fc.java

海量中文分词java接口

import java.io.*;
import java.util.*;

public class fc {
	//初始化海量分词系统，加载分词用数据。
	public static synchronized native boolean HLSplitInit();

	//卸载海量自动分词系统，释放分词系统所占资源
	public static synchronized native void HLFreeSplit();

	//分词：用到的接口有：
	//HANDLE HLOpenSplit()  创建自动中文分词结果句柄。
	//bool HLSplitWord(HANDLE hHandle , LPCTSTR lpText , int iExtraCalcFlag=0)  对一段字符串分词
	//int HLGetWordCnt(HANDLE hHandle)  获得分词结果的个数
	//SHLSegWord* HLGetWordAt(HANDLE hHandle , int nIndex)  获得指定的分词结果
	//void HLCloseSplit(HANDLE hHandle) 关闭海量分词句柄
	public synchronized native String seg(byte[] text, int nWordPos,
			int nKeyWords, int nFinger, int nForSearcher);

	//0=====>没有附加计算的分词结果 int nWordPos == 0
	//1=====>结果加注词性 int nWordPos == 1
	//2=====>显示关键词的相关信息 int nKeyWords == 1
	//3=====>显示语义指纹  int nFinger == 1
	//4=====>面向检索的分词结果  int nForSearcher == 1

	//装载用户自定义词典
	public static synchronized native boolean HLOpenUsrDict(byte[] fileName);

	//卸载用户自定义词典
	public static synchronized native void HLFreeUsrDict();

	public fc() {
		fc.HLSplitInit();
	}

	public static void main(String[] args) throws IOException {
		fc fcinstance = new fc();
		String s = "", segstr = "";

		try {
			FileReader fr = new FileReader("1001.txt");
			BufferedReader br = new BufferedReader(fr);
			while ((s = br.readLine()) != null) {
				segstr += s + "\n";
			}
			fr.close();
			br.close();
		} catch (IOException ex) {
			ex.printStackTrace();
		}

		//System.out.println("result:"+fc.HLSplitInit());

		long start = System.currentTimeMillis();

		String result = fcinstance.seg(segstr.getBytes(), 1, 1, 1, 0);
		
		String[] counts = fcinstance.seg(segstr.getBytes(),0,0,0,0).split(" ");
		
		int pp = 0;
		for(int i = 0; i<counts.length; i++){
			if(counts[i].equalsIgnoreCase("人工智能"))
				pp++;
		}
		System.out.println(pp);

		long end = System.currentTimeMillis();

		fcinstance.HLFreeSplit();

		System.out.println("\n用时：" +(end - start)+"ms\n"+ result);
	}

	static {
		System.loadLibrary("fc");
	}
}