Question

如果用户在搜索框中输入短语（带或不带引号），我希望首先显示的结果是文档标题中具有完全短语的文档，以及显示在其后的其他文档。这是我尝试过的，但它没有按顺序给我搜索结果：

在编制索引时我说：

AddStringFieldToDocument(document, "keyWord", this.BuildKeywordsString(), Field.Store.NO, Field.Index.ANALYZED, false);

AddStringFieldToDocument(document, "title", this.Title, Field.Store.NO, Field.Index.ANALYZED, false, 4f);

    private void AddStringFieldToDocument(Document document, string fieldName, string fieldValue, 
        Field.Store store, Field.Index index, bool setOmitTermFreqAndPositions)
    {
        if (fieldValue == null)
        {
            return;
        }
        var field = GetFieldToAddToDocument(document, fieldName, fieldValue, store, index, setOmitTermFreqAndPositions);
        document.Add(field);
    }

    private void AddStringFieldToDocument(Document document, string fieldName, string fieldValue,
        Field.Store store, Field.Index index, bool setOmitTermFreqAndPositions, Single boost)
    {
        if (fieldValue == null)
        {
            return;
        }

        var field = GetFieldToAddToDocument(document, fieldName, fieldValue, store, index, setOmitTermFreqAndPositions);
        field.SetBoost(boost); //boosting title
        document.Add(field);
    }

    private Field GetFieldToAddToDocument(Document document, string fieldName, string fieldValue, Field.Store store,
        Field.Index index, bool setOmitTermFreqAndPositions)
    {
        Field field = new Field(fieldName, fieldValue, store, index);
        field.SetOmitTermFreqAndPositions(setOmitTermFreqAndPositions);
        return field;
    }

在搜索时，作为我的BooleanQuery的一部分，我有：

if (!string.IsNullOrWhiteSpace(queryString))
        {
            QueryParser qpKeyWord = new QueryParser(myVersionUsed, "keyWord", StandardAnalyzer);

            Query qKeyWord = qpKeyWord.Parse(queryString);
            booleanQuery.Add(qKeyWord, BooleanClause.Occur.MUST);

            Term titleTerm = new Term("title", queryString);
            PhraseQuery qTitleWord = new PhraseQuery();
            qTitleWord.SetSlop(12);
            qTitleWord.Add(titleTerm);
            qTitleWord.SetBoost(5);
            booleanQuery.Add(qTitleWord, BooleanClause.Occur.SHOULD);

我得到的结果好坏参半。此外，当我运行IndexSearcher.Explain（query，docId）

时

我明白了：

Document Id: 92871
0.5439626 = (MATCH) product of:
  0.8159439 = (MATCH) sum of:
    0.5884751 = (MATCH) sum of:
      0.2580064 = (MATCH) weight(KeyWord:chicken in 92871), product of:
        0.2226703 = queryWeight(KeyWord:chicken), product of:
          3.236447 = idf(docFreq=25345, maxDocs=237239)
          0.06880084 = queryNorm
        1.158692 = (MATCH) fieldWeight(KeyWord:chicken in 92871), product of:
          4.582576 = tf(termFreq(KeyWord:chicken)=21)
          3.236447 = idf(docFreq=25345, maxDocs=237239)
          0.078125 = fieldNorm(field=KeyWord, doc=92871)
      0.3304687 = (MATCH) weight(KeyWord:parmesan in 92871), product of:
        0.2962231 = queryWeight(KeyWord:parmesan), product of:
          4.305515 = idf(docFreq=8701, maxDocs=237239)
          0.06880084 = queryNorm
        1.115608 = (MATCH) fieldWeight(KeyWord:parmesan in 92871), product of:
          3.316625 = tf(termFreq(KeyWord:parmesan)=11)
          4.305515 = idf(docFreq=8701, maxDocs=237239)
          0.078125 = fieldNorm(field=KeyWord, doc=92871)
    0.2274688 = (MATCH) weight(has_photo:y in 92871), product of:
      0.1251001 = queryWeight(has_photo:y), product of:
        1.818294 = idf(docFreq=104665, maxDocs=237239)
        0.06880084 = queryNorm
      1.818294 = (MATCH) fieldWeight(has_photo:y in 92871), product of:
        1 = tf(termFreq(has_photo:y)=1)
        1.818294 = idf(docFreq=104665, maxDocs=237239)
        1 = fieldNorm(field=has_photo, doc=92871)
  0.6666667 = coord(2/3)

没有与PhraseQuery相关联的数字，但每个keyWord都有单独的数字但是在搜索时我运行query.ToString（）我得到：

+(KeyWord:chicken KeyWord:parmesan) title:"Chicken Parmesan"~12^5.0

表示查询是正确的。对？我错过了什么？

Answer 1

你建立标题查询的方式我怀疑你从来没有得到来自标题条款的命中。

您构建PhraseQuery以查找单个术语：“Chicken Parmesan”，但当您将其编入索引时，StandardAnalyzer会生成两个词：“chicken”和“parmesan”。您需要使用这两个术语构建PhraseQuery。

您可以将QueryParser用于此目的：

    QueryParser qp = new QueryParser("keyWord", new StandardAnalyzer());
    Query q = qp.Parse("+(keyWord:chicken KeyWord:parmesan) title:\"Chicken Parmesan\"~12^5.0");
    var hits = searcher.Search(q);

如果您不想使用QueryParser，请使用TokenStream api来破坏令牌中的文本：

    PhraseQuery titleQuery = new PhraseQuery();
    titleQuery.SetSlop(12);
    titleQuery.SetBoost(5);
    BooleanQuery keywordQuery = new BooleanQuery();

    var standard = new StandardAnalyzer();
    TokenStream tokens = standard.TokenStream("title", new StringReader("Chicken Parmesan"));
    List<Term> terms = new List<Term>();
    while (tokens.IncrementToken())
    {
        TermAttribute termAttribute = (TermAttribute)tokens.GetAttribute(typeof(TermAttribute));

        titleQuery.Add(new Term("title", termAttribute.Term()));

        keywordQuery.Add(
            new TermQuery(
                new Term("keyWord", termAttribute.Term())),
            BooleanClause.Occur.SHOULD);  
    }

    BooleanQuery query = new BooleanQuery();
    query.Add(keywordQuery, BooleanClause.Occur.MUST);
    query.Add(titleQuery, BooleanClause.Occur.SHOULD);

    var hits = searcher.Search(query);

针对title字段的PhraseQuery和针对catch all字段的QueryParser不会产生我期望的结果

1 个答案: