Solr5.3.1整合IKAnalyzer

　　由於solr5.3.1本身不支持中文分詞，而msseg4j的分詞效果不明顯。因而采用IK進行分詞，然而參考http://www.superwu.cn/2015/05/08/2134/在google上下載的jar包放到solr目錄下直接報如下異常。

嚴重: Servlet.service() for servlet [default] in context with path [/solr] threw exception [Filter execution threw an exception] with root cause
java.lang.AbstractMethodError
    at org.apache.lucene.analysis.Analyzer.tokenStream(Analyzer.java:179)
    at org.apache.solr.handler.AnalysisRequestHandlerBase.analyzeValue(AnalysisRequestHandlerBase.java:91)
    at org.apache.solr.handler.FieldAnalysisRequestHandler.analyzeValues(FieldAnalysisRequestHandler.java:221)
    at org.apache.solr.handler.FieldAnalysisRequestHandler.handleAnalysisRequest(FieldAnalysisRequestHandler.java:182)
    at org.apache.solr.handler.FieldAnalysisRequestHandler.doAnalysis(FieldAnalysisRequestHandler.java:102)
    at org.apache.solr.handler.AnalysisRequestHandlerBase.handleRequestBody(AnalysisRequestHandlerBase.java:63)
    at org.apache.solr.handler.RequestHandlerBase.handleRequest(RequestHandlerBase.java:143)
    at org.apache.solr.core.SolrCore.execute(SolrCore.java:2068)
    at org.apache.solr.servlet.HttpSolrCall.execute(HttpSolrCall.java:669)
    at org.apache.solr.servlet.HttpSolrCall.call(HttpSolrCall.java:462)
    at org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:214)
    at org.apache.solr.servlet.SolrDispatchFilter.doFilter(SolrDispatchFilter.java:179)
    at org.apache.catalina.core.ApplicationFilterChain.internalDoFilter(ApplicationFilterChain.java:241)
    at org.apache.catalina.core.ApplicationFilterChain.doFilter(ApplicationFilterChain.java:208)
    at org.apache.catalina.core.StandardWrapperValve.invoke(StandardWrapperValve.java:220)
    at org.apache.catalina.core.StandardContextValve.invoke(StandardContextValve.java:122)
    at org.apache.catalina.core.StandardHostValve.invoke(StandardHostValve.java:170)
    at org.apache.catalina.valves.ErrorReportValve.invoke(ErrorReportValve.java:103)
    at org.apache.catalina.valves.AccessLogValve.invoke(AccessLogValve.java:956)
    at org.apache.catalina.core.StandardEngineValve.invoke(StandardEngineValve.java:116)
    at org.apache.catalina.connector.CoyoteAdapter.service(CoyoteAdapter.java:423)
    at org.apache.coyote.http11.AbstractHttp11Processor.process(AbstractHttp11Processor.java:1079)
    at org.apache.coyote.AbstractProtocol$AbstractConnectionHandler.process(AbstractProtocol.java:625)
    at org.apache.tomcat.util.net.AprEndpoint$SocketProcessor.doRun(AprEndpoint.java:2522)
    at org.apache.tomcat.util.net.AprEndpoint$SocketProcessor.run(AprEndpoint.java:2511)
    at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
    at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
    at org.apache.tomcat.util.threads.TaskThread$WrappingRunnable.run(TaskThread.java:61)
    at java.lang.Thread.run(Thread.java:745)

　　一開始以為是配置問題，怎么配都不行。后來看了下源碼，發現solr5.3.1中 Luecene的Analyzer接口的createComponents方法把第二個參數去掉了。因此修改源碼是在所難免了。源碼的修改可參考：http://iamyida.iteye.com/blog/2193513。也可以直接獲取改好的源碼重新打包即可。

　　主要修改部分、IKAnalyzer.java

/** 
     * 重載Analyzer接口，構造分詞組件 
     */  
    @Override  
    protected TokenStreamComponents createComponents(String text) {  
        Reader reader = new BufferedReader(new StringReader(text));  
        Tokenizer _IKTokenizer = new IKTokenizer(reader , this.useSmart());  
        return new TokenStreamComponents(_IKTokenizer);  
    } 

　　IKTokenizer.java中添加如下構造函數

    public IKTokenizer(AttributeFactory factory, boolean useSmart) {  
        super(factory);  
        offsetAtt = addAttribute(OffsetAttribute.class);  
        termAtt = addAttribute(CharTermAttribute.class);  
        typeAtt = addAttribute(TypeAttribute.class);  
        _IKImplement = new IKSegmenter(input , useSmart);  
    }

　　其它都是一些零零碎碎的修改。可查看修改后的源文件。

　　新建一個工程（附件中的IK-Analyzer-extra），添加工廠類IKTokenizerFactory，方便程序的擴展和維護。

package org.wltea.analyzer.util;

import java.util.Map;

import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.util.TokenizerFactory;
import org.apache.lucene.util.AttributeFactory;
import org.wltea.analyzer.lucene.IKTokenizer;

public class IKTokenizerFactory extends TokenizerFactory {
    private boolean useSmart;  

    public IKTokenizerFactory(Map<String, String> args) {  
        super(args);  
        useSmart = getBoolean(args, "useSmart", false);  
    }  
  
    @Override  
    public Tokenizer create(AttributeFactory attributeFactory) {  
        Tokenizer tokenizer = new IKTokenizer(attributeFactory,useSmart);  
        return tokenizer;  
    } 

}

　　最后是schema.xml中添加如下配置

    <fieldType name="text_ik" class="solr.TextField">
      <!--索引時候的分詞器-->
      <analyzer type="index">
        <tokenizer class="org.wltea.analyzer.util.IKTokenizerFactory" useSmart="true"/>
      </analyzer>
      <!--查詢時候的分詞器-->
      <analyzer type="query">
        <tokenizer class="org.wltea.analyzer.util.IKTokenizerFactory" useSmart="false"/>
      </analyzer>
    </fieldType>

　　最后將IK-Analyzer-5.3.1.jar和IK-Analyzer-extra-5.3.1.jar拷貝至solr項目的lib目錄下即可。

　　另外提醒下各位，IK的源碼已經搬遷至這了：http://git.oschina.net/wltea/IK-Analyzer-2012FF/。

　　工程文件：

　　　　http://pan.baidu.com/s/1skv1jCp

　　　　http://pan.baidu.com/s/1c1o0gI8

　　參考文獻：

　　http://iamyida.iteye.com/blog/2220474

　　http://iamyida.iteye.com/blog/2193513