diff options
Diffstat (limited to 'src/core/Analysis/LowerCaseTokenizer.cs')
-rw-r--r-- | src/core/Analysis/LowerCaseTokenizer.cs | 60 |
1 files changed, 60 insertions, 0 deletions
diff --git a/src/core/Analysis/LowerCaseTokenizer.cs b/src/core/Analysis/LowerCaseTokenizer.cs new file mode 100644 index 0000000..4cea217 --- /dev/null +++ b/src/core/Analysis/LowerCaseTokenizer.cs @@ -0,0 +1,60 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one or more + * contributor license agreements. See the NOTICE file distributed with + * this work for additional information regarding copyright ownership. + * The ASF licenses this file to You under the Apache License, Version 2.0 + * (the "License"); you may not use this file except in compliance with + * the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ + +using AttributeSource = Lucene.Net.Util.AttributeSource; + +namespace Lucene.Net.Analysis +{ + + /// <summary> LowerCaseTokenizer performs the function of LetterTokenizer + /// and LowerCaseFilter together. It divides text at non-letters and converts + /// them to lower case. While it is functionally equivalent to the combination + /// of LetterTokenizer and LowerCaseFilter, there is a performance advantage + /// to doing the two tasks at once, hence this (redundant) implementation. + /// <p/> + /// Note: this does a decent job for most European languages, but does a terrible + /// job for some Asian languages, where words are not separated by spaces. + /// </summary> + public sealed class LowerCaseTokenizer:LetterTokenizer + { + /// <summary>Construct a new LowerCaseTokenizer. </summary> + public LowerCaseTokenizer(System.IO.TextReader @in) + : base(@in) + { + } + + /// <summary>Construct a new LowerCaseTokenizer using a given <see cref="AttributeSource" />. </summary> + public LowerCaseTokenizer(AttributeSource source, System.IO.TextReader @in) + : base(source, @in) + { + } + + /// <summary>Construct a new LowerCaseTokenizer using a given <see cref="Lucene.Net.Util.AttributeSource.AttributeFactory" />. </summary> + public LowerCaseTokenizer(AttributeFactory factory, System.IO.TextReader @in) + : base(factory, @in) + { + } + + /// <summary>Converts char to lower case + /// <see cref="char.ToLower(char)" />. + /// </summary> + protected internal override char Normalize(char c) + { + return System.Char.ToLower(c); + } + } +}
\ No newline at end of file |