好吧，之前用的是舊版的，現在出了個新版的，優先選擇用新版的哈。

從官網下載相應的開發包，然后主要需要找到這幾個東西添加到項目工程里面，1.Data文件夾 2.NLPIR_JNI.DLL 3.NLPIR.jar 4.nlpir.properties

添加完那些東西后，需要配置的東西主要為nlpir.properties文件，大概內容如下:

dll_or_so_path=D\:\\Spiliter\\NLPIR_JNI.dll

data_dir_parent_path=.

主要要配置dll_or_so_path，里面的路徑為項目里面NLPIR_JNI.dll的絕對路徑

搞定后就可以開始寫代碼了:

package shell;

import java.io.BufferedInputStream;

import java.io.BufferedReader;

import java.io.BufferedWriter;

import java.io.File;

import java.io.FileInputStream;

import java.io.FileNotFoundException;

import java.io.FileOutputStream;

import java.io.FileReader;

import java.io.IOException;

import java.io.InputStream;

import java.io.InputStreamReader;

import java.io.OutputStreamWriter;

import java.io.UnsupportedEncodingException;

import java.io.Writer;

import java.net.URI;

import java.net.URISyntaxException;

import java.util.Properties;

import kevin.zhang.NLPIR;

public class Spliter {

NLPIR nlpir = null;

public Spliter(){

this.nlpir = new NLPIR();

String argu = "././";

try {

if (this.nlpir.NLPIR_Init(argu.getBytes("GB2312"),0,"0".getBytes("GB2312")) == false){

System.out.println("init failed");

}

} catch (UnsupportedEncodingException e) {

e.printStackTrace();

}

}

public void SliptFile(String file,int tag){

String encoding = "utf8";

try {

String of = file.replace(".", "_new.");

FileOutputStream out = null;

out = new FileOutputStream(new File(of));

InputStreamReader read = new InputStreamReader(new FileInputStream(file), encoding);

BufferedReader bw = new BufferedReader(read);

String line = null;

while((line = bw.readLine()) != null){

System.out.println(line);

String newLine = getSplitString(line,tag);

out.write((newLine + "\r\n").getBytes("utf8") );

}

bw.close();

out.close();

} catch (FileNotFoundException e) {

// TODO Auto-generated catch block

e.printStackTrace();

} catch (IOException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

}

public String getSplitString(String text,int tag){

String splitStr = null;

byte nativeBytes[];

try {

nativeBytes = nlpir.NLPIR_ParagraphProcess(text.getBytes("gbk"), tag);

//因為分詞是用c++編寫的所以最后有一個\0，這邊就不需要了，不然轉碼有問題的

splitStr = new String(nativeBytes, 0, nativeBytes.length - 1, "gbk");

System.out.println("分詞結果為： " + splitStr);

} catch (UnsupportedEncodingException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

return splitStr;

}

public static void main(String[] args){

Spliter s = new Spliter();

s.SliptFile("d:\\w.txt",0);

}

}