LUCENE3.0 自学吧 4 TermDocs

利用TermDocs也是可以得到一些有用的结果。。。代码如下

package com.fpi.lucene.studying.myfirstlucene; import java.io.File; import java.io.IOException; import org.apache.lucene.LucenePackage; import org.apache.lucene.analysis.Analyzer; import org.apache.lucene.analysis.standard.StandardAnalyzer; import org.apache.lucene.document.Document; import org.apache.lucene.index.CorruptIndexException; import org.apache.lucene.index.IndexFileNameFilter; import org.apache.lucene.index.IndexReader; import org.apache.lucene.index.Term; import org.apache.lucene.index.TermDocs; 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.TopScoreDocCollector; import org.apache.lucene.store.FSDirectory; import org.apache.lucene.util.Version; public class Searcher { // 关键字，要搜查的对象 public static String key_word = "about"; public static String field = "contents"; public static void search() throws CorruptIndexException, IOException, ParseException{ //打开索引所在地 IndexSearcher sr = new IndexSearcher(FSDirectory.open(new File("d://test//myindex")),true); //词法分析器 Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_30); //解析器 QueryParser parser = new QueryParser(Version.LUCENE_30,field,analyzer); //根据关键字查询 Query query = parser.parse(key_word); TopScoreDocCollector collector = TopScoreDocCollector.create(100, false); //将所搜寻出来的结果以特定的形式放在collector中 sr.search(query, collector); /** * topDocs():Returns the top docs that were collected by this collector. * 返回的是由这个collector收集的顶级文档。 * .scoreDocs():The top hits for the query. * 用于查询的最高命中。 */ ScoreDoc[] hits = collector.topDocs().scoreDocs; System.out.println("搜索到符合标准的文档数目："+hits.length); //检索，根据关键字在contents这个field里边找，本节关注点。 TermDocs temDocs = sr.getIndexReader().termDocs(new Term("contents",key_word)); while(temDocs.next()){ System.out.println("在文件"+sr.getIndexReader().document(temDocs.doc())+"中，" + "关键字出现了"+temDocs.freq()+"次。"); } System.out.println("-----------------我是无敌的分割线----------------"); for (int i = 0; i < hits.length; i++) { Document doc = sr.doc(hits[i].doc); //依此遍历符合标准的文档 System.out.println(doc.getField("filename")+" ---- "+hits[i].toString()+" ---- "); } System.out.println("you have " + collector.getTotalHits() + " file matched query '" + key_word + "':"); System.out.println("Lucene's position is in:"+LucenePackage.get()); } public static void main(String[] args) { try { search(); } catch (CorruptIndexException e) { // TODO Auto-generated catch block e.printStackTrace(); } catch (IOException e) { // TODO Auto-generated catch block e.printStackTrace(); } catch (ParseException e) { // TODO Auto-generated catch block e.printStackTrace(); } } }

 

要说明的是，如果将检索到的结果放在TopScoreDocCollector中 那么他里边的顺序是按照相关度得分从大到小排序的，也即是说最大的排最前。而利用TermDocs：

TermDocs temDocs = sr.getIndexReader().termDocs(new Term("contents",key_word)); while(temDocs.next()){ System.out.println("在文件"+sr.getIndexReader().document(temDocs.doc())+"中，" + "关键字出现了"+temDocs.freq()+"次。"); }

他这个“容器”里边的数据是无序的。

 

还有说明Term的初始化，有2个，一般常用的是new Term(field名称，关键字)；

如果将        TermDocs temDocs = sr.getIndexReader().termDocs(new Term("contents",key_word));
错误的写成   TermDocs temDocs = sr.getIndexReader().termDocs();       

 

也就是无参初始化，则得到的结果就是每个文件他的freq都会取到值是1.