Java Code Examples for org.apache.parquet.column.page.DataPageV1#getValueCount()

The following examples show how to use org.apache.parquet.column.page.DataPageV1#getValueCount() . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.

Example 1

Source File: BasePageIterator.java From iceberg with Apache License 2.0

6 votes

protected void initFromPage(DataPageV1 initPage) {
  this.triplesCount = initPage.getValueCount();
  ValuesReader rlReader = initPage.getRlEncoding().getValuesReader(desc, ValuesType.REPETITION_LEVEL);
  this.repetitionLevels = new ValuesReaderIntIterator(rlReader);
  try {
    BytesInput bytes = initPage.getBytes();
    LOG.debug("page size {} bytes and {} records", bytes.size(), triplesCount);
    LOG.debug("reading repetition levels at 0");
    ByteBufferInputStream in = bytes.toInputStream();
    rlReader.initFromPage(triplesCount, in);
    LOG.debug("reading definition levels at {}", in.position());
    initDefinitionLevelsReader(initPage, desc, in, triplesCount);
    LOG.debug("reading data at {}", in.position());
    initDataReader(initPage.getValueEncoding(), in, initPage.getValueCount());
  } catch (IOException e) {
    throw new ParquetDecodingException("could not read page " + initPage + " in col " + desc, e);
  }
}

Example 2

Source File: PageIterator.java From iceberg with Apache License 2.0

6 votes

private void initFromPage(DataPageV1 page) {
  this.triplesCount = page.getValueCount();
  ValuesReader rlReader = page.getRlEncoding().getValuesReader(desc, REPETITION_LEVEL);
  ValuesReader dlReader = page.getDlEncoding().getValuesReader(desc, DEFINITION_LEVEL);
  this.repetitionLevels = new ValuesReaderIntIterator(rlReader);
  this.definitionLevels = new ValuesReaderIntIterator(dlReader);
  try {
    BytesInput bytes = page.getBytes();
    LOG.debug("page size {} bytes and {} records", bytes.size(), triplesCount);
    LOG.debug("reading repetition levels at 0");
    ByteBufferInputStream in = bytes.toInputStream();
    rlReader.initFromPage(triplesCount, in);
    LOG.debug("reading definition levels at {}", in.position());
    dlReader.initFromPage(triplesCount, in);
    LOG.debug("reading data at {}", in.position());
    initDataReader(page.getValueEncoding(), in, page.getValueCount());
  } catch (IOException e) {
    throw new ParquetDecodingException("could not read page " + page + " in col " + desc, e);
  }
}

Example 3

Source File: AbstractColumnReader.java From flink with Apache License 2.0

6 votes

private void readPageV1(DataPageV1 page) throws IOException {
	this.pageValueCount = page.getValueCount();
	ValuesReader rlReader = page.getRlEncoding().getValuesReader(descriptor, REPETITION_LEVEL);

	// Initialize the decoders.
	if (page.getDlEncoding() != Encoding.RLE && descriptor.getMaxDefinitionLevel() != 0) {
		throw new UnsupportedOperationException("Unsupported encoding: " + page.getDlEncoding());
	}
	int bitWidth = BytesUtils.getWidthFromMaxInt(descriptor.getMaxDefinitionLevel());
	this.runLenDecoder = new RunLengthDecoder(bitWidth);
	try {
		BytesInput bytes = page.getBytes();
		ByteBufferInputStream in = bytes.toInputStream();
		rlReader.initFromPage(pageValueCount, in);
		this.runLenDecoder.initFromStream(pageValueCount, in);
		prepareNewPage(page.getValueEncoding(), in);
	} catch (IOException e) {
		throw new IOException("could not read page " + page + " in col " + descriptor, e);
	}
}

Example 4

Source File: ColumnReaderBase.java From parquet-mr with Apache License 2.0

6 votes

private void readPageV1(DataPageV1 page) {
  ValuesReader rlReader = page.getRlEncoding().getValuesReader(path, REPETITION_LEVEL);
  ValuesReader dlReader = page.getDlEncoding().getValuesReader(path, DEFINITION_LEVEL);
  this.repetitionLevelColumn = new ValuesReaderIntIterator(rlReader);
  this.definitionLevelColumn = new ValuesReaderIntIterator(dlReader);
  int valueCount = page.getValueCount();
  try {
    BytesInput bytes = page.getBytes();
    LOG.debug("page size {} bytes and {} values", bytes.size(), valueCount);
    LOG.debug("reading repetition levels at 0");
    ByteBufferInputStream in = bytes.toInputStream();
    rlReader.initFromPage(valueCount, in);
    LOG.debug("reading definition levels at {}", in.position());
    dlReader.initFromPage(valueCount, in);
    LOG.debug("reading data at {}", in.position());
    initDataReader(page.getValueEncoding(), in, valueCount);
  } catch (IOException e) {
    throw new ParquetDecodingException("could not read page " + page + " in col " + path, e);
  }
  newPageInitialized(page);
}

Example 5

Source File: ShowPagesCommand.java From parquet-mr with Apache License 2.0

5 votes

@Override
public String visit(DataPageV1 page) {
  String enc = encodingAsString(page.getValueEncoding(), false);
  long totalSize = page.getCompressedSize();
  int count = page.getValueCount();
  String numNulls = page.getStatistics().isNumNullsSet() ? Long.toString(page.getStatistics().getNumNulls()) : "";
  float perValue = ((float) totalSize) / count;
  String minMax = minMaxAsString(page.getStatistics());
  return String.format("%3d-%-3d  %-5s %s %-2s %-7d %-10s %-10s %-8s %-7s %s",
      rowGroupNum, pageNum, "data", shortCodec, enc, count, humanReadable(perValue),
      humanReadable(totalSize), "", numNulls, minMax);
}