A data structure for storing null-terminated text. More...

#include <category.h>

Inheritance diagram for ibis::text:

Classes
struct	tokenizer
	A tokenizer class to turn a string buffer into tokens. More...

Public Member Functions
virtual long	append (const char dt, const char df, const uint32_t nold, const uint32_t nnew, uint32_t nbuf, char *buf)
	Append the data file stored in directory `df` to the corresponding data file in directory `dt`. More...

virtual long	append (const void *, const ibis::bitvector &)
	Append the records in vals to the current working dataset. More...

void	delimitersForKeywordIndex (std::string &) const

virtual double	estimateCost (const ibis::qString &cmp) const
	Estimate the cost of evaluating a string lookup.

virtual double	estimateCost (const ibis::qAnyString &cmp) const
	Estimate the cost of looking up a group of strings.

virtual const char *	findString (const char *str) const
	If the input string is found in the data file, it is returned, else this function returns 0. More...

virtual int	getOpaque (uint32_t, ibis::opaque &) const
	Return the raw binary value for the `i`th row. More...

virtual int	getString (uint32_t i, std::string &val) const
	Return the string value for the `i`th row. More...

const column *	IDColumnForKeywordIndex () const
	!< Print header info. More...

virtual long	keywordSearch (const char *str, ibis::bitvector &hits) const

virtual long	keywordSearch (const std::vector< std::string > &strs, ibis::bitvector &hits) const

virtual long	keywordSearch (const char *) const

virtual long	keywordSearch (const std::vector< std::string > &) const

virtual void	loadIndex (const char *iopt=0, int ropt=0) const throw ()
	Load the index associated with the column. More...

virtual long	patternSearch (const char *, ibis::bitvector &) const

virtual long	patternSearch (const char *) const

virtual void	print (std::ostream &out) const
	!< Write the metadata entry.

virtual long	saveSelected (const ibis::bitvector &sel, const char dest, char buf, uint32_t nbuf)
	Write the selected values to the specified directory. More...

virtual array_t< int64_t > *	selectLongs (const bitvector &mask) const
	Return the starting positions of strings marked 1 in the mask. More...

virtual std::vector< std::string > *	selectStrings (const bitvector &mask) const
	Retrieve the string values from the rows marked 1 in mask. More...

virtual array_t< uint32_t > *	selectUInts (const bitvector &mask) const
	Return the positions of records marked 1 in the mask. More...

virtual long	stringSearch (const char *str, ibis::bitvector &hits) const
	Given a string literal, return a bitvector that marks the strings that matche it. More...

virtual long	stringSearch (const std::vector< std::string > &strs, ibis::bitvector &hits) const
	Locate the rows match any of the given strings. More...

virtual long	stringSearch (const char *str) const

virtual long	stringSearch (const std::vector< std::string > &strs) const

void	TDListForKeywordIndex (std::string &) const

	text (const part tbl, FILE file)

	text (const part tbl, const char name, ibis::TYPE_T t=ibis::TEXT)
	Construct a text object for a data partition with the given name.

	text (const ibis::column &col)
	Copy constructor. Copy from a column of the type TEXT.

virtual void	write (FILE *file) const
	Write the current metadata to -part.txt of the data partition.

Public Member Functions inherited from ibis::column
virtual int	attachIndex (double , uint64_t, int64_t , uint64_t, void *, FastBitReadBitmaps) const

virtual int	attachIndex (double , uint64_t, int64_t , uint64_t, uint32_t *, uint64_t) const

void	binWeights (std::vector< uint32_t > &) const
	Retrive the number of rows in each bin.

template<typename T >
long	castAndWrite (const array_t< double > &vals, ibis::bitvector &mask, const T special)
	Cast the incoming array into the specified type T before writing the values to the file for this column. More...

	column (const column &rhs)
	The copy constructor. More...

	column (const part tbl, FILE file)
	Reconstitute a column from the content of a file. More...

