Android--推断文本文件编码

方法1：利用windows文本文件编码特点。

windows下。Unicode、Unicode big endian和UTF-8编码的txt文件的开头会多出几个字节，各自是FF、FE（Unicode）,FE、FF（Unicode big endian）,EF、BB、BF（UTF-8）。

public static String getCharset(File file) {
        String charset = "GBK";
        byte[] first3Bytes = new byte[3];
        try {
            boolean checked = false;
            BufferedInputStream bis = new BufferedInputStream(
                  new FileInputStream(file));
            bis.mark(0);
            int read = bis.read(first3Bytes, 0, 3);
            if (read == -1)
                return charset;
            if (first3Bytes[0] == (byte) 0xFF && first3Bytes[1] == (byte) 0xFE) {
                charset = "UTF-16LE";
                checked = true;
            } else if (first3Bytes[0] == (byte) 0xFE && first3Bytes[1]
                == (byte) 0xFF) {
                charset = "UTF-16BE";
                checked = true;
            } else if (first3Bytes[0] == (byte) 0xEF && first3Bytes[1]
                    == (byte) 0xBB
                    && first3Bytes[2] == (byte) 0xBF) {
                charset = "UTF-8";
                checked = true;
            }
            bis.reset();
            if (!checked) {
                int loc = 0;
                while ((read = bis.read()) != -1) {
                    loc++;
                    if (read >= 0xF0)
                        break;
                    //单独出现BF下面的。也算是GBK
                    if (0x80 <= read && read <= 0xBF)
                        break;
                    if (0xC0 <= read && read <= 0xDF) {
                        read = bis.read();
                        if (0x80 <= read && read <= 0xBF)// 双字节 (0xC0 - 0xDF)
                            // (0x80 -
                            // 0xBF),也可能在GB编码内
                            continue;
                        else
                            break;
                     // 也有可能出错，可是几率较小
                    } else if (0xE0 <= read && read <= 0xEF) {
                        read = bis.read();
                        if (0x80 <= read && read <= 0xBF) {
                            read = bis.read();
                            if (0x80 <= read && read <= 0xBF) {
                                charset = "UTF-8";
                                break;
                            } else
                                break;
                        } else
                            break;
                    }
                }
                System.out.println(loc + " " + Integer.toHexString(read));
            }
            bis.close();
        } catch (Exception e) {
            e.printStackTrace();
        }
        return charset;
    }

缺点：不能这样去探測linux下的文件。

方法2：开源project JCharDet

http://www.iteye.com/topic/266501

package org.mozilla.intl.chardet;

import java.io.BufferedInputStream;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileNotFoundException;
import java.io.IOException;

/**
 * 借助JCharDet获取文件字符集
 * @author icer
 * PS:
 * JCharDet 是mozilla自己主动字符集探測算法代码的java移植，其官方主页为：
 *      http://jchardet.sourceforge.net/
 * @date	2008/11/13
 */
public class FileCharsetDetector {

	private boolean found = false;

	/**
	 * 假设全然匹配某个字符集检測算法, 则该属性保存该字符集的名称. 否则(如二进制文件)其值就为默认值 null, 这时应当查询属性
	 */
	private String encoding = null;

	public static void main(String[] argv) throws Exception {
		if (argv.length != 1 && argv.length != 2) {

			System.out
					.println("Usage: FileCharsetDetector <path> [<languageHint>]");

			System.out.println("");
			System.out.println("Where <path> is d:/demo.txt");
			System.out.println("For optional <languageHint>. Use following...");
			System.out.println("		1 => Japanese");
			System.out.println("		2 => Chinese");
			System.out.println("		3 => Simplified Chinese");
			System.out.println("		4 => Traditional Chinese");
			System.out.println("		5 => Korean");
			System.out.println("		6 => Dont know (default)");

			return;
		} else {
			String encoding = null;
			if (argv.length == 2) {
				encoding = new FileCharsetDetector().guestFileEncoding(argv[0],
						Integer.valueOf(argv[1]));
			} else {
				encoding = new FileCharsetDetector().guestFileEncoding(argv[0]);
			}
			System.out.println("文件编码:" + encoding);
		}
	}

	/**
	 * 传入一个文件(File)对象，检查文件编码
	 *
	 * @param file
	 *            File对象实例
	 * @return 文件编码。若无，则返回null
	 * @throws FileNotFoundException
	 * @throws IOException
	 */
	public String guestFileEncoding(File file) throws FileNotFoundException,
			IOException {
		return geestFileEncoding(file, new nsDetector());
	}

