📄 ktdictseganalyzer.cs
字号:
/**********************************************
* 采用KTDictSeg的Lucene.Net 中文分词分析器
* 参考 suyuan 的开源代码修改
* suyuan 的开源代码出处 http://www.cnblogs.com/suyuan/archive/2008/03/25/1120827.html
*********************************************/
using System;
using System.Collections;
using System.Collections.Generic;
using System.IO;
using System.Diagnostics;
namespace Lucene.Net.Analysis.KTDictSeg
{
public class KTDictSegAnalyzer : Analyzer
{
private static object m_LockObj = new object();
private static Stopwatch m_Duration = new Stopwatch();
/// <summary>
/// 统计分词占用时间
/// </summary>
public static long Duration
{
get
{
return m_Duration.ElapsedMilliseconds;
}
set
{
m_Duration.Reset();
}
}
public KTDictSegAnalyzer()
{
}
public override TokenStream TokenStream(string fieldName, TextReader reader)
{
lock (m_LockObj)
{
#if DEBUG
m_Duration.Start();
#endif
TokenStream result = new KTDictSegTokenizer(reader);
#if DEBUG
m_Duration.Stop();
#endif
result = new LowerCaseFilter(result);
return result;
}
}
}
}
⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -