上一篇中,实现了中文分词的操作,在实际试用中,发现众多搜索引擎的搜索框中,我们在不同的key之间使用空格来表示“或”的语义,并且也许我们的关键字在title或者content中,那么现在我们就需要实现“在一个(或者多个)字段中查找多个关键字”的需求。以下便来看看如何实现。
下面代码基于上一篇的代码修改(红色标注地方为重点关注点):
import java.io.IOException; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.document.Document; import org.apache.lucene.document.Field; import org.apache.lucene.document.StringField; import org.apache.lucene.document.TextField; import org.apache.lucene.index.DirectoryReader; import org.apache.lucene.index.IndexWriter; import org.apache.lucene.index.IndexWriterConfig; import org.apache.lucene.queryparser.classic.MultiFieldQueryParser; import org.apache.lucene.queryparser.classic.ParseException; import org.apache.lucene.search.BooleanClause.Occur; 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.store.RAMDirectory; import org.apache.lucene.util.Version; import org.wltea.analyzer.lucene.IKAnalyzer; public class IKAnalyzerDemo2 { /** * @param args * @throws IOException */ public static void main(String[] args) throws IOException { // TODO Auto-generated method stub //建立索引 String text1 = "IK Analyzer是一个结合词典分词和文法分词的中文分词开源工具包。它使用了全新的正向迭代最细粒度切" + "分算法。"; String title1="这是标题1"; String text2 = "中文分词工具包可以和lucene是一起使用的"; String title2="这是标题2"; String text3 = "中文分词,你妹"; String title3="这是标题3"; String fieldName = "contents"; Analyzer analyzer = new IKAnalyzer(); RAMDirectory directory = new RAMDirectory(); IndexWriterConfig writerConfig = new IndexWriterConfig(Version.LATEST, analyzer); IndexWriter indexWriter = new IndexWriter(directory, writerConfig); Document document1 = new Document(); document1.add(new StringField("ID", "1", Field.Store.YES)); document1.add(new TextField("title", title1, Field.Store.YES)); document1.add(new TextField(fieldName, text1, Field.Store.YES)); indexWriter.addDocument(document1); Document document2 = new Document(); document2.add(new StringField("ID", "2", Field.Store.YES)); document1.add(new TextField("title", title2, Field.Store.YES)); document2.add(new TextField(fieldName, text2, Field.Store.YES)); indexWriter.addDocument(document2); Document document3 = new Document(); document3.add(new StringField("ID", "3", Field.Store.YES)); document1.add(new TextField("title", title3, Field.Store.YES)); document3.add(new TextField(fieldName, text3, Field.Store.YES)); indexWriter.addDocument(document3); indexWriter.close(); //搜索 DirectoryReader indexReader = DirectoryReader.open(directory); IndexSearcher searcher = new IndexSearcher(indexReader); //要查找的字符串数组 String [] stringQuery={"可以","标题1"}; //待查找字符串对应的字段 String[] fields={"content","title"}; //Occur.MUST表示对应字段必须有查询值, Occur.MUST_NOT 表示对应字段必须没有查询值,Occur.SHOULD表示对应字段应该存在查询值(但不是必须) Occur[] occ={Occur.SHOULD,Occur.SHOULD}; try { Query query = MultiFieldQueryParser.parse(stringQuery, fields, occ, analyzer); TopDocs topDocs = searcher.search(query, 5); System.out.println("命中数:"+topDocs.totalHits); ScoreDoc[] docs = topDocs.scoreDocs; for(ScoreDoc doc : docs){ Document d = searcher.doc(doc.doc); System.out.println("内容:"+d.get(fieldName)); } } catch (ParseException e) { // TODO Auto-generated catch block e.printStackTrace(); }finally{ if(indexReader != null){ try{ indexReader.close(); }catch (IOException e) { e.printStackTrace(); } } if(directory != null){ try{ directory.close(); }catch (Exception e) { e.printStackTrace(); } } } } }
这里特殊地方为:Occur数组,通过这里,便可以实现比较复杂的判断,这里我们暂时都使用Occur.SHOULD(表示关键词有没有都可以),以方便测试,关于此值的用法,后续再继续研究讲解
by 刘迎光@萤火虫工作室
OpenBI交流群:495266201
MicroService 微服务交流群:217722918
mail: liuyg#liuyingguang.cn
博主首页(==防止爬虫==):http://blog.liuyingguang.cn