c# - Lucene.Net 搜索文件名/路径

Question

我第一次尝试使用 Lucene.Net

我有一个包含 500 个文档(html 和 pdf)的索引，其中包含一些字段，例如 url、内容、标题

当我搜索内容和/或标题时一切正常
但是当我搜索一个 Url 时，我没有得到任何结果

所以我找到了类似“/tlfdi/epapers/datenschutz2016/files/assets/common/downloads/page0004.pdf”但不是“page0004.pdf”的网址
还有“*”它不起作用。

索引和搜索使用 WhitespaceAnalyzer。使用 StandardAnalyzer，当我搜索“/kontakt/index.aspx”时，我得到的结果为零

搜索:

  WhitespaceAnalyzer analyzer = new WhitespaceAnalyzer();
  MultiFieldQueryParser parser = new MultiFieldQueryParser(Version.LUCENE_30,
    new[] { "url", "title", "description", "content", "keywords" }, analyzer);
  Query query = parseQuery(searchQuery, parser);
    Lucene.Net.Search.ScoreDoc[] hits = (Lucene.Net.Search.ScoreDoc[])searcher.Search(  
      query, null, hits_limit, Sort.RELEVANCE).ScoreDocs;

有人可以帮忙吗？

Answer 1

分析器的标准票价不会满足您的要求，相反，您必须编写自定义分词器和分析器。

这很简单!我们只需要草拟出一个分词器和一个分析器。

UrlTokenizer 负责生成 token 。

// UrlTokenizer delimits tokens by whitespace, '.' and '/'
using AttributeSource = Lucene.Net.Util.AttributeSource;  
public class UrlTokenizer : CharTokenizer
{
    public UrlTokenizer(System.IO.TextReader @in)
        : base(@in)
    {
    }
    public UrlTokenizer(AttributeSource source, System.IO.TextReader @in)
        : base(source, @in)
    {
    }

    public UrlTokenizer(AttributeFactory factory, System.IO.TextReader @in)
        : base(factory, @in)
    {
    }
    //
    // This is where all the magic happens for our UrlTokenizer!
    // Whitespace, forward slash or a period are a token boundary.
    // 
    protected override bool IsTokenChar(char c)
    {
        return !char.IsWhiteSpace(c) && c != '/' && c != '.';
    }
}

UrlAnalyzer 使用输入流并实现 UrlTokenizer 和 LowerCaseFilter 以进行不区分大小写的搜索。

// Custom Analyzer implementing UrlTokenizer and LowerCaseFilter.
public sealed class UrlAnalyzer : Analyzer
{
    public override TokenStream TokenStream(System.String fieldName, System.IO.TextReader reader)
    {
        //
        // This is where all the magic happens for UrlAnalyzer!
        // UrlTokenizer token text are filtered to lowercase text.
        return new LowerCaseFilter(new UrlTokenizer(reader));
    }
    public override TokenStream ReusableTokenStream(System.String fieldName, System.IO.TextReader reader)
    {
        Tokenizer tokenizer = (Tokenizer)PreviousTokenStream;
        if (tokenizer == null)
        {
            tokenizer = new UrlTokenizer(reader);
            PreviousTokenStream = tokenizer;
        }
        else
            tokenizer.Reset(reader);
        return tokenizer;
    }
}

所以这是演示 UrlAnalyzer 的代码。为了清楚起见，我用 QueryParser 替换了 MultiFieldQueryParser。

//
// Demonstrate UrlAnalyzer using an in memory index.
//
public static void testUrlAnalyzer()
{     
    string url = @"/tlfdi/epapers/datenschutz2016/files/assets/common/downloads/page0004.pdf";
    UrlAnalyzer analyzer = new UrlAnalyzer();
    Directory directory = new RAMDirectory();
    QueryParser parser = new QueryParser(Lucene.Net.Util.Version.LUCENE_30, "url", analyzer);
    IndexWriter writer = new IndexWriter(directory, analyzer, true, new IndexWriter.MaxFieldLength(2048));
    //
    // index a document. We're only interested in the "url" field of a document.
    //
    Document doc = new Document();
    Field field = new Field("url", url, Field.Store.NO, Field.Index.ANALYZED);
    doc.Add(field);
    writer.AddDocument(doc);
    writer.Commit();
    //
    // search the index for any documents having 'page004.pdf' in the url field.
    //
    string searchText = "url:page0004.pdf";
    IndexReader reader = IndexReader.Open(directory, true);
    IndexSearcher searcher = new IndexSearcher(reader);
    Query query = parser.Parse(searchText);
    ScoreDoc[] hits = searcher.Search(query, null, 10, Sort.RELEVANCE).ScoreDocs;
    if (hits.Length == 0)
        throw new System.Exception("RamblinRose is fail!");
    //
    // search the index for any documents having the full URL we indexed.
    //
    searchText = "url:\"" + url + "\"";
    query = parser.Parse(searchText);
    hits = searcher.Search(query, null, 10, Sort.RELEVANCE).ScoreDocs;
    if (hits.Length == 0)
        throw new System.Exception("RamblinRose is fail!");
}

Lucene.net 是个好东西。我希望这段代码能提高你对 Lucene 分析的理解。

祝你好运!

附注当心通配符搜索来解决问题，它是大型索引的真正 killer 。