org.apache.hadoop.hbase.regionserver

Class StoreFileReader

java.lang.Object

org.apache.hadoop.hbase.regionserver.StoreFileReader

Direct Known Subclasses:

HalfStoreFileReader

@InterfaceAudience.LimitedPrivate(value="Phoenix")
 @InterfaceStability.Evolving
public class StoreFileReader
extends Object

Reader for a StoreFile.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static interface	StoreFileReader.Listener

Field Summary

Fields

Modifier and Type	Field and Description
protected BloomType	bloomFilterType
protected BloomFilter	deleteFamilyBloomFilter
protected BloomFilter	generalBloomFilter
protected long	sequenceID
protected TimeRange	timeRange

Constructor Summary

Constructors

Constructor and Description
StoreFileReader(org.apache.hadoop.fs.FileSystem fs, org.apache.hadoop.fs.Path path, CacheConfig cacheConf, boolean primaryReplicaStoreFile, AtomicInteger refCount, boolean shared, org.apache.hadoop.conf.Configuration conf)
StoreFileReader(org.apache.hadoop.fs.FileSystem fs, org.apache.hadoop.fs.Path path, FSDataInputStreamWrapper in, long size, CacheConfig cacheConf, boolean primaryReplicaStoreFile, AtomicInteger refCount, boolean shared, org.apache.hadoop.conf.Configuration conf)

Method Summary

Modifier and Type	Method and Description
void	close(boolean evictOnClose)
BloomType	getBloomFilterType()
CellComparator	getComparator()
long	getDeleteFamilyCnt()
long	getEntries()
long	getFilterEntries() The number of Bloom filter entries in this store file, or an estimate thereof, if the Bloom filter is not loaded.
Optional<Cell>	getFirstKey()
int	getHFileMinorVersion()
HFile.Reader	getHFileReader()
int	getHFileVersion()
Optional<Cell>	getLastKey()
Optional<byte[]>	getLastRowKey()
long	getMaxTimestamp()
HFileScanner	getScanner(boolean cacheBlocks, boolean pread) Deprecated. Do not write further code which depends on this call. Instead use getStoreFileScanner() which uses the StoreFileScanner class/interface which is the preferred way to scan a store with higher level concepts.
HFileScanner	getScanner(boolean cacheBlocks, boolean pread, boolean isCompaction) Deprecated. Do not write further code which depends on this call. Instead use getStoreFileScanner() which uses the StoreFileScanner class/interface which is the preferred way to scan a store with higher level concepts.
long	getSequenceID()
StoreFileScanner	getStoreFileScanner(boolean cacheBlocks, boolean pread, boolean isCompaction, long readPt, long scannerOrder, boolean canOptimizeForNonNullColumn) Get a scanner to scan over this StoreFile.
long	getTotalBloomSize()
long	getTotalUncompressedBytes()
long	indexSize()
boolean	isBulkLoaded()
boolean	isPrimaryReplicaReader()
long	length()
void	loadBloomfilter()
void	loadBloomfilter(BlockType blockType)
Map<byte[],byte[]>	loadFileInfo()
Optional<Cell>	midKey()
boolean	passesDeleteFamilyBloomFilter(byte[] row, int rowOffset, int rowLen)
boolean	passesGeneralRowBloomFilter(byte[] row, int rowOffset, int rowLen) A method for checking Bloom filters.
boolean	passesGeneralRowColBloomFilter(Cell cell) A method for checking Bloom filters.
boolean	passesKeyRangeFilter(Scan scan) Checks whether the given scan rowkey range overlaps with the current storefile's
void	setBulkLoaded(boolean bulkLoadResult)
void	setDeleteFamilyBloomFilterFaulty()
void	setGeneralBloomFilterFaulty()
void	setListener(StoreFileReader.Listener listener)
void	setSequenceID(long sequenceID)

Methods inherited from class java.lang.Object

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

Field Detail

generalBloomFilter

protected BloomFilter generalBloomFilter

deleteFamilyBloomFilter

protected BloomFilter deleteFamilyBloomFilter

bloomFilterType

protected BloomType bloomFilterType

sequenceID

protected long sequenceID

timeRange

protected TimeRange timeRange

Constructor Detail

StoreFileReader

public StoreFileReader(org.apache.hadoop.fs.FileSystem fs,
                       org.apache.hadoop.fs.Path path,
                       CacheConfig cacheConf,
                       boolean primaryReplicaStoreFile,
                       AtomicInteger refCount,
                       boolean shared,
                       org.apache.hadoop.conf.Configuration conf)
                throws IOException

Throws:

IOException

StoreFileReader

public StoreFileReader(org.apache.hadoop.fs.FileSystem fs,
                       org.apache.hadoop.fs.Path path,
                       FSDataInputStreamWrapper in,
                       long size,
                       CacheConfig cacheConf,
                       boolean primaryReplicaStoreFile,
                       AtomicInteger refCount,
                       boolean shared,
                       org.apache.hadoop.conf.Configuration conf)
                throws IOException

Throws:

IOException

Method Detail

isPrimaryReplicaReader

public boolean isPrimaryReplicaReader()

getComparator

public CellComparator getComparator()

getStoreFileScanner

public StoreFileScanner getStoreFileScanner(boolean cacheBlocks,
                                            boolean pread,
                                            boolean isCompaction,
                                            long readPt,
                                            long scannerOrder,
                                            boolean canOptimizeForNonNullColumn)

Get a scanner to scan over this StoreFile.

