Class ibis::mensa contains multiple (horizontal) data partitions (ibis::part) to form a logical data table. More...

#include <mensa.h>

Inheritance diagram for ibis::mensa:

Classes
class	cursor

Public Member Functions
virtual int	addPartition (const char *)
	Add data partitions defined in the named directory. More...

virtual int	backup (const char dir, const char tname=0, const char *tdesc=0) const
	Write the current content to the specified output directory in the raw binary format. More...

virtual int	buildIndex (const char , const char )
	The following functions deal with auxillary data for accelerating query processing, primarily for building indexes. More...

virtual int	buildIndexes (const char *)
	Create indexes for every column of the table. More...

virtual int	buildIndexes (const ibis::table::stringArray &)
	The following functions deal with auxillary data for accelerating query processing, primarily for building indexes. More...

virtual stringArray	columnNames () const
	Return the column names in a list. More...

virtual typeArray	columnTypes () const
	Return the column types in a list.

virtual ibis::table::cursor *	createCursor () const
	Create a `cursor` object to perform row-wise data access.

virtual void	describe (std::ostream &) const
	!< Return data types. More...

virtual int	dropPartition (const char *)
	Remove the named data partition from this data table. More...

virtual int	dump (std::ostream &, const char *) const
	Print the values in ASCII form to the specified output stream. More...

virtual int	dump (std::ostream &, uint64_t, const char *) const
	Print the first nr rows.

virtual int	dump (std::ostream &, uint64_t, uint64_t, const char *) const
	Print nr rows starting with row offset. More...

virtual void	dumpNames (std::ostream &, const char *) const
	Print all column names on one line.

virtual void	estimate (const char *cond, uint64_t &nmin, uint64_t &nmax) const
	Estimate the number of rows satisfying the selection conditions. More...

virtual void	estimate (const ibis::qExpr *cond, uint64_t &nmin, uint64_t &nmax) const
	Estimate the number of rows satisfying the selection conditions. More...

virtual int64_t	getColumnAsBytes (const char , char , uint64_t=0, uint64_t=0) const
	Retrieve all values of the named column. More...

virtual int64_t	getColumnAsDoubles (const char , double , uint64_t=0, uint64_t=0) const

virtual int64_t	getColumnAsDoubles (const char *, std::vector< double > &, uint64_t=0, uint64_t=0) const
	Retrieve all values of the named column. More...

virtual int64_t	getColumnAsFloats (const char , float , uint64_t=0, uint64_t=0) const

virtual int64_t	getColumnAsInts (const char , int32_t , uint64_t=0, uint64_t=0) const
	Retrieve all values of the named column. More...

virtual int64_t	getColumnAsLongs (const char , int64_t , uint64_t=0, uint64_t=0) const

virtual int64_t	getColumnAsOpaques (const char *, std::vector< ibis::opaque > &, uint64_t=0, uint64_t=0) const
	Retrieve the blobs as ibis::opaque objects. More...

virtual int64_t	getColumnAsShorts (const char , int16_t , uint64_t=0, uint64_t=0) const
	Retrieve all values of the named column. More...

virtual int64_t	getColumnAsStrings (const char *, std::vector< std::string > &, uint64_t=0, uint64_t=0) const
	Convert values to their string form. More...

virtual int64_t	getColumnAsUBytes (const char , unsigned char , uint64_t=0, uint64_t=0) const
	Retrieve all values of the named column. More...

virtual int64_t	getColumnAsUInts (const char , uint32_t , uint64_t=0, uint64_t=0) const
	Retrieve all values of the named column. More...

virtual int64_t	getColumnAsULongs (const char , uint64_t , uint64_t=0, uint64_t=0) const

virtual int64_t	getColumnAsUShorts (const char , uint16_t , uint64_t=0, uint64_t=0) const
	Retrieve all values of the named column. More...

virtual double	getColumnMax (const char *) const
	Compute the maximum of all valid values in the name column. More...

virtual double	getColumnMin (const char *) const
	Compute the minimum of all valid values in the name column. More...

virtual long	getHistogram (const char , const char , double, double, double, std::vector< uint32_t > &) const

virtual long	getHistogram2D (const char , const char , double, double, double, const char *, double, double, double, std::vector< uint32_t > &) const
	Compute a two-dimension histogram on columns `cname1` and `cname2`. More...

virtual long	getHistogram3D (const char , const char , double, double, double, const char , double, double, double, const char , double, double, double, std::vector< uint32_t > &) const
	Compute a three-dimensional histogram on the named columns. More...

virtual int	getPartitions (ibis::constPartList &) const
	Retrieve the list of partitions.

virtual table *	groupby (const stringArray &) const
	Directly performing group-by on the base data (without selection) is not currently supported. More...

virtual table *	groupby (const char *) const
	Directly performing group-by on the base data (without selection) is not currently supported. More...

virtual const char *	indexSpec (const char *) const
	Retrieve the current indexing option. More...

virtual void	indexSpec (const char , const char )
	Replace the current indexing option. More...

	mensa (const char *dir)
	This function expects a valid data directory to find data partitions. More...

	mensa (const char dir1, const char dir2)
	This function expects a pair of data directories to define data partitions. More...

virtual int	mergeCategories (const ibis::table::stringArray &)
	Merge the dictionaries of categorical value from different data partitions. More...

virtual uint32_t	nColumns () const
	Number of columns. More...

virtual uint64_t	nRows () const
	The number of rows in this table.

virtual void	orderby (const stringArray &, const std::vector< bool > &)
	Reordering the rows using the specified columns. More...

virtual void	orderby (const stringArray &)
	Reordering the rows using the specified columns. More...

virtual void	orderby (const char *str)
	Reorder the rows. The column names are separated by commas.

virtual void	reverseRows ()
	Reversing the ordering of the rows on disk requires too much work but has no obvious benefit. More...

virtual table *	select (const char sel, const char cond) const
	Given a set of column names and a set of selection conditions, compute another table that represents the selected values. More...

virtual table *	select2 (const char sel, const char cond, const char *pts) const
	A variation of the function select defined in ibis::table. More...

Public Member Functions inherited from ibis::table
virtual const char *	description () const
	Free text description. May return a null pointer.

virtual const char *	name () const
	Name of the table. More...

virtual table *	select (const char sel, const ibis::qExpr cond) const
	Process the selection conditions and generate another table to hold the answer. More...

virtual	~table ()
	Destructor.

Protected Member Functions
void	clear ()
	Clear the existing content.

int64_t	computeHits (const char *cond) const
	Compute the number of hits.

Protected Member Functions inherited from ibis::table
	table ()
	!< Description of the table. More...

	table (const char na, const char de)
	Constructor. Use the user-supplied name and description.

Protected Attributes
ibis::table::namesTypes	naty
	A combined list of columns names.

uint64_t	nrows

ibis::partList	parts
	List of data partitions.

Protected Attributes inherited from ibis::table
std::string	desc_
	!< Name of the table.

std::string	name_

Friends
class	cursor

Additional Inherited Members
Public Types inherited from ibis::table
typedef ibis::array_t< void * >	bufferArray
	A list to hold the in-memory buffers. More...

typedef std::map< const char *, ibis::TYPE_T, ibis::lessi >	namesTypes
	An associative array of names and types.

typedef ibis::array_t< const char * >	stringArray
	A list of strings. More...

typedef std::vector< const char * >	stringVector

typedef ibis::array_t< ibis::TYPE_T >	typeArray
	A list of data types.

Static Public Member Functions inherited from ibis::table
static void *	allocateBuffer (ibis::TYPE_T, size_t)
	Allocate a buffer of the specified type and size.

static int64_t	computeHits (const ibis::constPartList &parts, const char *cond)
	Compute the number of rows satisfying the specified conditions. More...

static int64_t	computeHits (const ibis::constPartList &parts, const ibis::qExpr *cond)
	Compute the number of rows satisfying the specified query expression. More...

static void	consecrateName (char *)
	Remove unallowed characters from the given string to produce a valid column name. More...

static ibis::table *	create (ibis::part &)
	Create a simple of container of a partition. More...

static ibis::table *	create (const ibis::partList &)
	Create a container of externally managed data partitions. More...

static ibis::table *	create (const char *dir)
	Create a table object from the specified data directory. More...

static ibis::table *	create (const char dir1, const char dir2)
	Create a table object from a pair of data directories. More...

static void	freeBuffer (void *buffer, ibis::TYPE_T type)
	Freeing a buffer for storing in-memory values. More...

static void	freeBuffers (bufferArray &, typeArray &)
	Freeing a list of buffers. More...

static bool	isValidName (const char *)
	Is the given string a valid FastBit name for a data column?

static void	parseNames (char *in, stringVector &out)
	Parse the incoming string into a set of names. More...

static void	parseNames (char *in, stringArray &out)
	Parse the incoming string into a set of names. More...

static void	parseOrderby (char *in, stringArray &out, std::vector< bool > &direc)
	Parse the incoming string as an order-by clause. More...

static table *	select (const ibis::constPartList &parts, const char sel, const char cond)
	Perform the select operation on a list of data partitions. More...

static table *	select (const ibis::constPartList &parts, const char sel, const ibis::qExpr cond)
	Perform select operation using a user-supplied query expression. More...

Detailed Description

Class ibis::mensa contains multiple (horizontal) data partitions (ibis::part) to form a logical data table.

The base data contained in this table is logically immutable as reordering rows (through function orderby) does not change the overall content of the table. The functions reverseRows and groupby are not implmented.

Note: Mensa is a Latin word for "table."

Constructor & Destructor Documentation

ibis::mensa::mensa ( const char * dir )

explicit

This function expects a valid data directory to find data partitions.

If the incoming directory is not a valid string, it will use ibis::gParameter() to find data partitions.

References ibis::table::desc_, ibis::util::gatherParts(), ibis::gParameters(), naty, and parts.

ibis::mensa::mensa	(	const char *	dir1,
		const char *	dir2
	)

This function expects a pair of data directories to define data partitions.

If either dir1 and dir2 is not valid, it will attempt to find data partitions using global parameters ibis::gParameters().

References ibis::table::desc_, ibis::util::gatherParts(), ibis::gParameters(), naty, and parts.

Member Function Documentation

int ibis::mensa::addPartition ( const char * dir )

virtual

Add data partitions defined in the named directory.

It uses opendir and friends to traverse the subdirectories, which means it will only able to descend to subdirectories on unix and compatible systems.

Reimplemented from ibis::table.

Reimplemented in ibis::liga.

References ibis::util::gatherParts(), and ibis::gParameters().

int ibis::mensa::backup	(	const char *	dir,
		const char *	tname = `0`,
		const char *	tdesc = `0`
	)		const

virtual

Write the current content to the specified output directory in the raw binary format.

May optionally overwrite the name and description of the table.

Implements ibis::table.

int ibis::mensa::buildIndex	(	const char *	colname,
		const char *	option
	)

virtual

The following functions deal with auxillary data for accelerating query processing, primarily for building indexes.

Create the index for the named column. The existing index will be replaced. If an indexing option is not specified, it will use the internally recorded option for the named column or the table containing the column.

Note: Unless there is a specific instruction to not index a column, the querying functions will automatically build indexes as necessary. However, as building an index is relatively expensive, building an index on a column is on average about four or five times as expensive as reading the column from disk, this function is provided to build indexes beforehand.

Implements ibis::table.

References ibis::column::loadIndex(), and ibis::column::unloadIndex().

int ibis::mensa::buildIndexes ( const char * options )

virtual

Create indexes for every column of the table.

Existing indexes will be replaced. If an indexing option is not specified, the internally recorded options will be used.

See also: buildIndex

Implements ibis::table.

int ibis::mensa::buildIndexes ( const ibis::table::stringArray & )

virtual

The following functions deal with auxillary data for accelerating query processing, primarily for building indexes.

Create the index for the named column. The existing index will be replaced. If an indexing option is not specified, it will use the internally recorded option for the named column or the table containing the column.

Note: Unless there is a specific instruction to not index a column, the querying functions will automatically build indexes as necessary. However, as building an index is relatively expensive, building an index on a column is on average about four or five times as expensive as reading the column from disk, this function is provided to build indexes beforehand.

Implements ibis::table.

ibis::table::stringArray ibis::mensa::columnNames ( ) const

virtual

Return the column names in a list.

Note: this implementation only look at the first data partition in the list of data partitions.; the list of column names contains raw pointers to column names. If the underlying data partition is removed, these pointers will become invalid.

Implements ibis::table.

void ibis::mensa::describe ( std::ostream & ) const

virtual

!< Return data types.

Print a description of the table to the specified output stream.

Implements ibis::table.

References ibis::TYPESTRING.

int ibis::mensa::dropPartition ( const char * )

virtual

Remove the named data partition from this data table.

The incoming argument is expected to the name of the data partition.

Note: If it is not a name of any data partition, we check if it is the name of the data directory. In the process of matching directory names, we will match the leading port of the directory name only. This allows the data partitions added through a single call of addPartition to be dropped with a single call to this function using the same arguement.

Reimplemented from ibis::table.

References ibis::util::envLock.

int ibis::mensa::dump	(	std::ostream &	out,
		const char *	del
	)		const

virtual

Print the values in ASCII form to the specified output stream.

The default delimiter is coma (","), which produces Comma-Separated-Values (CSV).

Implements ibis::table.

References ibis::mensa::cursor::dumpBlock(), and ibis::mensa::cursor::fetch().

Referenced by ibis::mensa::cursor::dumpSome().

int ibis::mensa::dump	(	std::ostream &	out,
		uint64_t	offset,
		uint64_t	nr,
		const char *	del
	)		const

inlinevirtual

Print nr rows starting with row offset.

Note that the row number starts with 0, i.e., the first row is row 0.

Implements ibis::table.

References ibis::mensa::cursor::dumpSome(), ibis::mensa::cursor::fetch(), and parts.

void ibis::mensa::estimate	(	const char *	cond,
		uint64_t &	nmin,
		uint64_t &	nmax
	)		const

virtual

Estimate the number of rows satisfying the selection conditions.

The number of rows is between [nmin, nmax] (inclusive).

Implements ibis::table.

References ibis::countQuery::estimate(), ibis::countQuery::getMaxNumHits(), ibis::countQuery::getMinNumHits(), ibis::countQuery::setPartition(), and ibis::countQuery::setWhereClause().

void ibis::mensa::estimate	(	const ibis::qExpr *	cond,
		uint64_t &	nmin,
		uint64_t &	nmax
	)		const

virtual

Estimate the number of rows satisfying the selection conditions.

The number of rows is between [nmin, nmax] (inclusive).

Implements ibis::table.

References ibis::countQuery::estimate(), ibis::countQuery::getMaxNumHits(), ibis::countQuery::getMinNumHits(), ibis::countQuery::setPartition(), and ibis::countQuery::setWhereClause().

int64_t ibis::mensa::getColumnAsBytes	(	const char *	cname,
		char *	vals,
		uint64_t	begin = `0`,
		uint64_t	end = `0`
	)		const

virtual

Retrieve all values of the named column.

The member functions of this class only support access to one column at a time. Use table::cursor class for row-wise accesses.

The arguments begin and end are given in row numbers starting from 0. If begin < end, then rows begin till end-1 are packed into the output array. If 0 == end (i.e., leaving end as the default value), then the values from begin till end of the table is packed into the output array. The default values where both begin and end are 0 define a range covering all rows of the table.

These functions return the number of elements copied upon successful completion, otherwise they return a negative number to indicate failure.

Note: For fixed-width data types, the raw pointers are used to point to the values to be returned. In these cases, the caller is responsible for allocating enough storage for the values to be returned.

Implements ibis::table.

References ibis::part::getColumn(), ibis::column::getValuesArray(), ibis::part::nRows(), and ibis::UBYTE.

int64_t ibis::mensa::getColumnAsDoubles	(	const char *	cn,
		double *	vals,
		uint64_t	begin = `0`,
		uint64_t	end = `0`
	)		const

virtual

Note: Integers four-byte or less in length can be converted to double safely. Float values may also be converted into doubles.

Implements ibis::table.

References ibis::util::copy(), ibis::DOUBLE, ibis::FLOAT, ibis::part::getColumn(), ibis::column::getValuesArray(), ibis::INT, ibis::part::nRows(), ibis::SHORT, ibis::UBYTE, ibis::UINT, and ibis::USHORT.

int64_t ibis::mensa::getColumnAsDoubles	(	const char *	cname,
		std::vector< double > &	vals,
		uint64_t	begin = `0`,
		uint64_t	end = `0`
	)		const

virtual

Retrieve all values of the named column.

The member functions of this class only support access to one column at a time. Use table::cursor class for row-wise accesses.

The arguments begin and end are given in row numbers starting from 0. If begin < end, then rows begin till end-1 are packed into the output array. If 0 == end (i.e., leaving end as the default value), then the values from begin till end of the table is packed into the output array. The default values where both begin and end are 0 define a range covering all rows of the table.

These functions return the number of elements copied upon successful completion, otherwise they return a negative number to indicate failure.

Note: For fixed-width data types, the raw pointers are used to point to the values to be returned. In these cases, the caller is responsible for allocating enough storage for the values to be returned.

Implements ibis::table.

References ibis::DOUBLE, ibis::FLOAT, ibis::part::getColumn(), ibis::column::getValuesArray(), ibis::INT, ibis::part::nRows(), ibis::SHORT, ibis::UBYTE, ibis::UINT, and ibis::USHORT.

int64_t ibis::mensa::getColumnAsFloats	(	const char *	cn,
		float *	vals,
		uint64_t	begin = `0`,
		uint64_t	end = `0`
	)		const

virtual

Note: Integers two-byte or less in length can be converted safely to floats.

Implements ibis::table.

References ibis::util::copy(), ibis::FLOAT, ibis::part::getColumn(), ibis::column::getValuesArray(), ibis::part::nRows(), ibis::SHORT, ibis::UBYTE, and ibis::USHORT.

int64_t ibis::mensa::getColumnAsInts	(	const char *	cname,
		int32_t *	vals,
		uint64_t	begin = `0`,
		uint64_t	end = `0`
	)		const

virtual

Retrieve all values of the named column.

The member functions of this class only support access to one column at a time. Use table::cursor class for row-wise accesses.

The arguments begin and end are given in row numbers starting from 0. If begin < end, then rows begin till end-1 are packed into the output array. If 0 == end (i.e., leaving end as the default value), then the values from begin till end of the table is packed into the output array. The default values where both begin and end are 0 define a range covering all rows of the table.

These functions return the number of elements copied upon successful completion, otherwise they return a negative number to indicate failure.

Note: For fixed-width data types, the raw pointers are used to point to the values to be returned. In these cases, the caller is responsible for allocating enough storage for the values to be returned.

Implements ibis::table.

References ibis::util::copy(), ibis::part::getColumn(), ibis::column::getValuesArray(), ibis::INT, ibis::part::nRows(), ibis::SHORT, ibis::UBYTE, ibis::UINT, and ibis::USHORT.

int64_t ibis::mensa::getColumnAsLongs	(	const char *	cn,
		int64_t *	vals,
		uint64_t	begin = `0`,
		uint64_t	end = `0`
	)		const

virtual

Note: All integers 4-byte or shorter in length can be safely converted into int64_t. Values in uint64_t are treated as signed integers, which may create incorrect values.

Implements ibis::table.

References ibis::util::copy(), ibis::part::getColumn(), ibis::column::getValuesArray(), ibis::INT, ibis::LONG, ibis::part::nRows(), ibis::OID, ibis::SHORT, ibis::UBYTE, ibis::UINT, ibis::ULONG, and ibis::USHORT.

int64_t ibis::mensa::getColumnAsOpaques	(	const char *	cname,
		std::vector< ibis::opaque > &	vals,
		uint64_t	begin = `0`,
		uint64_t	end = `0`
	)		const

virtual

Retrieve the blobs as ibis::opaque objects.

Only work on the column type BLOB.

Implements ibis::table.

References ibis::BLOB, ibis::CATEGORY, ibis::util::copy(), ibis::DOUBLE, ibis::FLOAT, ibis::part::getColumn(), ibis::column::getOpaque(), ibis::column::getString(), ibis::column::getValuesArray(), ibis::INT, ibis::LONG, ibis::part::nRows(), ibis::OID, ibis::SHORT, ibis::TEXT, ibis::UBYTE, ibis::UINT, ibis::ULONG, and ibis::USHORT.

int64_t ibis::mensa::getColumnAsShorts	(	const char *	cname,
		int16_t *	vals,
		uint64_t	begin = `0`,
		uint64_t	end = `0`
	)		const

virtual

Retrieve all values of the named column.

The member functions of this class only support access to one column at a time. Use table::cursor class for row-wise accesses.

The arguments begin and end are given in row numbers starting from 0. If begin < end, then rows begin till end-1 are packed into the output array. If 0 == end (i.e., leaving end as the default value), then the values from begin till end of the table is packed into the output array. The default values where both begin and end are 0 define a range covering all rows of the table.

These functions return the number of elements copied upon successful completion, otherwise they return a negative number to indicate failure.

Note: For fixed-width data types, the raw pointers are used to point to the values to be returned. In these cases, the caller is responsible for allocating enough storage for the values to be returned.

Implements ibis::table.

References ibis::util::copy(), ibis::part::getColumn(), ibis::column::getValuesArray(), ibis::part::nRows(), ibis::SHORT, ibis::UBYTE, and ibis::USHORT.

int64_t ibis::mensa::getColumnAsStrings	(	const char *	cn,
		std::vector< std::string > &	vals,
		uint64_t	begin = `0`,
		uint64_t	end = `0`
	)		const

virtual

Convert values to their string form.

Many data types can be converted to strings, however, the conversion may take a significant amount of time.

Implements ibis::table.

References ibis::CATEGORY, ibis::DOUBLE, ibis::FLOAT, ibis::part::getColumn(), ibis::util::getString(), ibis::column::getValuesArray(), ibis::INT, ibis::LONG, ibis::part::nRows(), ibis::OID, ibis::SHORT, ibis::TEXT, ibis::UBYTE, ibis::UINT, ibis::ULONG, and ibis::USHORT.

int64_t ibis::mensa::getColumnAsUBytes	(	const char *	cname,
		unsigned char *	vals,
		uint64_t	begin = `0`,
		uint64_t	end = `0`
	)		const

virtual

Retrieve all values of the named column.

The member functions of this class only support access to one column at a time. Use table::cursor class for row-wise accesses.

The arguments begin and end are given in row numbers starting from 0. If begin < end, then rows begin till end-1 are packed into the output array. If 0 == end (i.e., leaving end as the default value), then the values from begin till end of the table is packed into the output array. The default values where both begin and end are 0 define a range covering all rows of the table.

These functions return the number of elements copied upon successful completion, otherwise they return a negative number to indicate failure.

Note: For fixed-width data types, the raw pointers are used to point to the values to be returned. In these cases, the caller is responsible for allocating enough storage for the values to be returned.

Implements ibis::table.

References ibis::part::getColumn(), ibis::column::getValuesArray(), ibis::part::nRows(), and ibis::UBYTE.

int64_t ibis::mensa::getColumnAsUInts	(	const char *	cname,
		uint32_t *	vals,
		uint64_t	begin = `0`,
		uint64_t	end = `0`
	)		const

virtual

Retrieve all values of the named column.

The member functions of this class only support access to one column at a time. Use table::cursor class for row-wise accesses.

The arguments begin and end are given in row numbers starting from 0. If begin < end, then rows begin till end-1 are packed into the output array. If 0 == end (i.e., leaving end as the default value), then the values from begin till end of the table is packed into the output array. The default values where both begin and end are 0 define a range covering all rows of the table.

These functions return the number of elements copied upon successful completion, otherwise they return a negative number to indicate failure.

