org.apache.hudi.common.util

Class HFileUtils

java.lang.Object

org.apache.hudi.common.util.FileFormatUtils

org.apache.hudi.common.util.HFileUtils

public class HFileUtils
extends FileFormatUtils

Utility functions for HFile files.

Nested Class Summary

Nested classes/interfaces inherited from class org.apache.hudi.common.util.FileFormatUtils

FileFormatUtils.HoodieKeyIterator

Constructor Summary

Constructors

Constructor and Description
HFileUtils()

Method Summary

Modifier and Type	Method and Description
ClosableIterator<Pair<HoodieKey,Long>>	fetchRecordKeysWithPositions(HoodieStorage storage, StoragePath filePath)
ClosableIterator<Pair<HoodieKey,Long>>	fetchRecordKeysWithPositions(HoodieStorage storage, StoragePath filePath, Option<BaseKeyGenerator> keyGeneratorOpt, Option<String> partitionPath)
Set<Pair<String,Long>>	filterRowKeys(HoodieStorage storage, StoragePath filePath, Set<String> filter)
HoodieFileFormat	getFormat()
static org.apache.hadoop.hbase.io.compress.Compression.Algorithm	getHFileCompressionAlgorithm(Map<String,String> paramsMap) Gets the Compression.Algorithm Enum based on the CompressionCodec name.
ClosableIterator<HoodieKey>	getHoodieKeyIterator(HoodieStorage storage, StoragePath filePath)
ClosableIterator<HoodieKey>	getHoodieKeyIterator(HoodieStorage storage, StoragePath filePath, Option<BaseKeyGenerator> keyGeneratorOpt, Option<String> partitionPath)
long	getRowCount(HoodieStorage storage, StoragePath filePath)
List<org.apache.avro.generic.GenericRecord>	readAvroRecords(HoodieStorage storage, StoragePath filePath)
List<org.apache.avro.generic.GenericRecord>	readAvroRecords(HoodieStorage storage, StoragePath filePath, org.apache.avro.Schema schema)
org.apache.avro.Schema	readAvroSchema(HoodieStorage storage, StoragePath filePath)
List<HoodieColumnRangeMetadata<Comparable>>	readColumnStatsFromMetadata(HoodieStorage storage, StoragePath filePath, List<String> columnList)
Map<String,String>	readFooter(HoodieStorage storage, boolean required, StoragePath filePath, String... footerNames)
ByteArrayOutputStream	serializeRecordsToLogBlock(HoodieStorage storage, List<HoodieRecord> records, org.apache.avro.Schema writerSchema, org.apache.avro.Schema readerSchema, String keyFieldName, Map<String,String> paramsMap)
void	writeMetaFile(HoodieStorage storage, StoragePath filePath, Properties props)

Methods inherited from class org.apache.hudi.common.util.FileFormatUtils

getColumnRangeInPartition, readBloomFilterFromMetadata, readMinMaxRecordKeys, readRowKeys

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

HFileUtils

public HFileUtils()

Method Detail

getHFileCompressionAlgorithm

public static org.apache.hadoop.hbase.io.compress.Compression.Algorithm getHFileCompressionAlgorithm(Map<String,String> paramsMap)

Gets the Compression.Algorithm Enum based on the CompressionCodec name.

Parameters:

paramsMap - parameter map containing the compression codec config.

Returns:

the Compression.Algorithm Enum.

readAvroRecords

public List<org.apache.avro.generic.GenericRecord> readAvroRecords(HoodieStorage storage,
                                                                   StoragePath filePath)

Specified by:

readAvroRecords in class FileFormatUtils

readAvroRecords

public List<org.apache.avro.generic.GenericRecord> readAvroRecords(HoodieStorage storage,
                                                                   StoragePath filePath,
                                                                   org.apache.avro.Schema schema)

Specified by:

readAvroRecords in class FileFormatUtils

readFooter

public Map<String,String> readFooter(HoodieStorage storage,
                                     boolean required,
                                     StoragePath filePath,
                                     String... footerNames)

Specified by:

readFooter in class FileFormatUtils

getRowCount

public long getRowCount(HoodieStorage storage,
                        StoragePath filePath)

Specified by:

getRowCount in class FileFormatUtils

filterRowKeys

public Set<Pair<String,Long>> filterRowKeys(HoodieStorage storage,
                                            StoragePath filePath,
                                            Set<String> filter)

Specified by:

filterRowKeys in class FileFormatUtils

fetchRecordKeysWithPositions

public ClosableIterator<Pair<HoodieKey,Long>> fetchRecordKeysWithPositions(HoodieStorage storage,
                                                                           StoragePath filePath)

Specified by:

fetchRecordKeysWithPositions in class FileFormatUtils

getHoodieKeyIterator

public ClosableIterator<HoodieKey> getHoodieKeyIterator(HoodieStorage storage,
                                                        StoragePath filePath,
                                                        Option<BaseKeyGenerator> keyGeneratorOpt,
                                                        Option<String> partitionPath)

Specified by:

getHoodieKeyIterator in class FileFormatUtils

getHoodieKeyIterator

public ClosableIterator<HoodieKey> getHoodieKeyIterator(HoodieStorage storage,
                                                        StoragePath filePath)

Specified by:

getHoodieKeyIterator in class FileFormatUtils

fetchRecordKeysWithPositions

public ClosableIterator<Pair<HoodieKey,Long>> fetchRecordKeysWithPositions(HoodieStorage storage,
                                                                           StoragePath filePath,
                                                                           Option<BaseKeyGenerator> keyGeneratorOpt,
                                                                           Option<String> partitionPath)

Specified by:

fetchRecordKeysWithPositions in class FileFormatUtils

readAvroSchema

public org.apache.avro.Schema readAvroSchema(HoodieStorage storage,
                                             StoragePath filePath)

Specified by:

readAvroSchema in class FileFormatUtils

readColumnStatsFromMetadata

public List<HoodieColumnRangeMetadata<Comparable>> readColumnStatsFromMetadata(HoodieStorage storage,
                                                                               StoragePath filePath,
                                                                               List<String> columnList)

Specified by:

readColumnStatsFromMetadata in class FileFormatUtils

getFormat

public HoodieFileFormat getFormat()

Specified by:

getFormat in class FileFormatUtils

writeMetaFile

public void writeMetaFile(HoodieStorage storage,
                          StoragePath filePath,
                          Properties props)
                   throws IOException

Specified by:

writeMetaFile in class FileFormatUtils

Throws:

IOException

serializeRecordsToLogBlock

public ByteArrayOutputStream serializeRecordsToLogBlock(HoodieStorage storage,
                                                        List<HoodieRecord> records,
                                                        org.apache.avro.Schema writerSchema,
                                                        org.apache.avro.Schema readerSchema,
                                                        String keyFieldName,
                                                        Map<String,String> paramsMap)
                                                 throws IOException

Specified by:

serializeRecordsToLogBlock in class FileFormatUtils

Throws:

IOException