Question

我想使用lucene进行增量搜索。我的词之间有空格。说“今日印度”。我的搜索查询返回

今日印度
今天的印度时间
今天的时间印度

我希望在sql中搜索结果，例如“India today％”。但这不会发生。我尝试使用短语查询，但这适用于精确搜索。我存储的数据是NOT_ANALYZED，以便我可以用空格搜索。

KeywordAnalyzer analyzer = new KeywordAnalyzer (); 

PhraseQuery pq = new  PhraseQuery();
pq.add(new Term("name", "MR DANIEL KELLEHER")); 


int hitsPerPage = 1000;
IndexReader reader = IndexReader.open(index);
IndexSearcher searcher = new IndexSearcher(reader);
TopScoreDocCollector collector = TopScoreDocCollector.create(hitsPerPage, true);
searcher.search(pq, collector);

我无法获得具有空间的查询。我已经在net和stackoverflow上引用了很多文章，但没有得到解决方案。

package org.lucenesample;

import org.apache.lucene.search.Query;

import org.apache.lucene.*;
import org.apache.lucene.analysis.*;
import org.apache.lucene.analysis.standard.*;
import org.apache.lucene.analysis.standard.std31.*;
import org.apache.lucene.analysis.tokenattributes.*;
import org.apache.lucene.collation.*;
import org.apache.lucene.document.*;
import org.apache.lucene.document.Field.Index;
import org.apache.lucene.document.Field.Store;
import org.apache.lucene.index.*;
import org.apache.lucene.index.IndexWriter.MaxFieldLength;
import org.apache.lucene.messages.*;
import org.apache.lucene.queryParser.*;
import org.apache.lucene.search.*;
import org.apache.lucene.search.function.*;
import org.apache.lucene.search.payloads.*;
import org.apache.lucene.search.spans.*;
import org.apache.lucene.store.*;
import org.apache.lucene.util.*;
import org.apache.lucene.util.fst.*;
import org.apache.lucene.util.packed.*;

import java.io.File;
import java.sql.*;
import java.util.HashMap;

public class ExactPhrasesearchUsingStandardAnalyser {

    /**
     * @param args
     */
    public static void main(String[] args) throws Exception {
        Directory directory = new RAMDirectory();
        StandardAnalyzer analyzer = new StandardAnalyzer(Version.LUCENE_35);
        MaxFieldLength mlf = MaxFieldLength.UNLIMITED;
        IndexWriter writer = new IndexWriter(directory, analyzer, true, mlf);
        writer.addDocument(createDocument1("1", "foo bar baz blue"));
        writer.addDocument(createDocument1("2", "red green blue"));
        writer.addDocument(createDocument1("3", "test panda foo & bar testt"));
        writer.addDocument(createDocument1("4", " bar test test foo in panda  red blue "));
        writer.addDocument(createDocument1("4", "test"));
        writer.close();

    IndexSearcher searcher = new IndexSearcher(directory);
    PhraseQuery query = new PhraseQuery();


    QueryParser qp2 = new QueryParser(Version.LUCENE_35, "contents", analyzer);
    //qp.setDefaultOperator(QueryParser.Operator.AND);
    Query queryx2 =qp2.parse("test foo in panda re*");//contains query
    Query queryx23 =qp2.parse("+red +green +blu*"  );//exact phrase match query.Make last word as followed by star
    Query queryx234 =qp2.parse("(+red +green +blu*)& (\"red* green\") "  );





     /*String term = "new york";
        // id and location are the fields in which i want to search the "term"
        MultiFieldQueryParser queryParser = new MultiFieldQueryParser(
                                           Version.LUCENE_35,
                                           { "contents"},
                                           new KeywordAnalyzer());
        Query query = queryParser.parse(term);
        System.out.println(query.toString());*/

    QueryParser qp = new QueryParser(Version.LUCENE_35, "contents", analyzer);
    //qp.setDefaultOperator(QueryParser.Operator.AND);

    Query queryx =qp.parse("\"air quality\"~10");
    System.out.println("******************Searching Code starts******************");
    TopDocs topDocs = searcher.search(queryx2, 10);
    for (ScoreDoc scoreDoc : topDocs.scoreDocs) {
        Document doc = searcher.doc(scoreDoc.doc);
        System.out.println(doc+"testtttttttt");
    }

}



   private static Document createDocument1(String id, String content) {
        Document doc = new Document();
        doc.add(new Field("id", id, Store.YES, Index.NOT_ANALYZED));
        doc.add(new Field("contents", content, Store.YES, Index.ANALYZED,
                Field.TermVector.WITH_POSITIONS_OFFSETS));
        System.out.println(content);
        return doc;
    }
}

我试过这种方式。我可以搜索包含格式。但是我无法获得选项的开头，这样当用户按下“印度到”然后“明天印度”和“今日印度”结果也会出现。我当我做“+ india * + to *”时能够接近它但是这会导致“今天的印度人”。我无法获得搜索结果，直到用户类型完成“今天”。基本上我想要短语查询“ “今日印度”上班。

Answer 1

对于已分析的字段，一种方法是使用已MultiPhraseQuery枚举的prefix terms：

<MultiPhraseQuery: field:"india (today todays)">

或者可以使用SpanQuery，其优点是可以处理术语扩展。

<SpanNearQuery: spanNear([field:india, SpanMultiTermQueryWrapper(field:today*)], 0, true)>

使用Lucene进行增量搜索

1 个答案: