Examples of WVTStemmer

Examples of edu.udo.cs.wvtool.generic.stemmer.WVTStemmer

34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
        WVTool wvt = new WVTool(false);

        // Initialize the configuration
        WVTConfiguration config = new WVTConfiguration();

        final WVTStemmer dummyStemmer = new DummyStemmer();
        final WVTStemmer porterStemmer = new PorterStemmerWrapper();

        config.setConfigurationRule(WVTConfiguration.STEP_STEMMER, new WVTConfigurationRule() {
            public Object getMatchingComponent(WVTDocumentInfo d) {

                if (d.getContentLanguage().equals("english"))
                    return porterStemmer;
                else
                    return dummyStemmer;
            }
        });

        WVTStemmer stemmer = new LovinsStemmerWrapper();

        config.setConfigurationRule(WVTConfiguration.STEP_STEMMER, new WVTConfigurationFact(stemmer));

        // Initialize the input list with two classes
        WVTFileInputList list = new WVTFileInputList(1);
View Full Code Here

Examples of edu.udo.cs.wvtool.generic.stemmer.WVTStemmer

30
31
32
33
34
35
36
37
38
39
40
41
        WVTool wvt = new WVTool(true);

        // Initialize the configuration
        WVTConfiguration config = new WVTConfiguration();

        final WVTStemmer dummyStemmer = new DummyStemmer();
        final WVTStemmer porterStemmer = new PorterStemmerWrapper();

        config.setConfigurationRule(WVTConfiguration.STEP_STEMMER, new WVTConfigurationRule() {
            public Object getMatchingComponent(WVTDocumentInfo d) {

                if (d.getContentLanguage().equals("english"))
View Full Code Here

Examples of edu.udo.cs.wvtool.generic.stemmer.WVTStemmer

131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
        WVTDocumentLoader loader = null;
        WVTInputFilter infilter = null;
        WVTCharConverter charConverter = null;
        WVTTokenizer tokenizer = null;
        WVTWordFilter wordFilter = null;
        WVTStemmer stemmer = null;

        // Obtain an expanded list of all documents to consider
        Iterator inList = input.getEntries();

        // Get through the list
        while (inList.hasNext()) {

            WVTDocumentInfo d = (WVTDocumentInfo) inList.next();

            try {

                // Intialize all required components for this document

                loader = (WVTDocumentLoader) config.getComponentForStep(WVTConfiguration.STEP_LOADER, d);
                infilter = (WVTInputFilter) config.getComponentForStep(WVTConfiguration.STEP_INPUT_FILTER, d);
                charConverter = (WVTCharConverter) config.getComponentForStep(WVTConfiguration.STEP_CHAR_MAPPER, d);
                tokenizer = (WVTTokenizer) config.getComponentForStep(WVTConfiguration.STEP_TOKENIZER, d);
                wordFilter = (WVTWordFilter) config.getComponentForStep(WVTConfiguration.STEP_WORDFILTER, d);
                stemmer = (WVTStemmer) config.getComponentForStep(WVTConfiguration.STEP_STEMMER, d);

                // Process the document

                TokenEnumeration tokens = stemmer.stem(wordFilter.filter(tokenizer.tokenize(charConverter.convertChars(infilter.convertToPlainText(loader.loadDocument(d), d), d), d), d), d);

                while (tokens.hasMoreTokens()) {
                    wordList.addWordOccurance(tokens.nextToken());
                }
View Full Code Here

Examples of edu.udo.cs.wvtool.generic.stemmer.WVTStemmer

244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
        WVTDocumentLoader loader = null;
        WVTInputFilter infilter = null;
        WVTCharConverter charConverter = null;
        WVTTokenizer tokenizer = null;
        WVTWordFilter wordFilter = null;
        WVTStemmer stemmer = null;
        WVTVectorCreator vectorCreator = null;
        WVTOutputFilter outputFilter = null;

