Solr初嘗試

時間 2019-11-22

標籤 solr 嘗試简体版

原文原文鏈接

準備Solr

下載運行solr

建立一個庫：

solr create -c mycore

簡單實例

package com.util;

import java.io.IOException;

import java.util.ArrayList;

import java.util.Collection;

import java.util.HashMap;

import java.util.UUID;

import org.apache.solr.client.solrj.SolrQuery;

import org.apache.solr.client.solrj.SolrServerException;

import org.apache.solr.client.solrj.impl.HttpSolrClient;

import org.apache.solr.client.solrj.request.UpdateRequest;

import org.apache.solr.client.solrj.response.QueryResponse;

import org.apache.solr.client.solrj.response.UpdateResponse;

import org.apache.solr.common.SolrDocumentList;

import org.apache.solr.common.SolrInputDocument;

public class SolrjUtil {

//solr 服務器地址

private String solrUrl;

//操做工具

private HttpSolrClient client;

//zookeeper 服務地址（咱們這邊能夠不用）

private String zkUrl;

private String collectionName;

/**

* 構造器

* @param solrUrl

* @param num

public SolrjUtil(String solrUrl, int num) {

this.solrUrl = solrUrl;

this.client = createNewSolrClient();

}

// public SolrjUtil(String zkUrl, int num, String collection) {

// this.zkUrl = zkUrl;

// this.num = num;

// collectionName = collection;

// this.client = createCouldSolrClient();

// }

/**

* @return

private HttpSolrClient createNewSolrClient() {

try {

System.out.println("server address:" + solrUrl);

HttpSolrClient client = new HttpSolrClient(solrUrl);

client.setConnectionTimeout(30000);

client.setDefaultMaxConnectionsPerHost(100);

client.setMaxTotalConnections(100);

client.setSoTimeout(30000);

return client;

} catch (Exception ex) {

throw new RuntimeException(ex);

}

// private SolrClient createCouldSolrClient() {

// CloudSolrClient client = new CloudSolrClient(zkUrl);

// client.setZkClientTimeout(30000);

// client.setZkConnectTimeout(50000);

// client.setDefaultCollection(collectionName);

// return client;

// }

/**

* client關閉方法

public void close() {

try {

client.close();

} catch (IOException e) {

e.printStackTrace();

}

/**

* 建立一個測試文檔

public void createOneDoc() {

System.out.println("======================add doc ===================");

SolrInputDocument doc1 = new SolrInputDocument();

doc1.addField("id", UUID.randomUUID().toString(), 1.0f);

doc1.addField("name", "bean");

doc1.addField("equIP_s", "192.168.2.104");

doc1.addField("level_s", "4");

doc1.addField("collectPro_s", "ffffffffffffffffffffjajajajajajdddddddddd");

doc1.addField("sourceType_s", "miaohqaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa");

doc1.addField("filePath_s", "/home/xxxx/test");

doc1.addField("filename_s", "zhonggggmaiaiadadadddddddddddddddddddddddddd");// doc1.addField("_route_",

// "shard1");

try {

UpdateResponse rsp = client.add(doc1);

System.out

.println("Add doc size 1, result:" + rsp.getStatus() + " Qtime:" + rsp.getQTime());

UpdateResponse rspcommit = client.commit();

System.out.println("commit doc to index" + " result:" + rsp.getStatus() + " Qtime:" + rsp.getQTime());

} catch (SolrServerException | IOException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

/**

* 批量建立測試文檔

* 這裏須要作：考慮傳遞多參數仍是引用對象，並修改該方法

* @param num 建立文檔的數量

public void createDocs(int num) {

System.out.println("======================add doc ===================");

Collection<SolrInputDocument> docs = new ArrayList<SolrInputDocument>();

for (int i = 1; i <= num; i++) {

SolrInputDocument doc1 = new SolrInputDocument();

doc1.addField("id", UUID.randomUUID().toString(), 1.0f);

doc1.addField("name", "bean");

doc1.addField("equIP_s", "192.168.2.104");

doc1.addField("level_s", "4");

doc1.addField("collectPro_s", "ffffffffffffffffffffjajajajajajdddddddddd");

doc1.addField("sourceType_s", "miaohqaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa");

doc1.addField("filePath_s", "/home/xxxx/test");

doc1.addField("filename_s", "zhonggggmaiaiadadadddddddddddddddddddddddddd");// doc1.addField("_route_",

// "shard1");

docs.add(doc1);

}

try {

UpdateResponse rsp = client.add(docs);

System.out

.println("Add doc size" + docs.size() + " result:" + rsp.getStatus() + " Qtime:" + rsp.getQTime());

UpdateResponse rspcommit = client.commit();

System.out.println("commit doc to index" + " result:" + rsp.getStatus() + " Qtime:" + rsp.getQTime());

} catch (SolrServerException | IOException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

/**

* 根據id刪除

* @param id

public void deleteById(String id) {

System.out.println("======================deleteById ===================");

try {

UpdateResponse rsp = client.deleteById(id);

client.commit();

System.out.println("delete id:" + id + " result:" + rsp.getStatus() + " Qtime:" + rsp.getQTime());

} catch (SolrServerException | IOException e) {

e.printStackTrace();

}

/**

* 根據屬性刪除

* @param queryCon

public void deleteByQuery(String queryCon) {

System.out.println("======================deleteByQuery ===================");

UpdateResponse rsp;

try {

UpdateRequest commit = new UpdateRequest();

commit.deleteByQuery(queryCon);

commit.setCommitWithin(5000);

commit.process(client);

System.out

.println("url:" + commit.getPath() + "\t xml:" + commit.getXML() + " method:" + commit.getMethod());

