c# - 使用 lucene.net 搜索 "mvc2"时没有命中

Question

我正在使用 lucene.net 进行索引和搜索，我的代码遇到的唯一问题是在搜索“mvc2”时它没有找到任何匹配项(它似乎适用于我搜索的所有其他词)，我尝试了不同的分析器(请参阅分析器的评论)和较旧的 lucene 代码，这是我的索引和搜索代码，如果有人能告诉我我哪里出错了，我将不胜感激，谢谢。

////Indexing code
public void DoIndexing(string CvContent)
    {
        //state the file location of the index
        const string indexFileLocation = @"C:\RecruitmentIndexer\IndexedCVs";

        //if directory does not exist, create it, and create new index for it.
        //if directory does exist, do not create directory, do not create new      //index(add field to previous index).
        bool creatNewDirectory;   //to pass into lucene GetDirectory
        bool createNewIndex;      //to pass into lucene indexWriter
        if (!Directory.Exists(indexFileLocation))
        {
            creatNewDirectory = true;
            createNewIndex = true;
        }
        else
        {
            creatNewDirectory = false;
            createNewIndex = false;
        }


        Lucene.Net.Store.Directory dir =
            Lucene.Net.Store.FSDirectory.GetDirectory(indexFileLocation, creatNewDirectory);//creates if true

        //create an analyzer to process the text
        Lucene.Net.Analysis.Analyzer analyzer = new
        Lucene.Net.Analysis.SimpleAnalyzer();              //this analyzer gets all //hits exept mvc2 
        //Lucene.Net.Analysis.Standard.StandardAnalyzer(); //this leaves out sql once //and mvc2 once

        //create the index writer with the directory and analyzer defined.
        Lucene.Net.Index.IndexWriter indexWriter = new
        Lucene.Net.Index.IndexWriter(dir, analyzer,
            /*true to create a new index*/ createNewIndex);

        //create a document, add in a single field
        Lucene.Net.Documents.Document doc = new
        Lucene.Net.Documents.Document();



        Lucene.Net.Documents.Field fldContent =
          new Lucene.Net.Documents.Field("content",
          CvContent,//"This is some text to search by indexing",
          Lucene.Net.Documents.Field.Store.YES,
        Lucene.Net.Documents.Field.Index.ANALYZED,
        Lucene.Net.Documents.Field.TermVector.YES);

        doc.Add(fldContent);

        //write the document to the index
        indexWriter.AddDocument(doc);

        //optimize and close the writer
        indexWriter.Optimize();
        indexWriter.Close();

    }

////search code
private void button2_Click(object sender, EventArgs e)
    {

        string SearchString = textBox1.Text;

        ///after creating an index, search
        //state the file location of the index
        const string indexFileLocation = @"C:\RecruitmentIndexer\IndexedCVs";

        Lucene.Net.Store.Directory dir =
        Lucene.Net.Store.FSDirectory.GetDirectory(indexFileLocation, false);

        //create an index searcher that will perform the search
        Lucene.Net.Search.IndexSearcher searcher = new
        Lucene.Net.Search.IndexSearcher(dir);

        SearchString = SearchString.Trim();
        SearchString = QueryParser.Escape(SearchString);


        //build a query object
        Lucene.Net.Index.Term searchTerm =
          new Lucene.Net.Index.Term("content", SearchString);
        Lucene.Net.Search.Query query = new Lucene.Net.Search.TermQuery(searchTerm);

        //execute the query
        Lucene.Net.Search.Hits hits = searcher.Search(query);

        label1.Text = hits.Length().ToString();

        //iterate over the results.
        for (int i = 0; i < hits.Length(); i++)
        {
           Lucene.Net.Documents.Document docMatch = hits.Doc(i);

            MessageBox.Show(docMatch.Get("content"));

        }

    }

Answer 1

我相信 StandardAnalyzer 实际上从“mvc2”中删除了“2”，留下索引词只有“mvc”。不过，我不确定 SimpleAnalyzer。您可以尝试使用 WhitespaceAnalyzer，我相信它不会去除数字。

您还应该像处理索引一样处理搜索输入。 TermQuery 是“相同”匹配，这意味着如果您尝试搜索“mvc2”，而索引中的实际字符串总是显示“mvc”，那么您将找不到匹配项。

除非我使用 QueryParser，否则我还没有找到真正使用分析器的方法，即使那样我也总是得到奇怪的结果。

您可以尝试这样做，以便以与索引文档相同的方式“标记化”您的搜索字符串，并对所有术语进行 bool AND 搜索:

    // We use a boolean query to combine all prefix queries
    var analyzer = new SimpleAnalyzer();
    var query = new BooleanQuery();

    using ( var reader = new StringReader( queryTerms ) )
    {
        // This is what we need to do in order to get the terms one by one, kind of messy but seemed to be the only way
        var tokenStream = analyzer.TokenStream( "why_do_I_need_this", reader );
        var termAttribute = tokenStream.GetAttribute( typeof( TermAttribute ) ) as TermAttribute;

        // This will return false when all tokens has been processed.
        while ( tokenStream.IncrementToken() )
        {
            var token = termAttribute.Term();
            query.Add( new PrefixQuery( new Term( KEYWORDS_FIELD_NAME, token ) ), BooleanClause.Occur.MUST );
        }

        // I don't know if this is necessary, but can't hurt
        tokenStream.Close();
    }

如果您只需要完全匹配，您可以将 PrefixQuery 替换为 TermQuery(PrefixQuery 将匹配任何以“search*”开头的内容)