#include <Concordance.h>

Inheritance diagram for CConcordance:

[legend]

Collaboration diagram for CConcordance:

[legend]

Public Member Functions
	CConcordance ()

	~CConcordance ()

void	RegisterIndicesToShow (const string &IndexListStr)
	wrapper for IndicesToShow option; now accepts integer position (min=1), long name, short name, or alias More...

string	GetIndicesToShowStr (bool Positional=false) const
	get opt-style string declaration for IndicesToShow (empty if default) More...

RML_RE::Options	GetRegexOptions () const
	return default pcre regex options More...

bool	IsDwdsCorpusInterface () const
	return true, if DDC outputs results in DWDS format More...

bool	IsGutenbergInterface () const
	return true, if DDC outputs results in Gutenberg project format More...

bool	HasContextOperator () const
	return true, if query context operator (#Cntxt) is switched off More...

bool	UseDwdsThesaurus () const
	return true, if DWDS thesaurus is enabled (index "Thes") More...

bool	OutputBibliographyOfHits () const
	return true, if DDC should output bibliographical information for hits instead of corpus file names More...

bool	IndexPunctuation () const
	wrapper for m_bIndexPunctuation More...

string	GetHtmlReference (size_t posFile) const
	get an HTML formatted reference to a corpus file More...

string	GetShortFilename (size_t posFile) const
	get a reference to a corpus file without the common left prefix More...

string	GetFileNameForCorpusFileNames () const
	get file name for storing corpus file names More...

string	GetFileNameForMaskedFiles () const
	get file name for masked files (strings) More...

string	GetFileNameForMaskedFileIds () const
	get file name for masked files (IDs, binary) More...

vector< string >	GetTokenFields (const COutputToken &tok)
	parse a delimited token into fields by splitting on m_InterpDelimiter More...

size_t	GetCorpusFilesCount () const
	get the number of indexed corpus files More...

string	GetCorpusFile (CFileNo FileNo) const
	get corpus file by index More...

size_t	GetMaskedFilesCount () const
	get count of masked files More...

void	LoadSourceFilesAndOptions (string FileName, bool reallyReadSourceFiles=true)
	load list of source files and parses option file (*.opt) More...

void	LoadCorpusFiles ()
	load list of corpus files (*.con) More...

string	GetCommonFilePrefix () const
	(re-)compute common prefix of corpus files in m_CorpusFiles More...

void	LoadMaskedFiles ()
	load list of masked (deleted)Corpus File Definition More...

void	LoadOptionsFromFile (const string &OptFile)
	loads options from a named file (calls LoadOptionsFromString()) More...

void	LoadProject (string FileName, bool includeSourceFiles=true)
	loads everything More...

time_t	UpdateTimestamp (const char *filename)
	update m_Timestamp to mtime of Filename if it is newer than the current m_Timestamp; More...

void	DumpBibliography (FILE *f=stdout) const
	dump loaded metadata to a stream (JSON) More...

string	DumpFileBibliography (DWORD FileNo) const
	dump file metadata to a string (JSON) More...

void	DumpFileIndexJson (DWORD FileNo, FILE *f=stdout) const
	dump file data to a file (JSON) More...

void	DumpIndex (string dirname, CIndexDumpFormat fmt=idfJson) const
	dump index data to a directory (format-dependent) More...

void	DumpIndexToSingleTabFile (FILE *outfp) const
	dump index data to a single tab formatted file More...

bool	SaveOptions (string FileName) const
	saves options to option file (*.opt) More...

bool	GetAllOccurrences (vector< CTokenNo > &occurrences, size_t searchPeriodNo) const
	moo: get a vector of all occurrences in a given search period; used by universal wildcard (*) queries More...

bool	GetOccurrencesByPosition (const string &BreakName, int anchor, vector< CTokenNo > &occurrences, size_t searchPeriodNo) const
	moo: search named break collection for matching positions, used by anchor queries More...

bool	UseTabFormatForLoading () const

Public Member Functions inherited from CStringIndexator
	CStringIndexator ()

	~CStringIndexator ()

bool	RegisterStringIndices (const string &IndicesStr)
	read index declarations from a string and register them More...

bool	RegisterIndexAliases (const string &IndexAliasStr)
	read index alias declarations from a string and register them; returns true iff all registrations were successful More...

bool	RegisterIndexAlias (const string &AliasFrom, const string &AliasTo)
	register a single index alias (low-level); returns true iff AliasTo resolves to a known index according to m_AliasMap More...

void	RegisterIndexAlias (const string &AliasFrom, CStringIndexSet *idx)
	register a single index label or alias (lowest-level); if idx is NULL, any existing entry for AliasFrom will be deleted More...

void	SetPath (string Path)
	set the path to the indices More...

string	GetIndicesString () const
	return all registered index declarations, in opt-file syntax More...

string	GetIndexAliasString () const
	return all registered index aliases, in opt-file syntax More...

size_t	GetSearchPeriodsCount () const
	return the number of corpus periods More...

const CTokenNo &	GetSearchPeriod (size_t i) const
	get a corpus period by an index More...

bool	StartIndexing (string Path)
	call CreateTempFiles for all registered indices More...

void	TerminateIndexing ()
	call DeleteTempFiles for all registered indices More...

bool	FinalSaveAllIndices (bool bAfterLoading)
	final saving all indices to disk (converting temp files to persistent) More...

bool	AddInputLoadIndexToMemoryLoadIndex ()
	unites input index with memory index and clears input load index More...

bool	AddMemoryLoadIndexToMainLoadIndex ()
	unites memory index with main index and clears memory load index More...

bool	SaveMemoryLoadIndex ()
	store memory load index on the disk More...

CStringIndexSet *	GetIndexByName (const string &Name)
	return a pointer to the index by CStringIndexSet::m_Name (linear search) More...

CStringIndexSet *	GetIndexByNameOrShortName (const string &Name)
	return a pointer to the index by CStringIndexSet::m_Name or CStringIndexSet::m_ShortName (linear search) More...

CStringIndexSet *	GetIndexByAlias (const string &Alias) const
	return a pointer to the index by long-name, short-name, or alias (most abstract, uses m_IndexMap) More...

CStringIndexSet *	GetTokenIndex ()
	return the first index that normally contains tokens themselves More...

const CStringIndexSet *	GetTokenIndex () const
	return the first index that normally contains tokens themselves More...

Public Member Functions inherited from CHitBorders
const CBreakCollection *	GetBreakCollectionByName (const string &Name) const
	moo: get break collection by long or short name More...

const vector< CBreakCollection > &	GetBreaks (void) const
	moo: get break collection map (dangerous) More...

	CHitBorders ()

string	GetBorderIndicesString () const
	return the string representation of break collection descriptions More...

string	WithinBreakName (const vector< string > &Within) const

const ddcBreakVector *	GetBreaksByName (const string &ShortName) const
	returns a break collection by a short name More...

