Examples of org.apache.lucene.index.IndexReader.terms()

Class org.apache.lucene.index.IndexReader

Examples of org.apache.lucene.index.IndexReader.terms()

org.apache.lucene.index.IndexReader.terms()
Returns an enumeration of all the terms in the index. The enumeration is ordered by Term.compareTo(). Each term is greater than all that precede it in the enumeration. Note that after calling terms(), {@link TermEnum#next()} must be calledon the resulting enumeration before calling other methods such as {@link TermEnum#term()}. @throws IOException if there is a low-level IO error

      int i = 0;
      long cnt = 0L;
      processedRecords = 0L;
      s1 = System.currentTimeMillis();
      delta = s1;
      TermEnum te = ir.terms();
      while(te.next()) {
        Term t = te.term();
        if (t == null) continue;
        if (!(t.field().equals("ch") || t.field().equals("uh"))) continue;
        cnt++;

View Full Code Here

        reader = IndexReader.open(args[i]);
      }
    }


    TermFreqQueue tiq = new TermFreqQueue(count);
    TermEnum terms = reader.terms();
      
    int minFreq = 0;
    while (terms.next()) {
      if (terms.docFreq() > minFreq) {
        tiq.put(new TermFreq(terms.term(), terms.docFreq()));

View Full Code Here

        reader = IndexReader.open(args[i]);
      }
    }


    TermFreqQueue tiq = new TermFreqQueue(count);
    TermEnum terms = reader.terms();
      
    int minFreq = 0;
    while (terms.next()) {
      if (terms.docFreq() > minFreq) {
        tiq.put(new TermFreq(terms.term(), terms.docFreq()));

View Full Code Here

      int i = 0;
      long cnt = 0L;
      processedRecords = 0L;
      s1 = System.currentTimeMillis();
      delta = s1;
      TermEnum te = ir.terms();
      while(te.next()) {
        Term t = te.term();
        if (t == null) continue;
        if (!(t.field().equals("ch") || t.field().equals("uh"))) continue;
        cnt++;

View Full Code Here

    try {
      final int size = r.numDocs();
      final OrdinalMap ordinalMap = map;
      ordinalMap.setSize(size);
      CategoryPath cp = new CategoryPath();
      TermEnum te = r.terms(Consts.FULL_TERM);
      TermDocs docs = r.termDocs();
      // we call next() first, to skip the root category which always exists.
      while (te.next()) {
        Term term = te.term();
        if (term.field() != Consts.FULL) break;

View Full Code Here

    "cyp3a4", 
    "dextromethorphan"});*/
    List<String> queryList = new ArrayList<String>();
    long time = System.currentTimeMillis();
    IndexReader ir = lis.getIndexReader();
    TermEnum termEnum = ir.terms();
    while(termEnum.next()) {
      Term t = termEnum.term();
      if(t.field().equals("txt") && termEnum.docFreq() > 20) queryList.add(t.text());
    }
    //queryList.addAll(lis.termsFromQuery(new TermQuery(new Term("txt", queryTerm))));

View Full Code Here

  public static void main(String[] args) throws Exception {
    LuceneIndexerSearcher lis = new LuceneIndexerSearcher(false);
    IndexSearcher is = lis.getIndexSearcher();
    IndexReader ir = lis.getIndexReader();
    
    TermEnum textEnum = ir.terms();
    Map<String,Integer> docFreqs = new HashMap<String,Integer>();
    float nd = ir.numDocs() * 1.0f;
    while(textEnum.next()) {
      Term t = textEnum.term();
      if("txt".equals(t.field())) {

View Full Code Here

  public static void main(String[] args) throws Exception{
    LuceneIndexerSearcher lis = new LuceneIndexerSearcher(false);
    IndexReader ir = lis.getIndexReader();
    
    int numDocs = ir.numDocs();
    TermEnum textEnum = ir.terms();
    Map<String,Integer> docFreqs = new HashMap<String,Integer>();
    while(textEnum.next()) {
      Term t = textEnum.term();
      if("txt".equals(t.field())) {
        String text = t.text();

View Full Code Here

    IndexReader ir = lis.getIndexReader();
    
    long allTime = System.currentTimeMillis();
    
    int numDocs = ir.numDocs();
    TermEnum textEnum = ir.terms();
    Map<String,Integer> docFreqs = new HashMap<String,Integer>();
    while(textEnum.next()) {
      Term t = textEnum.term();
      if("txt".equals(t.field())) {
        String text = t.text();

View Full Code Here

    List<String> docFiles = new ArrayList<String>();
    for(int i=0;i<ir.numDocs();i++) {
      docFiles.add(ir.document(i).getField("filename").stringValue().replaceAll("markedup", "source"));
    }
    
    TermEnum textEnum = ir.terms();
    Map<String,Integer> docFreqs = new HashMap<String,Integer>();
    while(textEnum.next()) {
      Term t = textEnum.term();
      if("txt".equals(t.field())) {
        String text = t.text();

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

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.