Examples of uk.ac.ucl.panda.utility.structure.Term

Package uk.ac.ucl.panda.utility.structure

Examples of uk.ac.ucl.panda.utility.structure.Term

uk.ac.ucl.panda.utility.structure.Term
A Term represents a word from text. This is the unit of search. It is composed of two elements, the text of the word, as a string, and the name of the field that the text occured in, an interned string. Note that terms may represent more than words from text fields, but also things like dates, email addresses, urls, etc.

     */
    public BitSet bits(IndexReader reader) throws IOException {
        BitSet bits = new BitSet(reader.maxDoc());
        TermEnum enumerator =
            (null != lowerTerm
             ? reader.terms(new Term(fieldName, lowerTerm))
             : reader.terms(new Term(fieldName,"")));
        
        try {
            
            if (enumerator.term() == null) {
                return bits;
            }
            
            boolean checkLower = false;
            if (!includeLower) // make adjustments to set to exclusive
                checkLower = true;
        
            TermDocs termDocs = reader.termDocs();
            try {
                
                do {
                    Term term = enumerator.term();
                    if (term != null && term.field().equals(fieldName)) {
                        if (!checkLower || null==lowerTerm || term.text().compareTo(lowerTerm) > 0) {
                            checkLower = false;
                            if (upperTerm != null) {
                                int compare = upperTerm.compareTo(term.text());
                                /* if beyond the upper term, or is exclusive and
                                 * this is equal to the upper term, break out */
                                if ((compare < 0) ||
                                    (!includeUpper && compare==0)) {
                                    break;

View Full Code Here

      }
      if (t == null)
        break;
   
        v.addElement(t);
        term.addElement(new Term(field,t.termText()));
   
      if (t.getPositionIncrement() != 0)
        positionCount += t.getPositionIncrement();
      else
        severalTokensAtSamePosition = true;

View Full Code Here

        fieldIterator = fieldToReader.tailMap(field).keySet().iterator();
        fieldIterator.next();                     // Skip field to get next one
      }
      while (fieldIterator.hasNext()) {
        field = (String) fieldIterator.next();
        termEnum = ((IndexReader)fieldToReader.get(field)).terms(new Term(field, ""));
        Term term = termEnum.term();
        if (term!=null && term.field()==field)
          return true;
        else
          termEnum.close();
      }

View Full Code Here

                                             IndexReader reader)
    throws CorruptIndexException, IOException {
    Iterator iter = deleteTerms.entrySet().iterator();
    while (iter.hasNext()) {
      Entry entry = (Entry) iter.next();
      Term term = (Term) entry.getKey();


      TermDocs docs = reader.termDocs(term);
      if (docs != null) {
        int num = ((DocumentsWriter.Num) entry.getValue()).getNum();
        try {

View Full Code Here

      int size = terms.length;
      double val = 0.0;
      for (int i = 0; i < size; i ++) {
        double temp = 0;
        int tf = termFreqs[i];
        int df = reader.docFreq(new Term("body", terms[i]));
        temp = (DocNum - df + 0.5) / (df + 0.5);
        temp = tf * Math.log(temp);
        val += temp;
      }
      val /= DL;

View Full Code Here

TOP

Related Classes of uk.ac.ucl.panda.utility.structure.Term

uk.ac.ucl.panda.indexing.io.IndexWriter

uk.ac.ucl.panda.indexing.io.ParallelReader$ParallelTermEnum

uk.ac.ucl.panda.retrieval.models.RawMaterial

uk.ac.ucl.panda.retrieval.RangeFilter

uk.ac.ucl.panda.utility.parser.QueryParser

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.