java读取文件时,识别文件编码格式

java技术文章

2018-07-14

196

0

     在开发web应用的过程中,我们需要读取不同的配置文件,struts的配置文件,hibernate的配置文件,spring的配置文件,但是如果编辑文件的格式不正确的话,最终导致读取数据内容出现乱码,出现一些不必要的问题。

     或者是调用第三方插件时,由于对方的编码格式和我们不匹配,最终需要我们自己去对配置文件进行文件编码转换。现在有如下方法,可以判断文件的编码格式,可以不用在猜对方用什么编码格式了。

/**
 * 
 */
 
import java.io.BufferedInputStream;
import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.InputStreamReader;
import java.io.OutputStreamWriter;
import java.io.Writer;
import java.util.BitSet;
 
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
 
/**
 * @author 自动识别文件编码格式
 *
 */
public class EncodeUtil {
	private static Logger logger = LoggerFactory.getLogger(EncodeUtil.class);
 
	private static int BYTE_SIZE = 8;
    public static String CODE_UTF8 = "UTF-8";
    public static String CODE_UTF8_BOM = "UTF-8_BOM";
    public static String CODE_GBK = "GBK";
 
    /**
     * 通过文件全名称获取编码集名称
     *
     * @param fullFileName
     * @param ignoreBom
     * @return
     * @throws Exception
     */
    public static String getEncode(String fullFileName, boolean ignoreBom) throws Exception {
    	logger.debug("fullFileName ; {}", fullFileName);
        BufferedInputStream bis = new BufferedInputStream(new FileInputStream(fullFileName));
        return getEncode(bis, ignoreBom);
    }
 
    /**
     * 通过文件缓存流获取编码集名称,文件流必须为未曾
     *
     * @param bis
     * @param ignoreBom 是否忽略utf-8 bom
     * @return
     * @throws Exception
     */
    public static String getEncode(BufferedInputStream bis, boolean ignoreBom) throws Exception {
        bis.mark(0);
 
        String encodeType = "未识别";
        byte[] head = new byte[3];
        bis.read(head);
        if (head[0] == -1 && head[1] == -2) {
            encodeType = "UTF-16";
        } else if (head[0] == -2 && head[1] == -1) {
            encodeType = "Unicode";
        } else if (head[0] == -17 && head[1] == -69 && head[2] == -65) { //带BOM
            if (ignoreBom) {
                encodeType = CODE_UTF8;
            } else {
                encodeType = CODE_UTF8_BOM;
            }
        } else if ("Unicode".equals(encodeType)) {
            encodeType = "UTF-16";
        } else if (isUTF8(bis)) {
            encodeType = CODE_UTF8;
        } else {
            encodeType = CODE_GBK;
        }
        logger.info("result encode type : " + encodeType);
        return encodeType;
    }
 
    /**
     * 是否是无BOM的UTF8格式,不判断常规场景,只区分无BOM UTF8和GBK
     *
     * @param bis
     * @return
     */
    private static boolean isUTF8( BufferedInputStream bis) throws Exception {
        bis.reset();
 
        //读取第一个字节
        int code = bis.read();
        do {
            BitSet bitSet = convert2BitSet(code);
            //判断是否为单字节
            if (bitSet.get(0)) {//多字节时,再读取N个字节
                if (!checkMultiByte(bis, bitSet)) {//未检测通过,直接返回
                    return false;
                }
            } else {
                //单字节时什么都不用做,再次读取字节
            }
            code = bis.read();
        } while (code != -1);
        return true;
    }
 
    /**
     * 检测多字节,判断是否为utf8,已经读取了一个字节
     *
     * @param bis
     * @param bitSet
     * @return
     */
    private static boolean checkMultiByte(BufferedInputStream bis, BitSet bitSet) throws Exception {
        int count = getCountOfSequential(bitSet);
        byte[] bytes = new byte[count - 1];//已经读取了一个字节,不能再读取
        bis.read(bytes);
        for (byte b : bytes) {
            if (!checkUtf8Byte(b)) {
                return false;
            }
        }
        return true;
    }
 
    /**
     * 检测单字节,判断是否为utf8
     *
     * @param b
     * @return
     */
    private static boolean checkUtf8Byte(byte b) throws Exception {
        BitSet bitSet = convert2BitSet(b);
        return bitSet.get(0) && !bitSet.get(1);
    }
 
    /**
     * 检测bitSet中从开始有多少个连续的1
     *
     * @param bitSet
     * @return
     */
    private static int getCountOfSequential( BitSet bitSet) {
        int count = 0;
        for (int i = 0; i < BYTE_SIZE; i++) {
            if (bitSet.get(i)) {
                count++;
            } else {
                break;
            }
        }
        return count;
    }
 
 
    /**
     * 将整形转为BitSet
     *
     * @param code
     * @return
     */
    private static BitSet convert2BitSet(int code) {
        BitSet bitSet = new BitSet(BYTE_SIZE);
 
        for (int i = 0; i < BYTE_SIZE; i++) {
            int tmp3 = code >> (BYTE_SIZE - i - 1);
            int tmp2 = 0x1 & tmp3;
            if (tmp2 == 1) {
                bitSet.set(i);
            }
        }
        return bitSet;
    }
 
    /**
     * 将一指定编码的文件转换为另一编码的文件
     *
     * @param oldFullFileName
     * @param oldCharsetName
     * @param newFullFileName
     * @param newCharsetName
     */
    public static void convert(String oldFullFileName, String oldCharsetName, String newFullFileName, String newCharsetName) throws Exception {
    	logger.info("the old file name is : {}, The oldCharsetName is : {}", oldFullFileName, oldCharsetName);
    	logger.info("the new file name is : {}, The newCharsetName is : {}", newFullFileName, newCharsetName);
 
        StringBuffer content = new StringBuffer();
 
        BufferedReader bin = new BufferedReader(new InputStreamReader(new FileInputStream(oldFullFileName), oldCharsetName));
        String line;
        while ((line = bin.readLine()) != null) {
            content.append(line);
            content.append(System.getProperty("line.separator"));
        }
        newFullFileName = newFullFileName.replace("\\", "/");
        File dir = new File(newFullFileName.substring(0, newFullFileName.lastIndexOf("/")));
        if (!dir.exists()) {
            dir.mkdirs();
        }
        Writer out = new OutputStreamWriter(new FileOutputStream(newFullFileName), newCharsetName);
        out.write(content.toString());
    }
 
}


调用方式
public static void main(String[] args) {
		try {
			String filePath ="/home/zhanghy/文档/国寿/实时计算paas/ee/error/分/config/function_list.properties";
			BufferedInputStream bis = new BufferedInputStream(new FileInputStream(filePath));
			String code = EncodeUtil.getEncode(bis, false);
                        System.out.println("文件编码格式为:"+code);
		} catch (Exception e) {
			e.printStackTrace();
		}
		
	}

 

欢迎访问:www.hongfu951.com博客,查看更多技术文章

发表评论

全部评论:0条

鸿福951

努力打造一个好用的webui

热评文章

推荐文章