Package org.apache.parquet.column
Class ParquetProperties
- java.lang.Object
-
- org.apache.parquet.column.ParquetProperties
-
public class ParquetProperties extends Object
This class represents all the configurable Parquet properties.
-
-
Nested Class Summary
Nested Classes Modifier and Type Class Description static classParquetProperties.Builderstatic classParquetProperties.WriterVersion
-
Field Summary
-
Method Summary
-
-
-
Field Detail
-
DEFAULT_PAGE_SIZE
public static final int DEFAULT_PAGE_SIZE
- See Also:
- Constant Field Values
-
DEFAULT_DICTIONARY_PAGE_SIZE
public static final int DEFAULT_DICTIONARY_PAGE_SIZE
- See Also:
- Constant Field Values
-
DEFAULT_IS_DICTIONARY_ENABLED
public static final boolean DEFAULT_IS_DICTIONARY_ENABLED
- See Also:
- Constant Field Values
-
DEFAULT_IS_BYTE_STREAM_SPLIT_ENABLED
public static final boolean DEFAULT_IS_BYTE_STREAM_SPLIT_ENABLED
- See Also:
- Constant Field Values
-
DEFAULT_WRITER_VERSION
public static final ParquetProperties.WriterVersion DEFAULT_WRITER_VERSION
-
DEFAULT_ESTIMATE_ROW_COUNT_FOR_PAGE_SIZE_CHECK
public static final boolean DEFAULT_ESTIMATE_ROW_COUNT_FOR_PAGE_SIZE_CHECK
- See Also:
- Constant Field Values
-
DEFAULT_MINIMUM_RECORD_COUNT_FOR_CHECK
public static final int DEFAULT_MINIMUM_RECORD_COUNT_FOR_CHECK
- See Also:
- Constant Field Values
-
DEFAULT_MAXIMUM_RECORD_COUNT_FOR_CHECK
public static final int DEFAULT_MAXIMUM_RECORD_COUNT_FOR_CHECK
- See Also:
- Constant Field Values
-
DEFAULT_PAGE_VALUE_COUNT_THRESHOLD
public static final int DEFAULT_PAGE_VALUE_COUNT_THRESHOLD
- See Also:
- Constant Field Values
-
DEFAULT_COLUMN_INDEX_TRUNCATE_LENGTH
public static final int DEFAULT_COLUMN_INDEX_TRUNCATE_LENGTH
- See Also:
- Constant Field Values
-
DEFAULT_STATISTICS_TRUNCATE_LENGTH
public static final int DEFAULT_STATISTICS_TRUNCATE_LENGTH
- See Also:
- Constant Field Values
-
DEFAULT_ROW_GROUP_ROW_COUNT_LIMIT
public static final int DEFAULT_ROW_GROUP_ROW_COUNT_LIMIT
- See Also:
- Constant Field Values
-
DEFAULT_PAGE_ROW_COUNT_LIMIT
public static final int DEFAULT_PAGE_ROW_COUNT_LIMIT
- See Also:
- Constant Field Values
-
DEFAULT_MAX_BLOOM_FILTER_BYTES
public static final int DEFAULT_MAX_BLOOM_FILTER_BYTES
- See Also:
- Constant Field Values
-
DEFAULT_BLOOM_FILTER_ENABLED
public static final boolean DEFAULT_BLOOM_FILTER_ENABLED
- See Also:
- Constant Field Values
-
DEFAULT_BLOOM_FILTER_FPP
public static final double DEFAULT_BLOOM_FILTER_FPP
- See Also:
- Constant Field Values
-
DEFAULT_ADAPTIVE_BLOOM_FILTER_ENABLED
public static final boolean DEFAULT_ADAPTIVE_BLOOM_FILTER_ENABLED
- See Also:
- Constant Field Values
-
DEFAULT_BLOOM_FILTER_CANDIDATES_NUMBER
public static final int DEFAULT_BLOOM_FILTER_CANDIDATES_NUMBER
- See Also:
- Constant Field Values
-
DEFAULT_STATISTICS_ENABLED
public static final boolean DEFAULT_STATISTICS_ENABLED
- See Also:
- Constant Field Values
-
DEFAULT_SIZE_STATISTICS_ENABLED
public static final boolean DEFAULT_SIZE_STATISTICS_ENABLED
- See Also:
- Constant Field Values
-
DEFAULT_PAGE_WRITE_CHECKSUM_ENABLED
public static final boolean DEFAULT_PAGE_WRITE_CHECKSUM_ENABLED
- See Also:
- Constant Field Values
-
DEFAULT_VALUES_WRITER_FACTORY
@Deprecated public static final ValuesWriterFactory DEFAULT_VALUES_WRITER_FACTORY
Deprecated.This shared instance can cause thread safety issues when used by multiple builders concurrently. Usenew DefaultValuesWriterFactory()instead to create individual instances.
