A postlist in a glass database. More...

#include <glass_postlist.h>

Inheritance diagram for GlassPostList:

Collaboration diagram for GlassPostList:

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

	~GlassPostList ()
	Destructor. More...

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

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...

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

void	operator= (const GlassPostList &)
	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...

	GlassPostList (Xapian::Internal::intrusive_ptr< const GlassDatabase > this_db_, const string &term, GlassCursor *cursor_)

void	init ()

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

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

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

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< GlassCursor >	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...

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

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...

Detailed Description

A postlist in a glass database.

Definition at line 55 of file glass_postlist.h.

Constructor & Destructor Documentation

◆ GlassPostList() [1/3]

GlassPostList::GlassPostList ( const GlassPostList & )

private

Copying is not allowed.

Referenced by open_nearby_postlist().

◆ GlassPostList() [2/3]

GlassPostList::GlassPostList	(	Xapian::Internal::intrusive_ptr< const GlassDatabase >	this_db_,
		const string &	term,
		GlassCursor *	cursor_
	)

private

Definition at line 711 of file glass_postlist.cc.

References Xapian::Internal::intrusive_ptr< T >::get(), init(), and LOGCALL_CTOR.

◆ GlassPostList() [3/3]

GlassPostList::GlassPostList	(	Xapian::Internal::intrusive_ptr< const GlassDatabase >	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 698 of file glass_postlist.cc.

References Xapian::Internal::intrusive_ptr< T >::get(), init(), and LOGCALL_CTOR.

◆ ~GlassPostList()

GlassPostList::~GlassPostList ( )

Destructor.

Definition at line 756 of file glass_postlist.cc.

References LOGCALL_DTOR.

Member Function Documentation

◆ at_end()

bool GlassPostList::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 210 of file glass_postlist.h.

Referenced by GlassAllDocsPostList::get_wdf().

◆ current_chunk_contains()

bool GlassPostList::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 892 of file glass_postlist.cc.

References first_did_in_chunk, last_did_in_chunk, LOGCALL, and RETURN.

Referenced by jump_to(), and skip_to().

◆ get_description()

string GlassPostList::get_description ( ) const

virtual

Get a description of the document.

Implements Xapian::PostingIterator::Internal.

Definition at line 1041 of file glass_postlist.cc.

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

◆ get_docid()

Xapian::docid GlassPostList::get_docid ( ) const

inlinevirtual

Returns the current docid.

Implements Xapian::PostingIterator::Internal.

Definition at line 182 of file glass_postlist.h.

References Assert.

◆ get_doclength()

Xapian::termcount GlassPostList::get_doclength ( ) const

virtual

Returns the length of current document.

Implements Xapian::PostingIterator::Internal.

Definition at line 773 of file glass_postlist.cc.

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

◆ get_termfreq()

Xapian::doccount GlassPostList::get_termfreq ( ) const

inlinevirtual

Returns number of docs indexed by this term.

This is the length of the postlist.

Implements LeafPostList.

Definition at line 179 of file glass_postlist.h.

◆ get_unique_terms()

Xapian::termcount GlassPostList::get_unique_terms ( ) const

virtual

Returns the number of unique terms in the current document.

Implements Xapian::PostingIterator::Internal.

Definition at line 782 of file glass_postlist.cc.

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

◆ get_wdf()

Xapian::termcount GlassPostList::get_wdf ( ) const

inlinevirtual

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

Reimplemented from Xapian::PostingIterator::Internal.

Definition at line 193 of file glass_postlist.h.

References Assert.

Referenced by GlassAllDocsPostList::get_doclength().

◆ get_wdf_upper_bound()

Xapian::termcount GlassPostList::get_wdf_upper_bound ( ) const

virtual

Implements LeafPostList.

Definition at line 1369 of file glass_postlist.cc.

References Assert, LeafPostList::term, and wdf_upper_bound.

◆ init()

void GlassPostList::init ( )

private

Definition at line 725 of file glass_postlist.cc.

References cursor, did, end, first_did_in_chunk, is_at_end, is_last_chunk, last_did_in_chunk, LOGLINE, GlassPostListTable::make_key(), number_of_entries, pos, read_start_of_chunk(), read_start_of_first_chunk(), read_wdf(), LeafPostList::term, wdf, and wdf_upper_bound.

Referenced by GlassPostList().

◆ jump_to()

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

Used for looking up doclens.

Returns: true if docid desired_did has a document length.

Definition at line 1012 of file glass_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 GlassPostList::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 951 of file glass_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 GlassPostList::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 903 of file glass_postlist.cc.

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

Referenced by jump_to(), and skip_to().

◆ next()

PostList * GlassPostList::next ( double w_min )

virtual

Move to the next document.

Implements Xapian::PostingIterator::Internal.

Definition at line 871 of file glass_postlist.cc.

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

◆ next_chunk()

void GlassPostList::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 808 of file glass_postlist.cc.

References 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, unpack_uint_preserving_sort(), and wdf.

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

◆ next_in_chunk()

bool GlassPostList::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 791 of file glass_postlist.cc.

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

Referenced by next().

◆ open_nearby_postlist()

LeafPostList * GlassPostList::open_nearby_postlist ( const std::string & term_ ) const

virtual

Open another postlist from the same database.

Parameters

term_ The term to open a postlist for. If term_ is near to this postlist's term, then this can be a lot more efficient (and if it isn't very near, there's not much of a penalty). Using this method can make a wildcard expansion much more memory efficient.

Returns: The new postlist object, or NULL if not supported (in which case the caller should probably open the postlist via the database instead).

Reimplemented from LeafPostList.

Definition at line 762 of file glass_postlist.cc.

References cursor, Xapian::Internal::intrusive_ptr< T >::get(), GlassPostList(), GlassTable::is_writable(), LOGCALL, GlassDatabase::postlist_table, RETURN, and this_db.

◆ open_position_list()

PositionList * GlassPostList::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 863 of file glass_postlist.cc.

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

◆ operator=()

void GlassPostList::operator= ( const GlassPostList & )

private

Assignment is not allowed.

◆ read_number_of_entries()

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

static

Read the number of entries and the collection frequency.

Read the number of entries in the posting list.

This must only be called when *posptr is pointing to the start of the first chunk of the posting list.

Definition at line 668 of file glass_postlist.cc.

References report_read_error(), and unpack_uint().

Referenced by GlassPostListTable::get_freqs(), read_start_of_first_chunk(), and GlassAllTermsList::read_termfreq().

◆ read_position_list()

PositionList * GlassPostList::read_position_list ( )

virtual

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

Reimplemented from Xapian::PostingIterator::Internal.

Definition at line 854 of file glass_postlist.cc.

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

◆ skip_to()

PostList * GlassPostList::skip_to	(	Xapian::docid	desired_did,
		double	w_min
	)

virtual

Skip to next document with docid >= docid.

Implements Xapian::PostingIterator::Internal.

Definition at line 977 of file glass_postlist.cc.

References Assert, current_chunk_contains(), did, have_started, is_at_end, LOGCALL, LOGLINE, move_forward_in_chunk_to_at_least(), move_to_chunk_containing(), RETURN, and wdf.

Member Data Documentation

◆ cursor

AutoPtr<GlassCursor> GlassPostList::cursor

private

Cursor pointing to current chunk of postlist.

Definition at line 75 of file glass_postlist.h.

Referenced by GlassPostListTable::get_chunk(), init(), GlassPostListTable::merge_changes(), move_to_chunk_containing(), next_chunk(), and open_nearby_postlist().

◆ did

Xapian::docid GlassPostList::did

private

Document id we're currently at.

Definition at line 90 of file glass_postlist.h.

Referenced by get_doclength(), GlassDatabase::get_postlist_cursor(), get_unique_terms(), init(), jump_to(), GlassPostListTable::merge_changes(), GlassPostListTable::merge_doclen_changes(), move_forward_in_chunk_to_at_least(), move_to_chunk_containing(), next(), next_chunk(), next_in_chunk(), open_position_list(), read_position_list(), and skip_to().

◆ end

const char* GlassPostList::end

private

Pointer to byte after end of current chunk.

Definition at line 87 of file glass_postlist.h.

Referenced by GlassPostListTable::get_chunk(), init(), GlassPostListTable::merge_changes(), move_forward_in_chunk_to_at_least(), move_to_chunk_containing(), next_chunk(), and next_in_chunk().

◆ first_did_in_chunk

Xapian::docid GlassPostList::first_did_in_chunk

private

The first document id in this chunk.

Definition at line 78 of file glass_postlist.h.

Referenced by current_chunk_contains(), GlassPostListTable::get_chunk(), init(), move_to_chunk_containing(), and next_chunk().

◆ have_started

bool GlassPostList::have_started

private

Whether we've started reading the list yet.

Definition at line 66 of file glass_postlist.h.

Referenced by get_doclength(), get_unique_terms(), jump_to(), next(), and skip_to().

◆ is_at_end

bool GlassPostList::is_at_end

private

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

Definition at line 72 of file glass_postlist.h.

Referenced by init(), jump_to(), move_to_chunk_containing(), next(), next_chunk(), and skip_to().

◆ is_last_chunk

bool GlassPostList::is_last_chunk

private

True if this is the last chunk.

Definition at line 69 of file glass_postlist.h.

Referenced by GlassPostListTable::get_chunk(), init(), move_to_chunk_containing(), and next_chunk().

◆ last_did_in_chunk

Xapian::docid GlassPostList::last_did_in_chunk

private

The last document id in this chunk.

Definition at line 81 of file glass_postlist.h.

Referenced by current_chunk_contains(), GlassPostListTable::get_chunk(), init(), move_forward_in_chunk_to_at_least(), move_to_chunk_containing(), next_chunk(), and next_in_chunk().

◆ number_of_entries

Xapian::doccount GlassPostList::number_of_entries

private

The number of entries in the posting list.

Definition at line 96 of file glass_postlist.h.

Referenced by get_description(), init(), and move_to_chunk_containing().

◆ pos

const char* GlassPostList::pos

private

Position of iteration through current chunk.

Definition at line 84 of file glass_postlist.h.

Referenced by GlassPostListTable::get_chunk(), init(), jump_to(), GlassPostListTable::merge_changes(), move_forward_in_chunk_to_at_least(), move_to_chunk_containing(), next_chunk(), and next_in_chunk().

◆ positionlist

GlassPositionList GlassPostList::positionlist

private

The position list object for this posting list.

Definition at line 63 of file glass_postlist.h.

Referenced by read_position_list().

◆ this_db

Xapian::Internal::intrusive_ptr<const GlassDatabase> GlassPostList::this_db

private

The database we are searching.

This pointer is held so that the database doesn't get deleted before us, and also to give us access to the position_table.

Definition at line 60 of file glass_postlist.h.

Referenced by get_doclength(), get_unique_terms(), open_nearby_postlist(), open_position_list(), and read_position_list().

◆ wdf

Xapian::termcount GlassPostList::wdf

private

The wdf of the current document.

Definition at line 93 of file glass_postlist.h.

Referenced by init(), move_forward_in_chunk_to_at_least(), move_to_chunk_containing(), next(), next_chunk(), next_in_chunk(), and skip_to().

◆ wdf_upper_bound

Xapian::termcount GlassPostList::wdf_upper_bound

private

Upper bound on wdf for this postlist.

Definition at line 99 of file glass_postlist.h.

Referenced by get_wdf_upper_bound(), and init().

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

backends/glass/glass_postlist.h
backends/glass/glass_postlist.cc

Public Member Functions

Static Public Member Functions

Private Member Functions

Private Attributes

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ GlassPostList() [1/3]

◆ GlassPostList() [2/3]

◆ GlassPostList() [3/3]

◆ ~GlassPostList()

Member Function Documentation

◆ at_end()

◆ current_chunk_contains()

◆ get_description()

◆ get_docid()

◆ get_doclength()

◆ get_termfreq()

◆ get_unique_terms()

◆ get_wdf()

◆ get_wdf_upper_bound()

◆ init()

◆ jump_to()

◆ move_forward_in_chunk_to_at_least()

◆ move_to_chunk_containing()

◆ next()

◆ next_chunk()

◆ next_in_chunk()

◆ open_nearby_postlist()

◆ open_position_list()

◆ operator=()

◆ read_number_of_entries()

◆ read_position_list()

◆ skip_to()

Member Data Documentation

◆ cursor

◆ did

◆ end

◆ first_did_in_chunk

◆ have_started

◆ is_at_end

◆ is_last_chunk

◆ last_did_in_chunk

◆ number_of_entries

◆ pos

◆ positionlist

◆ this_db

◆ wdf

◆ wdf_upper_bound