|
| typedef map< string, string > | IndexAliasMap |
| | typedef for index alias maps More...
|
| |
| typedef map< string, CStringIndexSet * > | IndexMap |
| | typedef for index symbol table More...
|
| |
| | 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 |
| |
| | 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...
|
| |
| 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...
|
| |
| | 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 |
| |
| 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...
|
| |
| 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...
|
| |
| 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...
|
| |
| 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...
|
| |
| vector< CTokenNo > | m_SearchPeriods |
| | search periods of the corpus More...
|
| |
| 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 |
| |
| vector< string > | m_SourceFiles |
| | Source files More...
|
| |
| bool | m_bModifiedListOfFiles |
| |
Protected Member Functions inherited from CConcordance
