码迷,mamicode.com
首页 > 编程语言 > 详细

java UTF-8 和 UTF-8 without BOM工具处理类

时间:2014-08-27 16:39:28      阅读:262      评论:0      收藏:0      [点我收藏+]

标签:os   java   io   for   ar   amp   sp   on   new   

package org.shefron.fc.utfwithbom;

import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.io.PushbackInputStream;

public class UTFFileHandler {

	/**
	 *
	 * @param file the filePath
	 * @return the FileInputStream
	 * @throws Exception
	 */
	public static InputStream getInputStream(String file) throws Exception{
		FileInputStream fis = null;
		try{
			fis = new FileInputStream(file);
		}catch(Exception e){
			System.out.println(e.getMessage());
			throw new Exception("IO Stream Error!");
		}
		return fis;

	}

	/**
	 *
	 * @param file the filePath
	 * @param enc  the default encoding
	 * @return the UTFFileHandler.UnicodeInputStream
	 * @throws Exception
	 */
	public static InputStream getInputStreamWithoutBom(String file,String enc) throws Exception{

		UnicodeInputStream stream = null;
		try{
			FileInputStream fis = new FileInputStream(file);
			stream = new UnicodeInputStream(fis,null);
			System.out.println("encoding:"+stream.getEncoding() );
		}catch(Exception e){
			System.out.println(e.getMessage());
			throw new Exception("IO Stream Error!");
		}
		return stream;

	}

	/**
	 * This inputstream will recognize unicode BOM marks and will skip bytes if
	 * getEncoding() method is called before any of the read(...) methods.
	 *
	 * Usage pattern: String enc = "ISO-8859-1"; // or NULL to use systemdefault
	 * FileInputStream fis = new FileInputStream(file); UnicodeInputStream uin = new
	 * UnicodeInputStream(fis, enc); enc = uin.getEncoding(); // check and skip
	 * possible BOM bytes InputStreamReader in; if (enc == null) in = new
	 * InputStreamReader(uin); else in = new InputStreamReader(uin, enc);
	 */
	public static class UnicodeInputStream extends InputStream {
	    PushbackInputStream internalIn;
	    boolean isInited = false;
	    String defaultEnc;
	    String encoding;

	    private static final int BOM_SIZE = 4;

	    public UnicodeInputStream(InputStream in, String defaultEnc) {
	        internalIn = new PushbackInputStream(in, BOM_SIZE);
	        this.defaultEnc = defaultEnc;
	    }

	    public String getDefaultEncoding() {
	        return defaultEnc;
	    }

	    public String getEncoding() {
	        if (!isInited) {
	            try {
	                init();
	            } catch (IOException ex) {
	                IllegalStateException ise = new IllegalStateException(
	                        "Init method failed.");
	                ise.initCause(ise);
	                throw ise;
	            }
	        }
	        return encoding;
	    }

	    /**
	     * Read-ahead four bytes and check for BOM marks. Extra bytes are unread
	     * back to the stream, only BOM bytes are skipped.
	     */
	    protected void init() throws IOException {
	        if (isInited)
	            return;

	        byte bom[] = new byte[BOM_SIZE];
	        int n, unread;
	        n = internalIn.read(bom, 0, bom.length);

	        if ((bom[0] == (byte) 0x00) && (bom[1] == (byte) 0x00)
	                && (bom[2] == (byte) 0xFE) && (bom[3] == (byte) 0xFF)) {
	            encoding = "UTF-32BE";
	            unread = n - 4;
	        } else if ((bom[0] == (byte) 0xFF) && (bom[1] == (byte) 0xFE)
	                && (bom[2] == (byte) 0x00) && (bom[3] == (byte) 0x00)) {
	            encoding = "UTF-32LE";
	            unread = n - 4;
	        } else if ((bom[0] == (byte) 0xEF) && (bom[1] == (byte) 0xBB)
	                && (bom[2] == (byte) 0xBF)) {
	            encoding = "UTF-8";
	            unread = n - 3;
	        } else if ((bom[0] == (byte) 0xFE) && (bom[1] == (byte) 0xFF)) {
	            encoding = "UTF-16BE";
	            unread = n - 2;
	        } else if ((bom[0] == (byte) 0xFF) && (bom[1] == (byte) 0xFE)) {
	            encoding = "UTF-16LE";
	            unread = n - 2;
	        } else {
	            // Unicode BOM mark not found, unread all bytes
	            encoding = defaultEnc;
	            unread = n;
	        }
	        // System.out.println("read=" + n + ", unread=" + unread);

	        if (unread > 0)
	            internalIn.unread(bom, (n - unread), unread);

	        isInited = true;
	    }

	    public void close() throws IOException {
	        // init();
//	        isInited = true;
	        internalIn.close();
	    }

	    public int read() throws IOException {
	        // init();
//	        isInited = true;
	        return internalIn.read();
	    }
	}

}


 

java UTF-8 和 UTF-8 without BOM工具处理类

标签:os   java   io   for   ar   amp   sp   on   new   

原文地址:http://blog.csdn.net/shefron/article/details/38871857

(0)
(0)
   
举报
评论 一句话评论(0
登录后才能评论!
© 2014 mamicode.com 版权所有  联系我们:gaon5@hotmail.com
迷上了代码!