Parameters:

cacheBlocks - should this scanner cache blocks?

pread - use pread (for highly concurrent small readers)

isCompaction - is scanner being used for compaction?

scannerOrder - Order of this scanner relative to other scanners. See KeyValueScanner.getScannerOrder().

canOptimizeForNonNullColumn - true if we can make sure there is no null column, otherwise false. This is a hint for optimization.

Returns:

a scanner

getScanner

@Deprecated
public HFileScanner getScanner(boolean cacheBlocks,
                                           boolean pread)

Deprecated. Do not write further code which depends on this call. Instead use getStoreFileScanner() which uses the StoreFileScanner class/interface which is the preferred way to scan a store with higher level concepts.

Parameters:

cacheBlocks - should we cache the blocks?

pread - use pread (for concurrent small readers)

Returns:

the underlying HFileScanner

getScanner

@Deprecated
public HFileScanner getScanner(boolean cacheBlocks,
                                           boolean pread,
                                           boolean isCompaction)

Deprecated. Do not write further code which depends on this call. Instead use getStoreFileScanner() which uses the StoreFileScanner class/interface which is the preferred way to scan a store with higher level concepts.

Parameters:

cacheBlocks - should we cache the blocks?

pread - use pread (for concurrent small readers)

isCompaction - is scanner being used for compaction?

Returns:

the underlying HFileScanner

close

public void close(boolean evictOnClose)
           throws IOException

Throws:

IOException

passesDeleteFamilyBloomFilter

public boolean passesDeleteFamilyBloomFilter(byte[] row,
                                             int rowOffset,
                                             int rowLen)

passesGeneralRowBloomFilter

public boolean passesGeneralRowBloomFilter(byte[] row,
                                           int rowOffset,
                                           int rowLen)

A method for checking Bloom filters. Called directly from StoreFileScanner in case of a multi-column query.

Returns:

True if passes

passesGeneralRowColBloomFilter

public boolean passesGeneralRowColBloomFilter(Cell cell)

A method for checking Bloom filters. Called directly from StoreFileScanner in case of a multi-column query.

Parameters:

cell - the cell to check if present in BloomFilter

Returns:

True if passes

passesKeyRangeFilter

public boolean passesKeyRangeFilter(Scan scan)

Checks whether the given scan rowkey range overlaps with the current storefile's

Parameters:

scan - the scan specification. Used to determine the rowkey range.

Returns:

true if there is overlap, false otherwise

loadFileInfo

public Map<byte[],byte[]> loadFileInfo()
                                throws IOException

Throws:

IOException

loadBloomfilter

public void loadBloomfilter()

loadBloomfilter

public void loadBloomfilter(BlockType blockType)

getFilterEntries

public long getFilterEntries()

The number of Bloom filter entries in this store file, or an estimate thereof, if the Bloom filter is not loaded. This always returns an upper bound of the number of Bloom filter entries.

Returns:

an estimate of the number of Bloom filter entries in this file

setGeneralBloomFilterFaulty

public void setGeneralBloomFilterFaulty()

setDeleteFamilyBloomFilterFaulty

public void setDeleteFamilyBloomFilterFaulty()

getLastKey

public Optional<Cell> getLastKey()

getLastRowKey

public Optional<byte[]> getLastRowKey()

midKey

public Optional<Cell> midKey()
                      throws IOException

Throws:

IOException

length

public long length()

getTotalUncompressedBytes

public long getTotalUncompressedBytes()

getEntries

public long getEntries()

getDeleteFamilyCnt

public long getDeleteFamilyCnt()

getFirstKey

public Optional<Cell> getFirstKey()

indexSize

public long indexSize()

getBloomFilterType

public BloomType getBloomFilterType()

getSequenceID

public long getSequenceID()

setSequenceID

public void setSequenceID(long sequenceID)

setBulkLoaded

public void setBulkLoaded(boolean bulkLoadResult)

isBulkLoaded

public boolean isBulkLoaded()

getTotalBloomSize

public long getTotalBloomSize()

getHFileVersion

public int getHFileVersion()

getHFileMinorVersion

public int getHFileMinorVersion()

getHFileReader

public HFile.Reader getHFileReader()

getMaxTimestamp

public long getMaxTimestamp()

setListener

public void setListener(StoreFileReader.Listener listener)