IKAnalyzer兼容Lucene 5.4.0版本抛出异常？

ava.lang.AbstractMethodError: org.apache.lucene.analysis.Analyzer.createComponents(Ljava/lang/String;)Lorg/apache/lucene/analysis/Analyzer$TokenStreamComponents;
    at org.apache.lucene.analysis.Analyzer.tokenStream(Analyzer.java:176)
    at org.apache.lucene.document.Field.tokenStream(Field.java:562)
    at org.apache.lucene.index.DefaultIndexingChain$PerField.invert(DefaultIndexingChain.java:607)
    at org.apache.lucene.index.DefaultIndexingChain.processField(DefaultIndexingChain.java:344)
    at org.apache.lucene.index.DefaultIndexingChain.processDocument(DefaultIndexingChain.java:300)
    at org.apache.lucene.index.DocumentsWriterPerThread.updateDocument(DocumentsWriterPerThread.java:234)
    at org.apache.lucene.index.DocumentsWriter.updateDocument(DocumentsWriter.java:450)
    at org.apache.lucene.index.IndexWriter.updateDocument(IndexWriter.java:1477)
    at org.apache.lucene.index.IndexWriter.addDocument(IndexWriter.java:1256)
    at com.study.lucene.demo.IndexFileTester.addDocument4(IndexFileTester.java:120)
    at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
    at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57)
    at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
    at java.lang.reflect.Method.invoke(Method.java:606)
    at org.junit.runners.model.FrameworkMethod$1.runReflectiveCall(FrameworkMethod.java:47)
    at org.junit.internal.runners.model.ReflectiveCallable.run(ReflectiveCallable.java:12)
    at org.junit.runners.model.FrameworkMethod.invokeExplosively(FrameworkMethod.java:44)
    at org.junit.internal.runners.statements.InvokeMethod.evaluate(InvokeMethod.java:17)
    at org.junit.runners.ParentRunner.runLeaf(ParentRunner.java:271)
    at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:70)
    at org.junit.runners.BlockJUnit4ClassRunner.runChild(BlockJUnit4ClassRunner.java:50)
    at org.junit.runners.ParentRunner$3.run(ParentRunner.java:238)
    at org.junit.runners.ParentRunner$1.schedule(ParentRunner.java:63)
    at org.junit.runners.ParentRunner.runChildren(ParentRunner.java:236)
    at org.junit.runners.ParentRunner.access$000(ParentRunner.java:53)

 

根据报错信息，原来是下载的IK Analyzer 2012FF_hf1.zip不兼容最新的Lucene 5.4.0版本(我下载的Lucene版本是5.4.0)，看了下IK Analyzer 2012FF_hf1.zip的源码，原来是其中的IKAnalyzer.java和IKTokenizer.java两个类不兼容Lucene 5.4.0版本的API（这两个文件是IKAnalyzer接入Lucene 的核心类），对其进行相应的改进吧，本来想通过继承方式的，但KAnalyzer.java和IKTokenizer.java两个类都是final的，没办法，只能重写了。

 

import org.apache.lucene.analysis.Analyzer;
import org.apache.lucene.analysis.Tokenizer;

public class ReIKAnalyzer extends Analyzer {

	private boolean useSmart;

	public boolean useSmart() {
		return useSmart;
	}

	public void setUseSmart(boolean useSmart) {
		this.useSmart = useSmart;
	}

	/**
	 * IK分词器Lucene 5.4.0 Analyzer接口实现类
	 * 
	 * 默认细粒度切分算法
	 */
	public ReIKAnalyzer() {
		this(false);
	}

	/**
	 * IK分词器Lucene 5.4.0 Analyzer接口实现类
	 * 
	 * @param useSmart
	 *            当为true时，分词器进行智能切分
	 */
	public ReIKAnalyzer(boolean useSmart) {
		super();
		this.useSmart = useSmart;
	}

	/**
	 * 重载Analyzer接口，构造分词组件
	 * 
	 * @param fieldName
	 *            the name of the fields content passed to the
	 *            TokenStreamComponents sink as a reader
	 */
	@Override
	protected TokenStreamComponents createComponents(String fieldName) {
		Tokenizer _IKTokenizer = new ReIKTokenizer(this.useSmart());
		return new TokenStreamComponents(_IKTokenizer);
	}
}

　　

import java.io.IOException;

import org.apache.lucene.analysis.Tokenizer;
import org.apache.lucene.analysis.tokenattributes.CharTermAttribute;
import org.apache.lucene.analysis.tokenattributes.OffsetAttribute;
import org.apache.lucene.analysis.tokenattributes.TypeAttribute;
import org.wltea.analyzer.core.IKSegmenter;
import org.wltea.analyzer.core.Lexeme;

public class ReIKTokenizer extends Tokenizer {

	// IK分词器实现
	private IKSegmenter _IKImplement;

	// 词元文本属性
	private final CharTermAttribute termAtt;
	// 词元位移属性
	private final OffsetAttribute offsetAtt;
	// 词元分类属性（该属性分类参考org.wltea.analyzer.core.Lexeme中的分类常量）
	private final TypeAttribute typeAtt;
	// 记录最后一个词元的结束位置
	private int endPosition;

	/**
	 * Lucene 5.4.0 Tokenizer适配器类构造函数
	 * 
	 * @param in
	 * @param useSmart
	 */
	public ReIKTokenizer(boolean useSmart) {
		super();
		offsetAtt = addAttribute(OffsetAttribute.class);
		termAtt = addAttribute(CharTermAttribute.class);
		typeAtt = addAttribute(TypeAttribute.class);
		_IKImplement = new IKSegmenter(input, useSmart);
	}

	@Override
	public boolean incrementToken() throws IOException {
		// 清除所有的词元属性
		clearAttributes();
		Lexeme nextLexeme = _IKImplement.next();
		if (nextLexeme != null) {
			// 将Lexeme转成Attributes
			// 设置词元文本
			termAtt.append(nextLexeme.getLexemeText());
			// 设置词元长度
			termAtt.setLength(nextLexeme.getLength());
			// 设置词元位移
			offsetAtt.setOffset(nextLexeme.getBeginPosition(),
					nextLexeme.getEndPosition());
			// 记录分词的最后位置
			endPosition = nextLexeme.getEndPosition();
			// 记录词元分类
			typeAtt.setType(nextLexeme.getLexemeTypeString());
			// 返会true告知还有下个词元
			return true;
		}
		// 返会false告知词元输出完毕
		return false;
	}

	@Override
	public void reset() throws IOException {
		super.reset();
		_IKImplement.reset(input);
	}

	@Override
	public final void end() {
		// set final offset
		int finalOffset = correctOffset(this.endPosition);
		offsetAtt.setOffset(finalOffset, finalOffset);
	}
}