CTokenNo	GetCorpusEndTokenNo () const
	returns the value of the last file break (which should be equal to the last value of any break collection) More...

const ddcBreakVector &	GetFileBreaks () const
	quick reference to file breaks More...

CTokenNo	GetFileStartTokenNo (size_t FileNo) const
	returns the start position of corpus file FileNo More...

DWORD	GetPageNumber (size_t No) const
	returns m_PageBreaks[No].m_PageNumber (see CPageNumber) More...

bool	IsRegisteredBreak (const string &ShortName) const
	returns true if a short name is found in m_Breaks More...

void	RegisterBorderIndices (const char *IndicesStr)
	creates empty elements of m_Breaks by its string descriptions More...

bool	LoadHitBorders (string Path, bool useMMap=false)
	load break collections from the disk More...

void	ConvertHitsToPageBreaks (vector< CHit >::const_iterator hits_begin, vector< CHit >::const_iterator hits_end, const ddcBreakVector &Breaks, DwordVector &PageBreaks) const
	converts hits to page breaks, which contains this breaks More...

ddcVecFile< CPageNumber >::const_iterator	GetTokenPageBreak (CTokenNo tok) const
	get page break for a given token number as an interator into m_PageBreaks More...

void	AddBreakByName (const string &ShortName, const CTokenNo &B)
	adds one break to a collection identified by a short name (during indexing) More...

void	BordersEndIndexing (string Path)
	closes all CBreakCollectionDescr::m_FileForIndexing from m_Breaks (during indexing) More...

void	StartTextAreaBorders ()
	must be called before indexing each text area in order to create at least on break in each text area More...

void	EndTextAreaBorders (DWORD TextAreaEndTokenNo)
	must be called after indexing each text area in order to create at least on break in each text area More...

Public Member Functions inherited from CSourceFileHolder
	CSourceFileHolder ()

bool	SaveSourceFileList (string FileName)
	Saves the list of source files to file *.con. More...

void	DeleteSourceFile (long ItemNo)
	Deletes a source file. More...

void	AddSourceFile (const char *FileName)
	Adds a source file. More...

void	DeleteAllSourceFiles ()
	deletes all Source File Definition source files More...

size_t	GetSourceFilesCount () const

string	GetSourceFile (size_t FileNo) const
	get the source file by the index More...

void	AddSourceFilesFrom (const CSourceFileHolder &X)

void	ReadSourceFileList (string FileName)

int	FoundNotExistedFile () const
	finds a source file which does not exist, if there is no such file, returns -1 More...

bool	IsModified () const

Public Attributes
MorphLanguageEnum	m_Language
	the language of the corpus More...

bool	m_bIndexMorphPatterns
	Enables the index of morph patterns. More...

bool	m_bIndexChunks
	Enables indexing and querying using chunks. More...

bool	m_bCaseSensitive
	if true, then the default search is case sensitive More...

bool	m_bShowNumberOfRelevantDocuments
	if true, then DDC always calculates the number of documents, where at lease one hit is found More...

bool	m_bQueryOnlyFiles
	prohibits sentence break collection under DWDS_Index or MorphXML_Index More...

bool	m_bArchiveIndex
	sets that index should be archived under DWDS_Index or MorphXML_Index More...

bool	m_bResumeOnIndexErrors
	if true, CConcIndexatorInvoker skips source documents with errors More...

ddcCorpusList	m_CorpusFiles
	Corpus files More...

CMaskedFileSet	m_MaskedFiles

CConcXml	m_BiblIndex
	a member which holds a index for bibliographical information More...

CHighlightTags	m_HtmlHighlighting
	highlighting tags for CConcHolder::m_ResultFormat == DDC_ResultHTML More...

CHighlightTags	m_TextHighlighting
	highlighting delimeters for CConcHolder::m_ResultFormat == DDC_ResultText More...

CHighlightTags	m_TableHighlighting
	highlighting delimeters for CConcHolder::m_ResultFormat == DDC_ResultTable More...

bool	m_bDisableDefaultQueryLexicalExpansion
	if true, then no default lexical expansion fo querz words occurs More...

int	m_LeftKwicContextSize
	the size of the left context of the highlighted words in document search More...

int	m_RightKwicContextSize
	the size of the right context of the highlighted words in document search More...

int	m_NumberOfKwicLinesInSnippets
	the maximal number of kwic lines in file snippets More...

double	m_TfIdfRank
	the parameter for TfIdf ranking More...

double	m_NearRank
	the parameter for Near ranking More...

double	m_PositionRank
	the parameter for Position ranking More...

string	m_InterpDelimiter
	delimiter to use between token index fields in output More...

string	m_TokenDelimiter
	delimiter to use between tokens in output More...

bool	m_Utf8
	whether to assume indexed data is utf8 encoded (default=no) More...

bool	m_bAllowUnsafeQueries
	potentially unsafe queries will throw an exception unless this is true (default=false) More...

bool	m_bAllowCountByTokenAttributes
	using any token attribute as a count-key will throw an exception unless this is true (default=true) More...

bool	m_bLemmaQueryUsesMorphPattern
	interpret "%foo" queries using MorphPattern? (default=true) More...

vector< size_t >	m_IndicesToShow
	indices to show for Free_Index More...

time_t	m_Timestamp
	moo: timestamp of project *._con file More...

size_t	m_MaxCachedHitsCount
	moo: maximum number of hits in a CConcHolder cache entry – query results with more than MaxCachedHitsCount hits will not be cached (default=512) More...

size_t	m_MaxQueryCacheSize
	moo: maximum number of queries to be cached by an associated CConcHolder (default=512) More...

TxDispatcher	m_Txd
	term expansion dispatcher; should define at least an entry for "default" More...

map< string, string >	m_OpDefaultIndexNames
	maps token-query operators to default index names; keys are as returned by CQToken::OperatorKey() More...

map< string, pair< bool, string > >	m_ServerInfo
	maps symbolic keys to string constants to be included in corpus 'info' response as info.user.KEY=VAL values are pairs (isFile,Value) s.t. Value is filename iff isFile is a true value, otherwise a literal value More...

Public Attributes inherited from CStringIndexator
string	m_Path
	where all indices are stored More...

bool	m_bMemoryMap
	whether to directly mmap() index file data (default=false) More...

vector< CStringIndexSet * >	m_Indices
	the registered indices, by positional index More...

IndexAliasMap	m_IndexAlias
	declared index aliases (FROM -> TO); not really used at runtime More...

IndexMap	m_IndexMap
	all registered indices, keyed by long-name, short-name, or label (LABEL -> INDEX) More...

size_t	m_MaxRegExpExpansionSize
	the maximal number of index items which can be included in an expansion set of one regular expression More...

CStringIndexSet *	m_pChunkIndex
	a quick reference to a chunk index, if CConcIndexator::m_bIndexChunks is on, otherwise null More...

