#include <IndexSet.h>

Inheritance diagram for CStringIndexSet:

Collaboration diagram for CStringIndexSet:

[legend]

Public Member Functions
template<class T >
const char *	GetIndexItemStr (const T &W) const
	this function returns a string(which was indexed by DDC) by an instance of CIndexItem or CItemIndexForLoading More...

	CStringIndexSet (const CStringIndexator *pParent)

	~CStringIndexSet ()

string	GetStorageFileName () const
	return file name for storage More...

void	CloseStorageFile ()
	close storage file More...

void	InitIndexSet (string Name, string ShortName, bool bCreateItemStorage, bool bCompress)
	initialize all class slots More...

void	ReadFromTheDisk ()
	read index from the disk More...

bool	DestroyIndexSet ()
	clear all vectors of the index and removes index files More...

bool	WriteToFile (bool bAfterLoading)
	write index to file More...

void	UnionIndexSets (const vector< CStringIndexSet *> &IndexSets, const vector< size_t > &TokenCounts)
	build union of multiple indices , throws CExpc if fails (new) More...

void	CreateSplitPartitions (vector< CStringIndexSet *> &Partitions, const vector< CTokenNo > &EndTokenNo) const
	partition this index into Paritions[] on EndTokenNo[] (exclusive) More...

void	EnsureSuffixIndex ()
	ensure that m_rIndex is non-empty, populating it from m_Index if required (called during index compilation) More...

bool	GetTokensFromStorage (const size_t start_offset, const size_t end_offset, vector< COutputToken > &Tokens) const
	return sequence of tokens(strings) [start_offset, end_offset] More...

DWORD	GetTokenIndexId (CTokenNo TokenNo) const

ddcVecFile< CIndexItem >::const_iterator	GetTypeIndexIdLowerBoundIter (const string &ValueStr) const

ddcVecFile< CIndexItem >::const_iterator	GetTypeIndexIdUpperBoundIter (const string &ValueStr) const

DWORD	GetTypeIndexIdLowerBound (const string &ValueStr) const

DWORD	GetTypeIndexId (const string &ValueStr) const
	gets index-local item-id of string type ValueStr, or DWORD_MAX if not in index More...

bool	GetContextBounds (CDDCFilterWithBounds &Filter, const string &LoValue, const string &HiValue) const
	populate bounds for context-sort operator More...

void	FindOccurrences (const vector< DWORD > &IndexItems, const size_t PeriodNo, vector< CTokenNo > &occurrences, CShortOccurCacheMap *pCaches, vector< int > &CacheIds) const
	find all occurrences of index items in subcorpora PeriodNo, using cache pCaches More...

void	FindChunkOccurrences (const vector< DWORD > &IndexItems, vector< CTokenNo > &occurrences, vector< DWORD > &ChunkLengths, size_t PeriodNo, CShortOccurCacheMap *pCaches, vector< int > &CacheIds) const
	find all occurrences of index items in subcorpora PeriodNo, using cache pCaches (if occurrences are written by chunks) More...

void	QueryTokenList (const string &WordForm, vector< DWORD > &MatchWords) const
	search for a string "WordForm", and add it to "MatchWords", if it is found More...

void	QueryTokenListWithRightTruncation (const string &Prefix, vector< DWORD > &MatchWords) const
	search for all strings, which begin with "Prefix", and add their IDs to "MatchWords" More...

void	QueryTokenListWithLeftTruncation (const string &Suffix, vector< DWORD > &MatchWords) const
	search for all strings, which end with "Suffix", adding their IDs to "MatchWords" (requires m_rIndex, introduced in v2.1.21) More...

void	QueryTokenListUsingRegExp (RML_RE &RegExp, vector< DWORD > &MatchWords, bool negated=false, bool ignore_diacritics=false) const
	search for all index items, which satisfy regular expession "RegExp", and add them to "MatchWords" More...

void	QueryTokenListUniversal (vector< DWORD > &MatchWords) const
	populate "MatchWords" with all index item indices More...

void	DumpStorage (FILE *output) const
	print the string representation of the whole storage to stdout More...

