java操作ES

package com.test.es;

import java.io.File;

import java.io.FileInputStream;

import java.io.InputStream;

import java.net.InetAddress;

import java.text.SimpleDateFormat;

import java.util.Date;

import java.util.HashMap;

import java.util.Map;

import org.apache.poi.xssf.usermodel.XSSFCell;

import org.apache.poi.xssf.usermodel.XSSFRow;

import org.apache.poi.xssf.usermodel.XSSFSheet;

import org.apache.poi.xssf.usermodel.XSSFWorkbook;

import org.elasticsearch.action.admin.indices.exists.indices.IndicesExistsResponse;

import org.elasticsearch.action.admin.indices.mapping.put.PutMappingRequest;

import org.elasticsearch.action.search.SearchResponse;

import org.elasticsearch.client.Client;

import org.elasticsearch.client.Requests;

import org.elasticsearch.client.transport.TransportClient;

import org.elasticsearch.common.settings.Settings;

import org.elasticsearch.common.text.Text;

import org.elasticsearch.common.transport.InetSocketTransportAddress;

import org.elasticsearch.common.xcontent.XContentBuilder;

import org.elasticsearch.common.xcontent.XContentFactory;

import org.elasticsearch.index.query.MultiMatchQueryBuilder;

import org.elasticsearch.index.query.QueryStringQueryBuilder;

import org.elasticsearch.search.SearchHit;

import org.elasticsearch.search.SearchHits;

import org.junit.Test;

import org.springframework.stereotype.Service;

@Service

public class IndexService {

//存放html文件的目录

public static String DATA_DIR="D:\\javaTool\\20180116-e.xlsx";//中文数据：20180116-c.xlsx 英文数据:20180116-e.xlsx

public static Client client;

static {

Settings settings = Settings.settingsBuilder()

.put("cluster.name", "es-hww").build();//链接服务器名称

try {

client = TransportClient

.builder()

.settings(settings)

.build()

.addTransportAddress(

new InetSocketTransportAddress(InetAddress

.getByName("192.168.12.114"), 9300)) //服务器的第一个节点服务器

.addTransportAddress(

new InetSocketTransportAddress(InetAddress

.getByName("192.168.12.115"), 9300)) //服务器的第二个节点服务器

.addTransportAddress(

new InetSocketTransportAddress(InetAddress

.getByName("192.168.12.116"), 9300)); //服务器的第三个节点服务器

} catch (Exception e) {

e.printStackTrace();

}

}

/**

* admin():管理索引库的。client.admin().indices()

*

* 索引数据的管理：client.prepare

*

*/

@Test

public void createIndex() throws Exception {

IndicesExistsResponse resp = client.admin().indices().prepareExists("hww-opinion").execute().actionGet();

if(resp.isExists()){ //先查询有没有该索引库，有就删除

client.admin().indices().prepareDelete("hww-opinion").execute().actionGet();

}

client.admin().indices().prepareCreate("hww-opinion").execute().actionGet();//没有就创建

new XContentFactory(); //处理web2.5兼容

//创建索引 基本都是固定格式

XContentBuilder builder = XContentFactory.jsonBuilder().startObject()

.startObject("htmlbean")

.startObject("properties")

.startObject("url").field("type", "string")//链接地址

.endObject()

.startObject("title").field("type", "string")//标题

.field("analyzer", "ik_max_word")

.field("search_analyzer", "ik_max_word")

.endObject()

.startObject("author").field("type", "string")//作者

.field("index", "not_analyzed")//设置不

.endObject()

.startObject("introduction").field("type", "string")//简介

.field("analyzer", "ik_max_word")

.field("search_analyzer", "ik_max_word")

.endObject()

.startObject("content").field("type", "string")//内容

.field("analyzer", "ik_max_word")

.field("search_analyzer", "ik_max_word")

.endObject()

.startObject("publishDate").field("type", "string")//时间

.field("index", "not_analyzed")

.endObject()

.startObject("mediaType").field("type", "string")//媒体类型

.field("index", "not_analyzed")

.endObject()

.startObject("area").field("type", "string")//地区

.field("index", "not_analyzed")

.endObject()

.startObject("attribute").field("type", "string")//舆情属性

.field("index", "not_analyzed")

.endObject()

.startObject("languages").field("type", "string")//语种

.field("index", "not_analyzed")

.endObject()

.startObject("source").field("type", "string")//来源

.field("index", "not_analyzed")

.endObject()

.endObject().endObject().endObject();

PutMappingRequest mapping = Requests.putMappingRequest("hww-opinion").type("htmlbean").source(builder);

client.admin().indices().putMapping(mapping).actionGet();

}

/**

* 把源数据html文件添加到索引库中（构建索引文件）

*/

@Test

public void addHtmlToES(){

try {

readExcel(new File(DATA_DIR));

} catch (Exception e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

}

/**

* @param 读取Excel

* @throws Exception

*/

public void readExcel(File file) throws Exception{

InputStream is = new FileInputStream(file);

XSSFWorkbook xssfWorkbook = new XSSFWorkbook(is);

// 获取每一个工作薄

for (int numSheet = 0; numSheet < xssfWorkbook.getNumberOfSheets(); numSheet++) {

XSSFSheet xssfSheet = xssfWorkbook.getSheetAt(numSheet);

if (xssfSheet == null) {

continue;

