A postlist in a chert database. More...

#include <chert_postlist.h>

Inheritance diagram for ChertPostList:

Collaboration diagram for ChertPostList:

Public Member Functions
	ChertPostList (Xapian::Internal::intrusive_ptr< const ChertDatabase > this_db_, const string &term, bool keep_reference)
	Default constructor. More...

	~ChertPostList ()
	Destructor. More...

bool	jump_to (Xapian::docid desired_did)
	Used for looking up doclens. More...

Xapian::doccount	get_termfreq () const
	Returns number of docs indexed by this term. More...

Xapian::docid	get_docid () const
	Returns the current docid. More...

Xapian::termcount	get_doclength () const
	Returns the length of current document. More...

Xapian::termcount	get_unique_terms () const
	Return the number of unique terms in the current document. More...

Xapian::termcount	get_wdf () const
	Returns the Within Document Frequency of the term in the current document. More...

PositionList *	read_position_list ()
	Get the list of positions of the term in the current document. More...

PositionList *	open_position_list () const
	Get the list of positions of the term in the current document. More...

PostList *	next (double w_min)
	Move to the next document. More...

PostList *	skip_to (Xapian::docid desired_did, double w_min)
	Skip to next document with docid >= docid. More...

bool	at_end () const
	Return true if and only if we're off the end of the list. More...

Xapian::termcount	get_wdf_upper_bound () const

std::string	get_description () const
	Get a description of the document. More...

Public Member Functions inherited from LeafPostList
	~LeafPostList ()

void	set_termweight (const Xapian::Weight *weight_)
	Set the weighting scheme to use during matching. More...

double	resolve_lazy_termweight (Xapian::Weight weight_, Xapian::Weight::Internal stats, Xapian::termcount qlen, Xapian::termcount wqf, double factor)

Xapian::doccount	get_termfreq_min () const
	Get a lower bound on the number of documents indexed by this term. More...

Xapian::doccount	get_termfreq_max () const
	Get an upper bound on the number of documents indexed by this term. More...

Xapian::doccount	get_termfreq_est () const
	Get an estimate of the number of documents indexed by this term. More...

double	get_maxweight () const
	Return an upper bound on what get_weight() can return. More...

double	get_weight () const
	Return the weight contribution for the current position. More...

double	recalc_maxweight ()
	Recalculate the upper bound on what get_weight() can return. More...

TermFreqs	get_termfreq_est_using_stats (const Xapian::Weight::Internal &stats) const
	Get an estimate for the termfreq and reltermfreq, given the stats. More...

Xapian::termcount	count_matching_subqs () const
	Count the number of leaf subqueries which match at the current position. More...

void	gather_position_lists (OrPositionList *orposlist)
	Gather PositionList* objects for a subtree. More...

virtual LeafPostList *	open_nearby_postlist (const std::string &term_) const
	Open another postlist from the same database. More...

void	set_term (const std::string &term_)
	Set the term name. More...

Public Member Functions inherited from Xapian::PostingIterator::Internal
virtual	~Internal ()
	We have virtual methods and want to be able to delete derived classes using a pointer to the base class, so we need a virtual destructor. More...

virtual const std::string *	get_sort_key () const

virtual const std::string *	get_collapse_key () const
	If the collapse key is already known, return it. More...

virtual Internal *	check (Xapian::docid did, double w_min, bool &valid)
	Check if the specified docid occurs in this postlist. More...

Internal *	next ()
	Advance the current position to the next document in the postlist. More...

Internal *	skip_to (Xapian::docid did)
	Skip forward to the specified docid. More...

Public Member Functions inherited from Xapian::Internal::intrusive_base
	intrusive_base ()
	Construct with no references. More...

Static Public Member Functions
static void	read_number_of_entries (const char *posptr, const char end, Xapian::doccount number_of_entries_ptr, Xapian::termcount collection_freq_ptr)
	Read the number of entries and the collection frequency. More...

Protected Attributes
Xapian::Internal::intrusive_ptr< const ChertDatabase >	this_db
	The database we are searching. More...

ChertPositionList	positionlist
	The position list object for this posting list. More...

bool	have_started
	Whether we've started reading the list yet. More...

Xapian::termcount	wdf_upper_bound
	Upper bound on wdf for this postlist. More...

Protected Attributes inherited from LeafPostList
const Xapian::Weight *	weight

bool	need_doclength

bool	need_unique_terms

std::string	term
	The term name for this postlist (empty for an alldocs postlist). More...

Private Member Functions
	ChertPostList (const ChertPostList &)
	Copying is not allowed. More...

void	operator= (const ChertPostList &)
	Assignment is not allowed. More...

bool	next_in_chunk ()
	Move to the next item in the chunk, if possible. More...

void	next_chunk ()
	Move to the next chunk. More...

bool	current_chunk_contains (Xapian::docid desired_did)
	Return true if the given document ID lies in the range covered by the current chunk. More...

void	move_to_chunk_containing (Xapian::docid desired_did)
	Move to chunk containing the specified document ID. More...

bool	move_forward_in_chunk_to_at_least (Xapian::docid desired_did)
	Scan forward in the current chunk for the specified document ID. More...

Private Attributes
bool	is_last_chunk
	True if this is the last chunk. More...

bool	is_at_end
	Whether we've run off the end of the list yet. More...

AutoPtr< ChertCursor >	cursor
	Cursor pointing to current chunk of postlist. More...

Xapian::docid	first_did_in_chunk
	The first document id in this chunk. More...

Xapian::docid	last_did_in_chunk
	The last document id in this chunk. More...

const char *	pos
	Position of iteration through current chunk. More...

const char *	end
	Pointer to byte after end of current chunk. More...

Xapian::docid	did
	Document id we're currently at. More...

Xapian::termcount	wdf
	The wdf of the current document. More...

Xapian::doccount	number_of_entries
	The number of entries in the posting list. More...

Additional Inherited Members
Public Attributes inherited from Xapian::Internal::intrusive_base
unsigned	_refs
	Reference count. More...

Protected Member Functions inherited from LeafPostList
	LeafPostList (const std::string &term_)
	Only constructable as a base class for derived classes. More...

Protected Member Functions inherited from Xapian::PostingIterator::Internal
	Internal ()
	Only constructable as a base class for derived classes. More...

Detailed Description

A postlist in a chert database.

Definition at line 132 of file chert_postlist.h.

Constructor & Destructor Documentation

◆ ChertPostList() [1/2]

ChertPostList::ChertPostList ( const ChertPostList & )

private

Copying is not allowed.

◆ ChertPostList() [2/2]

ChertPostList::ChertPostList	(	Xapian::Internal::intrusive_ptr< const ChertDatabase >	this_db_,
		const string &	term_,
		bool	keep_reference
	)

Default constructor.

The format of a postlist is:

Split into chunks. Key for first chunk is the termname (encoded as length : name). Key for subsequent chunks is the same, followed by the document ID of the first document in the chunk (encoded as length of representation in first byte, and then docid).

A chunk (except for the first chunk) contains:

1) bool - true if this is the last chunk. 2) difference between final docid in chunk and first docid. 3) wdf for the first item. 4) increment in docid to next item, followed by wdf for the item. 5) (4) repeatedly.

The first chunk begins with the number of entries, the collection frequency, then the docid of the first document, then has the header of a standard chunk.

Definition at line 669 of file chert_postlist.cc.

References cursor, did, end, first_did_in_chunk, Xapian::Internal::intrusive_ptr< T >::get(), is_at_end, is_last_chunk, last_did_in_chunk, LOGCALL_CTOR, LOGLINE, ChertPostListTable::make_key(), number_of_entries, pos, read_start_of_chunk(), read_start_of_first_chunk(), read_wdf(), LeafPostList::term, wdf, and wdf_upper_bound.

◆ ~ChertPostList()

ChertPostList::~ChertPostList ( )

Destructor.

Definition at line 708 of file chert_postlist.cc.

References LOGCALL_DTOR.

Member Function Documentation

◆ at_end()

bool ChertPostList::at_end ( ) const

inlinevirtual

Return true if and only if we're off the end of the list.

Implements Xapian::PostingIterator::Internal.

Definition at line 282 of file chert_postlist.h.

◆ current_chunk_contains()

bool ChertPostList::current_chunk_contains ( Xapian::docid desired_did )

private

Return true if the given document ID lies in the range covered by the current chunk.

This does not say whether the document ID is actually present. It will return false if the document ID is greater than the last document ID in the chunk, even if it is less than the first document ID in the next chunk: it is possible for no chunk to contain a particular document ID.

Definition at line 835 of file chert_postlist.cc.

References first_did_in_chunk, last_did_in_chunk, LOGCALL, and RETURN.

Referenced by jump_to(), and skip_to().

◆ get_description()

string ChertPostList::get_description ( ) const

virtual

Get a description of the document.

Implements Xapian::PostingIterator::Internal.

Definition at line 984 of file chert_postlist.cc.

References number_of_entries, Xapian::Internal::str(), and LeafPostList::term.

Referenced by ChertModifiedPostList::get_description().

◆ get_docid()

Xapian::docid ChertPostList::get_docid ( ) const

inlinevirtual

Returns the current docid.

Implements Xapian::PostingIterator::Internal.

Definition at line 255 of file chert_postlist.h.

References Assert.

◆ get_doclength()

Xapian::termcount ChertPostList::get_doclength ( ) const

virtual

Returns the length of current document.

Implements Xapian::PostingIterator::Internal.

Definition at line 714 of file chert_postlist.cc.

References Assert, did, Xapian::Internal::intrusive_ptr< T >::get(), ChertDatabase::get_doclength(), have_started, is_at_end, LOGCALL, RETURN, and this_db.

Referenced by ChertModifiedPostList::get_doclength().

◆ get_termfreq()

Xapian::doccount ChertPostList::get_termfreq ( ) const

inlinevirtual

Returns number of docs indexed by this term.

This is the length of the postlist.

Implements LeafPostList.

Definition at line 252 of file chert_postlist.h.

◆ get_unique_terms()

Xapian::termcount ChertPostList::get_unique_terms ( ) const

virtual

Return the number of unique terms in the current document.

Implements Xapian::PostingIterator::Internal.

Definition at line 724 of file chert_postlist.cc.

References Assert, did, Xapian::Internal::intrusive_ptr< T >::get(), ChertDatabase::get_unique_terms(), have_started, is_at_end, LOGCALL, RETURN, and this_db.

Referenced by ChertModifiedPostList::get_unique_terms().

◆ get_wdf()

Xapian::termcount ChertPostList::get_wdf ( ) const

inlinevirtual

Returns the Within Document Frequency of the term in the current document.

Reimplemented from Xapian::PostingIterator::Internal.

Definition at line 265 of file chert_postlist.h.

References Assert.

Referenced by ChertAllDocsPostList::get_doclength(), and ChertModifiedPostList::get_wdf().

◆ get_wdf_upper_bound()

Xapian::termcount ChertPostList::get_wdf_upper_bound ( ) const

virtual

Implements LeafPostList.

Definition at line 1312 of file chert_postlist.cc.

References wdf_upper_bound.

◆ jump_to()

bool ChertPostList::jump_to ( Xapian::docid desired_did )

Used for looking up doclens.

Returns: true if docid desired_did has a document length.

Definition at line 955 of file chert_postlist.cc.

References current_chunk_contains(), did, have_started, is_at_end, LOGCALL, move_forward_in_chunk_to_at_least(), move_to_chunk_containing(), pos, and RETURN.

◆ move_forward_in_chunk_to_at_least()

bool ChertPostList::move_forward_in_chunk_to_at_least ( Xapian::docid desired_did )

private

Scan forward in the current chunk for the specified document ID.

This is particularly efficient if the desired document ID is greater than the last in the chunk - it then skips straight to the end.

Returns: true if we moved to a valid document, false if we reached the end of the chunk.

Definition at line 894 of file chert_postlist.cc.

References Assert, did, end, last_did_in_chunk, LOGCALL, pos, read_did_increase(), read_wdf(), RETURN, and wdf.

Referenced by jump_to(), and skip_to().

◆ move_to_chunk_containing()

void ChertPostList::move_to_chunk_containing ( Xapian::docid desired_did )

private

Move to chunk containing the specified document ID.

This moves to the chunk whose starting document ID is <= desired_did, but such that the next chunk's starting document ID is > desired_did.

It is thus possible that current_chunk_contains(desired_did) will return false after this call, since the document ID might lie after the end of this chunk, but before the start of the next chunk.

Definition at line 846 of file chert_postlist.cc.

References Assert, C_unpack_uint_preserving_sort(), check_tname_in_key_lite(), cursor, did, end, first_did_in_chunk, is_at_end, is_last_chunk, last_did_in_chunk, LOGCALL_VOID, ChertPostListTable::make_key(), next_chunk(), number_of_entries, pos, read_start_of_chunk(), read_start_of_first_chunk(), read_wdf(), report_read_error(), LeafPostList::term, and wdf.

Referenced by jump_to(), and skip_to().

◆ next()

PostList * ChertPostList::next ( double w_min )

virtual

Move to the next document.

Implements Xapian::PostingIterator::Internal.

Definition at line 814 of file chert_postlist.cc.

References did, have_started, is_at_end, LOGCALL, LOGLINE, next_chunk(), next_in_chunk(), RETURN, and wdf.

◆ next_chunk()

void ChertPostList::next_chunk ( )

private

Move to the next chunk.

If there are no more chunks in this postlist, this will set is_at_end to true.

Definition at line 751 of file chert_postlist.cc.

References C_unpack_uint_preserving_sort(), check_tname_in_key_lite(), cursor, did, end, first_did_in_chunk, is_at_end, is_last_chunk, last_did_in_chunk, LOGCALL_VOID, pos, read_start_of_chunk(), read_wdf(), report_read_error(), Xapian::Internal::str(), LeafPostList::term, and wdf.

Referenced by ChertPostListTable::merge_changes(), move_to_chunk_containing(), and next().

◆ next_in_chunk()

bool ChertPostList::next_in_chunk ( )

private

Move to the next item in the chunk, if possible.

If already at the end of the chunk, returns false.

Definition at line 734 of file chert_postlist.cc.

References Assert, did, end, last_did_in_chunk, LOGCALL, pos, read_did_increase(), read_wdf(), RETURN, and wdf.

Referenced by next().

◆ open_position_list()

PositionList * ChertPostList::open_position_list ( ) const

virtual

Get the list of positions of the term in the current document.

Reimplemented from Xapian::PostingIterator::Internal.

Definition at line 806 of file chert_postlist.cc.

References Assert, did, Xapian::Internal::intrusive_ptr< T >::get(), LOGCALL, ChertDatabase::position_table, RETURN, LeafPostList::term, and this_db.

Referenced by ChertModifiedPostList::open_position_list().

◆ operator=()

void ChertPostList::operator= ( const ChertPostList & )

private

Assignment is not allowed.

◆ read_number_of_entries()

void ChertPostList::read_number_of_entries	(	const char **	posptr,
		const char *	end,
		Xapian::doccount *	number_of_entries_ptr,
		Xapian::termcount *	collection_freq_ptr
	)