detect();


            if (match == null) {
                if (testResults[idx] != null) {
                    errln("Unexpectedly got no results at index " + idx);
                }

View Full Code Here

    }


    private CharsetMatch _testIBM420_ar_rtl(String s, CharsetEncoder encoder) throws Exception {
        CharsetDetector det = new CharsetDetector();
        det.setText(encoder.encode(CharBuffer.wrap(s)).array());
        CharsetMatch m = det.detect();
        return m;
    }


    private CharsetMatch _testIBM420_ar_ltr(String s, CharsetEncoder encoder) throws Exception {
        /**

View Full Code Here

        StringBuffer ltrStrBuf = new StringBuffer(s);
        ltrStrBuf = ltrStrBuf.reverse();
        
        CharsetDetector det = new CharsetDetector();
        det.setText(encoder.encode(CharBuffer.wrap(ltrStrBuf.toString())).array());
        CharsetMatch m = det.detect();
        return m;
    }


    private CharsetMatch _test1256(String s) throws Exception {

View Full Code Here

    private CharsetMatch _test1256(String s) throws Exception {
        
        byte [] bytes = s.getBytes("windows-1256");
        CharsetDetector det = new CharsetDetector();
        det.setText(bytes);
        CharsetMatch m = det.detect();
        return m;
    }
//#endif


    public void TestHebrew() throws Exception {

View Full Code Here


    private CharsetMatch _test1255(String s) throws Exception {
        byte [] bytes = s.getBytes("ISO-8859-8");
        CharsetDetector det = new CharsetDetector();
        det.setText(bytes);
        CharsetMatch m = det.detect();
        return m;
    }
    
    private CharsetMatch _testIBM424_he_rtl(String s) throws Exception {
        byte [] bytes = s.getBytes("IBM424");

View Full Code Here

    
    private CharsetMatch _testIBM424_he_rtl(String s) throws Exception {
        byte [] bytes = s.getBytes("IBM424");        
        CharsetDetector det = new CharsetDetector();
        det.setText(bytes);
        CharsetMatch m = det.detect();
        return m;
    }
    
    private CharsetMatch _testIBM424_he_ltr(String s) throws Exception {
        /**

View Full Code Here

0 1 2 3

TOP

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.