Protected Types
enum	DDCIndexTypeEnum { DWDS_Index, MorphXML_Index, Free_Index, TabFormat_Index }
	enum DDCIndexTypeEnum contains index types. Each index type determines DDC indices and break collections. More...

Protected Member Functions
void	AssertHasPath () const

void	LoadOptionsFromString (string Options)
	loads options from a string More...

void	InitDefaultOptions ()

string	SaveOptionsToString () const
	saves options to a string More...

Protected Member Functions inherited from CStringIndexator
bool	RegisterChunkIndex ()
	register chunk index (chunks:NP, VP etc) More...

string	GetSearchPeriodsFileName () const
	return the file name for search periods More...

bool	DestroyIndices ()
	call DestroyIndexSet for all registered indices More...

void	ReadIndicesFromTheDisk ()
	call ReadFromTheDisk for all registered indices More...

void	ClearStringIndices ()
	clear m_Indices More...

void	IndexOneToken (CTokenIndexator document, const char Line, bool tryFixErrors=true)
	index one token and its properies (delimited by CConcCommon.h::globalFieldDelimeter) More...

void	IndexTokenFixLongColumns (const size_t MaxLen, const size_t nCols, const char InputLine, char Out)
	moo: truncate long columns in InputLine, storing result in Out More...

Protected Member Functions inherited from CHitBorders
string	GetPageBreaksFileName (string Path) const
	returns the file name for page breaks More...

string	GetShortNameByName (const string &BreakName) const
	returns the short name of a break collection by the long or the short name More...

bool	StartIndexing (string Path)
	opens for writing all CBreakCollectionDescr::m_FileForIndexing from m_Breaks More...

bool	RemoveHitBordersFileAndClear (string Path)
	deletes all break files More...

void	AddPageBreak (const CPageNumber &P)
	adds one page break More...

void	SavePageBreaks (const string &ProjectPath)
	save page break file More...

int	RegisterBreak (string ShortName, string LongName)

int	EnsureRegisteredBreak (string ShortName, string LongName)

int	GetBreakCollectionIndexByName (string ShortName) const

void	AddBreakByIndex (DWORD BreakCollectionNo, const CTokenNo &B)

Protected Attributes
DDCIndexTypeEnum	m_IndexType
	the type of index More...

bool	m_bIndexPunctuation
	Enables indexing all punctuation marks. More...

bool	m_bUseParagraphTagToDivide
	Enables using "<p>" tag as a paragraph delimiter. More...

bool	m_bEmptyLineIsSentenceDelim
	if m_bEmptyLineIsSentenceDelim is on, every empty line in the input file is considered to be the end of the sentence. More...

bool	m_bUseIndention
	if m_bUseIndention is on, the program tries to find paragraphs using indentions More...

DWORD	m_UserMaxTokenCountInOnePeriod
	The maximal number of occurrences in one subcorpora (defined by user) More...

DWORD	m_UserMaxInputLoadIndexSize
	The maximal number of occurrences in the input load index, by default 400000. More...

bool	m_bUseDwdsThesaurus
	Enables indexing and querying using DWDS Thesaurus. More...

Protected Attributes inherited from CStringIndexator
vector< CTokenNo >	m_SearchPeriods
	search periods of the corpus More...

Protected Attributes inherited from CHitBorders
vector< CBreakCollection >	m_Breaks
	all breaks More...

map< string, int >	m_ShortName2BreakCollection
	the map from CBreakCollection.m_ShortName to the index in m_Breaks More...

map< string, int >	m_LongName2BreakCollection
	the map from CBreakCollection.m_LongName to the index in m_Breaks More...

int	m_FileBreakCollectionNo
	a quick reference to file breaks (which are also stored in m_Breaks) More...

string	m_DefaultBreakName
	The name of the default break collection (written in the options file) More...

ddcVecFile< CPageNumber >	m_PageBreaks
	page number collection More...

vector< DWORD >	m_LastTextAreaBreaks

Protected Attributes inherited from CSourceFileHolder
vector< string >	m_SourceFiles
	Source files More...

bool	m_bModifiedListOfFiles

Private Member Functions
string	GetBiblIndexFileName () const

string	GetBiblFileName () const

bool	HasEqualOptions (const CConcordance &X) const
	checks if X has the same option More...

const char *	GetIndexTypeStr () const
	return a string representation of index type More...

bool	ReadIndexTypeFromStr (const string &s)
	read the index type from a string More...

void	DumpFileIndexTabs (DWORD FileNo, FILE *f) const
	dump file data to a file (tabs) More...

Private Attributes
vector< BYTE >	m_PcreCharacterTables
	a table of character properties for regular expressions which depend on CConcIndexator::m_Language More...

bool	m_bDwdsCorpusInterface
	if m_bDwdsCorpusInterface is on, the program outputs results in DWDS format More...

bool	m_bGutenbergInterface
	if m_bGutenbergInterface is on, the program outputs results in a format of Gutenberg project More...

bool	m_bNoContextOperator
	should we switch off context operator (#Cntxt) due copyright More...

bool	m_bOutputBibliographyOfHits
	Should we show bibliography of the hits instead of filename. More...

string	m_InternetPathPrefix

string	m_LocalPathPrefix

string	m_CommonFilePrefix

Additional Inherited Members
Public Types inherited from CStringIndexator
typedef map< string, string >	IndexAliasMap
	typedef for index alias maps More...

typedef map< string, CStringIndexSet * >	IndexMap
	typedef for index symbol table More...

Detailed Description

CConcordance is the central class of DDC technology. The most of its slots come from the two parent classes:CStringIndexator (indexing tokens and its properties) and CHitBorders (indexing corpus divisions) This class also contains a list of corpus files and some indexing and querying options.

Member Enumeration Documentation

◆ DDCIndexTypeEnum

enum CConcordance::DDCIndexTypeEnum

protected

enum DDCIndexTypeEnum contains index types. Each index type determines DDC indices and break collections.

Enumerator
DWDS_Index	A type for corpus without annotations, which are written for each word. Fr example the input text can be a plain text. DDC always builds a token index and a file break collection for this index type. Optionally DDC can build "Thes" index, "Morph" index and a sentence collection.
MorphXML_Index	A type for xml-texts, if their words have predefined and written annotations. DDC always builds a token index and a "MorphPattern" index. It also creates a file and a sentence break collection.
Free_Index	This index type is free and therefore it should be defined in the options file (fields "Indices" and "HitBorders"). The corpus should consists of xml-files with a bibliographical header and a body (text). The text is written in CWB format (http://www.ims.uni-stuttgart.de/projekte/CorpusWorkbench/CWBTutorial/cwb-tutorial.pdf). The original CWB format was changed in the following way. Instead of line breaks which are used to delimit records in the input file, DDC uses a special tag CConcCommon.h::PredefinedTableLineTag. This is done because line breaks are not preserved by the XML-parser.
TabFormat_Index	see http://odo.dwds.de/~moocow/software/ddc/ddc_tabs.html

Constructor & Destructor Documentation

◆ CConcordance()

CConcordance::CConcordance ( )

◆ ~CConcordance()

CConcordance::~CConcordance ( )

Member Function Documentation

◆ GetBiblIndexFileName()

string CConcordance::GetBiblIndexFileName ( ) const

private

◆ GetBiblFileName()

string CConcordance::GetBiblFileName ( ) const

private

◆ HasEqualOptions()

bool CConcordance::HasEqualOptions ( const CConcordance & X ) const

private

checks if X has the same option

References SaveOptionsToString().