}

int num=0;//计数

// 获取当前工作薄的每一行

for (int rowNum = 1; rowNum <= xssfSheet.getLastRowNum(); rowNum++) {

XSSFRow xssfRow = xssfSheet.getRow(rowNum);

if (xssfRow != null) {

num++;

XSSFCell one = xssfRow.getCell(0);

//读取第一列数据

XSSFCell two = xssfRow.getCell(1);

//读取第二列数据

XSSFCell three = xssfRow.getCell(2);

//读取第三列数据

XSSFCell four = xssfRow.getCell(3);

XSSFCell five = xssfRow.getCell(4);

//需要转换数据的话直接调用getValue获取字符串

Map<String, String> dataMap =new HashMap<String, String>();

dataMap.put("url", one==null?"":one.toString());//链接地址

dataMap.put("title", two==null?"":two.toString());//标题

dataMap.put("author", three==null?"":three.toString());//作者

dataMap.put("introduction", four==null?"":four.toString());//简介

dataMap.put("content", five==null?"":five.toString());//内容

Date date = new Date();

SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");

String createdate = sdf.format(date);

dataMap.put("publishDate", createdate);//发布时间

dataMap.put("mediaType", "新闻");//媒体属性

dataMap.put("area", "东京");//地区

dataMap.put("attribute", "正面");//舆情属性

dataMap.put("languages", "英文");//语种

dataMap.put("source", "人民网");//来源

//写索引

client.prepareIndex("hww-opinion", "htmlbean").setSource(dataMap).execute().actionGet();

System.out.println(num+"===================");

}

}

}

}

//转换数据格式

private String getValue(XSSFCell xssfRow) {

if (xssfRow.getCellType() == xssfRow.CELL_TYPE_BOOLEAN) {

return String.valueOf(xssfRow.getBooleanCellValue());

} else if (xssfRow.getCellType() == xssfRow.CELL_TYPE_NUMERIC) {

return String.valueOf(xssfRow.getNumericCellValue());

} else {

return String.valueOf(xssfRow.getStringCellValue());

}

}

/**

* 搜索

* @param kw

* @param num 当前第几页

* @return

* @throws Exception

*/

public PageBean<HWWHtmlBean> search(String kw,int num,int count) throws Exception{

PageBean<HWWHtmlBean> wr =new PageBean<HWWHtmlBean>();

wr.setIndex(num);

// //构建查询条件

// MatchQueryBuilder q1 =new MatchQueryBuilder("title", kw);

// MatchQueryBuilder q2 =new MatchQueryBuilder("content", kw);

//

// //构建一个多条件查询对象

// BoolQueryBuilder q =new BoolQueryBuilder(); //组合查询条件对象

// q.should(q1);

// q.should(q2);

// RangeQueryBuilder q1 =new RangeQueryBuilder("age");

// q1.from(18);

// q1.to(40);

//q为要查询的数据

// QueryStringQueryBuilder q = new QueryStringQueryBuilder(kw);

//analyzer为ik分词,即输入的keywords通过ik进行分词。

//查询的字段为title和content

// q.analyzer("ik").field("title").field("content");

MultiMatchQueryBuilder q =new MultiMatchQueryBuilder(kw, new String[]{"area","content"});

SearchResponse resp=null;

if(wr.getIndex()==1){

resp = client.prepareSearch("hww-opinion")

.setTypes("htmlbean")

.setQuery(q)

.addHighlightedField("title")

.addHighlightedField("content")

.setHighlighterPreTags("<font color=\"red\">")

.setHighlighterPostTags("</font>")

.setHighlighterFragmentSize(14)//设置显示结果中一个碎片段的长度

.setHighlighterNumOfFragments(3)//设置显示结果中每个结果最多显示碎片段，每个碎片段之间用...隔开

.setFrom(0)

.setSize(10)

.execute().actionGet();

}else{

wr.setTotalCount(count);

resp = client.prepareSearch("hww-opinion")

.setTypes("htmlbean")

.setQuery(q)

.addHighlightedField("title")

.addHighlightedField("content")

.setHighlighterPreTags("<font color=\"red\">")

.setHighlighterPostTags("</font>")

.setHighlighterFragmentSize(14)

.setHighlighterNumOfFragments(3)

.setFrom(wr.getStartRow())

.setSize(10)

.execute().actionGet();

}

SearchHits hits= resp.getHits();

wr.setTotalCount((int)hits.getTotalHits());

for(SearchHit hit : hits.getHits()){

HWWHtmlBean bean =new HWWHtmlBean();

if(hit.getHighlightFields().get("title")==null){//title中没有包含关键字

bean.setTitle(hit.getSource().get("title").toString());//获取原来的title（没有高亮的title）

}else{

bean.setTitle(hit.getHighlightFields().get("title").getFragments()[0].toString());

}

if(hit.getHighlightFields().get("content")==null){//content中没有包含关键字

bean.setContent(hit.getSource().get("content").toString());//获取原来的content（没有高亮的content）

}else{

StringBuilder sb =new StringBuilder();

for(Text text: hit.getHighlightFields().get("content").getFragments()){

sb.append(text.toString()+"...");

}

bean.setContent(sb.toString());

}

bean.setUrl(hit.getSource().get("url").toString());

wr.setBean(bean);

}

return wr;

}

}