Abstract base class for weighting schemes. More...

#include <weight.h>

Inheritance diagram for Xapian::Weight:

Classes
class	Internal
	Class to hold statistics for a given collection. More...

Public Member Functions
	Weight ()
	Default constructor, needed by subclass constructors. More...

virtual	~Weight ()
	Virtual destructor, because we have virtual methods. More...

virtual Weight *	clone () const =0
	Clone this object. More...

virtual std::string	name () const
	Return the name of this weighting scheme, e.g. More...

virtual std::string	serialise () const
	Return this object's parameters serialised as a single string. More...

virtual Weight *	unserialise (const std::string &serialised) const
	Unserialise parameters. More...

virtual double	get_sumpart (Xapian::termcount wdf, Xapian::termcount doclen, Xapian::termcount uniqterms, Xapian::termcount wdfdocmax) const =0
	Calculate the weight contribution for this object's term to a document. More...

virtual double	get_maxpart () const =0
	Return an upper bound on what get_sumpart() can return for any document. More...

virtual double	get_sumextra (Xapian::termcount doclen, Xapian::termcount uniqterms, Xapian::termcount wdfdocmax) const
	Calculate the term-independent weight component for a document. More...

virtual double	get_maxextra () const
	Return an upper bound on what get_sumextra() can return for any document. More...

virtual Weight *	create_from_parameters (const char *params) const
	Create from a human-readable parameter string. More...

Static Public Member Functions
static const Weight *	create (const std::string &scheme, const Registry &reg=Registry())
	Return the appropriate weighting scheme object. More...

Protected Types
enum	stat_flags { COLLECTION_SIZE = 0 , RSET_SIZE = 0 , AVERAGE_LENGTH = 4 , TERMFREQ = 1 , RELTERMFREQ = 1 , QUERY_LENGTH = 0 , WQF = 0 , WDF = 2 , DOC_LENGTH = 8 , DOC_LENGTH_MIN = 16 , DOC_LENGTH_MAX = 32 , WDF_MAX = 64 , COLLECTION_FREQ = 1 , UNIQUE_TERMS = 128 , TOTAL_LENGTH = 256 , WDF_DOC_MAX = 512 , UNIQUE_TERMS_MIN = 1024 , UNIQUE_TERMS_MAX = 2048 , DB_DOC_LENGTH_MIN = 4096 , DB_DOC_LENGTH_MAX = 8192 , DB_UNIQUE_TERMS_MIN = 16384 , DB_UNIQUE_TERMS_MAX = 32768 , DB_WDF_MAX = 65536 , IS_BOOLWEIGHT_ = static_cast<int>(0x80000000) }
	Stats which the weighting scheme can use (see need_stat()). More...

Protected Member Functions
void	need_stat (stat_flags flag)
	Tell Xapian that your subclass will want a particular statistic. More...

virtual void	init (double factor)=0
	Allow the subclass to perform any initialisation it needs to. More...

	Weight (const Weight &)
	Don't allow copying. More...

Xapian::doccount	get_collection_size () const
	The number of documents in the collection. More...

Xapian::doccount	get_rset_size () const
	The number of documents marked as relevant. More...

Xapian::doclength	get_average_length () const
	The average length of a document in the collection. More...

Xapian::doccount	get_termfreq () const
	The number of documents which this term indexes. More...

Xapian::doccount	get_reltermfreq () const
	The number of relevant documents which this term indexes. More...

Xapian::termcount	get_collection_freq () const
	The collection frequency of the term. More...

Xapian::termcount	get_query_length () const
	The length of the query. More...

Xapian::termcount	get_wqf () const
	The within-query-frequency of this term. More...

Xapian::termcount	get_doclength_upper_bound () const
	An upper bound on the maximum length of any document in the shard. More...

Xapian::termcount	get_doclength_lower_bound () const
	A lower bound on the minimum length of any document in the shard. More...

Xapian::termcount	get_wdf_upper_bound () const
	An upper bound on the wdf of this term in the shard. More...

Xapian::totallength	get_total_length () const
	Total length of all documents in the collection. More...

Xapian::termcount	get_unique_terms_upper_bound () const
	A lower bound on the number of unique terms in any document in the shard. More...

Xapian::termcount	get_unique_terms_lower_bound () const
	An upper bound on the number of unique terms in any document in the shard. More...

Xapian::termcount	get_db_doclength_upper_bound () const
	An upper bound on the maximum length of any document in the database. More...

Xapian::termcount	get_db_doclength_lower_bound () const
	A lower bound on the minimum length of any document in the database. More...

Xapian::termcount	get_db_unique_terms_upper_bound () const
	A lower bound on the number of unique terms in any document in the database. More...

Xapian::termcount	get_db_unique_terms_lower_bound () const
	An upper bound on the number of unique terms in any document in the database. More...

Xapian::termcount	get_db_wdf_upper_bound () const
	An upper bound on the wdf of this term in the database. More...

Private Member Functions
void	operator= (const Weight &)
	Don't allow assignment. More...

void	init_ (const Internal &stats, Xapian::termcount query_len_, const std::string &term, Xapian::termcount wqf_, double factor, const Xapian::Database::Internal shard, void postlist)

void	init_ (const Internal &stats, Xapian::termcount query_len_, double factor, Xapian::doccount termfreq, Xapian::doccount reltermfreq, Xapian::termcount collection_freq, const Xapian::Database::Internal *shard)

void	init_ (const Internal &stats, Xapian::termcount query_len_, const Xapian::Database::Internal *shard)

bool	get_sumpart_needs_doclength_ () const

bool	get_sumpart_needs_wdf_ () const

bool	get_sumpart_needs_uniqueterms_ () const

bool	is_bool_weight_ () const

bool	get_sumpart_needs_wdfdocmax_ () const

Private Attributes
stat_flags	stats_needed
	A bitmask of the statistics this weighting scheme needs. More...