Here is the call graph for this function:

◆ GetIndexTypeStr()

const char * CConcordance::GetIndexTypeStr ( ) const

private

return a string representation of index type

References DWDS_Index, Free_Index, m_IndexType, MorphXML_Index, and TabFormat_Index.

Referenced by LoadOptionsFromString(), and SaveOptionsToString().

Here is the caller graph for this function:

◆ ReadIndexTypeFromStr()

bool CConcordance::ReadIndexTypeFromStr ( const string & s )

private

read the index type from a string

References DWDS_Index, Free_Index, m_IndexType, MorphXML_Index, and TabFormat_Index.

Referenced by LoadOptionsFromString().

Here is the caller graph for this function:

◆ DumpFileIndexTabs()

void CConcordance::DumpFileIndexTabs	(	DWORD	FileNo,
		FILE *	f
	)		const

private

dump file data to a file (tabs)

References ddcVecFile< T >::begin(), ddcVecFile< T >::end(), CStringIndexSet::GetTokensFromStorage(), jsonStr(), CHitBorders::CBreakCollection::m_BreakOffsets, CIndexSetForLoadingStage::m_bUseItemStorage, CBibliography::m_DateStr, CHitBorders::CBreakCollection::m_LongName, CStringIndexSet::m_Name, CBibliography::m_OrigBibl, CBibliography::m_ScanBibl, CHitBorders::CBreakCollection::m_ShortName, CStringIndexSet::m_ShortName, CBibliography::m_StartPageInfo, ddcVecFile< T >::size(), and UnknownPageNumber.

Here is the call graph for this function:

◆ AssertHasPath()

void CConcordance::AssertHasPath ( ) const

protected

References errNonePath, and ErrorMessage().

Referenced by CConcIndexator::DestroyIndex().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ LoadOptionsFromString()

void CConcordance::LoadOptionsFromString ( string Options )

protected

loads options from a string

References CBiblIndex::AddBiblExpander(), TxDispatcher::addExpander(), BoolToString(), ddcLogDebug, ddcLogWarn, DWDS_Index, EchoOption(), EchoOptionLines(), TxDispatcher::ensureDefaultExpanders(), Format(), Free_Index, FreeBiblAttribOptionFieldName, CHitBorders::GetBorderIndicesString(), CHitBorders::GetBreakCollectionByName(), CBiblIndex::GetFreeBibiAttributesDescr(), CStringIndexator::GetIndexAliasString(), CStringIndexator::GetIndexByAlias(), GetIndexTypeStr(), CStringIndexator::GetIndicesString(), GetIndicesToShowStr(), GetLanguageByString(), GetRegexOptions(), GetStringByLanguage(), CBiblIndex::GetTextAreasDescr(), CBiblIndex::IsRegisteredBiblField(), LC_CTYPE_UTF8_DEFAULT, LC_NUMERIC_FORCE, LoadFileToString(), m_bAllowCountByTokenAttributes, m_bAllowUnsafeQueries, m_bArchiveIndex, m_bCaseSensitive, m_bDisableDefaultQueryLexicalExpansion, m_bDwdsCorpusInterface, m_bEmptyLineIsSentenceDelim, m_bGutenbergInterface, m_BiblIndex, m_bIndexChunks, m_bIndexMorphPatterns, m_bIndexPunctuation, m_bLemmaQueryUsesMorphPattern, CStringIndexator::m_bMemoryMap, m_bNoContextOperator, m_bOutputBibliographyOfHits, m_bQueryOnlyFiles, m_bResumeOnIndexErrors, m_bShowNumberOfRelevantDocuments, m_bUseDwdsThesaurus, m_bUseIndention, m_bUseParagraphTagToDivide, CBiblIndex::m_DefaultAttrName, m_HtmlHighlighting, m_IndexType, m_IndicesToShow, m_InternetPathPrefix, m_InterpDelimiter, m_Language, m_LeftKwicContextSize, m_LocalPathPrefix, m_MaxCachedHitsCount, m_MaxQueryCacheSize, CStringIndexator::m_MaxRegExpExpansionSize, m_NearRank, m_NumberOfKwicLinesInSnippets, m_OpDefaultIndexNames, CStringIndexator::m_Path, m_PcreCharacterTables, m_PositionRank, m_RightKwicContextSize, m_ServerInfo, m_TableHighlighting, m_TextHighlighting, m_TfIdfRank, m_TokenDelimiter, m_Txd, m_UserMaxInputLoadIndexSize, m_UserMaxTokenCountInOnePeriod, m_Utf8, morphEnglish, morphGeneric, morphUnknown, MorphXML_Index, CHighlightTags::ReadFromString(), ReadIndexTypeFromStr(), CHitBorders::RegisterBorderIndices(), CStringIndexator::RegisterChunkIndex(), CBiblIndex::RegisterFreeBiblAttributes(), CStringIndexator::RegisterIndexAliases(), RegisterIndicesToShow(), CStringIndexator::RegisterStringIndices(), CBiblIndex::RegisterTextAreas(), RelativeFileName(), RmlMakeLower(), RmlPcreMakeTables(), CBiblIndex::SetRegexOptions(), StringToBool(), TabFormat_Index, TextAreaOptionFieldName, CHighlightTags::ToString(), and unescapeCString().

Referenced by CConcIndexator::CreateAsUnion(), and LoadOptionsFromFile().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ InitDefaultOptions()

void CConcordance::InitDefaultOptions ( )

protected

References TxDispatcher::clear(), DefaultKwicContextSize, DefaultMaxInputLoadIndexSize, DefaultMaxTokenCountInOnePeriod, DWDS_Index, m_bAllowCountByTokenAttributes, m_bAllowUnsafeQueries, m_bArchiveIndex, m_bCaseSensitive, m_bDisableDefaultQueryLexicalExpansion, m_bDwdsCorpusInterface, m_bEmptyLineIsSentenceDelim, m_bGutenbergInterface, m_BiblIndex, m_bIndexChunks, m_bIndexMorphPatterns, m_bIndexPunctuation, m_bLemmaQueryUsesMorphPattern, CStringIndexator::m_bMemoryMap, m_bNoContextOperator, m_bOutputBibliographyOfHits, m_bQueryOnlyFiles, m_bResumeOnIndexErrors, m_bShowNumberOfRelevantDocuments, m_bUseDwdsThesaurus, m_bUseIndention, m_bUseParagraphTagToDivide, CBiblIndex::m_DefaultAttrName, CHighlightTags::m_FirstCloser, CHighlightTags::m_FirstOpener, m_HtmlHighlighting, m_IndexType, m_InterpDelimiter, m_Language, m_LeftKwicContextSize, m_MaxCachedHitsCount, m_MaxQueryCacheSize, m_NearRank, m_NumberOfKwicLinesInSnippets, m_OpDefaultIndexNames, CStringIndexator::m_Path, m_PositionRank, CHighlightTags::m_RestCloser, CHighlightTags::m_RestOpener, m_RightKwicContextSize, m_ServerInfo, m_TableHighlighting, m_TextHighlighting, m_TfIdfRank, m_Timestamp, m_TokenDelimiter, m_Txd, m_UserMaxInputLoadIndexSize, m_UserMaxTokenCountInOnePeriod, m_Utf8, and morphUnknown.

