Java CharsetMatch.getName方法代码示例

import com.ibm.icu.text.CharsetMatch; //导入方法依赖的package包/类
/**
     * 利用 icu4j 探测输入流编码，只能探测文本类型的输入流
     * -
     * 抛弃 juniversalchardet
     *
     * @param in
     * @return
     * @throws IOException
     */
    public static Charset detectEncoding(InputStream in) throws IOException {
        final CharsetDetector detector = new CharsetDetector();
        detector.setText(in);

        final CharsetMatch charsetMatch = detector.detect();
        if (charsetMatch == null) {
            log.info("Cannot detect source charset.");
            return null;
        }
        //This is an integer from 0 to 100. The higher the value, the more confidence
        //探测的相似度在 1~100 之间，相似度越高结果越准确。
        int confidence = charsetMatch.getConfidence();
        final String name = charsetMatch.getName();
        log.info("CharsetMatch: {} ({}% 相似度，相似度小于 50% 时，可能编码无法判断。)", name, confidence);
        //打印该文本编码，所有可能性
//        CharsetMatch[] matches = detector.detectAll();
//        System.out.println("All possibilities : " + Arrays.asList(matches));
        return Charset.forName(name);
    }
 

import com.ibm.icu.text.CharsetMatch; //导入方法依赖的package包/类
/**
 * Extract text to be indexed
 */
public static String getText(String mimeType, String encoding, InputStream isContent) throws IOException {
	BufferedInputStream bis = new BufferedInputStream(isContent);
	TextExtractor te = engine.get(mimeType);
	String text = null;

	if (te != null) {
		if (mimeType.startsWith("text/") && encoding == null) {
			CharsetDetector detector = new CharsetDetector();
			detector.setText(bis);
			CharsetMatch cm = detector.detect();
			encoding = cm.getName();
		}

		text = te.extractText(bis, mimeType, encoding);
	} else {
		throw new IOException("Full text indexing of '" + mimeType + "' is not supported");
	}


	IOUtils.closeQuietly(bis);
	return text;
}
 

import com.ibm.icu.text.CharsetMatch; //导入方法依赖的package包/类
protected String showEncode(Document doc) {
  String charsetName = "";
  try {
    String convertedPlainText = doc.getText(0, doc.getLength());
    try (InputStream is = convertStringToStream(convertedPlainText)) {
      CharsetMatch charsetMatch = new CharsetDetector().setText(is).detect();
      charsetName = charsetMatch.getName();
      charsetName = charsetName != null ? charsetName : "NULL";
      if (isPoorMatch(charsetMatch.getConfidence())) {
        charsetName = verifyPossibleUtf8(charsetName, is);
      }
      charsetName += showByteOfMark(is);
    }
  } catch (BadLocationException | IOException ex) {
    Exceptions.printStackTrace(ex);
  }
  return charsetName;
}
 

import com.ibm.icu.text.CharsetMatch; //导入方法依赖的package包/类
/**
 * Detect charset encoding of a byte array
 * 
 * @param bytes: the byte array to detect encoding from
 * @return the charset encoding
 */
public static String guessEncoding(byte[] bytes) {
	UniversalDetector detector = new UniversalDetector(null);

	detector.handleData(bytes, 0, bytes.length);
	detector.dataEnd();

	String encoding = detector.getDetectedCharset();
	detector.reset();

	if (encoding == null || "MACCYRILLIC".equals(encoding)) {
		// juniversalchardet incorrectly detects windows-1256 as MACCYRILLIC
		// If encoding is MACCYRILLIC or null, we use ICU4J
		CharsetMatch detected = new CharsetDetector().setText(bytes).detect();
		if (detected != null) {
			encoding = detected.getName();
		} else {
			encoding = "UTF-8";
		}
	}

	return encoding;
}
 

import com.ibm.icu.text.CharsetMatch; //导入方法依赖的package包/类
/**
 * Uses ICU4J to determine the charset of the given InputStream.
 * 
 * @param input
 * @return Detected charset name; null if not detected.
 * @throws IOException
 * @should detect charset correctly
 */
public static String getCharset(InputStream input) throws IOException {
    CharsetDetector cd = new CharsetDetector();
    try (BufferedInputStream bis = new BufferedInputStream(input)) {
        cd.setText(bis);
        CharsetMatch cm = cd.detect();
        if (cm != null) {
            return cm.getName();
        }
    }

    return null;
}
 

import com.ibm.icu.text.CharsetMatch; //导入方法依赖的package包/类
private String ibmICU4j(byte[] bytes) {
	CharsetDetector charsetDetector = new CharsetDetector();
	charsetDetector.setText(bytes);
	CharsetMatch charsetMatch = charsetDetector.detect();
	String charset = charsetMatch.getName();
	return charset;
}
 

import com.ibm.icu.text.CharsetMatch; //导入方法依赖的package包/类
protected String suggestEncoding(final byte[] bytes) {
    final CharsetDetector cd = new CharsetDetector();
    cd.setText(bytes);

    final CharsetMatch charsetMatch = cd.detect();
    final String charSet = charsetMatch.getName();

    final int confidence = charsetMatch.getConfidence();
    logger.info("CharsetMatch: {} ({}% confidence)", charSet, confidence);
    return charSet;
}
 

import com.ibm.icu.text.CharsetMatch; //导入方法依赖的package包/类
public String autoDetectEncoding(final byte[] bytes) {
    final CharsetDetector cd = new CharsetDetector();
    cd.setText(bytes);
    final CharsetMatch charsetMatch = cd.detect();
    final String charSet = charsetMatch.getName();