Xapian::doccount	collection_size_
	The number of documents in the collection. More...

Xapian::doccount	rset_size_
	The number of documents marked as relevant. More...

Xapian::doclength	average_length_
	The average length of a document in the collection. More...

Xapian::doccount	termfreq_
	The number of documents which this term indexes. More...

Xapian::termcount	collectionfreq_

Xapian::doccount	reltermfreq_
	The number of relevant documents which this term indexes. More...

Xapian::termcount	query_length_
	The length of the query. More...

Xapian::termcount	wqf_
	The within-query-frequency of this term. More...

Xapian::termcount	doclength_lower_bound_
	A lower bound on the minimum length of any document in the shard. More...

Xapian::termcount	doclength_upper_bound_
	An upper bound on the maximum length of any document in the shard. More...

Xapian::termcount	wdf_upper_bound_
	An upper bound on the wdf of this term in the shard. More...

Xapian::totallength	total_length_
	Total length of all documents in the collection. More...

Xapian::termcount	unique_terms_lower_bound_
	A lower bound on the number of unique terms in any document in the shard. More...

Xapian::termcount	unique_terms_upper_bound_
	An upper bound on the number of unique terms in any document in the shard. More...

Xapian::termcount	db_doclength_lower_bound_
	A lower bound on the minimum length of any document in the database. More...

Xapian::termcount	db_doclength_upper_bound_
	An upper bound on the maximum length of any document in the database. More...

Xapian::termcount	db_wdf_upper_bound_
	An upper bound on the wdf of this term in the database. More...

Xapian::termcount	db_unique_terms_lower_bound_
	A lower bound on the number of unique terms in any document in the database. More...

Xapian::termcount	db_unique_terms_upper_bound_
	An upper bound on the number of unique terms in any document in the database. More...

Detailed Description

Abstract base class for weighting schemes.

Definition at line 38 of file weight.h.

Member Enumeration Documentation

◆ stat_flags

enum Xapian::Weight::stat_flags

protected

Stats which the weighting scheme can use (see need_stat()).

Enumerator
COLLECTION_SIZE	Number of documents in the collection.
RSET_SIZE	Number of documents in the RSet.
AVERAGE_LENGTH	Average length of documents in the collection.
TERMFREQ	How many documents the current term is in.
RELTERMFREQ	How many documents in the RSet the current term is in.
QUERY_LENGTH	Sum of wqf for terms in the query.
WQF	Within-query-frequency of the current term.
WDF	Within-document-frequency of the current term in the current document.
DOC_LENGTH	Length of the current document (sum wdf).
DOC_LENGTH_MIN	Lower bound on (non-zero) document lengths. This bound is for the current shard and is suitable for using to calculate upper bounds to return from get_maxpart() and get_maxextra().
DOC_LENGTH_MAX	Upper bound on document lengths. This bound is for the current shard and is suitable for using to calculate upper bounds to return from get_maxpart() and get_maxextra(). If you need a bound for calculating a returned weight from get_sumpart() or get_sumextra() then you should use DB_DOC_LENGTH_MIN instead.
WDF_MAX	Upper bound on wdf. This bound is for the current shard and is suitable for using to calculate upper bounds to return from get_maxpart() and get_maxextra(). If you need a bound for calculating a returned weight from get_sumpart() or get_sumextra() then you should use DB_DOC_LENGTH_MAX instead.
COLLECTION_FREQ	Sum of wdf over the whole collection for the current term.
UNIQUE_TERMS	Number of unique terms in the current document.
TOTAL_LENGTH	Sum of lengths of all documents in the collection. This gives the total number of term occurrences.
WDF_DOC_MAX	Maximum wdf in the current document. @since 2.0.0
UNIQUE_TERMS_MIN	Lower bound on number of unique terms in a document. This bound is for the current shard and is suitable for using to calculate upper bounds to return from get_maxpart() and get_maxextra(). If you need a bound for calculating a returned weight from get_sumpart() or get_sumextra() then you should use DB_UNIQUE_TERMS_MIN instead. Since 2.0.0
UNIQUE_TERMS_MAX	Upper bound on number of unique terms in a document. This bound is for the current shard and is suitable for using to calculate upper bounds to return from get_maxpart() and get_maxextra(). If you need a bound for calculating a returned weight from get_sumpart() or get_sumextra() then you should use DB_UNIQUE_TERMS_MAX instead. Since 2.0.0
DB_DOC_LENGTH_MIN	Lower bound on (non-zero) document lengths. This is a suitable bound for calculating a returned weight from get_sumpart() or get_sumextra(). Since 2.0.0
DB_DOC_LENGTH_MAX	Upper bound on document lengths. This is a suitable bound for calculating a returned weight from get_sumpart() or get_sumextra(). Since 2.0.0
DB_UNIQUE_TERMS_MIN	Lower bound on number of unique terms in a document. This is a suitable bound for calculating a returned weight from get_sumpart() or get_sumextra(); Since 2.0.0
DB_UNIQUE_TERMS_MAX	Upper bound on number of unique terms in a document. This is a suitable bound for calculating a returned weight from get_sumpart() or get_sumextra(); Since 2.0.0
DB_WDF_MAX	Upper bound on wdf of this term. This is a suitable bound for calculating a returned weight from get_sumpart(). Since 2.0.0
IS_BOOLWEIGHT_	Flag only set for BoolWeight. This allows us to efficiently indentify BoolWeight objects.

Definition at line 41 of file weight.h.

Constructor & Destructor Documentation

◆ Weight() [1/2]

Xapian::Weight::Weight ( )

inline

Default constructor, needed by subclass constructors.

Definition at line 273 of file weight.h.

◆ ~Weight()

Xapian::Weight::~Weight ( )

virtual

Virtual destructor, because we have virtual methods.

Definition at line 183 of file weight.cc.

◆ Weight() [2/2]

Xapian::Weight::Weight ( const Weight & )

protected

Don't allow copying.

This would ideally be private, but that causes a compilation error with GCC 4.1 (which appears to be a bug).

Member Function Documentation

◆ clone()

virtual Weight* Xapian::Weight::clone ( ) const

pure virtual

Clone this object.

This method allocates and returns a copy of the object it is called on.

If your subclass is called FooWeight and has parameters a and b, then you would implement FooWeight::clone() like so:

FooWeight * FooWeight::clone() const { return new FooWeight(a, b); }

Note that the returned object will be deallocated by Xapian after use with "delete". If you want to handle the deletion in a special way (for example when wrapping the Xapian API for use from another language) then you can define a static operator delete method in your subclass as shown here: https://trac.xapian.org/ticket/554#comment:1

Implemented in CheckStatsWeight5, CheckStatsWeight, CheckInitWeight, ExceptionalWeight, ZWeight, MyWeight, LazyWeight, Xapian::DiceWeight, Xapian::CoordWeight, Xapian::LM2StageWeight, Xapian::LMAbsDiscountWeight, Xapian::LMDirichletWeight, Xapian::LMJMWeight, Xapian::DPHWeight, Xapian::PL2PlusWeight, Xapian::PL2Weight, Xapian::DLHWeight, Xapian::BB2Weight, Xapian::IneB2Weight, Xapian::IfB2Weight, Xapian::InL2Weight, Xapian::BM25PlusWeight, Xapian::BM25Weight, Xapian::TfIdfWeight, and Xapian::BoolWeight.

Referenced by LocalSubMatch::open_post_list(), and Xapian::Enquire::set_weighting_scheme().

◆ create()

const Weight * Xapian::Weight::create	(	const std::string &	scheme,
		const Registry &	reg = `Registry()`
	)

static

Return the appropriate weighting scheme object.

Parameters

scheme	the string containing a weighting scheme name and may also contain the parameters required by that weighting scheme. E.g. "bm25 1.0 0.8"
reg	Xapian::Registry object to allow users to add their own custom weighting schemes (default: standard registry).

Since: 2.0.0

Definition at line 225 of file weight.cc.

References Xapian::Weight::Internal::double_param(), Xapian::Registry::get_weighting_scheme(), p, and parameter_error().

Referenced by DEFINE_TESTCASE(), and main().

◆ create_from_parameters()

Weight * Xapian::Weight::create_from_parameters ( const char * params ) const

virtual

Create from a human-readable parameter string.

Parameters

params string containing weighting scheme parameter values.

Since: 2.0.0

Reimplemented in Xapian::DiceWeight, Xapian::CoordWeight, Xapian::LM2StageWeight, Xapian::LMAbsDiscountWeight, Xapian::LMDirichletWeight, Xapian::LMJMWeight, Xapian::DPHWeight, Xapian::PL2PlusWeight, Xapian::PL2Weight, Xapian::DLHWeight, Xapian::BB2Weight, Xapian::IneB2Weight, Xapian::IfB2Weight, Xapian::InL2Weight, Xapian::BM25PlusWeight, Xapian::BM25Weight, Xapian::TfIdfWeight, and Xapian::BoolWeight.

Definition at line 259 of file weight.cc.

◆ get_average_length()

Xapian::doclength Xapian::Weight::get_average_length ( ) const

inlineprotected

The average length of a document in the collection.

Definition at line 555 of file weight.h.

Referenced by Xapian::TfIdfWeight::get_wdfn(), Xapian::InL2Weight::init(), Xapian::IfB2Weight::init(), Xapian::IneB2Weight::init(), Xapian::BB2Weight::init(), Xapian::PL2Weight::init(), and Xapian::PL2PlusWeight::init().

◆ get_collection_freq()

Xapian::termcount Xapian::Weight::get_collection_freq ( ) const

inlineprotected

The collection frequency of the term.

Definition at line 564 of file weight.h.

Referenced by Xapian::TfIdfWeight::get_idfn(), Xapian::BB2Weight::get_sumpart(), Xapian::IfB2Weight::init(), Xapian::IneB2Weight::init(), Xapian::BB2Weight::init(), Xapian::PL2Weight::init(), and Xapian::PL2PlusWeight::init().

◆ get_collection_size()

Xapian::doccount Xapian::Weight::get_collection_size ( ) const

inlineprotected

The number of documents in the collection.

Definition at line 549 of file weight.h.

Referenced by Xapian::TfIdfWeight::get_idfn(), Xapian::BB2Weight::get_sumpart(), Xapian::InL2Weight::init(), Xapian::IfB2Weight::init(), Xapian::IneB2Weight::init(), Xapian::BB2Weight::init(), Xapian::PL2Weight::init(), and Xapian::PL2PlusWeight::init().

◆ get_db_doclength_lower_bound()

Xapian::termcount Xapian::Weight::get_db_doclength_lower_bound ( ) const

inlineprotected

A lower bound on the minimum length of any document in the database.

This bound does not include any zero-length documents.

Since: 2.0.0

Definition at line 641 of file weight.h.

◆ get_db_doclength_upper_bound()

Xapian::termcount Xapian::Weight::get_db_doclength_upper_bound ( ) const

inlineprotected

An upper bound on the maximum length of any document in the database.

Since: 2.0.0

Definition at line 631 of file weight.h.

◆ get_db_unique_terms_lower_bound()

Xapian::termcount Xapian::Weight::get_db_unique_terms_lower_bound ( ) const

inlineprotected

An upper bound on the number of unique terms in any document in the database.

Since: 2.0.0

Definition at line 661 of file weight.h.

◆ get_db_unique_terms_upper_bound()

Xapian::termcount Xapian::Weight::get_db_unique_terms_upper_bound ( ) const

inlineprotected

A lower bound on the number of unique terms in any document in the database.

This bound does not include any zero-length documents.

Since: 2.0.0

Definition at line 652 of file weight.h.

◆ get_db_wdf_upper_bound()

Xapian::termcount Xapian::Weight::get_db_wdf_upper_bound ( ) const

inlineprotected

An upper bound on the wdf of this term in the database.

Since: 2.0.0

Definition at line 669 of file weight.h.

◆ get_doclength_lower_bound()

Xapian::termcount Xapian::Weight::get_doclength_lower_bound ( ) const

inlineprotected

A lower bound on the minimum length of any document in the shard.

This bound does not include any zero-length documents.

This should only be used by get_maxpart() and get_maxextra().

Definition at line 586 of file weight.h.

Referenced by Xapian::TfIdfWeight::get_maxpart(), Xapian::InL2Weight::init(), Xapian::IfB2Weight::init(), Xapian::IneB2Weight::init(), Xapian::BB2Weight::init(), Xapian::PL2Weight::init(), and Xapian::PL2PlusWeight::init().

◆ get_doclength_upper_bound()

Xapian::termcount Xapian::Weight::get_doclength_upper_bound ( ) const

inlineprotected

An upper bound on the maximum length of any document in the shard.

This should only be used by get_maxpart() and get_maxextra().

Definition at line 576 of file weight.h.

Referenced by Xapian::BB2Weight::init(), Xapian::PL2Weight::init(), and Xapian::PL2PlusWeight::init().

◆ get_maxextra()

double Xapian::Weight::get_maxextra ( ) const

virtual

Return an upper bound on what get_sumextra() can return for any document.

The default implementation always returns 0 (in Xapian < 2.0.0 this was a pure virtual method).

This information is used by the matcher to perform various optimisations, so strive to make the bound as tight as possible.

Reimplemented in CheckStatsWeight, CheckInitWeight, ZWeight, LazyWeight, Xapian::LM2StageWeight, Xapian::LMAbsDiscountWeight, Xapian::LMDirichletWeight, Xapian::BM25PlusWeight, and Xapian::BM25Weight.

Definition at line 212 of file weight.cc.

◆ get_maxpart()

virtual double Xapian::Weight::get_maxpart ( ) const

pure virtual

Return an upper bound on what get_sumpart() can return for any document.

This information is used by the matcher to perform various optimisations, so strive to make the bound as tight as possible.

Implemented in CheckStatsWeight5, CheckStatsWeight, CheckInitWeight, ExceptionalWeight, ZWeight, MyWeight, LazyWeight, Xapian::DiceWeight, Xapian::CoordWeight, Xapian::LM2StageWeight, Xapian::LMAbsDiscountWeight, Xapian::LMDirichletWeight, Xapian::LMJMWeight, Xapian::DPHWeight, Xapian::PL2PlusWeight, Xapian::PL2Weight, Xapian::DLHWeight, Xapian::BB2Weight, Xapian::IneB2Weight, Xapian::IfB2Weight, Xapian::InL2Weight, Xapian::BM25PlusWeight, Xapian::BM25Weight, Xapian::TfIdfWeight, and Xapian::BoolWeight.

Referenced by LocalSubMatch::open_post_list(), and LeafPostList::resolve_lazy_termweight().

◆ get_query_length()

Xapian::termcount Xapian::Weight::get_query_length ( ) const

inlineprotected

The length of the query.

Definition at line 567 of file weight.h.

◆ get_reltermfreq()

Xapian::doccount Xapian::Weight::get_reltermfreq ( ) const

inlineprotected

The number of relevant documents which this term indexes.

Definition at line 561 of file weight.h.

◆ get_rset_size()

Xapian::doccount Xapian::Weight::get_rset_size ( ) const

inlineprotected

The number of documents marked as relevant.

Definition at line 552 of file weight.h.

◆ get_sumextra()

double Xapian::Weight::get_sumextra	(	Xapian::termcount	doclen,
		Xapian::termcount	uniqterms,
		Xapian::termcount	wdfdocmax
	)		const

virtual

Calculate the term-independent weight component for a document.

The default implementation always returns 0 (in Xapian < 2.0.0 this was a pure virtual method).

The parameter gives information about the document which may be used in the calculations:

Parameters

doclen	The document's length (unnormalised). You need to call need_stat(DOC_LENGTH) if you use this value.
uniqterms	Number of unique terms in the document. You need to call need_stat(UNIQUE_TERMS) if you use this value.
wdfdocmax	Maximum wdf value in the document. You need to call need_stat(WDF_DOC_MAX) if you use this value.

Since: The wdfdocmax parameter was added in Xapian 2.0.0.

Reimplemented in CheckStatsWeight, CheckInitWeight, ZWeight, Xapian::LMAbsDiscountWeight, Xapian::LMDirichletWeight, LazyWeight, Xapian::BM25PlusWeight, Xapian::BM25Weight, and Xapian::LM2StageWeight.

Definition at line 204 of file weight.cc.

◆ get_sumpart()

virtual double Xapian::Weight::get_sumpart	(	Xapian::termcount	wdf,
		Xapian::termcount	doclen,
		Xapian::termcount	uniqterms,
		Xapian::termcount	wdfdocmax
	)		const

pure virtual

Calculate the weight contribution for this object's term to a document.

The parameters give information about the document which may be used in the calculations:

Parameters

wdf	The within document frequency of the term in the document. You need to call need_stat(WDF) if you use this value.
doclen	The document's length (unnormalised). You need to call need_stat(DOC_LENGTH) if you use this value.
uniqterms	Number of unique terms in the document. You need to call need_stat(UNIQUE_TERMS) if you use this value.
wdfdocmax	Maximum wdf value in the document. You need to call need_stat(WDF_DOC_MAX) if you use this value.

You can rely of wdf <= doclen if you call both need_stat(WDF) and need_stat(DOC_LENGTH) - this is trivially true for terms, but Xapian also ensure it's true for OP_SYNONYM, where the wdf is approximated.

Since: The wdfdocmax parameter was added in Xapian 2.0.0.

Implemented in CheckInitWeight, ExceptionalWeight, ZWeight, MyWeight, CheckStatsWeight5, Xapian::LMAbsDiscountWeight, CheckStatsWeight, LazyWeight, Xapian::CoordWeight, Xapian::DPHWeight, Xapian::PL2PlusWeight, Xapian::PL2Weight, Xapian::DLHWeight, Xapian::BB2Weight, Xapian::IneB2Weight, Xapian::InL2Weight, Xapian::BM25PlusWeight, Xapian::BoolWeight, Xapian::DiceWeight, Xapian::LM2StageWeight, Xapian::LMDirichletWeight, Xapian::LMJMWeight, Xapian::IfB2Weight, Xapian::BM25Weight, and Xapian::TfIdfWeight.

◆ get_sumpart_needs_doclength_()

bool Xapian::Weight::get_sumpart_needs_doclength_ ( ) const

inlineprivate

Return true if the document length is needed.

If this method returns true, then the document length will be fetched and passed to get_sumpart(). Otherwise 0 may be passed for the document length.

Definition at line 475 of file weight.h.

◆ get_sumpart_needs_uniqueterms_()

bool Xapian::Weight::get_sumpart_needs_uniqueterms_ ( ) const

inlineprivate

Return true if the number of unique terms is needed.

If this method returns true, then the number of unique terms will be fetched and passed to get_sumpart(). Otherwise 0 may be passed for the number of unique terms.

Definition at line 494 of file weight.h.

◆ get_sumpart_needs_wdf_()

bool Xapian::Weight::get_sumpart_needs_wdf_ ( ) const

inlineprivate

Return true if the WDF is needed.

If this method returns true, then the WDF will be fetched and passed to get_sumpart(). Otherwise 0 may be passed for the wdf.

Definition at line 484 of file weight.h.

Referenced by SynonymPostList::set_weight(), and LocalSubMatch::weight_needs_wdf().

◆ get_sumpart_needs_wdfdocmax_()

bool Xapian::Weight::get_sumpart_needs_wdfdocmax_ ( ) const

inlineprivate

Return true if the max WDF of document is needed.

If this method returns true, then the max WDF will be fetched and passed to get_sumpart(). Otherwise 0 may be passed for the max wdf.

Since: Added in Xapian 2.0.0.

Definition at line 535 of file weight.h.

◆ get_termfreq()

Xapian::doccount Xapian::Weight::get_termfreq ( ) const

inlineprotected

The number of documents which this term indexes.

Definition at line 558 of file weight.h.

Referenced by Xapian::TfIdfWeight::get_idfn(), Xapian::InL2Weight::init(), Xapian::IfB2Weight::init(), Xapian::IneB2Weight::init(), and Xapian::BB2Weight::init().

◆ get_total_length()

Xapian::totallength Xapian::Weight::get_total_length ( ) const

inlineprotected

Total length of all documents in the collection.

Definition at line 599 of file weight.h.

◆ get_unique_terms_lower_bound()

Xapian::termcount Xapian::Weight::get_unique_terms_lower_bound ( ) const

inlineprotected

An upper bound on the number of unique terms in any document in the shard.

This should only be used by get_maxpart() and get_maxextra().

Since: 2.0.0

Definition at line 623 of file weight.h.

◆ get_unique_terms_upper_bound()

Xapian::termcount Xapian::Weight::get_unique_terms_upper_bound ( ) const

inlineprotected

A lower bound on the number of unique terms in any document in the shard.

This bound does not include any zero-length documents.

This should only be used by get_maxpart() and get_maxextra().

Since: 2.0.0

Definition at line 612 of file weight.h.

◆ get_wdf_upper_bound()

Xapian::termcount Xapian::Weight::get_wdf_upper_bound ( ) const

inlineprotected

An upper bound on the wdf of this term in the shard.

This should only be used by get_maxpart() and get_maxextra().

Definition at line 594 of file weight.h.

Referenced by Xapian::TfIdfWeight::get_maxpart(), Xapian::InL2Weight::init(), Xapian::IfB2Weight::init(), Xapian::IneB2Weight::init(), Xapian::BB2Weight::init(), Xapian::PL2Weight::init(), and Xapian::PL2PlusWeight::init().

◆ get_wqf()

Xapian::termcount Xapian::Weight::get_wqf ( ) const

inlineprotected

The within-query-frequency of this term.

Definition at line 570 of file weight.h.

Referenced by Xapian::TfIdfWeight::init(), Xapian::InL2Weight::init(), Xapian::IfB2Weight::init(), Xapian::IneB2Weight::init(), Xapian::BB2Weight::init(), Xapian::PL2Weight::init(), and Xapian::PL2PlusWeight::init().

◆ init()

virtual void Xapian::Weight::init ( double factor )

protectedpure virtual

Allow the subclass to perform any initialisation it needs to.

Parameters

factor Any scaling factor (e.g. from OP_SCALE_WEIGHT). If the Weight object is for the term-independent weight supplied by get_sumextra()/get_maxextra(), then init(0.0) is called (starting from Xapian 1.2.11 and 1.3.1 - earlier versions failed to call init() for such Weight objects).

Implemented in ExceptionalWeight, ZWeight, CheckStatsWeight5, CheckStatsWeight, CheckInitWeight, LazyWeight, Xapian::CoordWeight, Xapian::LM2StageWeight, Xapian::LMAbsDiscountWeight, Xapian::LMDirichletWeight, Xapian::LMJMWeight, Xapian::PL2PlusWeight, Xapian::PL2Weight, MyWeight, Xapian::DiceWeight, Xapian::DPHWeight, Xapian::DLHWeight, Xapian::BB2Weight, Xapian::IneB2Weight, Xapian::IfB2Weight, Xapian::InL2Weight, Xapian::BM25PlusWeight, Xapian::BM25Weight, Xapian::TfIdfWeight, and Xapian::BoolWeight.

◆ init_() [1/3]

void Xapian::Weight::init_	(	const Internal &	stats,
		Xapian::termcount	query_len_,
		const std::string &	term,
		Xapian::termcount	wqf_,
		double	factor,
		const Xapian::Database::Internal *	shard,
		void *	postlist
	)

private

Initialise this object to calculate weights for term term.

Parameters

stats	Source of statistics.
query_len_	Query length.
term	The term for the new object.
wqf_	The within-query-frequency of term.
factor	Any scaling factor (e.g. from OP_SCALE_WEIGHT).
postlist	Pointer to a LeafPostList for the term (cast to void* to avoid needing to forward declare class LeafPostList in public API headers) which can be used to get wdf upper bound

Definition at line 76 of file weight.cc.

Referenced by LocalSubMatch::open_post_list(), and LeafPostList::resolve_lazy_termweight().

◆ init_() [2/3]

void Xapian::Weight::init_	(	const Internal &	stats,
		Xapian::termcount	query_len_,
		const Xapian::Database::Internal *	shard
	)

private

Initialise this object to calculate the extra weight component.

Parameters

stats	Source of statistics.
query_len_	Query length.

Definition at line 40 of file weight.cc.

References Xapian::Weight::Internal::collection_size, Xapian::Weight::Internal::db_doclength_lower_bound, Xapian::Weight::Internal::db_doclength_upper_bound, Xapian::Weight::Internal::db_unique_terms_lower_bound, Xapian::Weight::Internal::db_unique_terms_upper_bound, Xapian::Weight::Internal::get_average_length(), Xapian::Database::Internal::get_doclength_lower_bound(), Xapian::Database::Internal::get_doclength_upper_bound(), Xapian::Database::Internal::get_unique_terms_lower_bound(), Xapian::Database::Internal::get_unique_terms_upper_bound(), LOGCALL_VOID, Xapian::Weight::Internal::rset_size, and Xapian::Weight::Internal::total_length.

◆ init_() [3/3]

void Xapian::Weight::init_	(	const Internal &	stats,
		Xapian::termcount	query_len_,
		double	factor,
		Xapian::doccount	termfreq,
		Xapian::doccount	reltermfreq,
		Xapian::termcount	collection_freq,
		const Xapian::Database::Internal *	shard
	)

private

Initialise this object to calculate weights for a synonym.

Parameters

stats	Source of statistics.
query_len_	Query length.
factor	Any scaling factor (e.g. from OP_SCALE_WEIGHT).
termfreq	The termfreq to use.
reltermfreq	The reltermfreq to use.
collection_freq	The collection frequency to use.

Definition at line 127 of file weight.cc.

References Xapian::Weight::Internal::collection_size, Xapian::Weight::Internal::db_doclength_lower_bound, Xapian::Weight::Internal::db_doclength_upper_bound, Xapian::Weight::Internal::db_unique_terms_lower_bound, Xapian::Weight::Internal::db_unique_terms_upper_bound, Xapian::Weight::Internal::get_average_length(), Xapian::Database::Internal::get_doclength_lower_bound(), Xapian::Database::Internal::get_doclength_upper_bound(), Xapian::Database::Internal::get_unique_terms_lower_bound(), Xapian::Database::Internal::get_unique_terms_upper_bound(), LOGCALL_VOID, Xapian::Weight::Internal::rset_size, and Xapian::Weight::Internal::total_length.

◆ is_bool_weight_()

bool Xapian::Weight::is_bool_weight_ ( ) const

inlineprivate

Test if this is a BoolWeight object.

Definition at line 520 of file weight.h.

◆ name()

string Xapian::Weight::name ( ) const

virtual

Return the name of this weighting scheme, e.g.

"bm25+".

This is the name that the weighting scheme gets registered under when passed to Xapian:Registry::register_weighting_scheme().

As a result:

this is the name that needs to be used in Weight::create() to create a Weight object from a human-readable string description.
it is also used by the remote backend where it is sent (along with the serialised parameters) to the remote server so that it knows which class to create.

For 1.4.x and earlier we recommended returning the full namespace-qualified name of your class here, but now we recommend returning a just the name in lower case, e.g. "foo" instead of "FooWeight", "bm25+" instead of "Xapian::BM25PlusWeight".

If you don't want to support creation via Weight::create() or the remote backend, you can use the default implementation which simply returns an empty string.

Reimplemented in ExceptionalWeight, MyWeight, LazyWeight, Xapian::DiceWeight, Xapian::CoordWeight, Xapian::LM2StageWeight, Xapian::LMAbsDiscountWeight, Xapian::LMDirichletWeight, Xapian::LMJMWeight, Xapian::DPHWeight, Xapian::PL2PlusWeight, Xapian::PL2Weight, Xapian::DLHWeight, Xapian::BB2Weight, Xapian::IneB2Weight, Xapian::IfB2Weight, Xapian::InL2Weight, Xapian::BM25PlusWeight, Xapian::BM25Weight, Xapian::TfIdfWeight, and Xapian::BoolWeight.

Definition at line 186 of file weight.cc.

Referenced by Xapian::Registry::Internal::add_defaults(), Xapian::Registry::register_weighting_scheme(), and RemoteDatabase::set_query().

◆ need_stat()

void Xapian::Weight::need_stat ( stat_flags flag )

inlineprotected

Tell Xapian that your subclass will want a particular statistic.

Some of the statistics can be costly to fetch or calculate, so Xapian needs to know which are actually going to be used. You should call need_stat() from your constructor for each statistic needed by the weighting scheme you are implementing (possibly conditional on the values of parameters of the weighting scheme).

Some of the statistics are currently available by default and their constants above have value 0 (e.g. COLLECTION_SIZE). You should still call need_stat() for these (the compiler should optimise away these calls and any conditional checks for them).

Some statistics are currently fetched together and so their constants have the same numeric value - if you need more than one of these statistics you should call need_stat() for each one. The compiler should optimise this too.

Prior to 2.0.0, it was assumed that if get_maxextra() returned a non-zero value then get_sumextra() needed the document length even if need(DOC_LENGTH) wasn't called - the logic was that get_sumextra() could only return a constant value if it didn't use the document length. However, this is no longer valid since it can also use the number of unique terms in the document, so now you need to specify explicitly.

Parameters

flag	The stat_flags value for a required statistic.

Definition at line 183 of file weight.h.

Referenced by Xapian::BB2Weight::BB2Weight(), Xapian::IfB2Weight::IfB2Weight(), Xapian::IneB2Weight::IneB2Weight(), Xapian::InL2Weight::InL2Weight(), Xapian::PL2PlusWeight::PL2PlusWeight(), Xapian::PL2Weight::PL2Weight(), and Xapian::TfIdfWeight::TfIdfWeight().

◆ operator=()

void Xapian::Weight::operator= ( const Weight & )

private

Don't allow assignment.

◆ serialise()

string Xapian::Weight::serialise ( ) const

virtual

Return this object's parameters serialised as a single string.

If you don't want to support the remote backend, you can use the default implementation which simply throws Xapian::UnimplementedError.

Reimplemented in MyWeight, LazyWeight, Xapian::DiceWeight, Xapian::CoordWeight, Xapian::LM2StageWeight, Xapian::LMAbsDiscountWeight, Xapian::LMDirichletWeight, Xapian::LMJMWeight, Xapian::DPHWeight, Xapian::PL2PlusWeight, Xapian::PL2Weight, Xapian::DLHWeight, Xapian::BB2Weight, Xapian::IneB2Weight, Xapian::IfB2Weight, Xapian::InL2Weight, Xapian::BM25PlusWeight, Xapian::BM25Weight, Xapian::TfIdfWeight, and Xapian::BoolWeight.

Definition at line 192 of file weight.cc.

Referenced by RemoteDatabase::set_query().

◆ unserialise()

Weight * Xapian::Weight::unserialise ( const std::string & serialised ) const

virtual

Unserialise parameters.

This method unserialises parameters serialised by the serialise() method and allocates and returns a new object initialised with them.

If you don't want to support the remote backend, you can use the default implementation which simply throws Xapian::UnimplementedError.

Note that the returned object will be deallocated by Xapian after use with "delete". If you want to handle the deletion in a special way (for example when wrapping the Xapian API for use from another language) then you can define a static operator delete method in your subclass as shown here: https://trac.xapian.org/ticket/554#comment:1

Parameters

serialised A string containing the serialised parameters.

Reimplemented in MyWeight, LazyWeight, Xapian::DiceWeight, Xapian::CoordWeight, Xapian::LM2StageWeight, Xapian::LMAbsDiscountWeight, Xapian::LMDirichletWeight, Xapian::LMJMWeight, Xapian::DPHWeight, Xapian::PL2PlusWeight, Xapian::PL2Weight, Xapian::DLHWeight, Xapian::BB2Weight, Xapian::IneB2Weight, Xapian::IfB2Weight, Xapian::InL2Weight, Xapian::BM25PlusWeight, Xapian::BM25Weight, Xapian::TfIdfWeight, and Xapian::BoolWeight.

Definition at line 198 of file weight.cc.

Referenced by RemoteServer::msg_query().

Member Data Documentation

◆ average_length_

Xapian::doclength Xapian::Weight::average_length_

private

The average length of a document in the collection.

Definition at line 212 of file weight.h.

◆ collection_size_

Xapian::doccount Xapian::Weight::collection_size_

private

The number of documents in the collection.

Definition at line 206 of file weight.h.

◆ collectionfreq_

Xapian::termcount Xapian::Weight::collectionfreq_

private

Definition at line 218 of file weight.h.

◆ db_doclength_lower_bound_

Xapian::termcount Xapian::Weight::db_doclength_lower_bound_

private

A lower bound on the minimum length of any document in the database.

Definition at line 252 of file weight.h.

◆ db_doclength_upper_bound_

Xapian::termcount Xapian::Weight::db_doclength_upper_bound_

private

An upper bound on the maximum length of any document in the database.

Definition at line 255 of file weight.h.

◆ db_unique_terms_lower_bound_

Xapian::termcount Xapian::Weight::db_unique_terms_lower_bound_

private

A lower bound on the number of unique terms in any document in the database.

Definition at line 263 of file weight.h.

◆ db_unique_terms_upper_bound_

Xapian::termcount Xapian::Weight::db_unique_terms_upper_bound_

private

An upper bound on the number of unique terms in any document in the database.

Definition at line 268 of file weight.h.

◆ db_wdf_upper_bound_

Xapian::termcount Xapian::Weight::db_wdf_upper_bound_

private

An upper bound on the wdf of this term in the database.

Definition at line 258 of file weight.h.

◆ doclength_lower_bound_

Xapian::termcount Xapian::Weight::doclength_lower_bound_

private

A lower bound on the minimum length of any document in the shard.

Definition at line 230 of file weight.h.

◆ doclength_upper_bound_

Xapian::termcount Xapian::Weight::doclength_upper_bound_

private

An upper bound on the maximum length of any document in the shard.

Definition at line 233 of file weight.h.

◆ query_length_

Xapian::termcount Xapian::Weight::query_length_

private

The length of the query.

Definition at line 224 of file weight.h.

◆ reltermfreq_

Xapian::doccount Xapian::Weight::reltermfreq_

private

The number of relevant documents which this term indexes.

Definition at line 221 of file weight.h.

◆ rset_size_

Xapian::doccount Xapian::Weight::rset_size_

private

The number of documents marked as relevant.

Definition at line 209 of file weight.h.

◆ stats_needed

stat_flags Xapian::Weight::stats_needed

private

A bitmask of the statistics this weighting scheme needs.

Definition at line 203 of file weight.h.

◆ termfreq_

Xapian::doccount Xapian::Weight::termfreq_

private

The number of documents which this term indexes.

Definition at line 215 of file weight.h.

◆ total_length_

Xapian::totallength Xapian::Weight::total_length_

private

Total length of all documents in the collection.

Definition at line 239 of file weight.h.

◆ unique_terms_lower_bound_

Xapian::termcount Xapian::Weight::unique_terms_lower_bound_

private

A lower bound on the number of unique terms in any document in the shard.

Definition at line 244 of file weight.h.

◆ unique_terms_upper_bound_

Xapian::termcount Xapian::Weight::unique_terms_upper_bound_

private

An upper bound on the number of unique terms in any document in the shard.

Definition at line 249 of file weight.h.

◆ wdf_upper_bound_

Xapian::termcount Xapian::Weight::wdf_upper_bound_

private

An upper bound on the wdf of this term in the shard.

Definition at line 236 of file weight.h.

◆ wqf_

Xapian::termcount Xapian::Weight::wqf_

private

The within-query-frequency of this term.

Definition at line 227 of file weight.h.

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

include/xapian/weight.h
weight/weight.cc

Classes

Public Member Functions

Static Public Member Functions

Protected Types

Protected Member Functions

Private Member Functions

Private Attributes

Detailed Description

Member Enumeration Documentation

◆ stat_flags

Constructor & Destructor Documentation

◆ Weight() [1/2]

◆ ~Weight()

◆ Weight() [2/2]

Member Function Documentation

◆ clone()

◆ create()

◆ create_from_parameters()

◆ get_average_length()

◆ get_collection_freq()

◆ get_collection_size()

◆ get_db_doclength_lower_bound()

◆ get_db_doclength_upper_bound()

◆ get_db_unique_terms_lower_bound()

◆ get_db_unique_terms_upper_bound()

◆ get_db_wdf_upper_bound()

◆ get_doclength_lower_bound()

◆ get_doclength_upper_bound()

◆ get_maxextra()

◆ get_maxpart()

◆ get_query_length()

◆ get_reltermfreq()

◆ get_rset_size()

◆ get_sumextra()

◆ get_sumpart()

◆ get_sumpart_needs_doclength_()

◆ get_sumpart_needs_uniqueterms_()

◆ get_sumpart_needs_wdf_()

◆ get_sumpart_needs_wdfdocmax_()

◆ get_termfreq()

◆ get_total_length()

◆ get_unique_terms_lower_bound()

◆ get_unique_terms_upper_bound()

◆ get_wdf_upper_bound()

◆ get_wqf()

◆ init()

◆ init_() [1/3]

◆ init_() [2/3]

◆ init_() [3/3]

◆ is_bool_weight_()

◆ name()

◆ need_stat()

◆ operator=()

◆ serialise()

◆ unserialise()

Member Data Documentation

◆ average_length_

◆ collection_size_

◆ collectionfreq_

◆ db_doclength_lower_bound_

◆ db_doclength_upper_bound_

◆ db_unique_terms_lower_bound_

◆ db_unique_terms_upper_bound_

◆ db_wdf_upper_bound_

◆ doclength_lower_bound_

◆ doclength_upper_bound_

◆ query_length_

◆ reltermfreq_

◆ rset_size_

◆ stats_needed

◆ termfreq_

◆ total_length_

◆ unique_terms_lower_bound_

◆ unique_terms_upper_bound_

◆ wdf_upper_bound_

◆ wqf_