Referenced by CConcIndexator::CConcIndexator().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ SaveOptionsToString()

string CConcordance::SaveOptionsToString ( ) const

protected

saves options to a string

References TxDispatcher::configString(), DefaultKwicContextSize, Format(), CHitBorders::GetBorderIndicesString(), CBiblIndex::GetFreeBibiAttributesDescr(), CStringIndexator::GetIndexAliasString(), GetIndexTypeStr(), CStringIndexator::GetIndicesString(), GetIndicesToShowStr(), GetStringByLanguage(), CBiblIndex::GetTextAreasDescr(), m_bAllowCountByTokenAttributes, m_bAllowUnsafeQueries, m_bArchiveIndex, m_bCaseSensitive, m_bDisableDefaultQueryLexicalExpansion, m_bDwdsCorpusInterface, m_bEmptyLineIsSentenceDelim, m_bGutenbergInterface, m_BiblIndex, m_bIndexChunks, m_bIndexMorphPatterns, m_bIndexPunctuation, CStringIndexator::m_bMemoryMap, m_bNoContextOperator, m_bOutputBibliographyOfHits, m_bQueryOnlyFiles, m_bResumeOnIndexErrors, m_bShowNumberOfRelevantDocuments, m_bUseDwdsThesaurus, m_bUseIndention, m_bUseParagraphTagToDivide, CHighlightTags::m_bWasReadFromString, CBiblIndex::m_DefaultAttrName, m_HtmlHighlighting, m_InternetPathPrefix, m_InterpDelimiter, m_Language, m_LeftKwicContextSize, m_LocalPathPrefix, m_MaxCachedHitsCount, m_MaxQueryCacheSize, CStringIndexator::m_MaxRegExpExpansionSize, m_NearRank, m_NumberOfKwicLinesInSnippets, m_OpDefaultIndexNames, m_PositionRank, m_RightKwicContextSize, m_TableHighlighting, m_TextHighlighting, m_TfIdfRank, m_Txd, m_UserMaxInputLoadIndexSize, m_UserMaxTokenCountInOnePeriod, m_Utf8, morphUnknown, and CHighlightTags::ToString().

Referenced by CConcIndexator::CreateAsUnion(), HasEqualOptions(), SaveOptions(), and CConcIndexator::SplitProject().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ RegisterIndicesToShow()

void CConcordance::RegisterIndicesToShow ( const string & IndexListStr )

wrapper for IndicesToShow option; now accepts integer position (min=1), long name, short name, or alias

References Format(), and StringTokenizer::val().

Referenced by LoadOptionsFromString().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ GetIndicesToShowStr()

string CConcordance::GetIndicesToShowStr ( bool Positional = false ) const

get opt-style string declaration for IndicesToShow (empty if default)

References Format(), and CStringIndexSet::m_Name.

Referenced by LoadOptionsFromString(), and SaveOptionsToString().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ GetRegexOptions()

RML_RE::Options CConcordance::GetRegexOptions ( ) const

inline

return default pcre regex options

Referenced by CQueryTokenNode::BuildRegExp(), CQueryOptions::CheckSatisfiable(), and LoadOptionsFromString().

Here is the caller graph for this function:

◆ IsDwdsCorpusInterface()

bool CConcordance::IsDwdsCorpusInterface ( ) const

inline

return true, if DDC outputs results in DWDS format

◆ IsGutenbergInterface()

bool CConcordance::IsGutenbergInterface ( ) const

inline

return true, if DDC outputs results in Gutenberg project format

◆ HasContextOperator()

bool CConcordance::HasContextOperator ( ) const

inline

return true, if query context operator (#Cntxt) is switched off

Referenced by CDDCLeafServer::handle__info().

Here is the caller graph for this function:

◆ UseDwdsThesaurus()

bool CConcordance::UseDwdsThesaurus ( ) const

inline

return true, if DWDS thesaurus is enabled (index "Thes")

Referenced by CDDCLeafServer::handle__info(), and CConcIndexator::StartIndexing().

Here is the caller graph for this function:

◆ OutputBibliographyOfHits()

bool CConcordance::OutputBibliographyOfHits ( ) const

inline

return true, if DDC should output bibliographical information for hits instead of corpus file names

◆ IndexPunctuation()

bool CConcordance::IndexPunctuation ( ) const

inline

wrapper for m_bIndexPunctuation

Referenced by CDDCLeafServer::handle__info().

Here is the caller graph for this function:

◆ GetHtmlReference()

string CConcordance::GetHtmlReference ( size_t posFile ) const

get an HTML formatted reference to a corpus file

References Format().

Here is the call graph for this function:

◆ GetShortFilename()

string CConcordance::GetShortFilename ( size_t posFile ) const

get a reference to a corpus file without the common left prefix

◆ GetFileNameForCorpusFileNames()

string CConcordance::GetFileNameForCorpusFileNames ( ) const

get file name for storing corpus file names

References MakeFName().

Referenced by CConcIndexator::CreateAsUnion(), CConcIndexator::DestroyIndex(), ConcIndexatorInvoker::FinalizeIndex(), CConcIndexator::SaveCorpusFileList(), and CConcIndexator::SplitProject().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ GetFileNameForMaskedFiles()

string CConcordance::GetFileNameForMaskedFiles ( ) const

get file name for masked files (strings)

References MakeFName().

Referenced by CConcIndexator::DestroyIndex().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ GetFileNameForMaskedFileIds()

string CConcordance::GetFileNameForMaskedFileIds ( ) const

get file name for masked files (IDs, binary)

References MakeFName().

Referenced by CConcIndexator::CreateAsUnion(), CConcIndexator::DestroyIndex(), and CConcIndexator::SaveMaskedFileIds().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ GetTokenFields()

vector< string > CConcordance::GetTokenFields ( const COutputToken & tok )

parse a delimited token into fields by splitting on m_InterpDelimiter

References COutputToken::m_InterpStr, and COutputToken::m_TokenStr.

◆ GetCorpusFilesCount()

size_t CConcordance::GetCorpusFilesCount ( ) const

inline

get the number of indexed corpus files

References ddcCorpusList< OffT_ >::size().