Note: For fixed-width data types, the raw pointers are used to point to the values to be returned. In these cases, the caller is responsible for allocating enough storage for the values to be returned.

Implements ibis::table.

References ibis::util::copy(), ibis::part::getColumn(), ibis::column::getValuesArray(), ibis::INT, ibis::part::nRows(), ibis::SHORT, ibis::UBYTE, ibis::UINT, and ibis::USHORT.

int64_t ibis::mensa::getColumnAsULongs	(	const char *	cn,
		uint64_t *	vals,
		uint64_t	begin = `0`,
		uint64_t	end = `0`
	)		const

virtual

Note: All integers can be converted to uint64_t, however, negative integers will be treated as unsigned integers.

Implements ibis::table.

References ibis::util::copy(), ibis::part::getColumn(), ibis::column::getValuesArray(), ibis::INT, ibis::LONG, ibis::part::nRows(), ibis::OID, ibis::SHORT, ibis::UBYTE, ibis::UINT, ibis::ULONG, and ibis::USHORT.

int64_t ibis::mensa::getColumnAsUShorts	(	const char *	cname,
		uint16_t *	vals,
		uint64_t	begin = `0`,
		uint64_t	end = `0`
	)		const

virtual

Retrieve all values of the named column.

The member functions of this class only support access to one column at a time. Use table::cursor class for row-wise accesses.

The arguments begin and end are given in row numbers starting from 0. If begin < end, then rows begin till end-1 are packed into the output array. If 0 == end (i.e., leaving end as the default value), then the values from begin till end of the table is packed into the output array. The default values where both begin and end are 0 define a range covering all rows of the table.

These functions return the number of elements copied upon successful completion, otherwise they return a negative number to indicate failure.

Note: For fixed-width data types, the raw pointers are used to point to the values to be returned. In these cases, the caller is responsible for allocating enough storage for the values to be returned.

Implements ibis::table.

References ibis::util::copy(), ibis::part::getColumn(), ibis::column::getValuesArray(), ibis::part::nRows(), ibis::SHORT, ibis::UBYTE, and ibis::USHORT.

double ibis::mensa::getColumnMax ( const char * cname ) const

virtual

Compute the maximum of all valid values in the name column.

In case of error, such as an invalid column name or an empty table, this function will return FASTBIT_DOUBLE_NULL or -DBL_MAX to ensure that the following test fails getColumnMin <= getColumnMax.

Implements ibis::table.

References ibis::column::getActualMax().

double ibis::mensa::getColumnMin ( const char * cname ) const

virtual

Compute the minimum of all valid values in the name column.

In case of error, such as an invalid column name or an empty table, this function will return FASTBIT_DOUBLE_NULL or DBL_MAX to ensure that the following test fails getColumnMin <= getColumnMax.

Implements ibis::table.

References ibis::column::getActualMin().

long ibis::mensa::getHistogram	(	const char *	constraints,
		const char *	cname,
		double	begin,
		double	end,
		double	stride,
		std::vector< uint32_t > &	counts
	)		const

virtual

Compute the histogram of the named column. This version uses the user specified bins:

[begin, begin+stride) [begin+stride, begin+2*stride) ....

A record is placed in bin

(x - begin) / stride,

where the first bin is bin 0. The total number of bins is

1 + floor((end - begin) / stride).

Note: Records (rows) outside of the range [begin, end] are not counted.; Non-positive stride is considered as an error.; If end is less than begin, an empty array counts is returned along with return value 0.

Implements ibis::table.

long ibis::mensa::getHistogram2D	(	const char *	constraints,
		const char *	cname1,
		double	begin1,
		double	end1,
		double	stride1,
		const char *	cname2,
		double	begin2,
		double	end2,
		double	stride2,
		std::vector< uint32_t > &	counts
	)		const

virtual

Compute a two-dimension histogram on columns cname1 and cname2.

The bins along each dimension are defined the same way as in function getHistogram. The array counts stores the two-dimensional bins with the first dimension as the slow varying dimension following C convention for ordering multi-dimensional arrays.

