blob: fd13261084aef353bfb2e09ff52ae83599395bf8 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
|
/*
* 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;
using Lucene.Net.Analysis.Tokenattributes;
using Token = Lucene.Net.Analysis.Token;
using TokenFilter = Lucene.Net.Analysis.TokenFilter;
using TokenStream = Lucene.Net.Analysis.TokenStream;
namespace Lucene.Net.Analysis.Standard
{
/// <summary>Normalizes tokens extracted with <see cref="StandardTokenizer" />. </summary>
public sealed class StandardFilter:TokenFilter
{
/// <summary>Construct filtering <i>in</i>. </summary>
public StandardFilter(TokenStream in_Renamed):base(in_Renamed)
{
termAtt = AddAttribute<ITermAttribute>();
typeAtt = AddAttribute<ITypeAttribute>();
}
private static readonly System.String APOSTROPHE_TYPE;
private static readonly System.String ACRONYM_TYPE;
// this filters uses attribute type
private ITypeAttribute typeAtt;
private ITermAttribute termAtt;
/// <summary>Returns the next token in the stream, or null at EOS.
/// <p/>Removes <tt>'s</tt> from the end of words.
/// <p/>Removes dots from acronyms.
/// </summary>
public override bool IncrementToken()
{
if (!input.IncrementToken())
{
return false;
}
char[] buffer = termAtt.TermBuffer();
int bufferLength = termAtt.TermLength();
System.String type = typeAtt.Type;
if ((System.Object) type == (System.Object) APOSTROPHE_TYPE && bufferLength >= 2 && buffer[bufferLength - 2] == '\'' && (buffer[bufferLength - 1] == 's' || buffer[bufferLength - 1] == 'S'))
{
// Strip last 2 characters off
termAtt.SetTermLength(bufferLength - 2);
}
else if ((System.Object) type == (System.Object) ACRONYM_TYPE)
{
// remove dots
int upto = 0;
for (int i = 0; i < bufferLength; i++)
{
char c = buffer[i];
if (c != '.')
buffer[upto++] = c;
}
termAtt.SetTermLength(upto);
}
return true;
}
static StandardFilter()
{
APOSTROPHE_TYPE = StandardTokenizerImpl.TOKEN_TYPES[StandardTokenizerImpl.APOSTROPHE];
ACRONYM_TYPE = StandardTokenizerImpl.TOKEN_TYPES[StandardTokenizerImpl.ACRONYM];
}
}
}
|