Examples of ParsedData

Examples of com.findwise.utils.tika.ParsedData

80
81
82
83
84
85
86
87
88
89
90
                URL url = it.next();
                URLConnection connection = createConnection(url);
                final InputStream inputStream = connection.getInputStream();
                try {
                    String prefix = field + num + "_";
                    ParsedData parsedData = inputStreamParser.parse(inputStream);
                    documentParserHelper.addParsedDataToDocument(parsedData, doc, prefix);
                } finally {
                    inputStream.close();
                }
            }
View Full Code Here

Examples of com.findwise.utils.tika.ParsedData

155
156
157
158
159
160
161
162
163
164
    }

    private void enrichDocumentWithFileContents(LocalDocument doc, InputStream stream) throws IOException,
            SAXException, TikaException {
        InputStreamParser inputStreamParser = new InputStreamParser();
        ParsedData parsedData = inputStreamParser.parse(stream);

        addTextToDocument(doc, parsedData.getContent());
        addMetadataToDocument(doc, parsedData.getMetadata());
    }
View Full Code Here

Examples of com.findwise.utils.tika.ParsedData

36
37
38
39
40
41
42
43
44
        DocumentParserHelper documentParserHelper = new DocumentParserHelper(addMetaData, addLanguage);
        for (String fileName : files) {
            DocumentFile<Local> df = doc.getFile(fileName);
            String prefix = fileName.replace('.', '_') + "_";
            InputStreamParser inputStreamParser = new InputStreamParser(parser);
            ParsedData parsedData = inputStreamParser.parse(df.getStream());
            documentParserHelper.addParsedDataToDocument(parsedData, doc, prefix);
        }
    }
View Full Code Here

Examples of seekfeel.utilities.stanfordwrapper.ParsedData

44
45
46
47
48
49
50
51
    public Sentiment classifyText(String text) {
        ArrayList<Word> allWords = StringToWordsTokenizer.tokenize(text);
        ParsingOptions popts = new ParsingOptions();
        popts.setParseRelations(true);
        popts.setPosTag(true);
        ParsedData result = sParser.parse(allWords, popts);
        return classifyTextByNouns(result, allWords);
    }
View Full Code Here

Examples of seekfeel.utilities.stanfordwrapper.ParsedData

65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
        feature = textAndFeat[1];
        ArrayList<Word> Words = StringToWordsTokenizer.tokenize(text);
        ParsingOptions opts = new ParsingOptions();
        opts.setPosTag(true);
        opts.setParseRelations(true);
        ParsedData resultData = sParser.parse(Words, opts);
        Word featureWord = new Word(feature);
        int featIndex = Words.indexOf(featureWord);
        Sentiment sentimentResult = Sentiment.Neutral;
        if (!feature.equals("") && featIndex != -1) {
            WordPos theFeature = resultData.getWordByIndex(featIndex);
            return classifyTextByFeatures(resultData, Words, theFeature);
        }
        // sentimentResult = classifyTextByNouns(resultData, Words);
        if (sentimentResult == Sentiment.Neutral) {
            sentimentResult = classifyTextByWords(resultData, Words);
View Full Code Here

Examples of seekfeel.utilities.stanfordwrapper.ParsedData

59
60
61
62
63
64
65
66
67
68
69
70
        ParsingOptions opts = new ParsingOptions();
        opts.setPosTag(true);
        opts.setNeededTags(neededTags);

        ParsedData outData = theParser.parse(allWords, opts);
        ArrayList<WordPos> taggedWords = outData.getTaggedWords();
        SWNEntryKey tempFeatKey;
        SentimentFeature tempFeature;

        for (WordPos word : taggedWords) {
            tempFeatKey = new SWNEntryKey(allWords.get(word.getWordIndex()).word(), TagParser.parseTagToGeneral(word.getWordTag()));
View Full Code Here

Examples of seekfeel.utilities.stanfordwrapper.ParsedData

31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
        TaggedStem temp;
        StanfordParser theParser = new StanfordParser(Language.Arabic);
        ParsingOptions opts = new ParsingOptions();
        opts.setPosTag(true);
        ArrayList<Word> textWords;
        ParsedData parsedOut;
        ArabicStemmerKhoja arabicStemmer = new ArabicStemmerKhoja();
        // Convert the Example into a tagged Stems Array
        textWords = StringToWordsTokenizer.tokenize(example.getDataBody());
        example.getDataBody();
        parsedOut = theParser.parse(textWords, opts);
        for (int i = 0; i < parsedOut.getTaggedWords().size(); i++) {
            temp = new TaggedStem();
            temp.setStemTag(parsedOut.getTaggedWords().get(i).getWordTag());
            temp.setTheStem(arabicStemmer.stem(textWords.get(i).word()));

            if (!taggedStems.contains(temp)) {
                taggedStems.add(temp);
            }
View Full Code Here

Examples of seekfeel.utilities.stanfordwrapper.ParsedData

52
53
54
55
56
57
58
59
60
61
62
        neededTags.add(PosTag.VBG);
        neededTags.add(PosTag.VBN);
        neededTags.add(PosTag.VBP);
        neededTags.add(PosTag.VBZ);

        ParsedData parsingResult = null;
        ParsingOptions opts = new ParsingOptions();
        opts.setNeededTags(neededTags);
        opts.setPosTag(true);

View Full Code Here

Examples of seekfeel.utilities.stanfordwrapper.ParsedData

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
        TaggedStem temp;
        StanfordParser theParser = new StanfordParser(Language.Arabic);
        ParsingOptions opts = new ParsingOptions();
        opts.setPosTag(true);
        ArrayList<Word> textWords;
        ParsedData parsedOut;
        ArabicStemmerKhoja arabicStemmer = new ArabicStemmerKhoja();
        for (DataUnit textUnit : positiveExs) {
            textWords = StringToWordsTokenizer.tokenize(textUnit.getDataBody());
            textUnit.getDataBody();
            parsedOut = theParser.parse(textWords, opts);
            for (int i = 0; i < parsedOut.getTaggedWords().size(); i++) {
                temp = new TaggedStem();
                temp.setStemTag(parsedOut.getTaggedWords().get(i).getWordTag());
                temp.setTheStem(arabicStemmer.stem(textWords.get(i).word()));

                if (!taggedStems.contains(temp)) {
                    taggedStems.add(temp);
                }
            }
        }
        for (DataUnit textUnit : negativeExs) {
            textWords = StringToWordsTokenizer.tokenize(textUnit.getDataBody());
            textUnit.getDataBody();
            parsedOut = theParser.parse(textWords, opts);
            for (int i = 0; i < parsedOut.getTaggedWords().size(); i++) {
                temp = new TaggedStem();
                temp.setStemTag(parsedOut.getTaggedWords().get(i).getWordTag());
                temp.setTheStem(arabicStemmer.stem(textWords.get(i).word()));

                if (!taggedStems.contains(temp)) {
                    taggedStems.add(temp);
                }
View Full Code Here

Examples of seekfeel.utilities.stanfordwrapper.ParsedData

37
38
39
40
41
42
43
44
45
46
47
48
49
50
        ParsingOptions popts = new ParsingOptions();
        popts.setParseRelations(true);
        popts.setPosTag(true);

        ParsedData result = sParser.parse(allWords, popts);
        ArrayList<WordPos> wordsPos = result.getTaggedWords();

        setTextDependencyRelations(result.getDependencyRelations());
        tokenizedSentence = new ArrayList<token>();

        int size = allWords.size();

        for (int i = 0; i < size; i++) {
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.