Public Member Functions inherited from CIndexSetForLoadingStage
	CIndexSetForLoadingStage ()

virtual	~CIndexSetForLoadingStage ()

bool	CreateTempFiles (string Path)
	creates temporary files for indexing More...

bool	DeleteTempFiles ()
	deletes temporary files after indexing More...

size_t	GetMemoryLoadIndexItemsCount () const
	gets the number of items in memory load index More...

bool	SaveMemoryLoadIndex ()
	saves memory index More...

bool	AddInputLoadIndexToMemoryLoadIndex ()
	add the input load index to the memory load index and clear the input load index More...

void	SortInputAndMemoryIndices ()
	sort the input and the memory load indices More...

bool	AddMemoryLoadIndexToMainLoadIndex ()
	add the memory load index to the main load index and clear the memory load index More...

void	InsertToInputLoadIndex (const char *Str, size_t StrLen, const vector< CTokenNo > &occurrences)
	updates input or memory load index with one string More...

void	RollbackLoadIndex (CTokenNo startTrimTokenNo)
	rolls back buffered index data starting at startTrimTokenNo More...

void	PrintLoadIndexStats (FILE *f=stderr) const
	debug: print input/memory load index stats More...

Public Member Functions inherited from CIndexSetForQueryingStage
	CIndexSetForQueryingStage (const CStringIndexator *pParent)

virtual	~CIndexSetForQueryingStage ()

bool	DestroyIndexSet ()
	destroy index set and remove index files More...

void	ReadAllOccurrences (size_t IndexItemNo, vector< CTokenNo > &Occurs) const
	reads all occurrences of IndexItemNo (this function can allocate much memory; it should be used carefully) More...

Public Attributes
string	m_Name
	the main name of the index set, for example "Token", "MorphPattern", "Thes", "Chunk"... More...

string	m_ShortName
	a short name of the index set, for example "m", "w", "t", "c" More...

Public Attributes inherited from CIndexSetForLoadingStage
bool	m_bUseItemStorage
	if true, then the program creates and uses a storage for this index More...

ddcVecFile< char >	m_StringBuffer
	a buffer for storing index strings (compile-time) More...

Public Attributes inherited from CIndexSetForQueryingStage
ddcVecFile< CIndexItem >	m_Index
	the main index(from strings to the ordered list of their occurrences) More...

CSuffixIndex	m_rIndex
	optional auxiliary index for suffix-queries; ItemIds lexicographically sorted by reverse string-value More...

PeriodsDivisionMapT	m_EndPeriodOffsets
	all corpus period divisions for the long occurrence lists More...

const CStringIndexator *	m_pParent
	a pointer to the collection of indices, which contains a reference to this index More...

bool	m_bCompressOccurrences
	if true, then the occurrences should be compresses (up to 30% for huge corpora) More...

Private Member Functions
bool	ConvertLoadIndexToWorkingIndex ()
	convert a temporal index set to the work index More...

void	CreateUnionTokenStorages (const vector< CStringIndexSet *> &IndexSets, const vector< size_t > &TokenCounts, const vector< vector< DWORD > > &xlateItemId)
	make concatenation of multiple storages (new) More...

void	OpenStorageFile ()
	open storage file More...

string	GetName () const
	return m_Name (an implementation of pure member CIndexSetForLoadingStage::GetName ) More...

bool	ConvertTempStorageToPersistent ()
	converts temporary index storage to persistent one (replacing a reference to m_StringBuffer by a index item no) More...

Private Attributes
ddcFileOrMMap	m_StorageFile
	a file for index storage More...

Additional Inherited Members
Protected Member Functions inherited from CIndexSetForLoadingStage
size_t	AddItemStrToBuffer (const char *Str, size_t StrLen)
	add a string to m_StringBuffer More...