        // Obtain an expanded list of all documents to consider
        Iterator inList = input.getEntries();

        // Get through the list
        while (inList.hasNext()) {

            WVTDocumentInfo d = (WVTDocumentInfo) inList.next();

            try {

                // Intialize all required components for this document

                loader = (WVTDocumentLoader) config.getComponentForStep(WVTConfiguration.STEP_LOADER, d);
                infilter = (WVTInputFilter) config.getComponentForStep(WVTConfiguration.STEP_INPUT_FILTER, d);
                charConverter = (WVTCharConverter) config.getComponentForStep(WVTConfiguration.STEP_CHAR_MAPPER, d);
                tokenizer = (WVTTokenizer) config.getComponentForStep(WVTConfiguration.STEP_TOKENIZER, d);
                wordFilter = (WVTWordFilter) config.getComponentForStep(WVTConfiguration.STEP_WORDFILTER, d);
                stemmer = (WVTStemmer) config.getComponentForStep(WVTConfiguration.STEP_STEMMER, d);

                vectorCreator = (WVTVectorCreator) config.getComponentForStep(WVTConfiguration.STEP_VECTOR_CREATION, d);

                outputFilter = (WVTOutputFilter) config.getComponentForStep(WVTConfiguration.STEP_OUTPUT, d);

                // Process the document

                TokenEnumeration tokens = stemmer.stem(wordFilter.filter(tokenizer.tokenize(charConverter.convertChars(infilter.convertToPlainText(loader.loadDocument(d), d), d), d), d), d);

                while (tokens.hasMoreTokens()) {
                    wordList.addWordOccurance(tokens.nextToken());
                }
View Full Code Here

Examples of edu.udo.cs.wvtool.generic.stemmer.WVTStemmer

325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
        // Initialize pointers to components for the individual steps

        WVTCharConverter charConverter = null;
        WVTTokenizer tokenizer = null;
        WVTWordFilter wordFilter = null;
        WVTStemmer stemmer = null;
        WVTVectorCreator vectorCreator = null;

        WVTWordVector result = null;

        try {

            // Intialize all required components for this document

            charConverter = (WVTCharConverter) config.getComponentForStep(WVTConfiguration.STEP_CHAR_MAPPER, d);
            tokenizer = (WVTTokenizer) config.getComponentForStep(WVTConfiguration.STEP_TOKENIZER, d);
            wordFilter = (WVTWordFilter) config.getComponentForStep(WVTConfiguration.STEP_WORDFILTER, d);
            stemmer = (WVTStemmer) config.getComponentForStep(WVTConfiguration.STEP_STEMMER, d);

            vectorCreator = (WVTVectorCreator) config.getComponentForStep(WVTConfiguration.STEP_VECTOR_CREATION, d);

            // Process the document

            TokenEnumeration tokens = stemmer.stem(wordFilter.filter(tokenizer.tokenize(charConverter.convertChars(new StringReader(text), d), d), d), d);

            while (tokens.hasMoreTokens()) {
                wordList.addWordOccurance(tokens.nextToken());
            }
View Full Code Here

Examples of edu.udo.cs.wvtool.generic.stemmer.WVTStemmer

401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
        WVTDocumentLoader loader = null;
        WVTInputFilter infilter = null;
        WVTCharConverter charConverter = null;
        WVTTokenizer tokenizer = null;
        WVTWordFilter wordFilter = null;
        WVTStemmer stemmer = null;

        // Obtain an expanded list of all documents to consider
        Iterator inList = input.getEntries();

