Lucene.net：查询并使用过滤器来限制结果

Question

像往常一样，我求助于 Stackoverflow 用户群的庞大脑力来帮助解决我正在解决的 Lucene.NET 问题。首先，对于 Lucene 和 Lucene.NET，我是一个十足的菜鸟，通过使用网上分散的教程和代码片段，我为我的场景拼凑了以下解决方案。

场景

我有一个以下结构的索引：

---------------------------------------------------------
| id  |    date    | security |           text          |
---------------------------------------------------------
|  1  | 2011-01-01 | -1-12-4- | some analyzed text here |
---------------------------------------------------------
|  2  | 2011-01-01 |  -11-3-  | some analyzed text here |
---------------------------------------------------------
|  3  | 2011-01-01 |    -1-   | some analyzed text here |
---------------------------------------------------------

我需要能够查询文本字段，但将结果限制为具有特定 roleId 的用户。

为了实现这一点，我想到的（在多次访问 Google 之后）是使用“安全字段”和 Lucene 过滤器来限制结果集，如下所述：

class SecurityFilter : Lucene.Net.Search.Filter
{
    public override System.Collections.BitArray Bits(Lucene.Net.Index.IndexReader indexReader)
    {
        BitArray bitarray = new BitArray(indexReader.MaxDoc());

        for (int i = 0; i < bitarray.Length; i++)
        {
            if (indexReader.Document(i).Get("security").Contains("-1-"))
            {
                bitarray.Set(i, true);
            }
        }

        return bitarray;
    }
}

...然后...

Lucene.Net.Search.Sort sort = new Lucene.Net.Search.Sort(new Lucene.Net.Search.SortField("date", true));
Lucene.Net.Analysis.Standard.StandardAnalyzer analyzer = new Lucene.Net.Analysis.Standard.StandardAnalyzer(Lucene.Net.Util.Version.LUCENE_29);
Lucene.Net.Search.IndexSearcher searcher = new Lucene.Net.Search.IndexSearcher(Lucene.Net.Store.FSDirectory.Open(indexDirectory), true);
Lucene.Net.QueryParsers.QueryParser parser = new Lucene.Net.QueryParsers.QueryParser(Lucene.Net.Util.Version.LUCENE_29, "text", analyzer);
Lucene.Net.Search.Query query = parser.Parse("some search phrase");
SecurityFilter filter = new SecurityFilter();
Lucene.Net.Search.Hits hits = searcher.Search(query, filter, sort);

这按预期工作并且只会返回 id 为 1 和 3 的文档。问题是，对于大型索引，此过程会变得非常慢。

最后，我的问题...是否有人对如何加快速度有任何提示，或者有比我在这里提出的更有效的替代解决方案？

Answer 1

如果您对安全字段进行了分析索引（这样它将您的安全字符串拆分为 1 12 4 ...），

您可以创建这样的过滤器

Filter filter = new QueryFilter(new TermQuery(new Term("security ", "1")));

或

形成类似 some text +security:1 的查询

Answer 2

我用一个简单的例子改变了我的答案，解释了我在之前的答案中的意思。

我很快就做到了这一点，不尊重最佳实践，但它应该给你这个想法。

请注意，安全字段需要标记化，以便其中的每个 ID 都是单独的标记，使用 WhitespaceAnalyzer。

using System;
using System.Collections.Generic;
using System.Linq;
using System.Text;
using Lucene.Net.Search;
using Lucene.Net.Documents;
using Lucene.Net.Index;
using Lucene.Net.Analysis.Standard;
using System.IO;

namespace ConsoleApplication1
{
    class Program
    {
        public class RoleFilterCache
        {
            static public Dictionary<string, Filter> Cache = new Dictionary<string,Filter>();

            static public Filter Get(string role)
            {
                Filter cached = null;
                if (!Cache.TryGetValue(role, out cached))
                {
                    return null;
                }
                return cached;
            }