	/**
	 * 获取文件的编码
	 *
	 * @param file
	 *            File对象实例
	 * @param languageHint
	 *            语言提示区域代码 eg：1 : Japanese; 2 : Chinese; 3 : Simplified Chinese;
	 *            4 : Traditional Chinese; 5 : Korean; 6 : Dont know (default)
	 * @return 文件编码，eg：UTF-8,GBK,GB2312形式。若无，则返回null
	 * @throws FileNotFoundException
	 * @throws IOException
	 */
	public String guestFileEncoding(File file, int languageHint)
			throws FileNotFoundException, IOException {
		return geestFileEncoding(file, new nsDetector(languageHint));
	}

	/**
	 * 获取文件的编码
	 *
	 * @param path
	 *            文件路径
	 * @return 文件编码，eg：UTF-8,GBK,GB2312形式，若无。则返回null
	 * @throws FileNotFoundException
	 * @throws IOException
	 */
	public String guestFileEncoding(String path) throws FileNotFoundException,
			IOException {
		return guestFileEncoding(new File(path));
	}

	/**
	 * 获取文件的编码
	 *
	 * @param path
	 *            文件路径
	 * @param languageHint
	 *            语言提示区域代码 eg：1 : Japanese; 2 : Chinese; 3 : Simplified Chinese;
	 *            4 : Traditional Chinese; 5 : Korean; 6 : Dont know (default)
	 * @return
	 * @throws FileNotFoundException
	 * @throws IOException
	 */
	public String guestFileEncoding(String path, int languageHint)
			throws FileNotFoundException, IOException {
		return guestFileEncoding(new File(path), languageHint);
	}

	/**
	 * 获取文件的编码
	 *
	 * @param file
	 * @param det
	 * @return
	 * @throws FileNotFoundException
	 * @throws IOException
	 */
	private String geestFileEncoding(File file, nsDetector det)
			throws FileNotFoundException, IOException {
		// Set an observer...
		// The Notify() will be called when a matching charset is found.
		det.Init(new nsICharsetDetectionObserver() {
			public void Notify(String charset) {
				found = true;
				encoding = charset;
			}
		});

		BufferedInputStream imp = new BufferedInputStream(new FileInputStream(
				file));

		byte[] buf = new byte[1024];
		int len;
		boolean done = false;
		boolean isAscii = true;

		while ((len = imp.read(buf, 0, buf.length)) != -1) {
			// Check if the stream is only ascii.
			if (isAscii)
				isAscii = det.isAscii(buf, len);

			// DoIt if non-ascii and not done yet.
			if (!isAscii && !done)
				done = det.DoIt(buf, len, false);
		}
		det.DataEnd();

		if (isAscii) {
			encoding = "ASCII";
			found = true;
		}

		if (!found) {
			String prob[] = det.getProbableCharsets();
			if (prob.length > 0) {
				// 在没有发现情况下，则取第一个可能的编码
				encoding = prob[0];
			} else {
				return null;
			}
		}
		return encoding;
	}
}

jar包下载地址：http://download.csdn.net/detail/u012587637/8047697

方法3：开源projectjuniversalcharde

http://code.google.com/p/juniversalchardet/

public static String getFileIncode(File file) {

		if (!file.exists()) {
			System.err.println("getFileIncode: file not exists!");
			return null;
		}

		byte[] buf = new byte[4096];
		FileInputStream fis = null;
		try {
			fis = new FileInputStream(file);
			// (1)
			UniversalDetector detector = new UniversalDetector(null);

			// (2)
			int nread;
			while ((nread = fis.read(buf)) > 0 && !detector.isDone()) {
				detector.handleData(buf, 0, nread);
			}
			// (3)
			detector.dataEnd();

			// (4)
			String encoding = detector.getDetectedCharset();
			if (encoding != null) {
				System.out.println("Detected encoding = " + encoding);
			} else {
				System.out.println("No encoding detected.");
			}

			// (5)
			detector.reset();
			fis.close();
			return encoding;
		} catch (Exception e) {
			e.printStackTrace();
		}

		return null;
	}

引入包的方法：

将包放入libs目录。

选中包，右键 --> build path--> add to build path。

jar包下载：http://download.csdn.net/detail/u012587637/8041181

说明：第三个方法要比第二个速度快些，也比較新，所以推荐使用第三个。