	column (const part tbl, ibis::TYPE_T t, const char name, const char *desc="", double low=DBL_MAX, double high=-DBL_MAX)
	Construct a new column object based on type and name.

virtual void	computeMinMax ()
	Compute the actual min/max values. More...

virtual void	computeMinMax (const char *dir)
	Compute the actual min/max values. More...

virtual void	computeMinMax (const char *dir, double &min, double &max, bool &asc) const
	Compute the actual min/max of the data in directory `dir`. More...

int	contractRange (ibis::qContinuousRange &rng) const
	Contract the range expression so that the new range falls exactly on the bin boundaries. More...

const char *	dataFileName (std::string &fname, const char *dir=0) const
	Name of the data file in the given data directory. More...

const char *	description () const
	Description of the column. Can be an arbitrary string.

void	description (const char *d)

int	elementSize () const
	Size of a data element in bytes.

virtual double	estimateCost (const ibis::qContinuousRange &cmp) const
	Estimate the cost of evaluating the query expression.

virtual double	estimateCost (const ibis::qDiscreteRange &cmp) const
	Estimate the cost of evaluating a dicreate range expression.

virtual double	estimateCost (const ibis::qIntHod &cmp) const
	Estimate the cost of evaluating a dicreate range expression.

virtual double	estimateCost (const ibis::qUIntHod &cmp) const
	Estimate the cost of evaluating a dicreate range expression.

virtual long	estimateRange (const ibis::qContinuousRange &cmp, ibis::bitvector &low, ibis::bitvector &high) const
	Compute a lower bound and an upper bound on the number of hits using the bitmap index. More...

virtual long	estimateRange (const ibis::qDiscreteRange &cmp, ibis::bitvector &low, ibis::bitvector &high) const
	Compute a lower bound and an upper bound for hits. More...

virtual long	estimateRange (const ibis::qIntHod &cmp, ibis::bitvector &low, ibis::bitvector &high) const
	Compute a lower bound and an upper bound for hits. More...

virtual long	estimateRange (const ibis::qUIntHod &cmp, ibis::bitvector &low, ibis::bitvector &high) const
	Compute a lower bound and an upper bound for hits. More...

virtual long	estimateRange (const ibis::qContinuousRange &cmp) const
	Use the index of the column to compute an upper bound on the number of hits. More...

virtual long	estimateRange (const ibis::qDiscreteRange &cmp) const

virtual long	estimateRange (const ibis::qIntHod &cmp) const
	Compute an upper bound on the number of hits. More...

virtual long	estimateRange (const ibis::qUIntHod &cmp) const
	Compute an upper bound on the number of hits. More...

virtual long	evaluateAndSelect (const ibis::qContinuousRange &, const ibis::bitvector &, void *, ibis::bitvector &) const
	Evaluate a range condition and retrieve the selected values. More...

virtual long	evaluateRange (const ibis::qContinuousRange &cmp, const ibis::bitvector &mask, ibis::bitvector &res) const
	Compute the exact answer. More...

virtual long	evaluateRange (const ibis::qDiscreteRange &cmp, const ibis::bitvector &mask, ibis::bitvector &res) const
	Compute the exact answer to a discrete range expression.

virtual long	evaluateRange (const ibis::qIntHod &cmp, const ibis::bitvector &mask, ibis::bitvector &res) const
	Compute the exact answer to a discrete range expression.

virtual long	evaluateRange (const ibis::qUIntHod &cmp, const ibis::bitvector &mask, ibis::bitvector &res) const
	Compute the exact answer to a discrete range expression.

int	expandRange (ibis::qContinuousRange &rng) const
	Expand the range expression so that the new range falls exactly on the bin boundaries. More...

std::string	fullname () const
	Fully qualified name. More...

int	getDataflag () const

virtual const ibis::dictionary *	getDictionary () const
	Return a pointer to a dictionary. More...

array_t< double > *	getDoubleArray () const
	Return all rows of the column as an array_t object.

array_t< float > *	getFloatArray () const
	Return all rows of the column as an array_t object.

array_t< int32_t > *	getIntArray () const
	Return all rows of the column as an array_t object. More...

void	getNullMask (bitvector &mask) const
	If there is a null mask stored already, return a shallow copy of it in mask. More...

virtual ibis::fileManager::storage *	getRawData () const
	Return the content of base data file as a storage object.

const unixTimeScribe *	getTimeFormat () const

virtual float	getUndecidable (const ibis::qContinuousRange &cmp, ibis::bitvector &iffy) const
	Compute the locations of the rows can not be decided by the index. More...

virtual float	getUndecidable (const ibis::qDiscreteRange &cmp, ibis::bitvector &iffy) const
	Find rows that can not be decided with the existing index.

virtual float	getUndecidable (const ibis::qIntHod &cmp, ibis::bitvector &iffy) const
	Find rows that can not be decided with the existing index. More...

virtual float	getUndecidable (const ibis::qUIntHod &cmp, ibis::bitvector &iffy) const
	Find rows that can not be decided with the existing index. More...

virtual int	getValuesArray (void *vals) const
	Copy all rows of the column into an array_t object. More...

bool	hasIndex () const
	!< Are the values sorted? More...

virtual bool	hasRawData () const
	Does the raw data file exist?

bool	hasRoster () const
	Is there a roster list built for this column? Returns true for yes, false for no. More...

uint32_t	indexedRows () const
	Compute the number of rows captured by the index of this column. More...

virtual void	indexSerialSizes (uint64_t &, uint64_t &, uint64_t &) const
	Compute the sizes (in number of elements) of three arrays that would be produced by writeIndex. More...

virtual long	indexSize () const
	Compute the index size (in bytes). More...

const char *	indexSpec () const

void	indexSpec (const char *spec)
	!< Retrieve the number of bins used. More...

void	indexSpeedTest () const
	Perform a set of built-in tests to determine the speed of common operations. More...

virtual int	indexWrite (ibis::array_t< double > &, ibis::array_t< int64_t > &, ibis::array_t< uint32_t > &) const
	Write the index into three arrays.

bool	isFloat () const
	Are they floating-point values?

bool	isInteger () const
	Are they integer values?

bool	isNumeric () const
	Are they numberical values?

bool	isSignedInteger () const
	Are they signed integer values?

bool	isSorted () const

void	isSorted (bool)
	Change the flag m_sorted. More...

bool	isUnsignedInteger () const
	Are they unsigned integer values?

void	logMessage (const char event, const char fmt,...) const
	Log messages using printf syntax.

void	logWarning (const char event, const char fmt,...) const
	Log warming message using printf syntax.

const double &	lowerBound () const
	The lower bound of the values.

void	lowerBound (double d)

const char *	name () const
	Name of the column.

void	name (const char *nm)
	Rename the column.

int	nRows () const

const char *	nullMaskName (std::string &fname) const
	Name of the NULL mask file. More...

uint32_t	numBins () const
	!< Retrieve the index specification.

const part *	partition () const

const part *&	partition ()

void	preferredBounds (std::vector< double > &) const
	Retrive the bin boundaries if the index currently in use.

void	purgeIndexFile (const char *dir=0) const
	Purge the index files assocated with the current column.

virtual array_t< signed char > *	selectBytes (const bitvector &mask) const
	Retrieve selected 1-byte integer values. More...

virtual array_t< double > *	selectDoubles (const bitvector &mask) const
	Put the selected values into an array as doubles. More...

virtual array_t< float > *	selectFloats (const bitvector &mask) const
	Put selected values of a float column into an array. More...

virtual array_t< int32_t > *	selectInts (const bitvector &mask) const
	Return selected rows of the column in an array_t object. More...

virtual std::vector< ibis::opaque > *	selectOpaques (const bitvector &mask) const

virtual array_t< int16_t > *	selectShorts (const bitvector &mask) const
	Return selected rows of the column in an array_t object. More...

virtual array_t< unsigned char > *	selectUBytes (const bitvector &mask) const
	Return selected rows of the column in an array_t object. More...

virtual array_t< uint64_t > *	selectULongs (const bitvector &mask) const
	Return selected rows of the column in an array_t object. More...

virtual array_t< uint16_t > *	selectUShorts (const bitvector &mask) const
	Return selected rows of the column in an array_t object. More...

long	selectValues (const bitvector &, void *) const
	Return selected rows of the column in an array_t object. More...

long	selectValues (const bitvector &, void *, array_t< uint32_t > &) const
	Return selected rows of the column in an array_t object along with their positions. More...

long	selectValues (const ibis::qContinuousRange &, void *) const
	Select the values satisfying the specified range condition.

void	setDataflag (int df)

int	setNullMask (const bitvector &)
	Change the null mask to the user specified one. More...

void	setTimeFormat (const char *)
	Add a custom format for the column to be interpretted as unix time stamps.

void	setTimeFormat (const unixTimeScribe &)

virtual long	truncateData (const char *dir, uint32_t nent, ibis::bitvector &mask) const
	Truncate the number of records in the named dir to nent. More...

ibis::TYPE_T	type () const
	Type of the data. More...

virtual void	unloadIndex () const
	Unload the index associated with the column. More...

const double &	upperBound () const
	The upper bound of the values.

void	upperBound (double d)

virtual long	writeData (const char dir, uint32_t nold, uint32_t nnew, ibis::bitvector &mask, const void va1, void *va2=0)
	Write the content in array va1 to directory dir. More...

virtual	~column ()
	Destructor. More...

virtual double	getActualMin () const
	A group of functions to compute some basic statistics for the column values. More...

virtual double	getActualMax () const
	Compute the actual maximum value by reading the data or examining the index. More...

virtual double	getSum () const
	Compute the sum of all values by reading the data.

long	getCumulativeDistribution (std::vector< double > &bounds, std::vector< uint32_t > &counts) const
	Compute the actual data distribution. More...

long	getDistribution (std::vector< double > &bbs, std::vector< uint32_t > &counts) const
	Count the number of records in each bin. More...

Protected Member Functions
int	readString (uint32_t i, std::string &val) const
	Read the string value of `i`th row. More...

int	readString (std::string &, int, long, long, char *, uint32_t, uint32_t &, off_t &) const
	Read one string from an open file. More...

int	readStrings1 (const ibis::bitvector &, std::vector< std::string > &) const
	Read the strings marked 1 in the mask. More...

int	readStrings2 (const ibis::bitvector &, std::vector< std::string > &) const
	Read the strings marked 1 in the mask. More...

void	startPositions (const char dir, char buf, uint32_t nbuf) const
	Locate the starting position of each string. More...

int	writeStrings (const char to, const char from, const char spto, const char spfrom, ibis::bitvector &msk, const ibis::bitvector &sel, char *buf, uint32_t nbuf) const
	Write the selected strings. More...

Protected Member Functions inherited from ibis::column
void	actualMinMax (const char *fname, const ibis::bitvector &mask, double &min, double &max, bool &asc) const
	Given the name of the data file, compute the actual minimum and the maximum value. More...

long	appendStrings (const std::vector< std::string > &, const ibis::bitvector &)
	Append the strings to the current data. More...

template<typename T >
long	appendValues (const array_t< T > &, const ibis::bitvector &)
	Append the content of incoming array to the current data. More...

double	computeMax () const
	Read the base data to compute the maximum value.

double	computeMin () const
	Read the data values and compute the minimum value.

double	computeSum () const
	Read the base data to compute the total sum.

template<typename T >
uint32_t	findLower (int fdes, const uint32_t nr, const T tgt) const
	Find the smallest value >= tgt. More...

template<typename T >
uint32_t	findUpper (int fdes, const uint32_t nr, const T tgt) const
	Find the smallest value > tgt. More...

void	logError (const char event, const char fmt,...) const
	Print messages started with "Error" and throw a string exception.

virtual int	searchSorted (const ibis::qContinuousRange &, ibis::bitvector &) const
	Resolve a continuous range condition on a sorted column.

virtual int	searchSorted (const ibis::qDiscreteRange &, ibis::bitvector &) const
	Resolve a discrete range condition on a sorted column.

virtual int	searchSorted (const ibis::qIntHod &, ibis::bitvector &) const
	Resolve a discrete range condition on a sorted column.

virtual int	searchSorted (const ibis::qUIntHod &, ibis::bitvector &) const
	Resolve a discrete range condition on a sorted column.

template<typename T >
int	searchSortedICC (const array_t< T > &vals, const ibis::qContinuousRange &rng, ibis::bitvector &hits) const
	Resolve a continuous range condition on an array of values.

template<typename T >
int	searchSortedICD (const array_t< T > &vals, const ibis::qDiscreteRange &rng, ibis::bitvector &hits) const
	Resolve a discrete range condition on an array of values.

template<typename T >
int	searchSortedICD (const array_t< T > &vals, const ibis::qIntHod &rng, ibis::bitvector &hits) const
	Resolve a discrete range condition on an array of values.

template<typename T >
int	searchSortedICD (const array_t< T > &vals, const ibis::qUIntHod &rng, ibis::bitvector &hits) const
	Resolve a discrete range condition on an array of values.

template<typename T >
int	searchSortedOOCC (const char *fname, const ibis::qContinuousRange &rng, ibis::bitvector &hits) const
	Resolve a continuous range condition using file operations. More...

template<typename T >
int	searchSortedOOCD (const char *fname, const ibis::qDiscreteRange &rng, ibis::bitvector &hits) const
	Resolve a discrete range condition using file operations. More...

template<typename T >
int	searchSortedOOCD (const char *fname, const ibis::qIntHod &rng, ibis::bitvector &hits) const
	Resolve a discrete range condition using file operations. More...

template<typename T >
int	searchSortedOOCD (const char *fname, const ibis::qUIntHod &rng, ibis::bitvector &hits) const
	Resolve a discrete range condition using file operations. More...

template<typename T >
long	selectToOpaques (const char *, const bitvector &, std::vector< ibis::opaque > &) const

template<typename T >
long	selectToStrings (const char *, const bitvector &, std::vector< std::string > &) const
	Extract the values masked 1 and convert them to strings.

template<>
long	selectToStrings (const char *, const bitvector &, std::vector< std::string > &) const

template<>
long	selectToStrings (const char *, const bitvector &, std::vector< std::string > &) const

template<>
long	selectToStrings (const char *dfn, const bitvector &mask, std::vector< std::string > &str) const

template<>
long	selectToStrings (const char *dfn, const bitvector &mask, std::vector< std::string > &str) const

template<typename T >
long	selectValuesT (const char *, const bitvector &, array_t< T > &) const
	Select values marked in the bitvector `mask`. More...

template<typename T >
long	selectValuesT (const char *, const bitvector &mask, array_t< T > &vals, array_t< uint32_t > &inds) const
	Select the values marked in the bitvector `mask`. More...

long	string2int (int fptr, dictionary &dic, uint32_t nbuf, char *buf, array_t< uint32_t > &out) const
	Convert strings in the opened file to a list of integers with the aid of a dictionary. More...

Additional Inherited Members
Static Public Member Functions inherited from ibis::column
template<typename T >
static void	actualMinMax (const array_t< T > &vals, const ibis::bitvector &mask, double &min, double &max, bool &asc)
	Compute the minimum and maximum of the values in the array.

template<typename T >
static T	computeMax (const array_t< T > &vals, const ibis::bitvector &mask)
	Compute the maximum value in the array.

template<typename T >
static T	computeMin (const array_t< T > &vals, const ibis::bitvector &mask)
	Compute the minimum value in the array.

template<typename T >
static double	computeSum (const array_t< T > &vals, const ibis::bitvector &mask)
	Compute the sum of values in the array.

Protected Attributes inherited from ibis::column
int	dataflag
	Presence of the data file. More...

ibis::index *	idx
	The index for this column. It is not considered as a must-have member.

ibis::util::sharedInt32	idxcnt
	The number of functions using the index.

double	lower
	!< Are the column values in ascending order?

std::string	m_bins
	!< Free-form description of the column.

std::string	m_desc
	!< Name of the column.

std::string	m_name
	!< Data type.

bool	m_sorted
	!< Index/binning specification.

ibis::TYPE_T	m_type
	!< The entries marked 1 are valid.

unixTimeScribe *	m_utscribe
	!< The maximum value.

ibis::bitvector	mask_
	!< Data partition containing this column.

const part *	thePart

double	upper
	!< The minimum value.

Detailed Description

A data structure for storing null-terminated text.

This is meant for string values that are relatively long and may have an internal structure. The most useful search operation supported on this type of data is the keyword search, also known as full-text search. The keyword search operation is implemented through a boolean term-document matrix (implemented as ibis::keywords).

See also: ibis::keywords

Member Function Documentation

long ibis::text::append	(	const char *	dt,
		const char *	df,
		const uint32_t	nold,
		const uint32_t	nnew,
		uint32_t	nbuf,
		char *	buf
	)

virtual

Append the data file stored in directory df to the corresponding data file in directory dt.

Use the buffer buf to copy data in large chuncks.

Note: No error checking is performed.; Does not check for missing entries. May cause records to be misaligned.

Reimplemented from ibis::column.

Reimplemented in ibis::category.

References UnixOpen.

virtual long ibis::text::append	(	const void *	vals,
		const ibis::bitvector &	msk
	)

inlinevirtual

Append the records in vals to the current working dataset.

The 'void*' in this function follows the convention of the function getValuesArray (not writeData), i.e., for the ten fixed-size elementary data types, it is array_t<type>* and for string-valued columns it is std::vector<std::string>*.

Return the number of entries actually written to disk or a negative number to indicate error conditions.

Reimplemented from ibis::column.

Reimplemented in ibis::category.

const char * ibis::text::findString ( const char * str ) const

virtual

If the input string is found in the data file, it is returned, else this function returns 0.

It needs to keep both the data file and the starting position file open at the same time.

Reimplemented from ibis::column.

References ibis::fileManager::buffer< T >::address(), ibis::fileManager::instance(), ibis::fileManager::recordPages(), and ibis::fileManager::buffer< T >::size().

int ibis::text::getOpaque	(	uint32_t	irow,
		ibis::opaque &	opq
	)		const

virtual

Return the raw binary value for the ith row.

This is primarily intended to retrieve values of blobs.

See also: ibis::blob

Reimplemented from ibis::column.

References ibis::util::getString().

virtual int ibis::text::getString	(	uint32_t	,
		std::string &
	)		const

inlinevirtual

Return the string value for the ith row.

Only implemented for ibis::text and ibis::category.

See also: ibis::text

Reimplemented from ibis::column.

Reimplemented in ibis::category.

References readString().

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

const ibis::column * ibis::text::IDColumnForKeywordIndex ( ) const

!< Print header info.

Locate the ID column for processing term-document list provided by the user.

This function checks indexSpec first for docIDName=xx for the name of the ID column, then checks the global parameter <table-name>.<column-name>.docIDName.

References ibis::util::getString(), ibis::gParameters(), and ibis::column::name().

void ibis::text::loadIndex	(	const char *	iopt = `0`,
		int	ropt = `0`
	)		const
throw	(
	)

virtual

Load the index associated with the column.

Parameters

iopt	This option is passed to ibis::index::create to be used if a new index is to be created.
ropt	This option is passed to ibis::index::create to control the reading operations for reconstitute the index object from an index file.

Note: Accesses to this function are serialized through a write lock on the column. It blocks while acquire the write lock.

Reimplemented from ibis::column.

Reimplemented in ibis::category.

References ibis::column::loadIndex().

int ibis::text::readString	(	uint32_t	i,
		std::string &	ret
	)		const

protected

Read the string value of ith row.

It goes through a two-stage process by reading from two files, first from the .sp file to read the position of the string in the second file and the second file contains the actual string values (with nil terminators). This can be quite slow!

References ibis::fileManager::instance(), ibis::fileManager::recordPages(), and UnixOpen.

Referenced by getString(), and ibis::category::getString().

int ibis::text::readString	(	std::string &	res,
		int	fdes,
		long	be,
		long	en,
		char *	buf,
		uint32_t	nbuf,
		uint32_t &	inbuf,
		off_t &	boffset
	)		const

protected

Read one string from an open file.

The string starts at position be and ends at en. The content may be in the array buf.

Returns 0 if successful, otherwise return a negative number to indicate error.

int ibis::text::readStrings1	(	const ibis::bitvector &	msk,
		std::vector< std::string > &	ret
	)		const

protected

Read the strings marked 1 in the mask.

It goes through a two-stage process by reading from two files, first from the .sp file to read the position of the string in the second file containing the actual string values (with nil terminators), and then go to the second file to read the string value. This can be quite slow if you are attempting to read a lot of strings, however it could be faster than readStrings2 if only a few strings are expected.

Note: This function assumes that the .sp file has been prepared properly.

References ibis::bitvector::cnt(), ibis::bitvector::empty(), ibis::fileManager::instance(), ibis::bitvector::indexSet::nIndices(), ibis::fileManager::recordPages(), and UnixOpen.

int ibis::text::readStrings2	(	const ibis::bitvector &	mask,
		std::vector< std::string > &	res
	)		const

protected

Read the strings marked 1 in the mask.

It creates a memory map of the .sp file before reading the actual string values. Because the process of creating the memory map can take more time than reading a few values, this function is much more appropriate for reading a relatively large number of string values.

Note: This function assumes that the .sp file has been prepared properly.

References ibis::fileManager::buffer< T >::address(), ibis::bitvector::cnt(), ibis::fileManager::instance(), ibis::bitvector::indexSet::nIndices(), ibis::util::readString(), ibis::fileManager::recordPages(), ibis::array_t< T >::size(), ibis::bitvector::size(), ibis::fileManager::buffer< T >::size(), and UnixOpen.

long ibis::text::saveSelected	(	const ibis::bitvector &	sel,
		const char *	dest,
		char *	buf,
		uint32_t	nbuf
	)

virtual

Write the selected values to the specified directory.

If the destination directory is the current data directory, the file containing existing string values will be renamed to be column-name.old, otherwise, the file in the destination directory is simply overwritten. In case of error, a negative number is returned, otherwise, the number of rows saved to the new file is returned.

Reimplemented from ibis::column.

References ibis::fileManager::flushFile(), and ibis::fileManager::instance().

ibis::array_t< int64_t > * ibis::text::selectLongs ( const bitvector & mask ) const

virtual

Return the starting positions of strings marked 1 in the mask.

The starting positions of the selected string values are stored in the returned array.

Reimplemented from ibis::column.

References ibis::fileManager::getFile(), ibis::util::getFileSize(), ibis::fileManager::instance(), ibis::bitvector::indexSet::nIndices(), ibis::array_t< T >::push_back(), ibis::array_t< T >::size(), and ibis::bitvector::size().

std::vector< std::string > * ibis::text::selectStrings ( const bitvector & mask ) const

virtual

Retrieve the string values from the rows marked 1 in mask.

Note: FastBit does not track the memory usage of neither std::vector nor std::string.

Reimplemented from ibis::column.

Reimplemented in ibis::category.

References ibis::fileManager::buffer< T >::address(), ibis::bitvector::cnt(), ibis::util::getFileSize(), ibis::bitvector::indexSet::nIndices(), ibis::util::readString(), ibis::bitvector::size(), ibis::fileManager::buffer< T >::size(), and UnixOpen.

Referenced by ibis::category::selectStrings().

ibis::array_t< uint32_t > * ibis::text::selectUInts ( const bitvector & mask ) const

virtual

Return the positions of records marked 1 in the mask.

This indicates to ibis::bundle that every string value is distinct.

It also forces the sorting procedure to produce an order following the order of the entries in the table. This makes the print out of an ibis::text field quite less useful than others!

Reimplemented from ibis::column.

Reimplemented in ibis::category.

References ibis::bitvector::indexSet::nIndices(), and ibis::array_t< T >::push_back().

void ibis::text::startPositions	(	const char *	dir,
		char *	buf,
		uint32_t	nbuf
	)		const

protected

Locate the starting position of each string.

Using the data file located in the named directory dir. If dir is a nil pointer, the directory defaults to the current working directory of the data partition.

It writes the starting positions as int64_t integers to a file with .sp as extension.

Argument buf (with nbuf bytes) is used as temporary work space. If nbuf = 0, this function allocates its own working space.

References ibis::fileManager::buffer< T >::address(), and ibis::fileManager::buffer< T >::size().

Referenced by text().

long ibis::text::stringSearch	(	const char *	str,
		ibis::bitvector &	hits
	)		const

virtual

Given a string literal, return a bitvector that marks the strings that matche it.

This is a relatively slow process since this function actually reads the string values from disk.

Reimplemented from ibis::column.

Reimplemented in ibis::category.

References ibis::fileManager::buffer< T >::address(), ibis::bitvector::adjustSize(), ibis::bitvector::clear(), ibis::bitvector::cnt(), ibis::fileManager::instance(), ibis::fileManager::recordPages(), ibis::bitvector::setBit(), ibis::bitvector::size(), and ibis::fileManager::buffer< T >::size().

Referenced by ibis::category::stringSearch().

long ibis::text::stringSearch	(	const std::vector< std::string > &	strs,
		ibis::bitvector &	hits
	)		const

virtual

Locate the rows match any of the given strings.

Return the number of hits upon successful completion of this function, otherwise return a negative number to indicate error.

Reimplemented from ibis::column.

Reimplemented in ibis::category.

References ibis::fileManager::buffer< T >::address(), ibis::bitvector::adjustSize(), ibis::bitvector::clear(), ibis::bitvector::cnt(), ibis::fileManager::instance(), ibis::fileManager::recordPages(), ibis::bitvector::set(), ibis::bitvector::setBit(), ibis::bitvector::size(), and ibis::fileManager::buffer< T >::size().

int ibis::text::writeStrings	(	const char *	to,
		const char *	from,
		const char *	spto,
		const char *	spfrom,
		ibis::bitvector &	msk,
		const ibis::bitvector &	sel,
		char *	buf,
		uint32_t	nbuf
	)		const

protected

Write the selected strings.

The caller manages the necessary locks for accessing this function.

References ibis::fileManager::buffer< T >::address(), ibis::bitvector::adjustSize(), ibis::bitvector::cnt(), ibis::bitvector::indexSet::nIndices(), ibis::fileManager::buffer< T >::size(), ibis::bitvector::subset(), and UnixOpen.

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

category.h
category-hc.cpp
category.cpp



	Contact us Disclaimers FastBit source code FastBit mailing list archive

Classes

Public Member Functions

Protected Member Functions

Additional Inherited Members

Detailed Description

Member Function Documentation