class that splits the recordIO file by record More...

#include <indexed_recordio_split.h>

Inheritance diagram for dmlc::io::IndexedRecordIOSplitter:

Public Member Functions
	IndexedRecordIOSplitter (FileSystem fs, const char uri, const char *index_uri, unsigned rank, unsigned nsplit, const size_t batch_size, const bool shuffle, const int seed=0)

bool	IsTextParser (void) override
	query whether this object is a text parser

bool	ExtractNextRecord (Blob out_rec, Chunk chunk) override
	extract next record from the chunk

bool	ReadChunk (void buf, size_t size) override
	read a chunk of data into buf the data can span multiple records, but cannot contain partial records

bool	NextChunk (Blob *out_chunk) override
	get a chunk of memory that can contain multiple records, the caller needs to parse the content of the resulting chunk, for text file, out_chunk can contain data of multiple lines for recordio, out_chunk can contain multiple records(including headers)

void	BeforeFirst (void) override
	reset the position of InputSplit to beginning

bool	NextBatch (Blob *out_chunk, size_t n_records) override
	get a chunk of memory that can contain multiple records, with hint for how many records is needed, the caller needs to parse the content of the resulting chunk, for text file, out_chunk can contain data of multiple lines for recordio, out_chunk can contain multiple records(including headers)

bool	NextRecord (Blob *out_rec) override
	get the next record, the returning value is valid until next call to NextRecord, NextChunk or NextBatch caller can modify the memory content of out_rec

void	SetRandomSeed (size_t seed)

void	SetBatchSize (int batch_size)

bool	NextChunkEx (Chunk *out_chunk) override
	fill the given chunk with new data without using internal temporary chunk

bool	NextBatchEx (Chunk *out_chunk, size_t n_records) override
	fill the given chunk with new batch of data without using internal temporary chunk

Public Member Functions inherited from dmlc::io::InputSplitBase
virtual void	HintChunkSize (size_t chunk_size)
	hint the inputsplit how large the chunk size it should return when implementing NextChunk this is a hint so may not be enforced, but InputSplit will try adjust its internal buffer size to the hinted value

virtual size_t	GetTotalSize (void)
	get the total size of the InputSplit

bool	ExtractNextChunk (Blob out_rchunk, Chunk chunk)
	extract next chunk from the chunk

Public Member Functions inherited from dmlc::InputSplit
virtual	~InputSplit (void) DMLC_THROW_EXCEPTION
	destructor

Protected Member Functions
size_t	SeekRecordBegin (Stream *fi) override
	seek to the beginning of the first record in current file pointer

const char *	FindLastRecordBegin (const char begin, const char end) override
	find the last occurance of record header

virtual void	ReadIndexFile (FileSystem *fs, const std::string &index_uri)

void	ResetPartition (unsigned rank, unsigned nsplit) override
	reset the Input split to a certain part id, The InputSplit will be pointed to the head of the new specified segment. This feature may not be supported by every implementation of InputSplit.

Protected Member Functions inherited from dmlc::io::InputSplitBase
void	Init (FileSystem fs, const char uri, size_t align_bytes, const bool recurse_directories=false)
	intialize the base before doing anything

std::vector< URI >	ConvertToURIs (const std::string &uri)
	split string list of files into vector of URIs

size_t	Read (void *ptr, size_t size)
	same as stream.Read

Protected Attributes
std::vector< std::pair< size_t, size_t > >	index_

std::vector< size_t >	permutation_

bool	shuffle_

size_t	current_index_

size_t	index_begin_

size_t	index_end_

size_t	batch_size_

size_t	n_overflow_

const int	kRandMagic = 111

std::mt19937	rnd_

Protected Attributes inherited from dmlc::io::InputSplitBase
FileSystem *	filesys_
	FileSystem.

std::vector< size_t >	file_offset_
	byte-offset of each file

size_t	offset_curr_
	get the current offset

size_t	offset_begin_
	beginning of offset

size_t	offset_end_
	end of the offset

std::vector< FileInfo >	files_
	information about files

SeekStream *	fs_
	current input stream

size_t	file_ptr_
	file pointer of which file to read on

size_t	file_ptr_end_
	file pointer where the end of file lies

Chunk	tmp_chunk_
	temporal chunk

size_t	buffer_size_
	buffer size

Additional Inherited Members
Static Public Member Functions inherited from dmlc::InputSplit
static InputSplit *	Create (const char uri, unsigned part_index, unsigned num_parts, const char type)
	factory function: create input split given a uri

static InputSplit *	Create (const char uri, const char index_uri, unsigned part_index, unsigned num_parts, const char *type, const bool shuffle=false, const int seed=0, const size_t batch_size=256, const bool recurse_directories=false)
	factory function: create input split given a uri for input and index

Static Public Attributes inherited from dmlc::io::InputSplitBase
static const size_t	kBufferSize = 2UL << 20UL

Detailed Description

class that splits the recordIO file by record

Member Function Documentation

◆ BeforeFirst()

void dmlc::io::IndexedRecordIOSplitter::BeforeFirst ( void )

overridevirtual

reset the position of InputSplit to beginning

Reimplemented from dmlc::io::InputSplitBase.

◆ ExtractNextRecord()

bool dmlc::io::IndexedRecordIOSplitter::ExtractNextRecord	(	Blob *	out_rec,
		Chunk *	chunk
	)

overridevirtual

extract next record from the chunk

Parameters

out_rec	the output record
chunk	the chunk information

Returns: true if non-empty record is extracted false if the chunk is already finishes its life

Implements dmlc::io::InputSplitBase.

