#include <compress.h>

Inheritance diagram for impala::SnappyCompressor:

Collaboration diagram for impala::SnappyCompressor:

Public Types
typedef std::map< const std::string, const THdfsCompression::type >	CodecMap
	Map from codec string to compression format. More...

Public Member Functions
virtual	~SnappyCompressor ()

virtual int64_t	MaxOutputLen (int64_t input_len, const uint8_t *input=NULL)

virtual Status	ProcessBlock (bool output_preallocated, int64_t input_length, const uint8_t input, int64_t output_length, uint8_t **output)
	Process a block of data, either compressing or decompressing it. More...

virtual std::string	file_extension () const
	File extension to use for this compression codec. More...

Status	ProcessBlock32 (bool output_preallocated, int input_length, const uint8_t input, int output_length, uint8_t **output)

virtual Status	ProcessBlockStreaming (int64_t input_length, const uint8_t input, int64_t input_bytes_read, int64_t output_length, uint8_t output, bool eos)

virtual void	Close ()
	Must be called on codec before destructor for final cleanup. More...

bool	reuse_output_buffer () const

Static Public Member Functions
static uint32_t	ComputeChecksum (int64_t input_len, const uint8_t *input)

static Status	CreateDecompressor (MemPool mem_pool, bool reuse, THdfsCompression::type format, boost::scoped_ptr< Codec > decompressor)

static Status	CreateDecompressor (MemPool mem_pool, bool reuse, const std::string &codec, boost::scoped_ptr< Codec > decompressor)
	Alternate factory method: takes a codec string and populates a scoped pointer. More...

static Status	CreateCompressor (MemPool mem_pool, bool reuse, THdfsCompression::type format, boost::scoped_ptr< Codec > compressor)

static Status	CreateCompressor (MemPool mem_pool, bool reuse, const std::string &codec, boost::scoped_ptr< Codec > compressor)
	Alternate factory method: takes a codec string and populates a scoped pointer. More...

static std::string	GetCodecName (THdfsCompression::type)
	Return the name of a compression algorithm. More...

static Status	GetHadoopCodecClassName (THdfsCompression::type, std::string *out_name)
	Returns the java class name for the given compression type. More...

Static Public Attributes
static const char *const	DEFAULT_COMPRESSION
	These are the codec string representations used in Hadoop. More...

static const char *const	GZIP_COMPRESSION = "org.apache.hadoop.io.compress.GzipCodec"

static const char *const	BZIP2_COMPRESSION = "org.apache.hadoop.io.compress.BZip2Codec"

static const char *const	SNAPPY_COMPRESSION = "org.apache.hadoop.io.compress.SnappyCodec"

static const char *const	UNKNOWN_CODEC_ERROR

static const CodecMap	CODEC_MAP

static const int	MAX_BLOCK_SIZE = (2L * 1024 * 1024 * 1024) - 1

Protected Attributes
MemPool *	memory_pool_
	Pool to allocate the buffer to hold transformed data. More...

boost::scoped_ptr< MemPool >	temp_memory_pool_

bool	reuse_buffer_
	Can we reuse the output buffer or do we need to allocate on each call? More...

uint8_t *	out_buffer_

int64_t	buffer_length_
	Length of the output buffer. More...

Private Member Functions
	SnappyCompressor (MemPool *mem_pool=NULL, bool reuse_buffer=false)

virtual Status	Init ()
	Initialize the codec. This should only be called once. More...

Friends
class	Codec

Detailed Description

Definition at line 98 of file compress.h.

Member Typedef Documentation

typedef std::map<const std::string, const THdfsCompression::type> impala::Codec::CodecMap

inherited

Map from codec string to compression format.

Definition at line 51 of file codec.h.

Constructor & Destructor Documentation

virtual impala::SnappyCompressor::~SnappyCompressor ( )

inlinevirtual

Definition at line 100 of file compress.h.

SnappyCompressor::SnappyCompressor	(	MemPool *	mem_pool = `NULL`,
		bool	reuse_buffer = `false`
	)

private

Definition at line 241 of file compress.cc.

Member Function Documentation

void Codec::Close ( )

virtualinherited

Must be called on codec before destructor for final cleanup.

