Examples of org.apache.lucene.index.IndexWriter.numDocs()

Class org.apache.lucene.index.IndexWriter

Examples of org.apache.lucene.index.IndexWriter.numDocs()

org.apache.lucene.index.IndexWriter.numDocs()
Returns total number of docs in this index, including docs not yet flushed (still in the RAM buffer), and including deletions. NOTE: buffered deletions are not counted. If you really need these to be counted you should call {@link #commit()} first. @see #numDocs

        Assert.assertTrue("writer has no deletions", w.hasDeletions());


      Assert.assertEquals("writer is missing some deleted docs", 
                          numDeletedDocs, w.maxDoc());
      Assert.assertEquals("writer has non-deleted docs", 
                          0, w.numDocs());
      w.close();
      IndexReader r = IndexReader.open(d, true);
      Assert.assertEquals("reader has wrong number of deleted docs", 
                          numDeletedDocs, r.numDeletedDocs());
      r.close();

View Full Code Here

                    new StandardAnalyzer(), true, IndexWriter.MaxFieldLength.UNLIMITED);
        writer.setUseCompoundFile(false);


        indexDirectory(writer, dataDir);


        int numIndexed = writer.numDocs();
        writer.optimize();
        writer.close();
        return numIndexed;
    }

View Full Code Here

        for (HdfsDirectory directory : indexesToImport) {
          LOG.info("Starting import [{0}], commiting on [{1}/{2}]", directory, shard, table);
          indexWriter.commit();
          boolean isSuccess = true;
          boolean isRollbackDueToException = false;
          boolean emitDeletes = indexWriter.numDocs() != 0;
          try {
            isSuccess = applyDeletes(directory, indexWriter, shard, emitDeletes);
          } catch (IOException e) {
            LOG.error("Some issue with deleting the old index on [{0}/{1}]", e, shard, table);
            isSuccess = false;

View Full Code Here

        Assert.assertTrue("writer has no deletions", w.hasDeletions());


      Assert.assertEquals("writer is missing some deleted docs", 
                          numDeletedDocs, w.maxDoc());
      Assert.assertEquals("writer has non-deleted docs", 
                          0, w.numDocs());
      w.close();
      IndexReader r = IndexReader.open(d);
      Assert.assertEquals("reader has wrong number of deleted docs", 
                          numDeletedDocs, r.numDeletedDocs());
      r.close();

View Full Code Here

        Assert.assertTrue("writer has no deletions", w.hasDeletions());


      Assert.assertEquals("writer is missing some deleted docs", 
                          numDeletedDocs, w.maxDoc());
      Assert.assertEquals("writer has non-deleted docs", 
                          0, w.numDocs());
      w.close();
      IndexReader r = IndexReader.open(d, true);
      Assert.assertEquals("reader has wrong number of deleted docs", 
                          numDeletedDocs, r.numDeletedDocs());
      r.close();

View Full Code Here

            doc.add(new Field("Deskriptor", descriptorValue, Field.Store.YES, Field.Index.NOT_ANALYZED));
            doc.add(new Field("Synonym", synonymValue, Field.Store.YES, Field.Index.NOT_ANALYZED));
            synonymWriter.addDocument(doc);
            log.debug("WRITE SYN " + objCount + " " + descriptorValue + " " + synonymValue);
            synonymWriter.commit();
            log.debug("Number of actual Synonym: " + synonymWriter.numDocs());
          }
        }
      } finally {
        // if documents where added to the index create a reopen file and
        // optimize the writer

View Full Code Here

          }
        }
      } finally {
        // if documents where added to the index create a reopen file and
        // optimize the writer
        log.debug("Number of indexed Synonyms finished: " + synonymWriter.numDocs());
        synonymAccessor.release(synonymWriter);
      }
  
      log.debug("Finished reindexing synonym index.");
      ucReIndex.stop();

View Full Code Here

      StandardAnalyzer analyzer = new StandardAnalyzer(luceneVersion);
      QueryParser qp = new QueryParser(luceneVersion, Lucene.rid.name(), analyzer);
      BooleanQuery query = new BooleanQuery();
      query.add(qp.parse(repository.getRID()), Occur.MUST);


      int numDocsBefore = writer.numDocs();
      writer.deleteDocuments(query);
      writer.commit();
      closeSearcher();
      int numDocsAfter = writer.numDocs();
      if (numDocsBefore == numDocsAfter) {

View Full Code Here


      int numDocsBefore = writer.numDocs();
      writer.deleteDocuments(query);
      writer.commit();
      closeSearcher();
      int numDocsAfter = writer.numDocs();
      if (numDocsBefore == numDocsAfter) {
        log.debug(MessageFormat.format("no records found to delete in {0}", repository));
        return false;
      } else {
        log.debug(MessageFormat.format("deleted {0} records in {1}", numDocsBefore - numDocsAfter, repository));

View Full Code Here

      testDocIDs.add(hits[docID].doc);
    }


    int totalDocs = ir.numDocs();
    for (int docID = 0; docID < totalDocs; ++docID) {
      if (trainIW.numDocs() >= numTraining && testIW.numDocs() >= numTesting)
        break;
      Document doc = ir.document(docID);
      if (testDocIDs.contains(docID)) {
        testIW.addDocument(doc);
      }

View Full Code Here

0 1 2

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.