◆ FindLastRecordBegin()

const char * dmlc::io::IndexedRecordIOSplitter::FindLastRecordBegin	(	const char *	begin,
		const char *	end
	)

overrideprotectedvirtual

find the last occurance of record header

Parameters

begin	beginning of the buffer
end	end of the buffer

Returns: the pointer between [begin, end] indicating the last record head

Implements dmlc::io::InputSplitBase.

◆ IsTextParser()

bool dmlc::io::IndexedRecordIOSplitter::IsTextParser ( void )

inlineoverridevirtual

query whether this object is a text parser

Returns: true if this object represents a text parser; false if it represents a binary parser

Implements dmlc::io::InputSplitBase.

◆ NextBatch()

bool dmlc::io::IndexedRecordIOSplitter::NextBatch	(	Blob *	out_chunk,
		size_t
	)

overridevirtual

get a chunk of memory that can contain multiple records, with hint for how many records is needed, the caller needs to parse the content of the resulting chunk, for text file, out_chunk can contain data of multiple lines for recordio, out_chunk can contain multiple records(including headers)

This function ensures there won't be partial record in the chunk caller can modify the memory content of out_chunk, the memory is valid until next call to NextRecord, NextChunk or NextBatch

Parameters

out_chunk used to store the result

Returns: true if we can successfully get next record false if we reached end of split

See also: InputSplit::Create for definition of record; RecordIOChunkReader to parse recordio content from out_chunk

Reimplemented from dmlc::InputSplit.

◆ NextBatchEx()

bool dmlc::io::IndexedRecordIOSplitter::NextBatchEx	(	Chunk *	chunk,
		size_t
	)

overridevirtual

fill the given chunk with new batch of data without using internal temporary chunk

Reimplemented from dmlc::io::InputSplitBase.

◆ NextChunk()

bool dmlc::io::IndexedRecordIOSplitter::NextChunk ( Blob * out_chunk )

overridevirtual

get a chunk of memory that can contain multiple records, the caller needs to parse the content of the resulting chunk, for text file, out_chunk can contain data of multiple lines for recordio, out_chunk can contain multiple records(including headers)

This function ensures there won't be partial record in the chunk caller can modify the memory content of out_chunk, the memory is valid until next call to NextRecord, NextChunk or NextBatch

Usually NextRecord is sufficient, NextChunk can be used by some multi-threaded parsers to parse the input content

Parameters

out_chunk used to store the result

Returns: true if we can successfully get next record false if we reached end of split

See also: InputSplit::Create for definition of record; RecordIOChunkReader to parse recordio content from out_chunk

Reimplemented from dmlc::io::InputSplitBase.

◆ NextChunkEx()

bool dmlc::io::IndexedRecordIOSplitter::NextChunkEx ( Chunk * chunk )

inlineoverridevirtual

fill the given chunk with new data without using internal temporary chunk

Reimplemented from dmlc::io::InputSplitBase.

◆ NextRecord()

bool dmlc::io::IndexedRecordIOSplitter::NextRecord ( Blob * out_rec )

inlineoverridevirtual

get the next record, the returning value is valid until next call to NextRecord, NextChunk or NextBatch caller can modify the memory content of out_rec

For text, out_rec contains a single line For recordio, out_rec contains one record content(with header striped)

Parameters

out_rec used to store the result

Returns: true if we can successfully get next record false if we reached end of split

See also: InputSplit::Create for definition of record

Reimplemented from dmlc::io::InputSplitBase.

◆ ReadChunk()

bool dmlc::io::IndexedRecordIOSplitter::ReadChunk	(	void *	buf,
		size_t *	size
	)

overridevirtual

read a chunk of data into buf the data can span multiple records, but cannot contain partial records

Parameters

buf	the memory region of the buffer, should be properly aligned to 64 bits
size	the maximum size of memory, after the function returns, it stores the size of the chunk

Returns: whether end of file was reached

Reimplemented from dmlc::io::InputSplitBase.

◆ ResetPartition()

void dmlc::io::IndexedRecordIOSplitter::ResetPartition	(	unsigned	part_index,
		unsigned	num_parts
	)

overrideprotectedvirtual

reset the Input split to a certain part id, The InputSplit will be pointed to the head of the new specified segment. This feature may not be supported by every implementation of InputSplit.

Parameters

part_index	The part id of the new input.
num_parts	The total number of parts.

Reimplemented from dmlc::io::InputSplitBase.

◆ SeekRecordBegin()

size_t dmlc::io::IndexedRecordIOSplitter::SeekRecordBegin ( Stream * fi )

overrideprotectedvirtual

seek to the beginning of the first record in current file pointer

Returns: how many bytes we read past

Implements dmlc::io::InputSplitBase.

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

External/xgboost/dmlc-core/src/io/indexed_recordio_split.h
External/xgboost/dmlc-core/src/io/indexed_recordio_split.cc

Public Member Functions

Protected Member Functions

Protected Attributes

Additional Inherited Members

Detailed Description

Member Function Documentation

◆ BeforeFirst()

◆ ExtractNextRecord()

◆ FindLastRecordBegin()

◆ IsTextParser()

◆ NextBatch()

◆ NextBatchEx()

◆ NextChunk()

◆ NextChunkEx()

◆ NextRecord()

◆ ReadChunk()

◆ ResetPartition()

◆ SeekRecordBegin()