文本聚类引擎¶

package clusterApiExample;

import org.json.JSONArray;
import org.json.JSONException;
import org.json.JSONObject;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStreamReader;

import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.JsonNode;
import com.mashape.unirest.http.Unirest;
import com.mashape.unirest.http.exceptions.UnirestException;

public class ClusterApiExample {
    // 请把TASK_ID换成您自己的ID
    public static final String CLUSTER_PUSH = "http://api.bosonnlp.com/cluster/push/TASK_ID";
    public static final String CLUSTER_ANALYSIS = "http://api.bosonnlp.com/cluster/analysis/TASK_ID";
    public static final String CLUSTER_STATUS = "http://api.bosonnlp.com/cluster/status/TASK_ID";
    public static final String CLUSTER_RESULT = "http://api.bosonnlp.com/cluster/result/TASK_ID";
    public static final String CLUSTER_CLEAR = "http://api.bosonnlp.com/cluster/clear/TASK_ID";
    // 请记得把 YOUR_API_TOKEN 换成您申请的 Token
    public static final String API_TOKEN = "YOUR_API_TOKEN";
    public static String filePath = "clusterInfos.txt";
    public static boolean flag;
    public static void main(String[] args) throws JSONException,
                                                  UnirestException, IOException {
        // 读取根目录下的clusterInfos.txt文件里的内容作为聚类上传的数据，请根据自身需求做更改
        flag = readTxtFile(filePath);

        // 聚类分析API调用
        HttpResponse<String> clusterAnalysisResponse = Unirest
            .get(CLUSTER_ANALYSIS)
            .header("Accept", "application/json")
            .header("X-Token", API_TOKEN)
            .asString();
        System.out.println(clusterAnalysisResponse.getCode());

        // 调用查看状态的API来查看任务处理进度，这里每隔一段时间查询一次
        while (flag) {
            // 聚类状态API调用
            HttpResponse<String> clusterStatusResponse = Unirest
                .get(CLUSTER_STATUS)
                .header("Accept", "application/json")
                .header("X-Token", API_TOKEN)
                .asString();
            JSONObject jsonObj = new JSONObject(clusterStatusResponse.getBody());
            String status = (String) jsonObj.get("status");

            try{
                Thread.sleep(2000);
            }catch(InterruptedException ie){
                ie.printStackTrace();
            }

            System.out.println(status);
            if ("DONE".equals(status)) {
                flag = false;
            }
            else
                System.out.println("请稍等，数据处理中...");
        }

        // 聚类结果API调用
        HttpResponse<JsonNode> clusterResultResponse = Unirest
            .get(CLUSTER_RESULT)
            .header("Accept", "application/json")
            .header("X-Token", API_TOKEN)
            .asJson();
        System.out.println("以下是返回的结果：");
        System.out.println(clusterResultResponse.getBody());

        // 聚类清除API调用
        HttpResponse<String> clusterClearResponse = Unirest
            .get(CLUSTER_CLEAR)
            .header("Accept", "application/json")
            .header("X-Token", API_TOKEN)
            .asString();
        // 返回的结果是一段JSON，num 指该 cluster 包含的文档数目，_id 指该 cluster最具代表性的文档
	// list 指所有属于该 cluster 的文档 _id
        System.out.println(clusterClearResponse.getBody());
    }

    public static boolean readTxtFile(String filePath ) {
        try {
            String encoding = "utf-8";
            File file = new File(filePath);
            if (file.isFile() && file.exists()) { // 判断文件是否存在
                InputStreamReader reader = new InputStreamReader(new FileInputStream(file), encoding);
                BufferedReader bufferedReader = new BufferedReader(reader);
                String lineTxt = null;
                int i = 0;
                while ((lineTxt = bufferedReader.readLine()) != null) {
                    System.out.println(i);
                    JSONArray jsonArray = new JSONArray();
                    JSONObject jsonObject = new JSONObject();
                    jsonObject.put("_id", ++i);
                    jsonObject.put("text", lineTxt);
                    jsonArray.put(jsonObject);
                    String body = jsonArray.toString();
                    System.out.println(body);

                    // 聚类上传API调用
                    // 上传的数据时JSON格式的，必须包含_id(文档的编号，可以采用整数或字符串)和text(文档的内容，原始的文章信息)
                    HttpResponse<JsonNode> clusterPushResponse = Unirest.post(CLUSTER_PUSH)
                        .header("Accept", "application/json")
                        .header("Content-Type","application/json")
                        .header("X-Token", API_TOKEN)
                        .body(body).asJson();
                }
                reader.close();
                return true;
            }else{
                System.out.println("找不到指定的文件");
                return false;
            }
        } catch (Exception e) {
            System.out.println("读取文件内容出错");
            e.printStackTrace();
            return false;
        }
    }
}