Referenced by CQCount::CountUniversal(), CDDCLeafServer::handle__info(), and CConcIndexator::SplitProject().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ GetCorpusFile()

string CConcordance::GetCorpusFile ( CFileNo FileNo ) const

inline

get corpus file by index

◆ GetMaskedFilesCount()

size_t CConcordance::GetMaskedFilesCount ( ) const

inline

get count of masked files

References idfJson.

Referenced by CDDCLeafServer::handle__info().

Here is the caller graph for this function:

◆ LoadSourceFilesAndOptions()

void CConcordance::LoadSourceFilesAndOptions	(	string	FileName,
		bool	reallyReadSourceFiles = `true`
	)

load list of source files and parses option file (*.opt)

References ddcLogWarn, Format(), LoadFileToString(), MakeFName(), and CSourceFileHolder::ReadSourceFileList().

Referenced by ConcIndexatorInvoker::BuildIndexStart().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ LoadCorpusFiles()

void CConcordance::LoadCorpusFiles ( )

load list of corpus files (*.con)

References ddc_format_version_check(), ddcLogWarn, FileExists(), LoadFileToString(), and Trim().

Here is the call graph for this function:

◆ GetCommonFilePrefix()

string CConcordance::GetCommonFilePrefix ( ) const

(re-)compute common prefix of corpus files in m_CorpusFiles

Referenced by CConcIndexator::SaveCorpusFileList().

Here is the caller graph for this function:

◆ LoadMaskedFiles()

void CConcordance::LoadMaskedFiles ( )

load list of masked (deleted)Corpus File Definition

References ddcVecFile< T >::begin(), ddcLogDebug, ddcLogWarn, ddcVecFile< T >::end(), FileExists(), Format(), ddcCorpusList< OffT_ >::NO_ID, ddcVecFile< T >::open(), ddcVecFile< T >::size(), and Trim().

Here is the call graph for this function:

◆ LoadOptionsFromFile()

void CConcordance::LoadOptionsFromFile ( const string & OptFile )

loads options from a named file (calls LoadOptionsFromString())

References Format(), LoadFileToString(), and LoadOptionsFromString().

Here is the call graph for this function:

◆ LoadProject()

void CConcordance::LoadProject	(	string	FileName,
		bool	includeSourceFiles = `true`
	)

loads everything

References Format().

Referenced by ConcIndexatorInvoker::BuildOnlyMorphIndex().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ UpdateTimestamp()

time_t CConcordance::UpdateTimestamp ( const char * filename )

update m_Timestamp to mtime of Filename if it is newer than the current m_Timestamp;

Returns: new m_Timestamp

References FileMTime().

Here is the call graph for this function:

◆ DumpBibliography()

void CConcordance::DumpBibliography ( FILE * f = stdout ) const

dump loaded metadata to a stream (JSON)

◆ DumpFileBibliography()

string CConcordance::DumpFileBibliography ( DWORD FileNo ) const

dump file metadata to a string (JSON)

References Format(), jsonStr(), CBibliography::m_DateStr, CBibliography::m_OrigBibl, CBibliography::m_ScanBibl, CBibliography::m_StartPageInfo, and UnknownPageNumber.

Here is the call graph for this function:

◆ DumpFileIndexJson()

void CConcordance::DumpFileIndexJson	(	DWORD	FileNo,
		FILE *	f = `stdout`
	)		const

dump file data to a file (JSON)

References ddcVecFile< T >::end(), jsonStr(), and CPageNumber::m_StartTokenNo.

Here is the call graph for this function:

◆ DumpIndex()

void CConcordance::DumpIndex	(	string	dirname,
		CIndexDumpFormat	fmt = `idfJson`
	)		const

dump index data to a directory (format-dependent)

References errRuntime, Format(), idfJson, idfTabs, and StrError().

Here is the call graph for this function:

◆ DumpIndexToSingleTabFile()

void CConcordance::DumpIndexToSingleTabFile ( FILE * outfp ) const

dump index data to a single tab formatted file

◆ SaveOptions()

bool CConcordance::SaveOptions ( string FileName ) const

saves options to option file (*.opt)

References MakeFName(), and SaveOptionsToString().

Referenced by CConcIndexator::CreateAsUnion().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ GetAllOccurrences()

bool CConcordance::GetAllOccurrences	(	vector< CTokenNo > &	occurrences,
		size_t	searchPeriodNo
	)		const

moo: get a vector of all occurrences in a given search period; used by universal wildcard (*) queries

Referenced by CQueryTokenNode::EvaluateWithoutHits().

Here is the caller graph for this function:

◆ GetOccurrencesByPosition()

bool CConcordance::GetOccurrencesByPosition	(	const string &	BreakName,
		int	anchor,
		vector< CTokenNo > &	occurrences,
		size_t	searchPeriodNo
	)		const

moo: search named break collection for matching positions, used by anchor queries

References ddcVecFile< T >::begin(), ddcVecFile< T >::end(), errRuntime, and CHitBorders::CBreakCollection::m_BreakOffsets.

Referenced by CQueryTokenNode::EvaluateWithoutHits().

Here is the call graph for this function:

Here is the caller graph for this function:

◆ UseTabFormatForLoading()

bool CConcordance::UseTabFormatForLoading ( ) const

inline

Referenced by CDocumentIterator::NextDocument().

Here is the caller graph for this function:

Member Data Documentation

◆ m_PcreCharacterTables

vector<BYTE> CConcordance::m_PcreCharacterTables

private

a table of character properties for regular expressions which depend on CConcIndexator::m_Language

Referenced by LoadOptionsFromString().

◆ m_bDwdsCorpusInterface

bool CConcordance::m_bDwdsCorpusInterface

private

if m_bDwdsCorpusInterface is on, the program outputs results in DWDS format

Referenced by InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_bGutenbergInterface

bool CConcordance::m_bGutenbergInterface

private

if m_bGutenbergInterface is on, the program outputs results in a format of Gutenberg project

Referenced by InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_bNoContextOperator

bool CConcordance::m_bNoContextOperator

private

should we switch off context operator (#Cntxt) due copyright

Referenced by InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_bOutputBibliographyOfHits

bool CConcordance::m_bOutputBibliographyOfHits

private

Should we show bibliography of the hits instead of filename.

Referenced by InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_InternetPathPrefix

string CConcordance::m_InternetPathPrefix

private

Referenced by LoadOptionsFromString(), and SaveOptionsToString().

◆ m_LocalPathPrefix

string CConcordance::m_LocalPathPrefix

private

Referenced by LoadOptionsFromString(), and SaveOptionsToString().

◆ m_CommonFilePrefix

string CConcordance::m_CommonFilePrefix

private

◆ m_IndexType

DDCIndexTypeEnum CConcordance::m_IndexType

protected

the type of index

Referenced by GetIndexTypeStr(), CConcIndexator::IndexOneFile(), InitDefaultOptions(), LoadOptionsFromString(), and ReadIndexTypeFromStr().

