Class RecordReaderImpl

java/core/src/java/org/apache/orc/impl/RecordReaderImpl.java:79–1734

import java.util.function.Consumer;

public class RecordReaderImpl implements RecordReader {
  static final Logger LOG = LoggerFactory.getLogger(RecordReaderImpl.class);
  private static final boolean isLogDebugEnabled = LOG.isDebugEnabled();
  // as public for use with test cases
  public static final OrcProto.ColumnStatistics EMPTY_COLUMN_STATISTICS =
      OrcProto.ColumnStatistics.newBuilder().setNumberOfValues(0)
          .setHasNull(false)
          .setBytesOnDisk(0)
          .build();
  protected final Path path;
  private final long firstRow;
  private final List<StripeInformation> stripes = new ArrayList<>();
  private OrcProto.StripeFooter stripeFooter;
  private final long totalRowCount;
  protected final TypeDescription schema;
  // the file included columns indexed by the file's column ids.
  private final boolean[] fileIncluded;
  private final long rowIndexStride;
  private long rowInStripe = 0;
  // position of the follow reader within the stripe
  private long followRowInStripe = 0;
  private int currentStripe = -1;
  private long rowBaseInStripe = 0;
  private long rowCountInStripe = 0;
  private final BatchReader reader;
  private final OrcIndex indexes;
  // identifies the columns requiring row indexes
  private final boolean[] rowIndexColsToRead;
  private final SargApplier sargApp;
  // an array about which row groups aren't skipped
  private boolean[] includedRowGroups = null;
  private final DataReader dataReader;
  private final int maxDiskRangeChunkLimit;
  private final StripePlanner planner;
  // identifies the type of read, ALL(read everything), LEADERS(read only the filter columns)
  private final TypeReader.ReadPhase startReadPhase;
  // identifies that follow columns bytes must be read
  private boolean needsFollowColumnsRead;
  private final boolean noSelectedVector;
  // identifies whether the file has bad bloom filters that we should not use.
  private final boolean skipBloomFilters;
  static final String[] BAD_CPP_BLOOM_FILTER_VERSIONS = {
      "1.6.0", "1.6.1", "1.6.2", "1.6.3", "1.6.4", "1.6.5", "1.6.6", "1.6.7", "1.6.8",
      "1.6.9", "1.6.10", "1.6.11", "1.7.0"};

  /**
   * Given a list of column names, find the given column and return the index.
   *
   * @param evolution the mapping from reader to file schema
   * @param columnName  the fully qualified column name to look for
   * @return the file column number or -1 if the column wasn't found in the file schema
   * @throws IllegalArgumentException if the column was not found in the reader schema
   */
  static int findColumns(SchemaEvolution evolution,
                         String columnName) {
    TypeDescription fileColumn = findColumnType(evolution, columnName);
    return fileColumn == null ? -1 : fileColumn.getId();
  }