        // Get through the list
        while (inList.hasNext()) {

            WVTDocumentInfo d = (WVTDocumentInfo) inList.next();
            listener.openNewDocument(d);

            try {

                // Intialize all required components for this document

                loader = (WVTDocumentLoader) config.getComponentForStep(WVTConfiguration.STEP_LOADER, d);
                infilter = (WVTInputFilter) config.getComponentForStep(WVTConfiguration.STEP_INPUT_FILTER, d);
                charConverter = (WVTCharConverter) config.getComponentForStep(WVTConfiguration.STEP_CHAR_MAPPER, d);
                tokenizer = (WVTTokenizer) config.getComponentForStep(WVTConfiguration.STEP_TOKENIZER, d);
                wordFilter = (WVTWordFilter) config.getComponentForStep(WVTConfiguration.STEP_WORDFILTER, d);
                stemmer = (WVTStemmer) config.getComponentForStep(WVTConfiguration.STEP_STEMMER, d);

                // Process the document

                TokenEnumeration tokens = stemmer.stem(wordFilter.filter(tokenizer.tokenize(charConverter.convertChars(infilter.convertToPlainText(loader.loadDocument(d), d), d), d), d), d);

                while (tokens.hasMoreTokens()) {
                    listener.processWord(tokens.nextToken());
                }
View Full Code Here

Examples of edu.udo.cs.wvtool.generic.stemmer.WVTStemmer

33
34
35
36
37
38
39
40
41
42
43
44
        WVTool wvt = new WVTool(false);

        // Initialize the configuration
        WVTConfiguration config = new WVTConfiguration();

        final WVTStemmer dummyStemmer = new DummyStemmer();
        final WVTStemmer porterStemmer = new PorterStemmerWrapper();

        config.setConfigurationRule(WVTConfiguration.STEP_STEMMER, new WVTConfigurationFact(new ToLowerCaseConverter()));

        // Initialize the input list with two classes
        WVTFileInputList list = new WVTFileInputList(0);
View Full Code Here

Examples of edu.udo.cs.wvtool.generic.stemmer.WVTStemmer

25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
        WVTool wvt = new WVTool(false);

        // Initialize the configuration
        WVTConfiguration config = new WVTConfiguration();

        final WVTStemmer dummyStemmer = new DummyStemmer();
        final WVTStemmer porterStemmer = new PorterStemmerWrapper();

        config.setConfigurationRule(WVTConfiguration.STEP_STEMMER, new WVTConfigurationRule() {
            public Object getMatchingComponent(WVTDocumentInfo d) {

                if (d.getContentLanguage().equals("english"))
                    return porterStemmer;
                else
                    return dummyStemmer;
            }
        });

        WVTStemmer stemmer = new LovinsStemmerWrapper();

        config.setConfigurationRule(WVTConfiguration.STEP_STEMMER, new WVTConfigurationFact(stemmer));

        // Initialize the input list with two classes
        WVTFileInputList list = new WVTFileInputList(2);
View Full Code Here

Examples of edu.udo.cs.wvtool.generic.stemmer.WVTStemmer

23
24
25
26
27
28
29
30
31
32
33
        WVTool wvt = new WVTool(false);

        // Initialize the configuration
        WVTConfiguration config = new WVTConfiguration();

        WVTStemmer stemmer = new WordNetHypernymStemmer();

        config.setConfigurationRule(WVTConfiguration.STEP_STEMMER, new WVTConfigurationFact(stemmer));

        // Initialize the input list with two classes
        WVTFileInputList list = new WVTFileInputList(2);
View Full Code Here

Examples of edu.udo.cs.wvtool.generic.stemmer.WVTStemmer

33
34
35
36
37
38
39
40
41
42
43
44
        WVTool wvt = new WVTool(false);

        // Initialize the configuration
        WVTConfiguration config = new WVTConfiguration();

        final WVTStemmer dummyStemmer = new DummyStemmer();
        final WVTStemmer porterStemmer = new PorterStemmerWrapper();

        config.setConfigurationRule(WVTConfiguration.STEP_STEMMER, new WVTConfigurationFact(new ToLowerCaseConverter()));

        // Initialize the input list with two classes
        WVTFileInputList list = new WVTFileInputList(0);
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. All rights reserved.
All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.