◆ m_bIndexPunctuation

bool CConcordance::m_bIndexPunctuation

protected

Enables indexing all punctuation marks.

Referenced by InitDefaultOptions(), CConcIndexator::IsDWDSToken(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_bUseParagraphTagToDivide

bool CConcordance::m_bUseParagraphTagToDivide

protected

Enables using "<p>" tag as a paragraph delimiter.

Referenced by InitDefaultOptions(), CConcIndexator::InitGraphan(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_bEmptyLineIsSentenceDelim

bool CConcordance::m_bEmptyLineIsSentenceDelim

protected

if m_bEmptyLineIsSentenceDelim is on, every empty line in the input file is considered to be the end of the sentence.

Referenced by InitDefaultOptions(), CConcIndexator::InitGraphan(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_bUseIndention

bool CConcordance::m_bUseIndention

protected

if m_bUseIndention is on, the program tries to find paragraphs using indentions

Referenced by InitDefaultOptions(), CConcIndexator::InitGraphan(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_UserMaxTokenCountInOnePeriod

DWORD CConcordance::m_UserMaxTokenCountInOnePeriod

protected

The maximal number of occurrences in one subcorpora (defined by user)

Referenced by CConcIndexator::GetMaxTokenCountInOnePeriod(), InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_UserMaxInputLoadIndexSize

DWORD CConcordance::m_UserMaxInputLoadIndexSize

protected

The maximal number of occurrences in the input load index, by default 400000.

Referenced by CConcIndexator::GetMaxInputLoadIndexSize(), InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_bUseDwdsThesaurus

bool CConcordance::m_bUseDwdsThesaurus

protected

Enables indexing and querying using DWDS Thesaurus.

Referenced by CConcIndexator::IndexTextOrHtmlFile(), InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_Language

MorphLanguageEnum CConcordance::m_Language

the language of the corpus

Referenced by CQueryTokenNode::CreateLemmaPattern(), CConcIndexator::CreateMorphIndexWrapper(), CQueryTokenNode::CreateThesPattern(), CDDCLeafServer::handle__info(), InitDefaultOptions(), CConcIndexator::InitGraphan(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_bIndexMorphPatterns

bool CConcordance::m_bIndexMorphPatterns

Enables the index of morph patterns.

Referenced by ConcIndexatorInvoker::FinalizeIndex(), CDDCLeafServer::handle__info(), InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_bIndexChunks

bool CConcordance::m_bIndexChunks

Enables indexing and querying using chunks.

Referenced by CDDCLeafServer::handle__info(), CConcIndexator::IndexOneTableTextArea(), InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_bCaseSensitive

bool CConcordance::m_bCaseSensitive

if true, then the default search is case sensitive

Referenced by CDDCLeafServer::handle__info(), InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_bShowNumberOfRelevantDocuments

bool CConcordance::m_bShowNumberOfRelevantDocuments

if true, then DDC always calculates the number of documents, where at lease one hit is found

Referenced by InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_bQueryOnlyFiles

bool CConcordance::m_bQueryOnlyFiles

prohibits sentence break collection under DWDS_Index or MorphXML_Index

Referenced by CConcIndexator::IndexTextOrHtmlFile(), InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_bArchiveIndex

bool CConcordance::m_bArchiveIndex

sets that index should be archived under DWDS_Index or MorphXML_Index

Referenced by InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_bResumeOnIndexErrors

bool CConcordance::m_bResumeOnIndexErrors

if true, CConcIndexatorInvoker skips source documents with errors

Referenced by ConcIndexatorInvoker::FinalizeIndex(), ConcIndexatorInvoker::IndexFile(), CConcIndexator::IndexMorphXml(), CConcIndexator::IndexOneTableTextArea(), CConcIndexator::IndexTextOrHtmlFile(), InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_CorpusFiles

ddcCorpusList CConcordance::m_CorpusFiles

Corpus files

Referenced by CConcIndexator::CalculateSearchPeriods(), CConcIndexator::CreateAsUnion(), CConcIndexator::DestroyIndex(), ConcIndexatorInvoker::IndexFile(), CConcIndexator::SaveCorpusFileList(), and CConcIndexator::SplitProject().

◆ m_MaskedFiles

CMaskedFileSet CConcordance::m_MaskedFiles

Referenced by CQCount::CountUniversal(), CConcIndexator::CreateAsUnion(), CConcIndexator::DestroyIndex(), CConcIndexator::SaveMaskedFileIds(), and CConcIndexator::SplitProject().

◆ m_BiblIndex

CConcXml CConcordance::m_BiblIndex

a member which holds a index for bibliographical information

Referenced by CQueryOptions::Compile(), CQFBiblSort::Compile(), CQFHasFieldValue::Compile(), CQFHasFieldRegex::Compile(), CQFHasFieldSet::Compile(), CQueryNode::ConvertOccurrencesToHits(), CQueryNode::ConvertOccurrencesToHitsForPatterns(), CQCount::CountUniversal(), CConcIndexator::CreateAsUnion(), CQFSort::GetBiblConstant(), CDDCLeafServer::handle__info(), CConcIndexator::IndexFreeIndex(), CConcIndexator::IndexMorphXml(), CConcIndexator::IndexTextOrHtmlFile(), InitDefaultOptions(), CConcIndexator::LoadFileIntoGraphan(), LoadOptionsFromString(), CConcIndexator::LoadXmlFile(), CConcIndexator::NormalEndIndexing(), CQFSort::ResolveAttributeName(), SaveOptionsToString(), CConcIndexator::SplitProject(), CConcIndexator::StartIndexing(), and CConcIndexator::TerminateIndexing().

◆ m_HtmlHighlighting

CHighlightTags CConcordance::m_HtmlHighlighting

highlighting tags for CConcHolder::m_ResultFormat == DDC_ResultHTML

Referenced by InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_TextHighlighting

CHighlightTags CConcordance::m_TextHighlighting

highlighting delimeters for CConcHolder::m_ResultFormat == DDC_ResultText

Referenced by InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_TableHighlighting

CHighlightTags CConcordance::m_TableHighlighting

highlighting delimeters for CConcHolder::m_ResultFormat == DDC_ResultTable

Referenced by InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_bDisableDefaultQueryLexicalExpansion

bool CConcordance::m_bDisableDefaultQueryLexicalExpansion

if true, then no default lexical expansion fo querz words occurs

Referenced by InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_LeftKwicContextSize

int CConcordance::m_LeftKwicContextSize

the size of the left context of the highlighted words in document search

Referenced by InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_RightKwicContextSize

int CConcordance::m_RightKwicContextSize

the size of the right context of the highlighted words in document search

Referenced by InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_NumberOfKwicLinesInSnippets

int CConcordance::m_NumberOfKwicLinesInSnippets

the maximal number of kwic lines in file snippets

Referenced by InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_TfIdfRank

double CConcordance::m_TfIdfRank

the parameter for TfIdf ranking

Referenced by InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_NearRank

double CConcordance::m_NearRank

the parameter for Near ranking

Referenced by InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_PositionRank

double CConcordance::m_PositionRank

the parameter for Position ranking

Referenced by InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_InterpDelimiter

string CConcordance::m_InterpDelimiter

delimiter to use between token index fields in output

Referenced by CDDCLeafServer::handle__info(), InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_TokenDelimiter

string CConcordance::m_TokenDelimiter

delimiter to use between tokens in output

Referenced by CDDCLeafServer::handle__info(), InitDefaultOptions(), and LoadOptionsFromString().

