CConcXml Class Reference

#include <Bibliography.h>

List of all members.

Classes

• class CFreeBiblIndex
• class CFreeBiblStringIndex
• class CTextArea

Public Member Functions

• CConcXml ()
• ~CConcXml ()
• void FreeBiblIndices ()

  clears m_FreeBiblIndices
  

• bool Start (string ProjectFileName)

  initialize building bibliography for corpus ProjectFileName
  

• bool AddIndexItem (const CBibliography &Bibliography)

  add one record Bibliography
  

• bool FinalSaveBibliography ()

  save all indices and stop indexing bibliography
  

• void ExitWithoutSave ()

  stop indexing bibliography an removes index files
  

• bool RegisterFreeBiblAttributes (string fields, string &ErrorStr)

  initializes free bibliographical attribute descriptions
  

• bool RegisterTextAreas (string fields, string &ErrorStr)

  initializes free text areas descriptions
  

• string GetFreeBibiAttributesDescr () const

  return free bibliographical attribute description
  

• string GetTextAreasDescr () const

  return full text area description
  

• void SetPath (string ProjectFileName)
• bool LoadBibl (string Path, size_t FileBreaksSize)
• CBibliography GetFullBibliographyOfHit (size_t FileNo) const

  returns the bibliographical record
  

• bool CheckBibl (size_t FileBreaksNumber) const

  Check bibliographical references.
  

• bool UniteBibliography (const CConcXml &B1, const CConcXml &B2)
• bool GetValueFromBiblSet (const RML_RE::Options &RegexOpts, string Value, CDDCFilterWithBounds &Filter) const

  initializes CDDCFilterWithBounds::m_LevelStart and CDDCFilterWithBounds::m_LevelEnd for filtering by bibliographical information
  

• bool LoadXmlAndReadBibliography (TiXmlDocument &doc, const char *pFileBuffer, CBibliography &Bibl, string &strError)

  load xml file into TiXmlDocument& doc and load bibliographical fileds to CBibliography& Bibl
  

• bool ReadMorphXmlFileIntoGraTable (string FileName, const char *pFileBuffer, vector< CXmlToken > &GraTable, string &strError, CBibliography &Bibl)

  load xml file under MorphXML_Index into vector<CXmlToken>& GraTable
  

• string GetVisibleFreeHeaderBiblAttributes (size_t FileNo, string Delim) const

  return values of all visible free bibliographical attributes for the given FileNo delimited by "Delim"
  

• string GetFreeHeaderBiblAttributesWithNames (size_t FileNo, char Delim) const

  return names and values of all free bibliographical attributes for the given FileNo delimited by "Delim"
  

• string GetFreeHeaderBiblAttributesJson (size_t FileNo, bool assume_utf8=true) const

  return names and values of all free bibliographical attributes for the given FileNo as JSON (without enclosing {})
  

• void SetFreeBiblAttribsEmpty (CBibliography &Bibl)

  set all free bibliographical attributes to ""
  

• bool GetTextAreaElements (const TiXmlDocument &doc, vector< TiXmlElement * > &Result, string &strError) const

  return all text area elements for this document ("doc")
  

• size_t GetTextAreasCount () const

  return all text area names
  

• int ProcessTextAreaNoInQueryStr (string &Query) const

  return text area index, which is specified in the input query (if nothing is specified, it returns UnknownTextAreaNo)
  

• void InitLessByDate (vector< CHit > &Hits) const
• void InitGreaterByDate (vector< CHit > &Hits) const
• void InitLessByBiblIntegerField (string FreeBiblAttribName, vector< CHit > &Hits) const
• void InitGreaterByBiblIntegerField (string FreeBiblAttribName, vector< CHit > &Hits) const
• void InitNoSort (vector< CHit > &Hits) const
• bool IsRegisteredBiblField (string FreeBiblAttribName) const

Private Types

• typedef map< string,
  CFreeBiblIndex * > FreeBiblStringMap

Private Member Functions

• void DeleteFiles ()
• string GetBiblIndexFileName () const
• string GetBiblFileName () const
• string GetBiblDateIndexFileName () const
• int GetTextAreaByName (const string &Name) const

Private Attributes

• FreeBiblStringMap m_FreeBiblIndices
• vector< file_off_t > m_EndOffsetsInBiblFile
• vector< int > m_Dates
• FILE * m_BiblBodyFile
• string m_Path
• size_t m_BiblBodyFileSize
• string m_OrigXPath
• string m_ScanXPath
• string m_DateXPath
• string m_StartPageXPath
• vector< CTextArea > m_TextAreas

---

Member Typedef Documentation

typedef map<string, CFreeBiblIndex*> CConcXml::FreeBiblStringMap [private]

---

Constructor & Destructor Documentation

CConcXml::CConcXml

(

)

References m_BiblBodyFile.

