KickJava   Java API By Example, From Geeks To Geeks.

Java > Open Source Codes > org > apache > lucene > analysis > cz > CzechAnalyzer


1 package org.apache.lucene.analysis.cz;
2
3 /**
4  * Copyright 2004-2005 The Apache Software Foundation
5  *
6  * Licensed under the Apache License, Version 2.0 (the "License");
7  * you may not use this file except in compliance with the License.
8  * You may obtain a copy of the License at
9  *
10  * http://www.apache.org/licenses/LICENSE-2.0
11  *
12  * Unless required by applicable law or agreed to in writing, software
13  * distributed under the License is distributed on an "AS IS" BASIS,
14  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
15  * See the License for the specific language governing permissions and
16  * limitations under the License.
17  */
18
19 import org.apache.lucene.analysis.Analyzer;
20 import org.apache.lucene.analysis.LowerCaseFilter;
21 import org.apache.lucene.analysis.StopFilter;
22 import org.apache.lucene.analysis.TokenStream;
23 import org.apache.lucene.analysis.WordlistLoader;
24 import org.apache.lucene.analysis.standard.StandardFilter;
25 import org.apache.lucene.analysis.standard.StandardTokenizer;
26
27 import java.io.*;
28 import java.util.Hashtable JavaDoc;
29 import java.util.HashSet JavaDoc;
30 import java.util.Set JavaDoc;
31
32 /**
33  * Analyzer for Czech language. Supports an external list of stopwords (words that
34  * will not be indexed at all).
35  * A default set of stopwords is used unless an alternative list is specified, the
36  * exclusion list is empty by default.
37  *
38  * @author Lukas Zapletal [lzap@root.cz]
39  */
40 public final class CzechAnalyzer extends Analyzer {
41
42     /**
43      * List of typical stopwords.
44      */
45     public final static String JavaDoc[] CZECH_STOP_WORDS = {
46         "a","s","k","o","i","u","v","z","dnes","cz","t\u00edmto","bude\u0161","budem",
47         "byli","jse\u0161","m\u016fj","sv\u00fdm","ta","tomto","tohle","tuto","tyto",
48         "jej","zda","pro\u010d","m\u00e1te","tato","kam","tohoto","kdo","kte\u0159\u00ed",
49         "mi","n\u00e1m","tom","tomuto","m\u00edt","nic","proto","kterou","byla",
50         "toho","proto\u017ee","asi","ho","na\u0161i","napi\u0161te","re","co\u017e","t\u00edm",
51         "tak\u017ee","sv\u00fdch","jej\u00ed","sv\u00fdmi","jste","aj","tu","tedy","teto",
52         "bylo","kde","ke","prav\u00e9","ji","nad","nejsou","\u010di","pod","t\u00e9ma",
53         "mezi","p\u0159es","ty","pak","v\u00e1m","ani","kdy\u017e","v\u0161ak","neg","jsem",
54         "tento","\u010dl\u00e1nku","\u010dl\u00e1nky","aby","jsme","p\u0159ed","pta","jejich",
55         "byl","je\u0161t\u011b","a\u017e","bez","tak\u00e9","pouze","prvn\u00ed","va\u0161e","kter\u00e1",
56         "n\u00e1s","nov\u00fd","tipy","pokud","m\u016f\u017ee","strana","jeho","sv\u00e9","jin\u00e9",
57         "zpr\u00e1vy","nov\u00e9","nen\u00ed","v\u00e1s","jen","podle","zde","u\u017e","b\u00fdt","v\u00edce",
58         "bude","ji\u017e","ne\u017e","kter\u00fd","by","kter\u00e9","co","nebo","ten","tak",
59         "m\u00e1","p\u0159i","od","po","jsou","jak","dal\u0161\u00ed","ale","si","se","ve",
60         "to","jako","za","zp\u011bt","ze","do","pro","je","na","atd","atp",
61         "jakmile","p\u0159i\u010dem\u017e","j\u00e1","on","ona","ono","oni","ony","my","vy",
62         "j\u00ed","ji","m\u011b","mne","jemu","tomu","t\u011bm","t\u011bmu","n\u011bmu","n\u011bmu\u017e",
63         "jeho\u017e","j\u00ed\u017e","jeliko\u017e","je\u017e","jako\u017e","na\u010de\u017e",
64     };
65
66     /**
67      * Contains the stopwords used with the StopFilter.
68      */
69     private Set JavaDoc stoptable;
70
71     /**
72      * Builds an analyzer with the default stop words ({@link #CZECH_STOP_WORDS}).
73      */
74     public CzechAnalyzer() {
75         stoptable = StopFilter.makeStopSet( CZECH_STOP_WORDS );
76     }
77
78     /**
79      * Builds an analyzer with the given stop words.
80      */
81     public CzechAnalyzer( String JavaDoc[] stopwords ) {
82         stoptable = StopFilter.makeStopSet( stopwords );
83     }
84
85     /**
86      * Builds an analyzer with the given stop words.
87    *
88    * @deprecated
89      */
90     public CzechAnalyzer( Hashtable JavaDoc stopwords ) {
91         stoptable = new HashSet JavaDoc(stopwords.keySet());
92     }
93
94     public CzechAnalyzer( HashSet JavaDoc stopwords ) {
95         stoptable = stopwords;
96     }
97
98     /**
99      * Builds an analyzer with the given stop words.
100      */
101     public CzechAnalyzer( File stopwords ) throws IOException {
102         stoptable = WordlistLoader.getWordSet( stopwords );
103     }
104
105     /**
106      * Loads stopwords hash from resource stream (file, database...).
107      * @param wordfile File containing the wordlist
108      * @param encoding Encoding used (win-1250, iso-8859-2, ...), null for default system encoding
109      */
110     public void loadStopWords( InputStream wordfile, String JavaDoc encoding ) {
111         if ( wordfile == null ) {
112             stoptable = new HashSet JavaDoc();
113             return;
114         }
115         try {
116             // clear any previous table (if present)
117 stoptable = new HashSet JavaDoc();
118
119             InputStreamReader isr;
120             if (encoding == null)
121                 isr = new InputStreamReader(wordfile);
122             else
123                 isr = new InputStreamReader(wordfile, encoding);
124
125             LineNumberReader lnr = new LineNumberReader(isr);
126             String JavaDoc word;
127             while ( ( word = lnr.readLine() ) != null ) {
128                 stoptable.add(word);
129             }
130
131         } catch ( IOException e ) {
132             stoptable = null;
133         }
134     }
135
136     /**
137      * Creates a TokenStream which tokenizes all the text in the provided Reader.
138      *
139      * @return A TokenStream build from a StandardTokenizer filtered with
140      * StandardFilter, LowerCaseFilter, and StopFilter
141      */
142     public final TokenStream tokenStream( String JavaDoc fieldName, Reader reader ) {
143         TokenStream result = new StandardTokenizer( reader );
144         result = new StandardFilter( result );
145         result = new LowerCaseFilter( result );
146         result = new StopFilter( result, stoptable );
147         return result;
148     }
149 }
150
151
Popular Tags