isolatin1accentfilter.cs

Lucene.Net 版本源码 测试通过

/*
 * 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 System;

namespace Lucene.Net.Analysis
{
	
    /// <summary> A filter that replaces accented characters in the ISO Latin 1 character set 
    /// (ISO-8859-1) by their unaccented equivalent. The case will not be altered.
    /// <p>
    /// For instance, '&agrave;' will be replaced by 'a'.
    /// <p>
    /// </summary>
    public class ISOLatin1AccentFilter : TokenFilter
    {
        public ISOLatin1AccentFilter(TokenStream input) : base(input)
        {
        }
		
		public override Token Next()
		{
			Token t = input.Next();
			if (t != null)
				t.SetTermText(RemoveAccents(t.TermText()));
			return t;
		}
		
        /// <summary> To replace accented characters in a String by unaccented equivalents.</summary>
        public static System.String RemoveAccents(System.String input)
        {
            System.Text.StringBuilder output = new System.Text.StringBuilder();
            for (int i = 0; i < input.Length; i++)
            {
                long val = input[i];

                switch (input[i])
                {
					
                    case '\u00C0':  // À
                    case '\u00C1':  // Ã?
                    case '\u00C2':  // Â
                    case '\u00C3':  // Ã
                    case '\u00C4':  // Ä
                    case '\u00C5':  // Ã…
                        output.Append("A");
                        break;
					
                    case '\u00C6':  // Æ
                        output.Append("AE");
                        break;
					
                    case '\u00C7':  // Ç
                        output.Append("C");
                        break;
					
                    case '\u00C8':  // È
                    case '\u00C9':  // É
                    case '\u00CA':  // Ê
                    case '\u00CB':  // Ë
                        output.Append("E");
                        break;
					
                    case '\u00CC':  // Ì
                    case '\u00CD':  // Ã?
                    case '\u00CE':  // ÃŽ
                    case '\u00CF':  // Ã?
                        output.Append("I");
                        break;
					
                    case '\u00D0':  // Ã?
                        output.Append("D");
                        break;
					
                    case '\u00D1':  // Ñ
                        output.Append("N");
                        break;
					
                    case '\u00D2':  // Ã’
                    case '\u00D3':  // Ó
                    case '\u00D4':  // Ô
                    case '\u00D5':  // Õ
                    case '\u00D6':  // Ö
                    case '\u00D8':  // Ø
                        output.Append("O");
                        break;
					
                    case '\u0152':  // Å’
                        output.Append("OE");
                        break;
					
                    case '\u00DE':  // Þ
                        output.Append("TH");
                        break;
					
                    case '\u00D9':  // Ù
                    case '\u00DA':  // Ú
                    case '\u00DB':  // Û
                    case '\u00DC':  // Ü
                        output.Append("U");
                        break;
					
                    case '\u00DD':  // Ã?
                    case '\u0178':  // Ÿ
                        output.Append("Y");
                        break;
					
                    case '\u00E0':  // à
                    case '\u00E1':  // á
                    case '\u00E2':  // â
                    case '\u00E3':  // ã
                    case '\u00E4':  // ä
                    case '\u00E5':  // å
                        output.Append("a");
                        break;
					
                    case '\u00E6':  // æ
                        output.Append("ae");
                        break;
					
                    case '\u00E7':  // ç
                        output.Append("c");
                        break;
					
                    case '\u00E8':  // è
                    case '\u00E9':  // é
                    case '\u00EA':  // ê
                    case '\u00EB':  // ë
                        output.Append("e");
                        break;
					
                    case '\u00EC':  // ì
                    case '\u00ED':  // í
                    case '\u00EE':  // î
                    case '\u00EF':  // ï
                        output.Append("i");
                        break;
					
                    case '\u00F0':  // ð
                        output.Append("d");
                        break;
					
                    case '\u00F1':  // ñ
                        output.Append("n");
                        break;
					
                    case '\u00F2':  // ò
                    case '\u00F3':  // ó
                    case '\u00F4':  // ô
                    case '\u00F5':  // õ
                    case '\u00F6':  // ö
                    case '\u00F8':  // ø
                        output.Append("o");
                        break;
					
                    case '\u0153':  // Å“
                        output.Append("oe");
                        break;
					
                    case '\u00DF':  // ß
                        output.Append("ss");
                        break;
					
                    case '\u00FE':  // þ
                        output.Append("th");
                        break;
					
                    case '\u00F9':  // ù
                    case '\u00FA':  // ú
                    case '\u00FB':  // û
                    case '\u00FC':  // ü
                        output.Append("u");
                        break;
					
                    case '\u00FD':  // ý
                    case '\u00FF':  // ÿ
                        output.Append("y");
                        break;
					
                    default: 
                        output.Append(input[i]);
                        break;
					
                }
            }
            return output.ToString();
        }
    }
}