    final int confidence = charsetMatch.getConfidence();
    logger.info("CharsetMatch: {} ({}% confidence)", charSet, confidence);
    setSelectedItem(charSet);
    return charSet;
}
 

import com.ibm.icu.text.CharsetMatch; //导入方法依赖的package包/类
private BufferedReader readFile(File file)
		throws UnsupportedEncodingException, FileNotFoundException {
	// InputStreamReader isr = new InputStreamReader(new
	// FileInputStream(file));
	// System.out.println(isr.getEncoding());
	// System.exit(0);
	String charSet = "UTF-8";

	final BufferedInputStream bis = new BufferedInputStream(
			new FileInputStream(file));
	final CharsetDetector cd = new CharsetDetector();
	try {
		cd.setText(bis);
		final CharsetMatch cm = cd.detect();

		if (cm != null && cm.getName() == "ISO-8859-1") {
			charSet = cm.getName();
		}
	} catch (final IOException e) {
		// TODO Auto-generated catch block
		e.printStackTrace();
	}
	// System.out.println(charSet);
	// String charSet = "UTF-8"; //"ISO-8859-1";
	final BufferedReader bf = new BufferedReader(new InputStreamReader(
			new FileInputStream(file), charSet));

	return bf;

}
 

import com.ibm.icu.text.CharsetMatch; //导入方法依赖的package包/类
/**
 * Detect encoding by analyzing characters in the array
 */
public static Charset detectEncoding(byte[] bytes) {
	String encoding = "UTF-8";

	CharsetDetector detector = new CharsetDetector();
	detector.setText(bytes);
	CharsetMatch match = detector.detect();
	if (match != null) {
		encoding = match.getName();
	}
	if (encoding.equalsIgnoreCase("ISO-8859-1")) {
		encoding = "windows-1252";
	}
	return Charset.forName(encoding);
}
 

import com.ibm.icu.text.CharsetMatch; //导入方法依赖的package包/类
public String uploadHlog(FileTransfer file,String fileName, Integer type){
		if(type == 3 ){//上传数据同步文件
			return uploadDataSyncFile(file,fileName);
		}
		String msg = "";
		BufferedReader br = null;//该buffreredReader是对ByteArrayInputStream的封装 不需要关闭
		ByteArrayOutputStream byteOut = null;
		try {
			String extensions = fileName.substring(fileName.lastIndexOf("."));// 后缀名
			if (fileName.indexOf(".") <= 0||!extensions.equals(".csv")) {
				msg = "文件类型不正确！";
			}
			int length = 0;
			byte[] buff = new byte[1024];
			byteOut = new ByteArrayOutputStream();
			InputStream in = file.getInputStream();
			while((length = in.read(buff)) != -1){
				byteOut.write(buff,0,length);
			}
			byte[] fileBytes = byteOut.toByteArray();
			byteOut = null;
			
//			//判断上传文件的编码
			CharsetDetector detec = new CharsetDetector();
			detec.setText(fileBytes);
		    CharsetMatch match = detec.detect();
		    if(match == null){
		    	throw new Exception("未知的文件编码");
		    }
		    String encoding = match.getName();
		    logger.info("-------- file["+fileName+"] encoding:"+encoding+" --------");
			br = new BufferedReader(new InputStreamReader(new ByteArrayInputStream(fileBytes),encoding));
			String[] mapping = DATA_MAPPING.get(type);
			Strategy[] strategies = PARSE_STRATEGIES.get(type);
			List<Hlog> hlogList = new ArrayList<Hlog>();
			br.readLine();//过滤表头
			if (null != mapping) {
				String line = "";
				while ((line = br.readLine())!=null) {
					String[] values = line.split(",");
					Hlog hlog= new Hlog();
					hlog.setTstat((short)2);//交易状态为成功
					hlog.setType((short)5);//增值业务
					hlog.setMid("325");//商户号 325
					BeanWrapper bw = new BeanWrapperImpl(hlog);
					for (int i = 0;i<mapping.length;i++) {
						String fieldName = mapping[i];
						if(StringUtils.isNotBlank(fieldName)){
							Strategy stra = strategies[i];
							String value = values[i].trim();
							if(stra != null){
								stra.setValue(fieldName,value,bw);//需要自定义转换
							}else if(StringUtils.isNotBlank(value)){
								bw.setPropertyValue(fieldName, value);//直接set
							}else{
								throw new Exception("["+fieldName+"]不能为空");
							}
						}
					}
					hlogList.add(hlog);
				}
				fileBytes = null;
				if (!hlogList.isEmpty()) {
					int count = dao.batchAdd(hlogList);
					if (count != 0) {
						msg = "上传成功,共上传 " + count + " 条记录";
					}else{
						msg = "上传失败";
					}
				}else{
					msg = "上传失败,上传文件中没有订单数据";
				}
			}else{
				msg = "上传失败,未知的业务类型";
			}
		} catch (Exception e) {
			msg = "上传失败";
			LogUtil.printErrorLog(getClass().getCanonicalName(), "uploadHlog", "fileName="+fileName+" type="+type, e);
		}
		return msg;
	}
 

import com.ibm.icu.text.CharsetMatch; //导入方法依赖的package包/类
private String ibmICU4j(byte[] bytes) {
	CharsetDetector charsetDetector = new CharsetDetector();
	charsetDetector.setText(bytes);
	CharsetMatch charsetMatch = charsetDetector.detect();
	return charsetMatch.getName();
}
 

import com.ibm.icu.text.CharsetMatch; //导入方法依赖的package包/类
public static String detect(CharsetDetector detector) {
	final CharsetMatch match = detector.detect();
	return match == null ? null : match.getName();
}