            static public void Put(string role, Filter filter)
            {
                if (role != null)
                {
                    Cache[role] = filter;
                }
            }
        }

        public class User
        {
            public string Username;
            public List<string> Roles;
        }

        public static Filter GetFilterForUser(User u)
        {
            BooleanFilter userFilter = new BooleanFilter();
            foreach (string rolename in u.Roles)
            {   
                // call GetFilterForRole and add to the BooleanFilter
                userFilter.Add(
                    new BooleanFilterClause(GetFilterForRole(rolename), BooleanClause.Occur.SHOULD)
                );
            }
            return userFilter;
        }

        public static Filter GetFilterForRole(string role)
        {
            Filter roleFilter = RoleFilterCache.Get(role);
            if (roleFilter == null)
            {
                roleFilter =
                    // the caching wrapper filter makes it cache the BitSet per segmentreader
                    new CachingWrapperFilter(
                        // builds the filter from the index and not from iterating
                        // stored doc content which is much faster
                        new QueryWrapperFilter(
                            new TermQuery(
                                new Term("security", role)
                            )
                        )
                );
                // put in cache
                RoleFilterCache.Put(role, roleFilter);
            }
            return roleFilter;
        }


        static void Main(string[] args)
        {
            IndexWriter iw = new IndexWriter(new FileInfo("C:\\example\\"), new StandardAnalyzer(), true);
            Document d = new Document();

            Field aField = new Field("content", "", Field.Store.YES, Field.Index.ANALYZED);
            Field securityField = new Field("security", "", Field.Store.NO, Field.Index.ANALYZED);

            d.Add(aField);
            d.Add(securityField);

            aField.SetValue("Only one can see.");
            securityField.SetValue("1");
            iw.AddDocument(d);
            aField.SetValue("One and two can see.");
            securityField.SetValue("1 2");
            iw.AddDocument(d);
            aField.SetValue("One and two can see.");
            securityField.SetValue("1 2");
            iw.AddDocument(d);
            aField.SetValue("Only two can see.");
            securityField.SetValue("2");
            iw.AddDocument(d);

            iw.Close();

            User userone = new User()
            {
                Username = "User one",
                Roles = new List<string>()
            };
            userone.Roles.Add("1");
            User usertwo = new User()
            {
                Username = "User two",
                Roles = new List<string>()
            };
            usertwo.Roles.Add("2");
            User userthree = new User()
            {
                Username = "User three",
                Roles = new List<string>()
            };
            userthree.Roles.Add("1");
            userthree.Roles.Add("2");

            PhraseQuery phraseQuery = new PhraseQuery();
            phraseQuery.Add(new Term("content", "can"));
            phraseQuery.Add(new Term("content", "see"));

            IndexSearcher searcher = new IndexSearcher("C:\\example\\", true);

            Filter securityFilter = GetFilterForUser(userone);
            TopDocs results = searcher.Search(phraseQuery, securityFilter,25);
            Console.WriteLine("User One Results:");
            foreach (var aResult in results.ScoreDocs)
            {
                Console.WriteLine(
                    searcher.Doc(aResult.doc).
                    Get("content")
                );
            }
            Console.WriteLine("\n\n");

            securityFilter = GetFilterForUser(usertwo);
            results = searcher.Search(phraseQuery, securityFilter, 25);
            Console.WriteLine("User two Results:");
            foreach (var aResult in results.ScoreDocs)
            {
                Console.WriteLine(
                    searcher.Doc(aResult.doc).
                    Get("content")
                );
            }
            Console.WriteLine("\n\n");

            securityFilter = GetFilterForUser(userthree);
            results = searcher.Search(phraseQuery, securityFilter, 25);
            Console.WriteLine("User three Results (should see everything):");
            foreach (var aResult in results.ScoreDocs)
            {
                Console.WriteLine(
                    searcher.Doc(aResult.doc).
                    Get("content")
                );
            }
            Console.WriteLine("\n\n");
            Console.ReadKey();
        }
    }
}