◆ m_Utf8

bool CConcordance::m_Utf8

whether to assume indexed data is utf8 encoded (default=no)

Referenced by CDDCLeafServer::handle__info(), InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_bAllowUnsafeQueries

bool CConcordance::m_bAllowUnsafeQueries

potentially unsafe queries will throw an exception unless this is true (default=false)

Referenced by CQTokFile::Create(), CDDCLeafServer::handle__info(), InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_bAllowCountByTokenAttributes

bool CConcordance::m_bAllowCountByTokenAttributes

using any token attribute as a count-key will throw an exception unless this is true (default=true)

Referenced by CQCountKeyExprToken::Compile(), CDDCLeafServer::handle__info(), InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_bLemmaQueryUsesMorphPattern

bool CConcordance::m_bLemmaQueryUsesMorphPattern

interpret "%foo" queries using MorphPattern? (default=true)

Referenced by CQTokLemma::Create(), InitDefaultOptions(), and LoadOptionsFromString().

◆ m_IndicesToShow

vector<size_t> CConcordance::m_IndicesToShow

indices to show for Free_Index

Referenced by CDDCLeafServer::handle__info(), and LoadOptionsFromString().

◆ m_Timestamp

time_t CConcordance::m_Timestamp

moo: timestamp of project *._con file

Referenced by CDDCLeafServer::handle__info(), and InitDefaultOptions().

◆ m_MaxCachedHitsCount

size_t CConcordance::m_MaxCachedHitsCount

moo: maximum number of hits in a CConcHolder cache entry – query results with more than MaxCachedHitsCount hits will not be cached (default=512)

Referenced by CConcSessionContext::CacheGet(), CConcSessionContext::CacheSet(), InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_MaxQueryCacheSize

size_t CConcordance::m_MaxQueryCacheSize

moo: maximum number of queries to be cached by an associated CConcHolder (default=512)

Referenced by CConcSessionContext::CacheSet(), InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_Txd

TxDispatcher CConcordance::m_Txd

term expansion dispatcher; should define at least an entry for "default"

Referenced by CConcSession::GetTxDispatcher(), InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_OpDefaultIndexNames

map<string, string> CConcordance::m_OpDefaultIndexNames

maps token-query operators to default index names; keys are as returned by CQToken::OperatorKey()

"_" ~ CQTokInfl (Token)
"@_" ~ CQTokExact (Token)
"%_" ~ CQTokLemma (Lemma)
"/_/" ~ CQTokRegex, CQTokSuffix, CQTokPrefix, CQTokInfix (Token)
"[_]" ~ CQTokMorph (MorphPattern)
":{_}" ~ CQTokThes (Thes)
"^_" ~ CQTokChunk (Chunk)
"<_" ~ CQTokFile (Token)
"." ~ CQTokAnchor (sentence: should resolve to a break name rather than a token-level index name)
"*" ~ generic fallback (Token)

Referenced by CQToken::BreakName(), CDDCLeafServer::handle__info(), CQToken::IndexName(), InitDefaultOptions(), LoadOptionsFromString(), and SaveOptionsToString().

◆ m_ServerInfo

map<string, pair<bool, string> > CConcordance::m_ServerInfo

maps symbolic keys to string constants to be included in corpus 'info' response as info.user.KEY=VAL values are pairs (isFile,Value) s.t. Value is filename iff isFile is a true value, otherwise a literal value

Referenced by CDDCLeafServer::handle__info(), InitDefaultOptions(), and LoadOptionsFromString().

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

Public Member Functions

Public Attributes

Protected Types

Protected Member Functions

Protected Attributes

Private Member Functions

Private Attributes

Additional Inherited Members

Detailed Description

Member Enumeration Documentation

◆ DDCIndexTypeEnum

Constructor & Destructor Documentation

◆ CConcordance()

◆ ~CConcordance()

Member Function Documentation

◆ GetBiblIndexFileName()

◆ GetBiblFileName()

◆ HasEqualOptions()

◆ GetIndexTypeStr()

◆ ReadIndexTypeFromStr()

◆ DumpFileIndexTabs()

◆ AssertHasPath()

◆ LoadOptionsFromString()

◆ InitDefaultOptions()

◆ SaveOptionsToString()

◆ RegisterIndicesToShow()

◆ GetIndicesToShowStr()

◆ GetRegexOptions()

◆ IsDwdsCorpusInterface()

◆ IsGutenbergInterface()

◆ HasContextOperator()

◆ UseDwdsThesaurus()

◆ OutputBibliographyOfHits()

◆ IndexPunctuation()

◆ GetHtmlReference()

◆ GetShortFilename()

◆ GetFileNameForCorpusFileNames()

◆ GetFileNameForMaskedFiles()

◆ GetFileNameForMaskedFileIds()

◆ GetTokenFields()

◆ GetCorpusFilesCount()

◆ GetCorpusFile()

◆ GetMaskedFilesCount()

◆ LoadSourceFilesAndOptions()

◆ LoadCorpusFiles()

◆ GetCommonFilePrefix()

◆ LoadMaskedFiles()

◆ LoadOptionsFromFile()

◆ LoadProject()

◆ UpdateTimestamp()

◆ DumpBibliography()

◆ DumpFileBibliography()

◆ DumpFileIndexJson()

◆ DumpIndex()

◆ DumpIndexToSingleTabFile()

◆ SaveOptions()

◆ GetAllOccurrences()

◆ GetOccurrencesByPosition()

◆ UseTabFormatForLoading()

Member Data Documentation

◆ m_PcreCharacterTables

◆ m_bDwdsCorpusInterface

◆ m_bGutenbergInterface

◆ m_bNoContextOperator

◆ m_bOutputBibliographyOfHits

◆ m_InternetPathPrefix

◆ m_LocalPathPrefix

◆ m_CommonFilePrefix

◆ m_IndexType

◆ m_bIndexPunctuation

◆ m_bUseParagraphTagToDivide

◆ m_bEmptyLineIsSentenceDelim

◆ m_bUseIndention

◆ m_UserMaxTokenCountInOnePeriod

◆ m_UserMaxInputLoadIndexSize

◆ m_bUseDwdsThesaurus

◆ m_Language

◆ m_bIndexMorphPatterns

◆ m_bIndexChunks

◆ m_bCaseSensitive