Protected Member Functions inherited from CIndexSetForQueryingStage
void	AssertHasPath () const
	return true, if the project path is initialized More...

void	AddOccurs (size_t IndexItemNo, const bool bOneOccurrence, const size_t StartOccurNo, const size_t EndOccurNo, vector< CTokenNo > &Occurs, size_t PeriodNo, COccurrBuffer &OccursBuffer, CShortOccurCache *pCacheByIndexSet, int &CacheId) const
	a function for reading occurrences for one index item More...

string	GetOccursFileName () const
	return the file name for the file occurrences More...

string	GetOccHdrFileName () const
	return the name of file for m_Index More...

string	GetSuffixFileName () const
	return the name of file for m_rIndex (for suffix-queries) More...

string	GetPeriodsDivisionFileName () const
	return the name of file for occurrences period division More...

string	GetFileNameForInfos () const
	return the name of file for CIndexSetForLoadingStage::m_StringBuffer More...

file_off_t	GetOccurrsFileSize () const
	return the size of the file for occurrences More...

size_t	GetStartOccurNo (size_t IndexNo) const
	get the offset of the first occurrence of index item no IndexNo in the file of occurrences(m_OccursFp) More...

bool	BuildPeriodsDivisionAndCompress (const DWORD TokenId, vector< CTokenNo > &InputTokens)
	build a period division for one index item More...

bool	AddOneIndexItem (CItemIndexForLoading &M, FILE *res_fp, size_t &CurrPositionInResFile, const CTokenNo EndTokeNo)
	write one index item to result file More...

bool	WritePeriodsDivision ()
	write index item's period division to disk More...

bool	LoadIndexSet (bool bLoadHeaderOfOccurrences=true)
	load index set from binaries More...

Protected Attributes inherited from CIndexSetForLoadingStage
FILE *	m_TempStorageFile
	a temporal file for index storage More...

string	m_TempStorageFileName
	a temporary file, where the index storage is stored More...

string	m_MainOccurTempFileName
	a temporary file, where the main index is stored More...

Detailed Description

Class CStringIndexSet is the upmost implementation of one index set. The main functions deals with the searching of strings in index and with the retrieving its occurrences. On the other hand, this class is an inheritor of CIndexSetForLoadingStage and CIndexSetForQueryingStage, and therefore it provides a connection between them during the load phase (for example CStringIndexSet::ConvertLoadIndexToWorkingIndex).

Constructor & Destructor Documentation

◆ CStringIndexSet()

CStringIndexSet::CStringIndexSet ( const CStringIndexator * pParent )

◆ ~CStringIndexSet()

CStringIndexSet::~CStringIndexSet ( )

References CloseStorageFile().

Here is the call graph for this function:

Member Function Documentation

◆ ConvertLoadIndexToWorkingIndex()

bool CStringIndexSet::ConvertLoadIndexToWorkingIndex ( )

private

convert a temporal index set to the work index

References CIndexSetForQueryingStage::AddOneIndexItem(), ddcVecFile< T >::clear(), ddcMapFile< KeyT, ValT >::clear(), ddcVecFile< T >::empty(), CItemIndexForLoading::FreeOccurs(), CIndexSetForQueryingStage::GetOccursFileName(), CStringIndexator::GetSearchPeriod(), CStringIndexator::GetSearchPeriodsCount(), CItemIndexForLoading::InitOccurs(), CIndexSetForQueryingStage::m_EndPeriodOffsets, CIndexSetForQueryingStage::m_Index, CIndexSetForLoadingStage::m_MainOccurTempFileName, CIndexSetForQueryingStage::m_pParent, CItemIndexForLoading::ReadFromTemporalFile(), and CIndexSetForQueryingStage::WritePeriodsDivision().

Referenced by WriteToFile().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ CreateUnionTokenStorages()

void CStringIndexSet::CreateUnionTokenStorages	(	const vector< CStringIndexSet *> &	IndexSets,
		const vector< size_t > &	TokenCounts,
		const vector< vector< DWORD > > &	xlateItemId
	)

private

make concatenation of multiple storages (new)

References CloseStorageFile(), Format(), GetStorageFileName(), CIndexSetForLoadingStage::m_bUseItemStorage, OpenStorageFile(), and SaveOnePartOfUnionTokenStorage().

Referenced by UnionIndexSets().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ OpenStorageFile()

void CStringIndexSet::OpenStorageFile ( )

private

open storage file

References CloseStorageFile(), GetStorageFileName(), CStringIndexator::m_bMemoryMap, CIndexSetForQueryingStage::m_pParent, m_StorageFile, and ddcFileOrMMap::Open().

Referenced by CreateUnionTokenStorages(), ReadFromTheDisk(), and WriteToFile().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ GetName()

string CStringIndexSet::GetName ( ) const

privatevirtual

return m_Name (an implementation of pure member CIndexSetForLoadingStage::GetName )

Implements CIndexSetForLoadingStage.

References m_Name.

Referenced by FindChunkOccurrences(), FindOccurrences(), and GetStorageFileName().

Here is the caller graph for this function:

◆ ConvertTempStorageToPersistent()

bool CStringIndexSet::ConvertTempStorageToPersistent ( )

private

converts temporary index storage to persistent one (replacing a reference to m_StringBuffer by a index item no)

References ddcVecFile< T >::empty(), ddcVecFile< T >::ensureVec(), GetStorageFileName(), CIndexSetForLoadingStage::m_bUseItemStorage, CIndexSetForQueryingStage::m_Index, CIndexSetForLoadingStage::m_TempStorageFile, CIndexSetForLoadingStage::m_TempStorageFileName, and ddcVecFile< T >::m_vec.

Referenced by WriteToFile().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ GetIndexItemStr()

template<class T >

const char* CStringIndexSet::GetIndexItemStr ( const T & W ) const

inline

this function returns a string(which was indexed by DDC) by an instance of CIndexItem or CItemIndexForLoading

References Name.

Referenced by CreateMorphIndex(), CreateSplitPartitions(), DumpStorage(), FindChunkOccurrences(), GetTokensFromStorage(), GetTypeIndexId(), CConcSession::InitSortByContext(), QueryTokenList(), and QueryTokenListUsingRegExp().

Here is the caller graph for this function:

◆ GetStorageFileName()

string CStringIndexSet::GetStorageFileName ( ) const

return file name for storage

References GetName(), CStringIndexator::m_Path, CIndexSetForQueryingStage::m_pParent, and MakeFName().

Referenced by ConvertTempStorageToPersistent(), CreatePartitionStorage(), CreateSplitPartitions(), CreateUnionTokenStorages(), DestroyIndexSet(), DumpStorage(), and OpenStorageFile().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ CloseStorageFile()

void CStringIndexSet::CloseStorageFile ( )

close storage file

References ddcFileOrMMap::Close(), and m_StorageFile.

Referenced by CreateUnionTokenStorages(), DestroyIndexSet(), OpenStorageFile(), and ~CStringIndexSet().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ InitIndexSet()

void CStringIndexSet::InitIndexSet	(	string	Name,
		string	ShortName,
		bool	bCreateItemStorage,
		bool	bCompress
	)

initialize all class slots

References CIndexSetForQueryingStage::m_bCompressOccurrences, CIndexSetForLoadingStage::m_bUseItemStorage, m_Name, m_ShortName, and Name.

Referenced by CStringIndexator::RegisterChunkIndex(), and CStringIndexator::RegisterStringIndices().

Here is the caller graph for this function:

◆ ReadFromTheDisk()

void CStringIndexSet::ReadFromTheDisk ( )

read index from the disk

References CIndexSetForQueryingStage::GetFileNameForInfos(), CIndexSetForQueryingStage::LoadIndexSet(), CStringIndexator::m_bMemoryMap, CIndexSetForLoadingStage::m_bUseItemStorage, CIndexSetForQueryingStage::m_pParent, CIndexSetForLoadingStage::m_StringBuffer, ddcVecFile< T >::open(), and OpenStorageFile().

Referenced by CreateMorphIndex().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ DestroyIndexSet()

bool CStringIndexSet::DestroyIndexSet ( )

clear all vectors of the index and removes index files

References ddcVecFile< T >::close(), CloseStorageFile(), CIndexSetForQueryingStage::DestroyIndexSet(), FileExists(), GetStorageFileName(), and CIndexSetForLoadingStage::m_StringBuffer.

Referenced by CreateMorphIndex().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ WriteToFile()

bool CStringIndexSet::WriteToFile ( bool bAfterLoading )

write index to file

References ConvertLoadIndexToWorkingIndex(), ConvertTempStorageToPersistent(), CIndexSetForLoadingStage::DeleteTempFiles(), EnsureSuffixIndex(), ddcVecFile< T >::ensureVec(), CIndexSetForQueryingStage::GetFileNameForInfos(), CIndexSetForQueryingStage::GetOccHdrFileName(), CIndexSetForQueryingStage::GetSuffixFileName(), CIndexSetForLoadingStage::m_bUseItemStorage, CIndexSetForQueryingStage::m_Index, CIndexSetForQueryingStage::m_rIndex, CIndexSetForLoadingStage::m_StringBuffer, ddcVecFile< T >::m_vec, OpenStorageFile(), and WriteVector().

Referenced by CreateMorphIndex().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ UnionIndexSets()

void CStringIndexSet::UnionIndexSets	(	const vector< CStringIndexSet *> &	IndexSets,
		const vector< size_t > &	TokenCounts
	)

build union of multiple indices , throws CExpc if fails (new)

References CIndexSetForLoadingStage::AddItemStrToBuffer(), CIndexSetForQueryingStage::AddOneIndexItem(), ddcVecFile< T >::clear(), CreateUnionTokenStorages(), ddcLogDebug, ddcVecFile< T >::ensureVec(), Format(), CItemIndexForLoading::FreeOccurs(), CItemIndexForLoading::GetIndexItemOffset(), CItemIndexForLoading::GetOccurs(), CIndexSetForQueryingStage::GetOccursFileName(), CItemIndexForLoading::InitOccurs(), CIndexSetForLoadingStage::m_bUseItemStorage, CIndexSetForQueryingStage::m_Index, m_Name, m_ShortName, CIndexSetForLoadingStage::m_StringBuffer, ddcVecFile< T >::m_vec, CItemIndexForLoading::SetIndexItemOffset(), ddcVecFile< T >::size(), utrace, and CIndexSetForQueryingStage::WritePeriodsDivision().

Referenced by CConcIndexator::CreateAsUnion().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ CreateSplitPartitions()

void CStringIndexSet::CreateSplitPartitions	(	vector< CStringIndexSet *> &	Partitions,
		const vector< CTokenNo > &	EndTokenNo
	)		const

partition this index into Paritions[] on EndTokenNo[] (exclusive)

References CIndexSetForQueryingStage::AddOneIndexItem(), ClearVector(), CreatePartitionStorage(), ddcLogTrace, Format(), GetIndexItemStr(), CIndexSetForQueryingStage::GetOccursFileName(), GetStorageFileName(), CIndexSetForLoadingStage::m_bUseItemStorage, CIndexSetForQueryingStage::m_Index, m_Name, CIndexSetForLoadingStage::m_StringBuffer, ddcVecFile< T >::m_vec, CIndexSetForQueryingStage::ReadAllOccurrences(), ddcVecFile< T >::size(), and CIndexSetForQueryingStage::WritePeriodsDivision().

Referenced by CConcIndexator::SplitProject().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ EnsureSuffixIndex()

void CStringIndexSet::EnsureSuffixIndex ( )

ensure that m_rIndex is non-empty, populating it from m_Index if required (called during index compilation)

References ddcVecFile< T >::ensureVec(), CIndexSetForQueryingStage::m_Index, CIndexSetForQueryingStage::m_rIndex, CIndexSetForLoadingStage::m_StringBuffer, ddcVecFile< T >::m_vec, and ddcVecFile< T >::size().

Referenced by WriteToFile().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ GetTokensFromStorage()

bool CStringIndexSet::GetTokensFromStorage	(	const size_t	start_offset,
		const size_t	end_offset,
		vector< COutputToken > &	Tokens
	)		const

return sequence of tokens(strings) [start_offset, end_offset]

References GetIndexItemStr(), CIndexSetForLoadingStage::m_bUseItemStorage, CIndexSetForQueryingStage::m_Index, m_StorageFile, ddcFileOrMMap::ReadBuffer(), and ddcVecFile< T >::size().

Referenced by CConcordance::DumpFileIndexTabs(), and CConcSession::GetTokensFromStorageByBreak().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ GetTokenIndexId()

DWORD CStringIndexSet::GetTokenIndexId ( CTokenNo TokenNo ) const

gets index-local item-id of token number TokenNo

basically a pared-down single-token version of GetTokensFromStorage()
Returns
integer ItemId such that CIndexItem TokenItem = m_Index[ItemId] is the indexed attribute for token number TokenNo, or DWORD_MAX if an error occurs (e.g. no such token)

References CIndexSetForLoadingStage::m_bUseItemStorage, CIndexSetForQueryingStage::m_Index, m_StorageFile, ddcFileOrMMap::ReadBuffer(), and ddcVecFile< T >::size().

Referenced by CConcSession::InitSortByContext().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ GetTypeIndexIdLowerBoundIter()

ddcVecFile< CIndexItem >::const_iterator CStringIndexSet::GetTypeIndexIdLowerBoundIter ( const string & ValueStr ) const

gets local m_Index iterator (lower-bound) for type ValueStr

guts for QueryTokenList(string& WordForm)
really just a wrapper for std::lower_bound(m_Index.begin(), m_Index.end(), ValueStr.c_str(), LessIndexString1<CIndexItem>(&m_StringBuffer))
Returns
lower-bound iterator for ValueStr

References ddcVecFile< T >::begin(), ddcVecFile< T >::end(), ddcVecFile< T >::m_data, CIndexSetForQueryingStage::m_Index, and CIndexSetForLoadingStage::m_StringBuffer.

Referenced by GetContextBounds(), GetTypeIndexId(), GetTypeIndexIdLowerBound(), and QueryTokenList().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ GetTypeIndexIdUpperBoundIter()

ddcVecFile< CIndexItem >::const_iterator CStringIndexSet::GetTypeIndexIdUpperBoundIter ( const string & ValueStr ) const

gets local m_Index iterator (upper bound) for string type ValueStr

guts for QueryTokenList(string& WordForm)
really just a wrapper for std::upper_bound(m_Index.begin(), m_Index.end(), ValueStr.c_str(), LessIndexString1<CIndexItem>(&m_StringBuffer))
Returns
upper-bound iterator for ValueStr

References ddcVecFile< T >::begin(), ddcVecFile< T >::end(), ddcVecFile< T >::m_data, CIndexSetForQueryingStage::m_Index, and CIndexSetForLoadingStage::m_StringBuffer.

Referenced by GetContextBounds().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ GetTypeIndexIdLowerBound()

DWORD CStringIndexSet::GetTypeIndexIdLowerBound ( const string & ValueStr ) const

gets index-local item-id (lower bound) of string type ValueStr

wrapper for GetTypeIndexIdLowerBoundIter(), returns item-id rather than iterator
Returns
lower-bound item-id for ValueStr

References ddcVecFile< T >::begin(), GetTypeIndexIdLowerBoundIter(), and CIndexSetForQueryingStage::m_Index.

Referenced by CConcSession::SortKeyLB().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ GetTypeIndexId()

DWORD CStringIndexSet::GetTypeIndexId ( const string & ValueStr ) const

gets index-local item-id of string type ValueStr, or DWORD_MAX if not in index

References ddcVecFile< T >::begin(), ddcVecFile< T >::end(), GetIndexItemStr(), GetTypeIndexIdLowerBoundIter(), and CIndexSetForQueryingStage::m_Index.

Here is the call graph for this function:

◆ GetContextBounds()

bool CStringIndexSet::GetContextBounds	(	CDDCFilterWithBounds &	Filter,
		const string &	LoValue,
		const string &	HiValue
	)		const

populate bounds for context-sort operator

References CHitSortKey::assign(), ddcVecFile< T >::begin(), CDDCFilterWithBounds::clear(), ddcVecFile< T >::end(), GetTypeIndexIdLowerBoundIter(), GetTypeIndexIdUpperBoundIter(), CHitSortKey::i, CDDCFilterWithBounds::m_bSet, CIndexSetForQueryingStage::m_Index, CDDCFilterWithBounds::m_KeyHi, CDDCFilterWithBounds::m_KeyLo, and ddcVecFile< T >::size().

Referenced by CQFContextSort::Compile().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ FindOccurrences()

void CStringIndexSet::FindOccurrences	(	const vector< DWORD > &	IndexItems,
		const size_t	PeriodNo,
		vector< CTokenNo > &	occurrences,
		CShortOccurCacheMap *	pCaches,
		vector< int > &	CacheIds
	)		const

find all occurrences of index items in subcorpora PeriodNo, using cache pCaches

References CIndexSetForQueryingStage::AddOccurs(), CIndexItem::GetEndOccurOffset(), GetName(), CIndexSetForQueryingStage::GetStartOccurNo(), CIndexItem::HasOneOccurrence(), CIndexSetForQueryingStage::m_Index, and SortOccurrences().

Referenced by CQueryTokenNode::EvaluateWithoutHits().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ FindChunkOccurrences()

void CStringIndexSet::FindChunkOccurrences	(	const vector< DWORD > &	IndexItems,
		vector< CTokenNo > &	occurrences,
		vector< DWORD > &	ChunkLengths,
		size_t	PeriodNo,
		CShortOccurCacheMap *	pCaches,
		vector< int > &	CacheIds
	)		const

find all occurrences of index items in subcorpora PeriodNo, using cache pCaches (if occurrences are written by chunks)

References CIndexSetForQueryingStage::AddOccurs(), GetIndexItemStr(), GetName(), CIndexSetForQueryingStage::GetStartOccurNo(), and CIndexSetForQueryingStage::m_Index.

Referenced by CQueryTokenNode::EvaluateWithoutHits().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ QueryTokenList()

void CStringIndexSet::QueryTokenList	(	const string &	WordForm,
		vector< DWORD > &	MatchWords
	)		const

search for a string "WordForm", and add it to "MatchWords", if it is found

References ddcVecFile< T >::begin(), ddcVecFile< T >::end(), GetIndexItemStr(), GetTypeIndexIdLowerBoundIter(), CIndexSetForQueryingStage::m_Index, CStringIndexator::m_MaxRegExpExpansionSize, and CIndexSetForQueryingStage::m_pParent.

Referenced by CQueryTokenNode::CreateSetPattern(), and CQueryTokenNode::CreateStringPattern().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ QueryTokenListWithRightTruncation()

void CStringIndexSet::QueryTokenListWithRightTruncation	(	const string &	Prefix,
		vector< DWORD > &	MatchWords
	)		const

search for all strings, which begin with "Prefix", and add their IDs to "MatchWords"

References ddcVecFile< T >::begin(), ddcVecFile< T >::end(), ddcVecFile< T >::m_data, CIndexSetForQueryingStage::m_Index, CStringIndexator::m_MaxRegExpExpansionSize, CIndexSetForQueryingStage::m_pParent, and CIndexSetForLoadingStage::m_StringBuffer.

Referenced by CQueryTokenNode::CreatePrefixSetPattern().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ QueryTokenListWithLeftTruncation()

void CStringIndexSet::QueryTokenListWithLeftTruncation	(	const string &	Suffix,
		vector< DWORD > &	MatchWords
	)		const

search for all strings, which end with "Suffix", adding their IDs to "MatchWords" (requires m_rIndex, introduced in v2.1.21)

References ddcVecFile< T >::begin(), ddcVecFile< T >::end(), ddcVecFile< T >::m_data, CIndexSetForQueryingStage::m_Index, CStringIndexator::m_MaxRegExpExpansionSize, CIndexSetForQueryingStage::m_pParent, CIndexSetForQueryingStage::m_rIndex, and CIndexSetForLoadingStage::m_StringBuffer.

Referenced by CQueryTokenNode::CreateSuffixSetPattern().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ QueryTokenListUsingRegExp()

void CStringIndexSet::QueryTokenListUsingRegExp	(	RML_RE &	RegExp,
		vector< DWORD > &	MatchWords,
		bool	negated = `false`,
		bool	ignore_diacritics = `false`
	)		const