Lucene V3.0.2分词、高亮

Lucene版本升级到3.0以后，原来的分词方式(token=tokenStream.next())的方式已经被抛弃，转而使用TermAttribute，本例使用SmartChineseAnalyzer演示如何分词，此外，本例还演示了如何对命中文档域进行高亮显示。

 

package index;import java.io.File;import java.io.IOException;import java.io.StringReader;import org.apache.lucene.analysis.Analyzer;import org.apache.lucene.analysis.TokenStream;import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;import org.apache.lucene.analysis.tokenattributes.TermAttribute;import org.apache.lucene.document.Document;import org.apache.lucene.document.Field;import org.apache.lucene.document.Field.Index;import org.apache.lucene.document.Field.Store;import org.apache.lucene.index.CorruptIndexException;import org.apache.lucene.index.IndexWriter;import org.apache.lucene.index.IndexWriter.MaxFieldLength;import org.apache.lucene.queryParser.ParseException;import org.apache.lucene.queryParser.QueryParser;import org.apache.lucene.search.IndexSearcher;import org.apache.lucene.search.Query;import org.apache.lucene.search.ScoreDoc;import org.apache.lucene.search.TopDocs;import org.apache.lucene.search.highlight.Highlighter;import org.apache.lucene.search.highlight.InvalidTokenOffsetsException;import org.apache.lucene.search.highlight.QueryScorer;import org.apache.lucene.search.highlight.SimpleFragmenter;import org.apache.lucene.search.highlight.SimpleHTMLFormatter;import org.apache.lucene.store.FSDirectory;import org.apache.lucene.store.LockObtainFailedException;import org.apache.lucene.util.Version;public class AnalzyerTest {/** * lucene3.0开始已经抛弃了原来的分词方式，转而使用新的分词方式<br> * 本方法以SmartChineseAnalyzer为例，演示如何分词以及取得分词之后的term * * @throws Exception */public static void analysis() throws Exception {Analyzer analyzer = new SmartChineseAnalyzer(Version.LUCENE_30);String string = "中国人民银行采取了一系列措施防止人民币升值，但是很遗憾，这些措施在今天看来其作用是微乎其微的。难道真的就没有什么别的措施防止人民币再次疯狂升值了吗?";StringReader reader = new StringReader(string);TokenStream ts = analyzer.tokenStream("", reader);TermAttribute termAttribute = ts.getAttribute(TermAttribute.class);while (ts.incrementToken()) {System.out.print(termAttribute.term() + " ");}System.out.println();}/** * 建索引<br> * 在构造IndexWriter时必须使用Directory作为参数了 * * @throws CorruptIndexException * @throws LockObtainFailedException * @throws IOException */private static void build() throws CorruptIndexException, LockObtainFailedException, IOException {String path = "index";IndexWriter writer = new IndexWriter(FSDirectory.open(new File(path)), new SmartChineseAnalyzer(Version.LUCENE_30), true, MaxFieldLength.LIMITED);Document document = new Document();document.add(new Field("text", "中国人民银行采取了一系列措施防止人民币升值，但是很遗憾，这些措施在今天看来其作用是微乎其微的。难道真的就没有什么别的措施防止人民币再次疯狂升值了吗？", Store.YES, Index.ANALYZED));writer.addDocument(document);writer.optimize();writer.close();}/** * 搜索也没有返回Hits类型结果的方法了 * * @param keyword * @throws CorruptIndexException * @throws IOException * @throws ParseException * @throws InvalidTokenOffsetsException */private static void search(String keyword) throws CorruptIndexException, IOException, ParseException, InvalidTokenOffsetsException {Analyzer analyzer = new SmartChineseAnalyzer(Version.LUCENE_30);QueryParser parser = new QueryParser(Version.LUCENE_30, "text", analyzer);IndexSearcher searcher = new IndexSearcher(FSDirectory.open(new File("index")));Query query = parser.parse(keyword);System.out.println(query);TopDocs topDocs = searcher.search(query, 10);ScoreDoc[] scoreDocs = topDocs.scoreDocs;System.out.println("hits:" + topDocs.totalHits);for (ScoreDoc scoreDoc : scoreDocs) {Document doc = searcher.doc(scoreDoc.doc);String text = doc.get("text");System.out.println(highlight(text, query, analyzer));}}/** * 高亮关键词 * * @param content * 需要高亮的内容 * @param query * 搜索时使用的Query对象 * @param analyzer * 分词器 * @return 高亮之后的文本 * @throws IOException * @throws InvalidTokenOffsetsException */private static String highlight(String content, Query query, Analyzer analyzer) throws IOException, InvalidTokenOffsetsException {SimpleHTMLFormatter formatter = new SimpleHTMLFormatter("<b>", "</b>");Highlighter highlighter = new Highlighter(formatter, new QueryScorer(query));highlighter.setTextFragmenter(new SimpleFragmenter(25));String resultString = highlighter.getBestFragment(analyzer.tokenStream("", new StringReader(content)), content);return resultString + "...";}public static void main(String[] args) throws Exception {analysis();build();search("中国 人民币 升值");}} 

本例需要使用四个jar包：

lucene-core-3.0.3.jar 

lucene-highlighter-3.0.2.jar

lucene-smartcn-3.0.2.jar

lucene-memory-3.0.2.jar

 

在高亮时有一个特别需要注意的问题：

当输入的查询词为"人民币升值"时，会抛出NoClassDefFoundError：org/apache/lucene/index/memory/MemoryIndex异常，如果将“人民币”与“升值”使用空格分开，则不会出现此异常。

解决方式是将lucene-memory-3.0.2.jar添加到classpath中。