CConcXml::~CConcXml

(

)

References FreeBiblIndices(), and m_BiblBodyFile.

Here is the call graph for this function:

---

Member Function Documentation

void CConcXml::DeleteFiles

(

)

[private]

References GetBiblDateIndexFileName(), GetBiblFileName(), GetBiblIndexFileName(), m_FreeBiblIndices, and m_Path.

Referenced by ExitWithoutSave().

Here is the call graph for this function:

Here is the caller graph for this function:

string CConcXml::GetBiblIndexFileName

(

)

const [private]

References m_Path, and MakeFName().

Referenced by DeleteFiles(), FinalSaveBibliography(), LoadBibl(), and UniteBibliography().

Here is the call graph for this function:

Here is the caller graph for this function:

string CConcXml::GetBiblFileName

(

)

const [private]

References m_Path, and MakeFName().

Referenced by CheckBibl(), DeleteFiles(), LoadBibl(), Start(), and UniteBibliography().

Here is the call graph for this function:

Here is the caller graph for this function:

string CConcXml::GetBiblDateIndexFileName

(

)

const [private]

References m_Path, and MakeFName().

Referenced by DeleteFiles(), FinalSaveBibliography(), LoadBibl(), and UniteBibliography().

Here is the call graph for this function:

Here is the caller graph for this function:

int CConcXml::GetTextAreaByName

(

const string &

Name

)

const [private]

References m_TextAreas, and UnknownTextAreaNo.

Referenced by ProcessTextAreaNoInQueryStr().

Here is the caller graph for this function:

void CConcXml::FreeBiblIndices

(

)

clears m_FreeBiblIndices

References m_FreeBiblIndices.

Referenced by RegisterFreeBiblAttributes(), and ~CConcXml().

Here is the caller graph for this function:

bool CConcXml::Start

(

string

ProjectFileName

)

initialize building bibliography for corpus ProjectFileName

References GetBiblFileName(), m_BiblBodyFile, m_BiblBodyFileSize, m_Dates, m_EndOffsetsInBiblFile, m_FreeBiblIndices, and SetPath().

Referenced by CConcIndexator::StartIndexing().

Here is the call graph for this function:

Here is the caller graph for this function:

bool CConcXml::AddIndexItem

(

const CBibliography &

Bibliography

)

add one record Bibliography

References CBibliography::ConvertDateToInt(), CBibliography::m_BiblAttribs, m_BiblBodyFile, m_BiblBodyFileSize, m_Dates, m_EndOffsetsInBiblFile, m_FreeBiblIndices, and CBibliography::WriteToString().

Referenced by CConcIndexator::IndexMorphXml(), CConcIndexator::IndexTable(), and CConcIndexator::IndexTextOrHtmlFile().

Here is the call graph for this function:

Here is the caller graph for this function:

bool CConcXml::FinalSaveBibliography

(

)

save all indices and stop indexing bibliography

References FileExists(), GetBiblDateIndexFileName(), GetBiblIndexFileName(), m_BiblBodyFile, m_BiblBodyFileSize, m_Dates, m_EndOffsetsInBiblFile, m_FreeBiblIndices, m_Path, and WriteVector().

Referenced by CConcIndexator::NormalEndIndexing().

Here is the call graph for this function:

Here is the caller graph for this function:

void CConcXml::ExitWithoutSave

(

)

stop indexing bibliography an removes index files

References DeleteFiles(), m_BiblBodyFile, and m_BiblBodyFileSize.

Referenced by CConcIndexator::TerminateIndexing().

