Examples of TagExtractor

Examples of com.cybozu.labs.langdetect.util.TagExtractor

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
89
90
91
        InputStream is = null;
        try {
            is = new BufferedInputStream(new FileInputStream(file));
            if (file.getName().endsWith(".gz")) is = new GZIPInputStream(is);

            TagExtractor tagextractor = new TagExtractor("abstract", 100);

            XMLStreamReader reader = null;
            try {
                XMLInputFactory factory = XMLInputFactory.newInstance();
                reader = factory.createXMLStreamReader(is);
                while (reader.hasNext()) {
                    switch (reader.next()) {
                    case XMLStreamReader.START_ELEMENT:
                        tagextractor.setTag(reader.getName().toString());
                        break;
                    case XMLStreamReader.CHARACTERS:
                        tagextractor.add(reader.getText());
                        break;
                    case XMLStreamReader.END_ELEMENT:
                        tagextractor.closeTag(profile);
                        break;
                    }
                }
            } catch (XMLStreamException e) {
                throw new LangDetectException(ErrorCode.TrainDataFormatError, "Training database file '" + file.getName() + "' is an invalid XML.");
            } finally {
                try {
                    if (reader != null) reader.close();
                } catch (XMLStreamException e) { /* ignore exception */ }
            }
            System.out.println(lang + ":" + tagextractor.count());

        } catch (IOException e) {
            throw new LangDetectException(ErrorCode.CantOpenTrainData, "Can't open training database file '" + file.getName() + "'");
        } finally {
            IOUtils.closeQuietly(is);
View Full Code Here

Examples of com.cybozu.labs.langdetect.util.TagExtractor

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
        try {
            InputStream is = new FileInputStream(file);
            if (file.getName().endsWith(".gz")) is = new GZIPInputStream(is);
            br = new BufferedReader(new InputStreamReader(is, "utf-8"));

            TagExtractor tagextractor = new TagExtractor("abstract", 100);

            XMLStreamReader reader = null;
            try {
                XMLInputFactory factory = XMLInputFactory.newInstance();
                reader = factory.createXMLStreamReader(br);
                while (reader.hasNext()) {
                    switch (reader.next()) {
                    case XMLStreamReader.START_ELEMENT:
                        tagextractor.setTag(reader.getName().toString());
                        break;
                    case XMLStreamReader.CHARACTERS:
                        tagextractor.add(reader.getText());
                        break;
                    case XMLStreamReader.END_ELEMENT:
                        String text = tagextractor.closeTag();
                        if (text != null) profile.update(text);
                        break;
                    }
                }
            } catch (XMLStreamException e) {
                throw new LangDetectException(ErrorCode.TrainDataFormatError, "Training database file '" + file.getName() + "' is an invalid XML.");
            } finally {
                try {
                    if (reader != null) reader.close();
                } catch (XMLStreamException e) {}
            }
            System.out.println(lang + ":" + tagextractor.count());

        } catch (IOException e) {
            throw new LangDetectException(ErrorCode.CantOpenTrainData, "Can't open training database file '" + file.getName() + "'");
        } finally {
            try {
View Full Code Here

Examples of opennlp.ccg.realize.hypertagger.TagExtractor

86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
    htVocabFile = options.valueOf(ht_vocab_s);
    if(options.has("q"))
      quiet = true;
    LFLoader lfs = new LFLoader(options.valueOf(gr_s), options.valueOf(corpusDir_s), options.nonOptionArguments());
    if(options.has("pos")) {
      TagExtractor tex = new ZLPOSTagger();
      if(posPriorModelFile != null && posVocabFile != null) {
        debug("Loading POS model priors from " + posPriorModelFile);
        debug("Loading POS model vocab from " + posVocabFile);
        tex.loadPriorModel(posPriorModelFile, posVocabFile);
      }
      debug("Extracting POS features...");
      t = new TagExtract(tex);
    }
    else {
      // extracting hypertags
      // using GS pos tags
      TagExtractor tex = new ZLMaxentHypertagger();
      if(htPriorModelFile != null && htVocabFile != null) {
        debug("Loading HT model priors from " + htPriorModelFile);
        debug("Loading HT model vocab from " + htVocabFile);
        tex.loadPriorModel(htPriorModelFile,htVocabFile);
      }
      if(hyperModelFile != null) {
        debug("Loading proto-HT model from " + hyperModelFile);
        tex.loadProtoModel(hyperModelFile);
      }
      debug("Extracting hypertagger features...");
      t = new TagExtract(tex);
    }
    t.setOutput(output);
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.