Implements ibis::table.

long ibis::mensa::getHistogram3D	(	const char *	constraints,
		const char *	cname1,
		double	begin1,
		double	end1,
		double	stride1,
		const char *	cname2,
		double	begin2,
		double	end2,
		double	stride2,
		const char *	cname3,
		double	begin3,
		double	end3,
		double	stride3,
		std::vector< uint32_t > &	counts
	)		const

virtual

Compute a three-dimensional histogram on the named columns.

The triplets <begin, end, stride> are used the same ways in getHistogram and getHistogram2D. The three dimensional bins are linearized in counts with the first being the slowest varying dimension and the third being the fastest varying dimension following the C convention for ordering multi-dimensional arrays.

Implements ibis::table.

virtual table* ibis::mensa::groupby ( const stringArray & ) const

inlinevirtual

Directly performing group-by on the base data (without selection) is not currently supported.

Implements ibis::table.

virtual table* ibis::mensa::groupby ( const char * ) const

inlinevirtual

Directly performing group-by on the base data (without selection) is not currently supported.

Reimplemented from ibis::table.

const char * ibis::mensa::indexSpec ( const char * colname ) const

virtual

Retrieve the current indexing option.

If no column name is specified, it retrieve the indexing option for the table.

Implements ibis::table.

void ibis::mensa::indexSpec	(	const char *	opt,
		const char *	colname
	)

virtual

Replace the current indexing option.

If no column name is specified, it resets the indexing option for the table.

Implements ibis::table.

int ibis::mensa::mergeCategories ( const ibis::table::stringArray & )

virtual

Merge the dictionaries of categorical value from different data partitions.

The argument is a list of column names. If the incoming list is empty, then dictionaries of categorical columns with the same names are combined. If a list is provided by the caller, then all columns with the given names will be placed in a single dictionary. Additionally, all indexes associated with the columns will be updated to make use of the new combined dictionary.

A default implementation is provided. This default implementation does nothing and returns 0. This action is valid for a table with only a single partition and the incoming list is empty.

Reimplemented from ibis::table.

References ibis::CATEGORY, ibis::category::getDictionary(), ibis::category::loadIndex(), ibis::dictionary::merge(), ibis::column::name(), ibis::array_t< T >::push_back(), ibis::util::ref(), ibis::category::setDictionary(), ibis::dictionary::size(), ibis::array_t< T >::size(), and ibis::dictionary::sort().

uint32_t ibis::mensa::nColumns ( ) const

virtual

Number of columns.

It actually returns the number of columns of the first data partition. This is consistent with other functions such as columnTypes and columnNames.

Implements ibis::table.

void ibis::mensa::orderby	(	const stringArray &	names,
		const std::vector< bool > &	asc
	)

virtual

Reordering the rows using the specified columns.

Each data partition is reordered separately.

Implements ibis::table.

void ibis::mensa::orderby ( const stringArray & names )

virtual

Reordering the rows using the specified columns.

Each data partition is reordered separately.

Implements ibis::table.

virtual void ibis::mensa::reverseRows ( )

inlinevirtual

Reversing the ordering of the rows on disk requires too much work but has no obvious benefit.

Implements ibis::table.

ibis::table * ibis::mensa::select	(	const char *	sel,
		const char *	cond
	)		const

virtual

Given a set of column names and a set of selection conditions, compute another table that represents the selected values.

Implements ibis::table.

References ibis::table::select().

ibis::table * ibis::mensa::select2	(	const char *	sel,
		const char *	cond,
		const char *	pts
	)		const

virtual

A variation of the function select defined in ibis::table.

It accepts an extra argument for caller to specify a list of names of data partitions that will participate in the select operation. The argument pts may contain wild characters accepted by SQL function 'LIKE', more specifically, '_' and ''. If the argument pts is a nil pointer or an empty string

References ibis::table::computeHits(), ibis::table::select(), and ibis::util::strMatch().

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

mensa.h
mensa.cpp



	Contact us Disclaimers FastBit source code FastBit mailing list archive

Classes

Public Member Functions

Protected Member Functions

Protected Attributes

Friends

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

Member Function Documentation