-
-
Method Detail
-
builder
public static ParquetProperties.Builder builder()
-
copy
public static ParquetProperties.Builder copy(ParquetProperties toCopy)
-
newRepetitionLevelWriter
public ValuesWriter newRepetitionLevelWriter(ColumnDescriptor path)
-
newDefinitionLevelWriter
public ValuesWriter newDefinitionLevelWriter(ColumnDescriptor path)
-
newRepetitionLevelEncoder
public RunLengthBitPackingHybridEncoder newRepetitionLevelEncoder(ColumnDescriptor path)
-
newDefinitionLevelEncoder
public RunLengthBitPackingHybridEncoder newDefinitionLevelEncoder(ColumnDescriptor path)
-
newValuesWriter
public ValuesWriter newValuesWriter(ColumnDescriptor path)
-
getPageSizeThreshold
public int getPageSizeThreshold()
-
getPageValueCountThreshold
public int getPageValueCountThreshold()
-
getInitialSlabSize
public int getInitialSlabSize()
-
getDictionaryPageSizeThreshold
public int getDictionaryPageSizeThreshold()
-
getWriterVersion
public ParquetProperties.WriterVersion getWriterVersion()
-
isEnableDictionary
@Deprecated public boolean isEnableDictionary()
Deprecated.
-
isDictionaryEnabled
public boolean isDictionaryEnabled(ColumnDescriptor column)
-
isByteStreamSplitEnabled
@Deprecated public boolean isByteStreamSplitEnabled()
Deprecated.
-
isByteStreamSplitEnabled
public boolean isByteStreamSplitEnabled(ColumnDescriptor column)
-
getAllocator
public ByteBufferAllocator getAllocator()
-
newColumnWriteStore
public ColumnWriteStore newColumnWriteStore(MessageType schema, PageWriteStore pageStore)
-
newColumnWriteStore
public ColumnWriteStore newColumnWriteStore(MessageType schema, PageWriteStore pageStore, BloomFilterWriteStore bloomFilterWriteStore)
-
getMinRowCountForPageSizeCheck
public int getMinRowCountForPageSizeCheck()
-
getMaxRowCountForPageSizeCheck
public int getMaxRowCountForPageSizeCheck()
-
getValuesWriterFactory
public ValuesWriterFactory getValuesWriterFactory()
-
getColumnIndexTruncateLength
public int getColumnIndexTruncateLength()
-
getStatisticsTruncateLength
public int getStatisticsTruncateLength()
-
estimateNextSizeCheck
public boolean estimateNextSizeCheck()
-
getRowGroupRowCountLimit
public int getRowGroupRowCountLimit()
-
getPageRowCountLimit
public int getPageRowCountLimit()
-
getPageWriteChecksumEnabled
public boolean getPageWriteChecksumEnabled()
-
getBloomFilterNDV
public OptionalLong getBloomFilterNDV(ColumnDescriptor column)
-
getBloomFilterFPP
public OptionalDouble getBloomFilterFPP(ColumnDescriptor column)
-
isBloomFilterEnabled
public boolean isBloomFilterEnabled(ColumnDescriptor column)
-
getMaxBloomFilterBytes
public int getMaxBloomFilterBytes()
-
getAdaptiveBloomFilterEnabled
public boolean getAdaptiveBloomFilterEnabled(ColumnDescriptor column)
-
getBloomFilterCandidatesCount
public int getBloomFilterCandidatesCount(ColumnDescriptor column)
-
getStatisticsEnabled
public boolean getStatisticsEnabled(ColumnDescriptor column)
-
getSizeStatisticsEnabled
public boolean getSizeStatisticsEnabled(ColumnDescriptor column)
-
-