Thumbnail file hits. Based on a patch from D Bera
[beagle.git] / beagled / Lucene.Net / Analysis / LowerCaseTokenizer.cs
blobef69730914c720ebd85942809f6212fc5e3368f3
1 /*
2 * Copyright 2004 The Apache Software Foundation
3 *
4 * Licensed under the Apache License, Version 2.0 (the "License");
5 * you may not use this file except in compliance with the License.
6 * You may obtain a copy of the License at
7 *
8 * http://www.apache.org/licenses/LICENSE-2.0
9 *
10 * Unless required by applicable law or agreed to in writing, software
11 * distributed under the License is distributed on an "AS IS" BASIS,
12 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
13 * See the License for the specific language governing permissions and
14 * limitations under the License.
16 using System;
17 namespace Lucene.Net.Analysis
20 /// <summary> LowerCaseTokenizer performs the function of LetterTokenizer
21 /// and LowerCaseFilter together. It divides text at non-letters and converts
22 /// them to lower case. While it is functionally equivalent to the combination
23 /// of LetterTokenizer and LowerCaseFilter, there is a performance advantage
24 /// to doing the two tasks at once, hence this (redundant) implementation.
25 /// <P>
26 /// Note: this does a decent job for most European languages, but does a terrible
27 /// job for some Asian languages, where words are not separated by spaces.
28 /// </summary>
29 public sealed class LowerCaseTokenizer : LetterTokenizer
31 /// <summary>Construct a new LowerCaseTokenizer. </summary>
32 public LowerCaseTokenizer(System.IO.TextReader in_Renamed) : base(in_Renamed)
36 /// <summary>Collects only characters which satisfy
37 /// {@link Character#isLetter(char)}.
38 /// </summary>
39 protected internal override char Normalize(char c)
41 return System.Char.ToLower(c);