solr php里中文分词怎么用
Posted
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了solr php里中文分词怎么用相关的知识，希望对你有一定的参考价值。
参考技术A 可以看手册。希望我的回答可以帮到你，有什么不懂可以追问。
Solr配置中文分词器IKAnalyzer及增删改查调用
一、配置IKAnalyzer中文分词器
Solr 版本5.2.1
IKAnalyzer2012_u6.jar报错 ,用IKAnalyzer2012_FF_hf1.jar 替换可解决
解决lucene4.0与IKAnalyzer的冲突。解决Exception in thread "main" java.lang.VerifyError: class org.wltea.analyzer.lucene.IKAnalyzer overrides final method tokenStream.(Ljava/lang/String;Ljava/io/Reader;)Lorg/apache/lucene/analysis/TokenStream;原因IKAnalyzer中参考手册中的例子是使用的lucene3.4，与4.0已经是不兼容了。使用IKAnalyzer2012_FF_hf1.jar可以解决问题
java.lang.AbstractMethodError
Caused by: java.lang.AbstractMethodError at org.apache.lucene.analysis.Analyzer.tokenStream(Analyzer.java:179)
lucene版本跟IK分词版本不一致导致，这块版本一定要对应上
由于solr版本较高暂时无法解决
<field name="messageId" type="string" indexed="true" stored="true" required="true" multiValued="false"/> <field name="msg_title" type="text_ik" stored="true" indexed="true"/> <field name="msg_content" type="text_ik" stored="true" indexed="true" multiValued="true"/> <uniqueKey>messageId</uniqueKey> <!-- IKAnalyzer 中文分词--> <fieldType name="text_ik" class="solr.TextField"> <analyzer type="index" class="org.wltea.analyzer.lucene.IKAnalyzer" /> <analyzer type="query" class="org.wltea.analyzer.lucene.IKAnalyzer" /> </fieldType>
二、添加、删除、查询索引
需要除了solr相关包还需要下面的jar包
Message.java
package org.itat.lucene.solr.test;
import org.apache.solr.client.solrj.beans.Field;
public class Message {
private String messageId;
private String title;
private String[] content;
public Message() {
super();
}
public Message(String messageId, String title, String[] content) {
super();
this.messageId = messageId;
this.title = title;
this.content = content;
}
public String getMessageId() {
return messageId;
}
@Field
public void setMessageId(String messageId) {
this.messageId = messageId;
}
public String getTitle() {
return title;
}
@Field("msg_title")
public void setTitle(String title) {
this.title = title;
}
public String[] getContent() {
return content;
}
@Field("msg_content")
public void setContent(String[] content) {
this.content = content;
}
}增删改查demo
package org.itat.lucene.solr.test;
import java.io.IOException;
import java.net.MalformedURLException;
import java.util.ArrayList;
import java.util.List;
import org.apache.solr.client.solrj.SolrQuery;
import org.apache.solr.client.solrj.SolrServerException;
import org.apache.solr.client.solrj.impl.CloudSolrServer;
import org.apache.solr.client.solrj.impl.ConcurrentUpdateSolrServer;
import org.apache.solr.client.solrj.impl.HttpSolrClient;
import org.apache.solr.client.solrj.impl.HttpSolrServer;
import org.apache.solr.client.solrj.response.QueryResponse;
import org.apache.solr.client.solrj.response.UpdateResponse;
import org.apache.solr.common.SolrDocument;
import org.apache.solr.common.SolrDocumentList;
import org.apache.solr.common.SolrInputDocument;
import org.junit.Before;
import org.junit.Test;
public class SolrTest {
private final static String URL = "http://localhost:8080/solr/mail";
private HttpSolrServer server = null;
@Before
public void init() {
server = new HttpSolrServer(URL);
}
@Test
public void addOneOrDelete() {
/*HttpSolrServer server=new HttpSolrServer(URL);*/
/*ConcurrentUpdateSolrServer cs=new ConcurrentUpdateSolrServer(URL,1,1);
*新版已被ConcurrentUpdateSolrClient取代
* */
/*CloudSolrServer css=new CloudSolrServer("192.168.0.1");//zookeeper地址
*已被CloudSolrClient
*/
HttpSolrClient server= new HttpSolrClient(URL);//新版已经取代了HttpSolrServer
SolrInputDocument doc = new SolrInputDocument();
//id是唯一的主键，当多次添加的时候，最后添加的相同id的域会覆盖前面的域
doc.addField("messageId","3");
doc.addField("msg_title", "这是我的第一个solrj的程序");
doc.addField("msg_content","我的solrj的程序究竟能不能跑得起来呢？");
try {
UpdateResponse ur=server.add(doc);
System.out.println(ur);
/*server.deleteByQuery("*:*");*/
server.commit(null,true,true,false);
server.close();
} catch (SolrServerException e) {
// TODO Auto-generated catch block
e.printStackTrace();
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
}
//一下添加多个
@Test
public void addList() {
try {
List<SolrInputDocument> docs = new ArrayList<SolrInputDocument>();
SolrInputDocument doc = new SolrInputDocument();
doc.addField("messageId", "2");
doc.addField("msg_title", "很好！solr可以工作了");
doc.addField("msg_content","slor总算可以正式工作了");
docs.add(doc);
doc = new SolrInputDocument();
doc.addField("messageId", "3");
doc.addField("msg_title", "测试一下solr的添加");
doc.addField("msg_content","看看能不能添加一个列表信息");
docs.add(doc);
server.add(docs);
server.commit();
} catch (SolrServerException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
//基于java bean的添加
@Test
public void addBean() {
try {
List<Message> msgs = new ArrayList<Message>();
msgs.add(new Message("4","基于java bean的添加",
new String[]{"通过java bean完成添加","java bean的添加附件"}));
msgs.add(new Message("5","基于java bean的列表数据的添加",
new String[]{"测试如何通过一个对象完成添加","通过对象完成添加的附件"}));
server.addBeans(msgs);
server.commit();
} catch (SolrServerException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
//查询
@Test
public void test04() {
try {
//定义查询字符串
SolrQuery query = new SolrQuery("*");
query.setStart(0);
query.setRows(5);
QueryResponse resp=null;
try {
resp = server.query(query);
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
//查询出来的结果都保存在SolrDocumentList中
SolrDocumentList sdl = resp.getResults();
System.out.println(sdl.getNumFound());
for(SolrDocument sd:sdl) {
// System.out.println(sd);
System.out.println(sd.getFieldValue("msg_title")+","+sd.getFieldValue("msg_content"));
}
} catch (SolrServerException e) {
e.printStackTrace();
}
}
//基于javabean查询
@Test
public void test05() {
try {
SolrQuery query = new SolrQuery("*");
query.setStart(0);
query.setRows(5);
QueryResponse resp=null;
try {
resp = server.query(query);
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
//可以直接查询相应的bean对象，但是不是很常用,无法得到查询总条数
List<Message> list = resp.getBeans(Message.class);
System.out.println(list.size());
for(Message msg:list) {
System.out.println(msg.getTitle());
}
} catch (SolrServerException e) {
e.printStackTrace();
}
}
//高亮
@Test
public void test06() {
try {
SolrQuery query = new SolrQuery("msg_content:测试 OR msg_title:测试");
query.setHighlight(true).setHighlightSimplePre("<span class=‘highligter‘>")
.setHighlightSimplePost("</span>")
.setStart(0).setRows(5);
query.setParam("hl.fl", "msg_title,msg_content");
QueryResponse resp=null;
try {
resp = server.query(query);
} catch (IOException e) {
// TODO Auto-generated catch block
e.printStackTrace();
}
//查询出来的结果都保存在SolrDocumentList中
SolrDocumentList sdl = resp.getResults();
System.out.println(sdl.getNumFound());
for(SolrDocument sd:sdl) {
String id = (String)sd.getFieldValue("messageId");
System.out.println(resp.getHighlighting().get(id).get("msg_content"));
//高亮结果以唯一索引为key
}
} catch (SolrServerException e) {
e.printStackTrace();
}
}
}本文出自 “点滴积累” 博客，请务必保留此出处http://tianxingzhe.blog.51cto.com/3390077/1753167
以上是关于solr php里中文分词怎么用的主要内容，如果未能解决你的问题，请参考以下文章