Lucene“结尾为”查询

Question

I am using lucene.net version 2.9.2.2 with .net4. I am looking for "ends with" query along with path. where it should not tokenize and return TRUE if it occurs in between.

Indexed paths:

C:\Users\vj\folder1\lucene\
C:\Users\vj\folder1\lucene\folder1\folder2
C:\Users\vj\folder2\lucene2\folder1\lucene\

Index Code:

new Field("PATH", strPath, Field.Store.YES, Field.Index.NOT_ANALYZED));
//Standard Analyzer
Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_29);
var writer = new IndexWriter(directory, analyzer, true, IndexWriter.MaxFieldLength.LIMITED);

Search Code:

Analyzer analyzer = new StandardAnalyzer(Version.LUCENE_29);
var queryParser = new QueryParser(Version.LUCENE_29, "PATH", analyzer);
var query = queryParser.Parse(strPath);

---

search query: folder1\\lucene\\

expected result:

C:\Users\vj\folder1\lucene\
C:\Users\vj\folder2\lucene2\folder1\lucene\

How to get above result. I have seen many questions on SO regarding same. but none contains piece of working code.

Answer 1

Here is a sample program that gives the output you are looking for.

Things to note:

• The QueryParser by default does not allow a leading wildcard (for performance-reasons).
• The field 'Path' is not analyzed, so the analyzer passed to the IndexWriter is not used.
• The StandardAnalyzer strips backslashes, so the program uses a WhitespaceAnalyzer which leaves them intact.
• Backslashes needs to be escaped when passing them to QueryParser.

Hope this helps you.

using System;
using Lucene.Net.Analysis;
using Lucene.Net.Analysis.Standard;
using Lucene.Net.Documents;
using Lucene.Net.Index;
using Lucene.Net.QueryParsers;
using Lucene.Net.Search;
using Lucene.Net.Store;

namespace TestProgram
{
  class Program
  {
    static void Main(string[] args)
    {
      FSDirectory directory = FSDirectory.Open(@"c:\temp\myindex");

      BuildIndex(directory);
      QueryIndex(directory);
    }

    static void BuildIndex(Directory directory)
    {
      string[] paths = new[]
      {
        @"C:\Users\vj\folder1\lucene\",
        @"C:\Users\vj\folder1\lucene\folder1\folder2",
        @"C:\Users\vj\folder2\lucene2\folder1\lucene\"
      };

      Analyzer analyzer = new WhitespaceAnalyzer();

      using (var writer = new IndexWriter(directory, analyzer, true, IndexWriter.MaxFieldLength.LIMITED))
      {
        foreach (string path in paths)
        {
          Document doc = new Document();
          var field = new Field("Path", path, Field.Store.YES, Field.Index.NOT_ANALYZED);
          doc.Add(field);

          writer.AddDocument(doc);
        }
      }
    }

    private static void QueryIndex(Directory directory)
    {
      string userQueryString = @"folder1\lucene\";

      Analyzer analyzer = new WhitespaceAnalyzer();
      var queryParser = new QueryParser(Lucene.Net.Util.Version.LUCENE_29, "Path", analyzer);
      queryParser.AllowLeadingWildcard = true;

      string queryString = "*" + userQueryString.Replace(@"\", @"\\");

      var query = queryParser.Parse(queryString);

      IndexSearcher searcher = new IndexSearcher(directory);
      IndexReader reader = searcher.IndexReader;
      TopDocs topDocs = searcher.Search(query, 100);

      foreach (ScoreDoc doc in topDocs.ScoreDocs)
      {
        string path = reader.Document(doc.Doc).Get("Path");
        Console.WriteLine(path);
      }
      Console.ReadKey();
    }
  }
}