如何使用Lucene.net实现自定义过滤器？

Question

The code below is from the Lucene In Action book (originally in Java). It's for building a list of 'allowed' documents (from a user permission point of view) to filter search results with. The problem is the termsDocs.Read() method does not accept the 'doc' and 'freq' arrays to be passed by reference, so they're still empty when it comes to setting the bit in the bit array.

Can anyone help, examples of using Lucene custom filters (especially in .net) seem to be thin on the ground. Thanks.

public class LuceneCustomFilter : Lucene.Net.Search.Filter
{
    string[] _luceneIds;

    public LuceneCustomFilter(string[] luceneIds)
    {
        _luceneIds = luceneIds;
    }

    public override BitArray Bits(Lucene.Net.Index.IndexReader indexReader)
    {
        BitArray bitarray = new BitArray(indexReader.MaxDoc());

        int[] docs = new int[1];
        int[] freq = new int[1];

        for (int i = 0; i < _luceneIds.Length; i++)
        {
            if (!string.IsNullOrEmpty(_luceneIds[i]))
            {
                Lucene.Net.Index.TermDocs termDocs = indexReader.TermDocs(
                    new Lucene.Net.Index.Term(@"luceneId", _luceneIds[i]));

                int count = termDocs.Read(docs, freq);

                if (count == 1)
                {
                    bitarray.Set(docs[0], true);
                }
            }
        }

        return bitarray;
    }
}

I'm using Lucene.net 2.0.0.4, but the TermDocs interface still appears to be the same in the latest branch here: https://svn.apache.org/repos/asf/incubator/lucene.net/trunk/C%23/src/Lucene.Net/Index/TermDocs.cs

Answer 1

Here's a working example of Lucene.NET using a custom filter you might take a look at:

using System;
using System.Collections;
using Lucene.Net.Analysis;
using Lucene.Net.Documents;
using Lucene.Net.Index;
using Lucene.Net.Search;
using Lucene.Net.Store;

class Program
{
    static void Main(string[] args)
    {
        Directory index = new RAMDirectory();
        Analyzer analyzer = new KeywordAnalyzer();
        IndexWriter writer = new IndexWriter(index, analyzer, true);

        Document doc = new Document();
        doc.Add(new Field("title", "t1", Field.Store.YES, 
            Field.Index.TOKENIZED));
        writer.AddDocument(doc);
        doc = new Document();
        doc.Add(new Field("title", "t2", Field.Store.YES, 
            Field.Index.TOKENIZED));
        writer.AddDocument(doc);

        writer.Close();

        Searcher searcher = new IndexSearcher(index);
        Query query = new MatchAllDocsQuery();
        Filter filter = new LuceneCustomFilter();
        Sort sort = new Sort("title", true);
        Hits hits = searcher.Search(query, filter, sort);
        IEnumerator hitsEnumerator = hits.Iterator();

        while (hitsEnumerator.MoveNext())
        {
            Hit hit = (Hit)hitsEnumerator.Current;
            Console.WriteLine(hit.GetDocument().GetField("title").
                StringValue());
        }
    }
}

public class LuceneCustomFilter : Filter
{
    public override BitArray Bits(IndexReader indexReader)
    {
        BitArray bitarray = new BitArray(indexReader.MaxDoc());

        int[] docs = new int[1];
        int[] freq = new int[1];

        TermDocs termDocs = indexReader.TermDocs(
                new Term(@"title", "t1"));

        int count = termDocs.Read(docs, freq);
        if (count == 1)
        {
            bitarray.Set(docs[0], true);
        }
        return bitarray;
    }
}

Answer 2

A bit confused here because passing an array does in fact pass it by reference. For instance the following blurb will print 10 10 10 10 10 showing that the array values have been updated.

Am I missing something here?

    public void TestPassing()
    {
        int[] stuff = new int[] {5, 5, 5, 5};

        Add(stuff, 5);
        for (int i = 0; i < stuff.Length; i++)
        {
            Console.Write(stuff[i]);
        }
    }

    public void Add(int[] stuff, int x)
    {
        for(int i = 0; i < stuff.Length; i++)
        {
            stuff[i] = stuff[i] + x;
        }
    }