如何使用Lucene.net实现自定义过滤器?

时间:2009-07-03 15:53:55

标签: c# .net filter lucene.net

以下代码来自Lucene In Action一书(最初是Java)。它用于构建“允许”文档列表(从用户权限的角度来看)以过滤搜索结果。问题是termsDocs.Read()方法不接受'doc'和'freq'数组通过引用传递,因此在设置位数组中的位时它们仍然是空的。

任何人都可以提供帮助,使用Lucene自定义过滤器(尤其是.net)的示例似乎很薄。感谢。

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;
    }
}

我正在使用Lucene.net 2.0.0.4,但TermDocs界面在最新的分支中看起来仍然相同:https://svn.apache.org/repos/asf/incubator/lucene.net/trunk/C%23/src/Lucene.Net/Index/TermDocs.cs

2 个答案:

答案 0 :(得分:15)

以下是使用自定义过滤器的Lucene.NET的工作示例,您可以查看:

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;
    }
}

答案 1 :(得分:2)

这里有点困惑,因为传递数组确实通过引用传递它。 例如,以下blurb将打印10 10 10 10 10,表明数组值已更新。

我在这里错过了什么吗?

    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;
        }
    }