Question

下面的代码可以直接与Lucene 7.3.1一起运行

您只需要更改索引存储路径的路径即可。

import java.io.IOException;
import java.nio.file.Paths;
import java.util.ArrayList;
import java.util.List;

import org.apache.lucene.index.IndexReader;
import org.apache.lucene.analysis.cn.smart.SmartChineseAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.document.Field;
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.index.IndexWriterConfig.OpenMode;
import org.apache.lucene.index.MultiTerms;
import org.apache.lucene.index.Term;
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.MultiPhraseQuery;
import org.apache.lucene.search.MultiTermQuery;
import org.apache.lucene.search.PhraseQuery;
import org.apache.lucene.search.Query;
import org.apache.lucene.search.ScoreDoc;
import org.apache.lucene.search.TermQuery;
import org.apache.lucene.search.TopDocs;
import org.apache.lucene.search.similarities.BM25Similarity;
import org.apache.lucene.store.FSDirectory;
import org.apache.lucene.store.IOContext;
import org.apache.lucene.store.RAMDirectory;

public class Example {

    public static IndexWriter writer;
    public static RAMDirectory idxDir;
    public static SmartChineseAnalyzer analyzer;

    public static void makeIndex() throws IOException {

        FSDirectory fsDir = FSDirectory.open(Paths.get("C:\\Users\\gt\\Desktop\\example"));
        idxDir = new RAMDirectory(fsDir, IOContext.DEFAULT);
        analyzer = new SmartChineseAnalyzer();
        IndexWriterConfig iwc = new IndexWriterConfig(analyzer);
        iwc.setSimilarity(new BM25Similarity());

        iwc.setOpenMode(OpenMode.CREATE_OR_APPEND);
        writer = new IndexWriter(idxDir, iwc);

        List<String> listSent = new ArrayList<String>();
        listSent.add("金古江湖是最好玩的金庸游戏1");
        listSent.add("金古江湖是最好玩的金庸游戏2");
        int id = 0;
        for (String sent : listSent) {
            id++;
            Document doc = new Document();
            doc.add(new TextField("questionType", "A", Field.Store.YES));
            doc.add(new TextField("questionId", "62650ACA7FEB446B9140B088EE7C2FF0", Field.Store.YES));
            doc.add(new TextField("question", sent.trim(), Field.Store.YES));
            writer.addDocument(doc);
        }

        writer.commit();
        writer.close();
    }

    public static void main(String[] args) throws IOException, ParseException {
        makeIndex();

        String[] stringQuery = { "A", "62650ACA7FEB446B9140B088EE7C2FF0aaaa", "金古江湖" };
        String[] fields = { "questionType", "questionId", "question" };
        Occur[] occ = { Occur.MUST, Occur.MUST, Occur.MUST };

//        Query query = new TermQuery(new Term("questionId","1"));
        Query query = MultiFieldQueryParser.parse(stringQuery, fields, occ, analyzer);


        TopDocs results = null;
        IndexReader reader = DirectoryReader.open(idxDir);
        IndexSearcher searcher = new IndexSearcher(reader);
        results = searcher.search(query, 5);
        ScoreDoc[] hits = results.scoreDocs;
        for (int i = 0; i < hits.length; ++i) {
            Document doc = searcher.doc(hits[i].doc);
            String strDocSent = doc.get("question");
            System.out.println(strDocSent);
        }
    }
}

在代码中，我添加了两个文档并为其创建索引。

然后我搜索文档。

我希望questionId字段完全匹配，但现在不匹配。

如何搜索多个词，其中一个词必须完全匹配，并且其他词的搜索策略可以是模糊的。

Answer 1

它并没有执行任何形式的模糊搜索，而是您的分析仪正在尝试将字段拆分成单词。您的questionId 62650ACA7FEB446B9140B088EE7C2FF0aaaa被拆分为以下令牌：

62650，aca，7、2月，446，b，9140，b，088，ee，7，c，2，ff，0，aaaa

由于您希望它是完全匹配的，并且通常表现得像一个ID，因此您不应该对其应用通常的分析器。通常，这样的ID应该用StringField而不是TextField索引，因为不分析StringFields。

在查询方面，您可以只使用一个简单的TermQuery，然后通过BooleanQuery将其与查询的其余部分合并。或者，如果您想将其用于QueryParser，则需要使用PerFieldAnalyzerWrapper，类似于：

Map<String,Analyzer> analyzerlist = new HashMap<>();
analyzerlist.put("questionId", new KeywordAnalyzer());
PerFieldAnalyzerWrapper analyzer = new PerFieldAnalyzerWrapper(new SmartChineseAnalyzer(), analyzerlist);

Lucene，多词搜索，一个词必须完全匹配

1 个答案: