test.java

重新写的海量分词研究版的JNI程序

package test;

import java.io.*;
import java.net.URLEncoder;
import sun.io.ByteToCharConverter;
import sun.io.CharToByteConverter;

import hl.fc;

//CharToByteConverter  and   ByteToCharConverter
public class test {		
	public static void main(String[] argv)throws Exception{
		fc myfc = new fc();
		String fileName = "2.txt";
		String encoding="GB2312";			
		String segstr ="",s="";		
		try {
			RandomAccessFile fr = new RandomAccessFile(fileName,"r");
			String tmp = "";
			long fileLength = fr.length();
			byte[] buffer = new byte[(int)fileLength];
			int ch;
			while ((ch = fr.read(buffer)) != -1) {
				segstr += new String(buffer,0,ch,encoding);
			}
			fr.close();
		} catch (IOException ex) {
			ex.printStackTrace();
		}		
		//System.out.println(segstr);
		String resultStr = myfc.seg(segstr.getBytes(), 1, 1, 1, 0);
		//String resultStr = myfc.seg(segstr.getBytes(), 1, 0, 0, 0);
		System.out.println(resultStr);
		
		String tmpStr = "浠庡皬瀛︽瘯涓氾紝浠庡皬瀛︾數鑴戯紒";
		String result = myfc.seg(tmpStr.getBytes(), 1, 0, 0, 0);
		System.out.println(result.substring(result.indexOf(myfc.pos)+myfc.pos.length()));
		
		result = myfc.seg("鎴戣禐鎴愬畨涔愭