Package edu.udo.cs.wvtool.generic.vectorcreation

Examples of edu.udo.cs.wvtool.generic.vectorcreation.WVTVectorCreator


        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());
                }

                outputFilter.write(vectorCreator.createVector(wordList.getFrequenciesForCurrentDocument(), wordList.getTermCountForCurrentDocument(), wordList, d));

                wordList.closeDocument(d);
                loader.close(d);

            } catch (WVToolException e) {
View Full Code Here


        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());
            }

            result = vectorCreator.createVector(wordList.getFrequenciesForCurrentDocument(), wordList.getTermCountForCurrentDocument(), wordList, d);

            wordList.closeDocument(d);

        } catch (WVToolException e) {
View Full Code Here

TOP

Related Classes of edu.udo.cs.wvtool.generic.vectorcreation.WVTVectorCreator

Copyright © 2018 www.massapicom. 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.