private void readPageV1(DataPageV1 page) { ValuesReader rlReader = page.getRlEncoding().getValuesReader(descriptor, REPETITION_LEVEL); ValuesReader dlReader = page.getDlEncoding().getValuesReader(descriptor, DEFINITION_LEVEL); this.repetitionLevelColumn = new ValuesReaderIntIterator(rlReader); this.definitionLevelColumn = new ValuesReaderIntIterator(dlReader); try { BytesInput bytes = page.getBytes(); LOG.debug("page size " + bytes.size() + " bytes and " + pageValueCount + " records"); ByteBufferInputStream in = bytes.toInputStream(); LOG.debug("reading repetition levels at " + in.position()); rlReader.initFromPage(pageValueCount, in); LOG.debug("reading definition levels at " + in.position()); dlReader.initFromPage(pageValueCount, 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 " + descriptor, e); } }
private void validateContains(MessageType schema, PageReadStore pages, String[] path, int values, BytesInput bytes) throws IOException { PageReader pageReader = pages.getPageReader(schema.getColumnDescription(path)); DataPageV1 page = (DataPageV1) pageReader.readPage(); assertEquals(values, page.getValueCount()); assertArrayEquals(bytes.toByteArray(), page.getBytes().toByteArray()); }
@Override public String toString() { return "Page [bytes.size=" + bytes.size() + ", valueCount=" + getValueCount() + ", uncompressedSize=" + getUncompressedSize() + "]"; }
HadoopStreams.wrap(in).readFully(buffer); buffer.flip(); return new DataPageV1( decompressor.decompress(BytesInput.from(buffer), pageHeader.getUncompressed_page_size()), pageHeader.data_page_header.num_values,
@Override public String toString() { return "Page [bytes.size=" + bytes.size() + ", valueCount=" + getValueCount() + ", uncompressedSize=" + getUncompressedSize() + "]"; }
DataPageHeader dataHeaderV1 = pageHeader.getData_page_header(); pagesInChunk.add( new DataPageV1( this.readAsBytesInput(compressedPageSize), dataHeaderV1.getNum_values(),
private void readPageV1(DataPageV1 page) throws IOException { this.pageValueCount = page.getValueCount(); ValuesReader rlReader = page.getRlEncoding().getValuesReader(descriptor, REPETITION_LEVEL); ValuesReader dlReader; // 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.defColumn = new VectorizedRleValuesReader(bitWidth); dlReader = this.defColumn; this.repetitionLevelColumn = new ValuesReaderIntIterator(rlReader); this.definitionLevelColumn = new ValuesReaderIntIterator(dlReader); try { BytesInput bytes = page.getBytes(); ByteBufferInputStream in = bytes.toInputStream(); rlReader.initFromPage(pageValueCount, in); dlReader.initFromPage(pageValueCount, in); initDataReader(page.getValueEncoding(), in); } catch (IOException e) { throw new IOException("could not read page " + page + " in col " + descriptor, e); } }
DataPageHeader dataHeaderV1 = pageHeader.getData_page_header(); pagesInChunk.add( new DataPageV1( this.readAsBytesInput(compressedPageSize), dataHeaderV1.getNum_values(),
private void readPageV1(DataPageV1 page) throws IOException { this.pageValueCount = page.getValueCount(); ValuesReader rlReader = page.getRlEncoding().getValuesReader(descriptor, REPETITION_LEVEL); ValuesReader dlReader; // 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.defColumn = new VectorizedRleValuesReader(bitWidth); dlReader = this.defColumn; this.repetitionLevelColumn = new ValuesReaderIntIterator(rlReader); this.definitionLevelColumn = new ValuesReaderIntIterator(dlReader); try { BytesInput bytes = page.getBytes(); ByteBufferInputStream in = bytes.toInputStream(); rlReader.initFromPage(pageValueCount, in); dlReader.initFromPage(pageValueCount, in); initDataReader(page.getValueEncoding(), in); } catch (IOException e) { throw new IOException("could not read page " + page + " in col " + descriptor, e); } }
valueReadSoFar += pageHeader.data_page_header.getNum_values(); ByteBuffer destBuffer = uncompressPage(pageHeader, true); return new DataPageV1( BytesInput.from(destBuffer, 0, pageHeader.uncompressed_page_size), pageHeader.data_page_header.num_values,
private void readPageV1(DataPageV1 page) throws IOException { this.pageValueCount = page.getValueCount(); ValuesReader rlReader = page.getRlEncoding().getValuesReader(descriptor, REPETITION_LEVEL); ValuesReader dlReader; // 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.defColumn = new VectorizedRleValuesReader(bitWidth); dlReader = this.defColumn; this.repetitionLevelColumn = new ValuesReaderIntIterator(rlReader); this.definitionLevelColumn = new ValuesReaderIntIterator(dlReader); try { byte[] bytes = page.getBytes().toByteArray(); rlReader.initFromPage(pageValueCount, bytes, 0); int next = rlReader.getNextOffset(); dlReader.initFromPage(pageValueCount, bytes, next); next = dlReader.getNextOffset(); initDataReader(page.getValueEncoding(), bytes, next); } catch (IOException e) { throw new IOException("could not read page " + page + " in col " + descriptor, e); } }
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); } }
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); try { BytesInput bytes = page.getBytes(); LOG.debug("page size {} bytes and {} records", bytes.size(), pageValueCount); LOG.debug("reading repetition levels at 0"); ByteBufferInputStream in = bytes.toInputStream(); rlReader.initFromPage(pageValueCount, in); LOG.debug("reading definition levels at {}", in.position()); dlReader.initFromPage(pageValueCount, 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 " + path, e); } }
private void readPageV1(DataPageV1 page) { 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.defColumn = new VectorizedDefValuesReader(bitWidth); ValuesReader dlReader = this.defColumn; try { byte[] bytes = page.getBytes().toByteArray(); LOG.debug("page size " + bytes.length + " bytes and " + pageValueCount + " records"); LOG.debug("reading repetition levels at 0"); rlReader.initFromPage(pageValueCount, bytes, 0); int next = rlReader.getNextOffset(); LOG.debug("reading definition levels at " + next); dlReader.initFromPage(pageValueCount, bytes, next); next = dlReader.getNextOffset(); LOG.debug("reading data at " + next); initDataReader(page.getValueEncoding(), bytes, next); } catch (IOException e) { throw new ParquetDecodingException("could not read page " + page + " in col " + descriptor, e); } }
private void readPageV1(DataPageV1 page) throws IOException { this.pageValueCount = page.getValueCount(); ValuesReader rlReader = page.getRlEncoding().getValuesReader(descriptor, REPETITION_LEVEL); ValuesReader dlReader; // 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.defColumn = new VectorizedRleValuesReader(bitWidth); dlReader = this.defColumn; this.repetitionLevelColumn = new ValuesReaderIntIterator(rlReader); this.definitionLevelColumn = new ValuesReaderIntIterator(dlReader); try { byte[] bytes = page.getBytes().toByteArray(); rlReader.initFromPage(pageValueCount, bytes, 0); int next = rlReader.getNextOffset(); dlReader.initFromPage(pageValueCount, bytes, next); next = dlReader.getNextOffset(); initDataReader(page.getValueEncoding(), bytes, next); } catch (IOException e) { throw new IOException("could not read page " + page + " in col " + descriptor, e); } }
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); }