// rsp = client.deleteByQuery(queryCon);

// client.commit();

// System.out.println("delete query:" + queryCon + " result:" + rsp.getStatus()

// + " Qtime:" + rsp.getQTime());

} catch (SolrServerException | IOException e) {

// TODO Auto-generated catch block

e.printStackTrace();

}

/**

* 查詢方法1

* @throws Exception

public void query1000() throws Exception {

SolrQuery query = new SolrQuery();

query.setQuery("*:*");

query.setStart(0);// 開始記錄數

query.setRows(10000);// 總條數

QueryResponse queryResponse = client.query(query);

SolrDocumentList results = queryResponse.getResults();

System.out.println("總條數爲：" + results.getNumFound());

for (int i = 0; i < results.size(); i++) {

System.out.println(results.get(i).getFieldNames());

for (String name : results.get(i).getFieldNames()) {

System.out.println(results.get(i).getFieldValue(name));

}

/**

* 查詢方法2

public void queryDocs() {

SolrQuery params = new SolrQuery();

System.out.println("======================query===================");

// params.setQuery("name:bean");

// params.setQuery("level_s:4");

params.set("q", "name:bean");

params.set("start", 0);

params.set("rows", 2);

params.set("sort", "accesstime_s desc");

try {

QueryResponse rsp = client.query(params);

SolrDocumentList docs = rsp.getResults();

System.out.println("查詢內容:" + params);

System.out.println("文檔數量：" + docs.getNumFound());

System.out.println("查詢花費時間:" + rsp.getQTime());

System.out.println("------query data:------");

// for (SolrDocument doc : docs) {

// // 多值查詢

// @SuppressWarnings("unchecked")

// List<String> collectTime = (List<String>) doc.getFieldValue("collectTime");

// String clientmac_s = (String) doc.getFieldValue("clientmac_s");

// System.out.println("collectTime:" + collectTime + "\t clientmac_s:" + clientmac_s);

// }

SolrDocumentList results = rsp.getResults();

for (int i = 0; i < results.size(); i++) {

System.out.println("////////////////////////////////////////////////////////");

System.out.println("//第" + (i+1) +"個值");

System.out.println("////////////////////////////////////////////////////////");

// System.out.println("******************全部FieldName*****************");

// System.out.println(results.get(i).getFieldNames());

System.out.println("******************全部FieldName和FieldValue*****************");

Object[] names = results.get(i).getFieldNames().toArray();

int j = 0;

for (String name : results.get(i).getFieldNames()) {

System.out.println(names[j++] + ":" + results.get(i).getFieldValue(name));

}

System.out.println("-----------------------");

} catch (Exception e) {

e.printStackTrace();

}

/**

* 修改文檔屬性

* @param id

* @param fieldName

* @param fieldValue

public void updateField(String id, String fieldName, Object fieldValue) {

System.out.println("======================updateField ===================");

HashMap<String, Object> oper = new HashMap<String, Object>();

// 多值更新方法

// List<String> mulitValues = new ArrayList<String>();

// mulitValues.add(fieldName);

// mulitValues.add((String)fieldValue);

oper.put("set", fieldValue);

SolrInputDocument doc = new SolrInputDocument();

doc.addField("id", id);

doc.addField(fieldName, oper);

try {

UpdateResponse rsp = client.add(doc);

System.out.println("update doc id" + id + " result:" + rsp.getStatus() + " Qtime:" + rsp.getQTime());

UpdateResponse rspCommit = client.commit();

System.out.println(

"commit doc to index" + " result:" + rspCommit.getStatus() + " Qtime:" + rspCommit.getQTime());

} catch (SolrServerException | IOException e) {

e.printStackTrace();

}

public static void main(String args[]) {

//地址說明：ip:port/solr/庫名；建立庫命令： solr create -c mycore

String url = "http://localhost:8983/solr/mycore";

String zkUrl = "127.0.0.1:9983";

// PropertyConfigurator.configure("./etc/log4j.properties");

SolrjUtil ss = new SolrjUtil(url, 2);

// SolrjUtil sc = new SolrjUtil(zkUrl, 2, "test201607");

// 添加文檔

// ss.createDocs(3);

// ss.createOneDoc();

// 刪除文檔

// ss.deleteById("00cda454-bd3d-4945-814f-afa7110dcd21");

// ss.deleteByQuery("name:bean");

//更新文檔

// ss.updateField("bd67564f-4939-4de1-9a83-3483ebbbbbee", "name", "1233313131313");

// ss.close();

// 查詢文檔

ss.queryDocs();

// try {

// ss.queryAll();

// } catch (Exception e) {

// // TODO Auto-generated catch block

// e.printStackTrace();

// }

ss.close();

}

依賴關係

爲何使用

solr 是基於lucene搜索庫的一個搜索引擎框架。
一、簡單來講所謂的索引是爲了全文數據存儲和查詢準備的，全文數據即非結構化數據，好比一篇文章，若是你要用通常的手段進行搜索的話，好比用數據庫的like命令會有很多限制，並且還不能支持一些相同語義的問題。
舉個簡單的例子，你在亞馬遜上面搜索solr，卻能夠查詢出來lucene內容，這就是關聯性查詢和語義查詢。java

二、高性能的，上億條數據經過索引的方式能夠秒級查詢出來，優化後可能更好。mysql

三、solr將非結構化數據，經過分詞、詞法分析、過濾停詞、語義分析等手段來轉成結構化數據，存儲爲索引，裏面有文檔概念這個和mysql的一條記錄又相似。

<wiz_tmp_tag id="wiz-table-range-border" contenteditable="false" style="display: none;">sql

相關標籤/搜索

每日一句

每一个你不满意的现在，都有一个你没有努力的曾经。