Definition at line 174 of file codec.cc.

References impala::MemPool::AcquireData(), impala::Codec::memory_pool_, and impala::Codec::temp_memory_pool_.

uint32_t SnappyCompressor::ComputeChecksum	(	int64_t	input_len,
		const uint8_t *	input
	)

static

Computes the crc checksum that snappy expects when used in a framing format. This checksum needs to come after the compressed data. http://code.google.com/p/snappy/source/browse/trunk/framing_format.txt

Definition at line 273 of file compress.cc.

Referenced by impala::HdfsAvroTableWriter::Flush().

static Status impala::Codec::CreateCompressor	(	MemPool *	mem_pool,
		bool	reuse,
		THdfsCompression::type	format,
		boost::scoped_ptr< Codec > *	compressor
	)

staticinherited

Create a compressor. Input: mem_pool: the memory pool used to store the compressed data. reuse: if true the allocated buffer can be reused. format: The type of compressor to create. Output: compressor: scoped pointer to the compressor class to use.

Referenced by impala::HdfsParquetTableWriter::BaseColumnWriter::BaseColumnWriter(), impala::HdfsSequenceTableWriter::Init(), impala::HdfsTextTableWriter::Init(), impala::HdfsAvroTableWriter::Init(), impala::DecompressorTest::RunTest(), impala::DecompressorTest::RunTestStreaming(), impala::RowBatch::Serialize(), impala::TEST_F(), and impala::TestCompression().

static Status impala::Codec::CreateCompressor	(	MemPool *	mem_pool,
		bool	reuse,
		const std::string &	codec,
		boost::scoped_ptr< Codec > *	compressor
	)

staticinherited

Alternate factory method: takes a codec string and populates a scoped pointer.

static Status impala::Codec::CreateDecompressor	(	MemPool *	mem_pool,
		bool	reuse,
		THdfsCompression::type	format,
		boost::scoped_ptr< Codec > *	decompressor
	)

staticinherited

Create a decompressor. Input: mem_pool: the memory pool used to store the decompressed data. reuse: if true the allocated buffer can be reused. format: the type of decompressor to create. Output: decompressor: scoped pointer to the decompressor class to use. If mem_pool is NULL, then the resulting codec will never allocate memory and the caller must be responsible for it.

Referenced by impala::HdfsRCFileScanner::InitNewRange(), impala::HdfsParquetScanner::BaseColumnReader::Reset(), impala::RowBatch::RowBatch(), impala::DecompressorTest::RunTest(), impala::DecompressorTest::RunTestStreaming(), and impala::HdfsScanner::UpdateDecompressor().

static Status impala::Codec::CreateDecompressor	(	MemPool *	mem_pool,
		bool	reuse,
		const std::string &	codec,
		boost::scoped_ptr< Codec > *	decompressor
	)

staticinherited

Alternate factory method: takes a codec string and populates a scoped pointer.

virtual std::string impala::SnappyCompressor::file_extension ( ) const

inlinevirtual

File extension to use for this compression codec.

Implements impala::Codec.

Definition at line 104 of file compress.h.

string Codec::GetCodecName ( THdfsCompression::type type )

staticinherited

Return the name of a compression algorithm.

Definition at line 50 of file codec.cc.

Referenced by impala::HdfsParquetTableWriter::Init().

Status Codec::GetHadoopCodecClassName	(	THdfsCompression::type	,
		std::string *	out_name
	)

staticinherited

Returns the java class name for the given compression type.

Definition at line 59 of file codec.cc.

References impala::Status::OK.

Referenced by impala::HdfsSequenceTableWriter::Init().

virtual Status impala::SnappyCompressor::Init ( )

inlineprivatevirtual

Initialize the codec. This should only be called once.

Implements impala::Codec.

Definition at line 114 of file compress.h.

References impala::Status::OK.

int64_t SnappyCompressor::MaxOutputLen	(	int64_t	input_len,
		const uint8_t *	input = `NULL`
	)

virtual

Returns the maximum result length from applying the codec to input. Note this is not the exact result length, simply a bound to allow preallocating a buffer. This must be an O(1) operation (i.e. cannot read all of input). Codecs that don't support this should return -1.

