cvsimport
[beagle.git] / beagled / Lucene.Net / Analysis / LowerCaseTokenizer.cs
blobfa410326f5ad876f2421303994834959c53ab13f
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.
17 using System;
19 namespace Lucene.Net.Analysis
22 /// <summary> LowerCaseTokenizer performs the function of LetterTokenizer
23 /// and LowerCaseFilter together. It divides text at non-letters and converts
24 /// them to lower case. While it is functionally equivalent to the combination
25 /// of LetterTokenizer and LowerCaseFilter, there is a performance advantage
26 /// to doing the two tasks at once, hence this (redundant) implementation.
27 /// <P>
28 /// Note: this does a decent job for most European languages, but does a terrible
29 /// job for some Asian languages, where words are not separated by spaces.
30 /// </summary>
31 public sealed class LowerCaseTokenizer : LetterTokenizer
33 /// <summary>Construct a new LowerCaseTokenizer. </summary>
34 public LowerCaseTokenizer(System.IO.TextReader in_Renamed) : base(in_Renamed)
38 /// <summary>Collects only characters which satisfy
39 /// {@link Character#isLetter(char)}.
40 /// </summary>
41 protected internal override char Normalize(char c)
43 return System.Char.ToLower(c);