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

    public void dump() throws XMLStreamException, FactoryConfigurationError,
            CorruptIndexException, IOException {
        XMLStreamWriter out = XMLOutputFactory.newInstance().createXMLStreamWriter(System.out);


        IndexReader reader = IndexReader.open(FSDirectory.open(new File(dir)), true);
        TermEnum terms = reader.terms();
        
        while (terms.next()) { // &&  (terms.docFreq() > 2)) {
            if (terms.docFreq() > 1000) {
              System.out.print( terms.term().text());
              System.out.print(" -- ");

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

  public LinkedList generateInvertedIndex(String indexDir,
      String[] searchable, String nodeid) {
    LinkedList invertedIndex = new LinkedList();
    try {
      IndexReader indexReader = IndexReader.open(indexDir);
      TermEnum terms = indexReader.terms();
      while (terms.next()) {
        RemoteDocList docList = new RemoteDocList();
        Term term = terms.term();
        docList.term = term.text();
        if (contain(searchable, term.field())) {

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

  TermDocs termDocs = null;
  try {
      reader = IndexReader.open(dir);
      termCounts = new int[reader.maxDoc()];
      try {
    termEnum = reader.terms(new Term(field,""));
    try {
        termDocs = reader.termDocs();
        do {
      Term term = termEnum.term();
      if (term != null && term.field().equals(fieldName)) {

View Full Code Here

            TermEnum terms = null;
            try
            {
                indexReader = IndexReader.open( indexLocation );


                terms = indexReader.terms( new Term( fieldName, "" ) );
                while ( fieldName.equals( terms.term().field() ) )
                {
                    keys.add( terms.term().text() );


                    if ( !terms.next() )

View Full Code Here

        LinkedList termsWithPrefix = new LinkedList();
        IndexReader ir = IndexReader.open(indexStore);


        // this TermEnum gives "piccadilly", "pie" and "pizza".
        String prefix = "pi";
        TermEnum te = ir.terms(new Term("body", prefix));
        do {
            if (te.term().text().startsWith(prefix))
            {
                termsWithPrefix.add(te.term());
            }

View Full Code Here


        // search for "blue* pizza":
        MultiPhraseQuery query3 = new MultiPhraseQuery();
        termsWithPrefix.clear();
        prefix = "blue";
        te = ir.terms(new Term("body", prefix));
        do {
            if (te.term().text().startsWith(prefix))
            {
                termsWithPrefix.add(te.term());
            }

View Full Code Here

        LinkedList termsWithPrefix = new LinkedList();
        IndexReader ir = IndexReader.open(indexStore);


        // this TermEnum gives "piccadilly", "pie" and "pizza".
        String prefix = "pi";
        TermEnum te = ir.terms(new Term("body", prefix + "*"));
        do {
            if (te.term().text().startsWith(prefix))
            {
                termsWithPrefix.add(te.term());
            }

View Full Code Here

     * in the entire index. To get the in-cluster frequency, we need to query the index to get the term
     * frequencies in each document. The number of results of this call will be the in-cluster document
     * frequency.
     */


    TermEnum te = reader.terms(new Term(contentField, ""));
    int count = 0;


    Map<String, TermEntry> termEntryMap = new LinkedHashMap<String, TermEntry>();
    do {
      Term term = te.term();

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.