Implements impala::Codec.

Definition at line 245 of file compress.cc.

Referenced by ProcessBlock().

Status SnappyCompressor::ProcessBlock	(	bool	output_preallocated,
		int64_t	input_length,
		const uint8_t *	input,
		int64_t *	output_length,
		uint8_t **	output
	)

virtual

Process a block of data, either compressing or decompressing it.

If output_preallocated is true, *output_length must be the length of *output and data will be written directly to *output (*output must be big enough to contain the transformed output). If output_preallocated is false, *output will be allocated from the codec's mempool. In this case, a mempool must have been passed into the c'tor. In either case, *output_length will be set to the actual length of the transformed output. Inputs: input_length: length of the data to process input: data to process

Implements impala::Codec.

Definition at line 249 of file compress.cc.

References impala::MemPool::Allocate(), impala::Codec::buffer_length_, MaxOutputLen(), impala::Codec::memory_pool_, impala::Status::OK, impala::Codec::out_buffer_, and impala::Codec::reuse_buffer_.

Status Codec::ProcessBlock32	(	bool	output_preallocated,
		int	input_length,
		const uint8_t *	input,
		int *	output_length,
		uint8_t **	output
	)

inherited

Wrapper to the actual ProcessBlock() function. This wrapper uses lengths as ints and not int64_ts. We need to keep this interface because the Parquet thrift uses ints. See IMPALA-1116.

Definition at line 181 of file codec.cc.

References impala::Status::OK, impala::Codec::ProcessBlock(), RETURN_IF_ERROR, and UNLIKELY.

virtual Status impala::Codec::ProcessBlockStreaming	(	int64_t	input_length,
		const uint8_t *	input,
		int64_t *	input_bytes_read,
		int64_t *	output_length,
		uint8_t **	output,
		bool *	eos
	)

inlinevirtualinherited

Process data like ProcessBlock(), but can consume partial input and may only produce partial output. *input_bytes_read returns the number of bytes of input that have been consumed. Even if all input has been consumed, the caller must continue calling to fetch output until *eos returns true.

Reimplemented in impala::GzipDecompressor.

Definition at line 117 of file codec.h.

Referenced by impala::DecompressorTest::CompressAndStreamingDecompress().

bool impala::Codec::reuse_output_buffer ( ) const

inlineinherited

Definition at line 135 of file codec.h.

References impala::Codec::reuse_buffer_.

Friends And Related Function Documentation

friend class Codec

friend

Definition at line 112 of file compress.h.

Member Data Documentation

int64_t impala::Codec::buffer_length_

protectedinherited

Length of the output buffer.

Definition at line 168 of file codec.h.

Referenced by impala::GzipDecompressor::ProcessBlock(), impala::GzipCompressor::ProcessBlock(), impala::BzipDecompressor::ProcessBlock(), impala::BzipCompressor::ProcessBlock(), impala::SnappyDecompressor::ProcessBlock(), impala::SnappyBlockCompressor::ProcessBlock(), ProcessBlock(), impala::SnappyBlockDecompressor::ProcessBlock(), and impala::GzipDecompressor::ProcessBlockStreaming().

const char *const Codec::BZIP2_COMPRESSION = "org.apache.hadoop.io.compress.BZip2Codec"

staticinherited

Definition at line 46 of file codec.h.

const Codec::CodecMap Codec::CODEC_MAP

staticinherited

Initial value:

= map_list_of
  ("", THdfsCompression::NONE)
  (DEFAULT_COMPRESSION, THdfsCompression::DEFAULT)
  (GZIP_COMPRESSION, THdfsCompression::GZIP)
  (BZIP2_COMPRESSION, THdfsCompression::BZIP2)
  (SNAPPY_COMPRESSION, THdfsCompression::SNAPPY_BLOCKED)

Definition at line 52 of file codec.h.

Referenced by impala::HdfsSequenceScanner::ReadFileHeader(), and impala::HdfsRCFileScanner::ReadFileHeader().

const char *const Codec::DEFAULT_COMPRESSION

staticinherited

Initial value:

=

"org.apache.hadoop.io.compress.DefaultCodec"

These are the codec string representations used in Hadoop.

