lucene-SpanQuery跨度查询基础

1、跨度查询SpanQuery5个子类

SpanQuery类型                            描述

SpanTermQuery                和其他跨度查询结合使用，单独使用相当于TermQuery

SpanFirstQuery               用来匹配域中的第一个部分内的各个spans

SpanNearQuery                用来匹配临近的spans

SpanNotQuery                 用来匹配不重叠的spans

SpanOrQuery                  span查询的聚合匹配

2、测试SpanQuery

public class SpanQueryTest extends TestCase{

    private RAMDirectory directory;

    private IndexSearcher searcher;

    private IndexReader reader;

   

    private SpanTermQuery quick;

    private SpanTermQuery brown;

    private SpanTermQuery red;

    private SpanTermQuery fox;

    private SpanTermQuery lazy;

    private SpanTermQuery Sleepy;

    private SpanTermQuery dog;

    private SpanTermQuery cat;

    private Analyzer analyzer;

  

    protected void setUp() throws Exception{

          directory=new RAMDirectory();

         

          analyzer=new WhitespaceAnalyzer();

          IndexWriter writer=new IndexWriter(directory,analyzer,true);

          Document doc=new Document();

          doc.add(Field.Text("f","the quck brown fox jumps over the lazy dog"));

          writer.addDocument(doc);

             

          doc=new Document();

          doc.add(Field.Text("f","the quick red fox jumps over the sleepy cat"));

          writer.addDocument(doc);

          writer.close();

         

          searcher=nwe IndexSearcher(directory);

          reader=IndexReader.open(directory);

 

          quick=new SpanTermQuery(new Term("f","quick"));

          brown=new SpanTermQuery(new Term("f","brown"));

          red=new SpanTermQuery(new Term("f","red"));

          fox=new SpanTermQuery(new Term("f","fox"));

          lazy=new SpanTermQuery(new Term("f","lazy"));

          sleepy=new SpanTermQuery(new Term("f","dog"));

          dog=new SpanTermQuery(new Term("f","cat"));
    }

   

    private void assertOnlyBrownFox(Query query) throws Exception{//检查是否返回一个匹配结果

         Hits hits=searcher.search(query);

         assertEquals(1,hits.length());

         assertEquals("wrong doc",0,hits.id(0));

    }

    private void assertBothFoxes(Query query) throws Exception{//检查是否返回2个匹配结果

        Hits hits=searcher.search(query);

        assertEquals(2.hits.length());

    }

    private void assertNotMatch(Query query) throws Exception{

         Hits hits=searcher.search(query);

         assertEquals(0,hits.length());

    }

}

3、使用SpanTermQuery类，它匹配文档的方式与TermQuery相似，但是它会记录一个文档中的相同项在文档中出现的不同位置。

　　　SpanQuery对象一直跟踪它所匹配的结果：对于每个正进行匹配的文档，它记录下被匹配的查询文本的所有起点和终点位置（以语汇单元为一个位置）。

      dumpSpans(new SpanTermQuery(new Term("f","the")));//查询文本为the，带the的所有文档，并显示查询细节

      定义一个方法dumpSpans()调用SpanQuery的一些底层API为我们查询细节。

public void dumpSpans(SpanQuery query) throws IOException{

    Spans spans=query.getSpans(reader);

    System.out.println(query+":");

    int numSpans=0;

   

    Hits hits=searcher.search(query);

    Float[] scores=new float[2];

    for (int i0;i<hits.length();i++){

        scores[hits.id(i)]=hits.score(i);

    }

    while (spans.next()){//spans里是单个查询文本匹配情况情况，记录着query在文档中的位置，

                         //next表示query在文档中的下一个位置，以及查询文本所在的文档号

          numSpans++;

         

          int id=spans.doc();

          Document doc=reader.document(id);

          Token[] tokens=AnaylzerUtilts.tokensFromAnalysis(analyzer,doc.get("f"));

          StringBuffer buffer=new StringBuffer();

          buffer.append("  ");

          for (int i=0;i<tokens.length;i++){

               if (i==spans.start()){

                   buffer.append("<");

               }

               buffer.append(tokens[i].termText());

               if (i+1==spans.end()){

                   buffer.append(">");

               }

               buffer.append(" ");

          }

          buffer.append("("+scores[id]+")");

          System.out.println(buffer);//输出spans的查询文本的在文档中本次出现的信息。        

    }

    if (numspans==0){

        System.out.println("   no  spans");//没有任何匹配

    }

    System.out.println();

}     

 

第1次spans.next循环所输出:<the> quick brown fox jumps over the lazy dog(0.18123456)

第2次spans.next循环所输出:the quick brown fox jumps over <the> lazy dog(0.18123456)

第3次spans.next循环所输出:<the> quick red fox jumps over the sleep dog(0.18123456)

第4次spans.next循环所输出:the quick red fox jumps over <the> sleep dog(0.18123456)