Package edu.udo.cs.wvtool.generic.loader

Examples of edu.udo.cs.wvtool.generic.loader.WVTDocumentLoader.loadDocument()


    public InputStream getInputStream(WVTDocumentInfo d, WVTConfiguration config) throws WVToolException {

        WVTDocumentLoader loader = null;
        loader = (WVTDocumentLoader) config.getComponentForStep(WVTConfiguration.STEP_LOADER, d);

        return loader.loadDocument(d);

    }

    public Reader getReader(WVTDocumentInfo d, WVTConfiguration config) throws WVToolException {
View Full Code Here


        WVTInputFilter infilter = null;

        loader = (WVTDocumentLoader) config.getComponentForStep(WVTConfiguration.STEP_LOADER, d);
        infilter = (WVTInputFilter) config.getComponentForStep(WVTConfiguration.STEP_INPUT_FILTER, d);

        return infilter.convertToPlainText(loader.loadDocument(d), d);

    }

    /**
     * Create a word list from scrat based on the given texts.
View Full Code Here

                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

                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

                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

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.