Definition at line 44 of file codec.h.

const char *const Codec::GZIP_COMPRESSION = "org.apache.hadoop.io.compress.GzipCodec"

staticinherited

Definition at line 45 of file codec.h.

const int impala::Codec::MAX_BLOCK_SIZE = (2L * 1024 * 1024 * 1024) - 1

staticinherited

Largest block we will compress/decompress: 2GB. We are dealing with compressed blocks that are never this big but we want to guard against a corrupt file that has the block length as some large number.

Definition at line 140 of file codec.h.

Referenced by impala::GzipDecompressor::ProcessBlock(), impala::BzipDecompressor::ProcessBlock(), impala::SnappyDecompressor::ProcessBlock(), impala::SnappyBlockDecompressor::ProcessBlock(), and SnappyBlockDecompress().

MemPool* impala::Codec::memory_pool_

protectedinherited

Pool to allocate the buffer to hold transformed data.

Definition at line 154 of file codec.h.

Referenced by impala::Codec::Close(), impala::Codec::Codec(), impala::GzipDecompressor::ProcessBlock(), impala::GzipCompressor::ProcessBlock(), impala::BzipDecompressor::ProcessBlock(), impala::BzipCompressor::ProcessBlock(), impala::SnappyDecompressor::ProcessBlock(), impala::SnappyBlockCompressor::ProcessBlock(), ProcessBlock(), impala::SnappyBlockDecompressor::ProcessBlock(), and impala::GzipDecompressor::ProcessBlockStreaming().

uint8_t* impala::Codec::out_buffer_

protectedinherited

Buffer to hold transformed data. Either passed from the caller or allocated from memory_pool_.

Definition at line 165 of file codec.h.

Referenced by impala::GzipDecompressor::ProcessBlock(), impala::GzipCompressor::ProcessBlock(), impala::BzipDecompressor::ProcessBlock(), impala::BzipCompressor::ProcessBlock(), impala::SnappyDecompressor::ProcessBlock(), impala::SnappyBlockCompressor::ProcessBlock(), ProcessBlock(), impala::SnappyBlockDecompressor::ProcessBlock(), and impala::GzipDecompressor::ProcessBlockStreaming().

bool impala::Codec::reuse_buffer_

protectedinherited

Can we reuse the output buffer or do we need to allocate on each call?

Definition at line 161 of file codec.h.

Referenced by impala::GzipDecompressor::ProcessBlock(), impala::GzipCompressor::ProcessBlock(), impala::BzipDecompressor::ProcessBlock(), impala::BzipCompressor::ProcessBlock(), impala::SnappyDecompressor::ProcessBlock(), impala::SnappyBlockCompressor::ProcessBlock(), ProcessBlock(), impala::SnappyBlockDecompressor::ProcessBlock(), impala::GzipDecompressor::ProcessBlockStreaming(), and impala::Codec::reuse_output_buffer().

const char *const Codec::SNAPPY_COMPRESSION = "org.apache.hadoop.io.compress.SnappyCodec"

staticinherited

Definition at line 47 of file codec.h.

boost::scoped_ptr<MemPool> impala::Codec::temp_memory_pool_

protectedinherited

Temporary memory pool: in case we get the output size too small we can use this to free unused buffers.

Definition at line 158 of file codec.h.

Referenced by impala::Codec::Close(), impala::Codec::Codec(), impala::GzipDecompressor::ProcessBlock(), impala::BzipDecompressor::ProcessBlock(), and impala::BzipCompressor::ProcessBlock().

const char *const Codec::UNKNOWN_CODEC_ERROR

staticinherited

Initial value:

=

"This compression codec is currently unsupported: "

Definition at line 48 of file codec.h.

The documentation for this class was generated from the following files:

be/src/util/compress.h
be/src/util/compress.cc

Public Types

Public Member Functions

Static Public Member Functions

Static Public Attributes

Protected Attributes

Private Member Functions

Friends

Detailed Description

Member Typedef Documentation

Constructor & Destructor Documentation

Member Function Documentation

Friends And Related Function Documentation

Member Data Documentation