Lucene.net:查询和使用过滤器来限制结果
本文关键字：过滤器 结果 net 查询 Lucene | 更新日期: 2023-09-27 18:10:12
像往常一样，我求助于Stackoverflow用户群的大量脑力来帮助解决Lucene问题。. NET问题，我正在与之斗争。首先，当谈到Lucene和Lucene时，我完全是个新手。通过使用分散的教程和在线代码片段，我为我的场景拼凑了以下解决方案。
场景
我有以下结构的索引:
---------------------------------------------------------
| 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。
我想到了什么来实现这一点(经过多次访问谷歌)是使用一个"安全字段"和一个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);
按预期工作，只返回id为1和3的文档。问题是，在大索引上，这个过程变得非常慢。
最后，我的问题是……有没有人有任何加快速度的建议，或者有比我在这里展示的更有效的替代解决方案?
如果你索引你的安全字段作为分析(这样它分割你的安全字符串为1 12 4…)
你可以创建一个像这样的过滤器
Filter filter = new QueryFilter(new TermQuery(new Term("security ", "1")));
或
形成一个类似some text +security:1
我用一个简单的例子来解释我在上一个答案中的意思。
我做得很快，不尊重最佳实践，但它应该给你一个想法。
注意，需要对安全字段进行标记，以便其中的每个ID都是单独的标记，例如使用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();
}
}
}