Examples of de.tud.kom.stringmatching.shinglecloud.ShingleList

import de.tud.kom.stringutils.preprocessing.Preprocess;


public class TEIComparatorShingleCloud extends ShingleCloud {


  public TEIComparatorShingleCloud(Document doc, Preprocess preprocessingAlgorithm, int nGramSize, int minimumNumberOfOnes, int minimumNumberOfZeros) {
    ShingleList haystack = generateShingleListForDocument(doc, preprocessingAlgorithm, nGramSize);
    
    this.haystackShingles = haystack;
    this.nGramSize = haystackShingles.getNGramSize();
    this.minimumNumberOfOnesInMatch = minimumNumberOfOnes;
    this.maximumNumberOfZerosBetweenMatches = minimumNumberOfZeros;

   * @param doc
   * @return
   */
  private ShingleList generateShingleListForDocument(Document doc, Preprocess preprocessingAlgorithm, int nGramSize) {
    // generate shingle list and configure it
    ShingleList list = new ShingleList();
    list.setPreprocessingAlgorithm(preprocessingAlgorithm);
    list.setNGramSize(nGramSize);
    list.setMagicWords(new String[]{"illegible"});
    
    generateShingleListForDocument_recursive(doc, doc.getDocumentElement(), list, false);
    
    return list;
  }

Related Classes of de.tud.kom.stringmatching.shinglecloud.ShingleList

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.