Here is the call graph for this function:

Here is the caller graph for this function:

bool CConcXml::RegisterFreeBiblAttributes	(	string	fields,
		string &	ErrorStr
	)

initializes free bibliographical attribute descriptions

References CheckXPath(), Format(), FreeBiblAttribOptionFieldName, FreeBiblIndices(), IntegerTypeStr, CConcXml::CFreeBiblIndex::m_bShowInHeader, m_DateXPath, m_FreeBiblIndices, CConcXml::CFreeBiblIndex::m_Name, m_OrigXPath, m_ScanXPath, m_StartPageXPath, CConcXml::CFreeBiblIndex::m_Xpath, Name, StringTypeStr, and Trim().

Referenced by CConcIndexator::LoadOptionsFromString(), and UniteBibliography().

Here is the call graph for this function:

Here is the caller graph for this function:

bool CConcXml::RegisterTextAreas	(	string	fields,
		string &	ErrorStr
	)

initializes free text areas descriptions

References CheckXPath(), CConcXml::CTextArea::m_TextAreaName, m_TextAreas, CConcXml::CTextArea::m_Xpath, morphEnglish, RmlMakeLower(), TextAreaOptionFieldName, and Trim().

Referenced by CConcIndexator::LoadOptionsFromString(), and UniteBibliography().

Here is the call graph for this function:

Here is the caller graph for this function:

string CConcXml::GetFreeBibiAttributesDescr

(

)

const

return free bibliographical attribute description

References Format(), FreeBiblAttribOptionFieldName, m_DateXPath, m_FreeBiblIndices, m_OrigXPath, m_ScanXPath, and m_StartPageXPath.

Referenced by CConcIndexator::LoadOptionsFromString(), CConcIndexator::SaveOptionsToString(), and UniteBibliography().

Here is the call graph for this function:

Here is the caller graph for this function:

string CConcXml::GetTextAreasDescr

(

)

const

return full text area description

References Format(), m_TextAreas, and TextAreaOptionFieldName.

Referenced by CConcIndexator::LoadOptionsFromString(), and UniteBibliography().

Here is the call graph for this function:

Here is the caller graph for this function:

void CConcXml::SetPath

(

string

ProjectFileName

)

References m_Path.

Referenced by CConcIndexator::CreateAsUnion(), LoadBibl(), and Start().

Here is the caller graph for this function:

bool CConcXml::LoadBibl	(	string	Path,
		size_t	FileBreaksSize
	)

References ErrorMessage(), Format(), GetBiblDateIndexFileName(), GetBiblFileName(), GetBiblIndexFileName(), m_BiblBodyFile, m_Dates, m_EndOffsetsInBiblFile, m_FreeBiblIndices, m_Path, ReadVector(), and SetPath().

Referenced by CConcIndexator::LoadProject().

Here is the call graph for this function:

Here is the caller graph for this function:

CBibliography CConcXml::GetFullBibliographyOfHit

(

size_t

FileNo

)

const

returns the bibliographical record

References FSeek(), m_BiblBodyFile, m_EndOffsetsInBiblFile, and CBibliography::ReadFromString().

Referenced by CConcHolder::GenerateOneHitStringJson(), CConcHolder::ShowBibliographyForTable(), and CConcHolder::ShowBibliographyForTextOrHtml().

Here is the call graph for this function:

Here is the caller graph for this function:

bool CConcXml::CheckBibl

(

size_t

FileBreaksNumber

)

const

Check bibliographical references.

References FileSize(), GetBiblFileName(), and m_EndOffsetsInBiblFile.

Here is the call graph for this function:

bool CConcXml::UniteBibliography	(	const CConcXml &	B1,
		const CConcXml &	B2
	)

References AddFile(), FileExists(), FileSize(), GetBiblDateIndexFileName(), GetBiblFileName(), GetBiblIndexFileName(), GetFreeBibiAttributesDescr(), GetTextAreasDescr(), m_Dates, m_EndOffsetsInBiblFile, m_FreeBiblIndices, m_Path, RegisterFreeBiblAttributes(), RegisterTextAreas(), and WriteVector().

Referenced by CConcIndexator::CreateAsUnion().

Here is the call graph for this function:

Here is the caller graph for this function:

bool CConcXml::GetValueFromBiblSet	(	const RML_RE::Options &	RegexOpts,
		string	Value,
		CDDCFilterWithBounds &	Filter
	)			const

initializes CDDCFilterWithBounds::m_LevelStart and CDDCFilterWithBounds::m_LevelEnd for filtering by bibliographical information

References CDDCFilterWithBounds::m_bRegExp, CDDCFilterWithBounds::m_FreeBiblAttribName, m_FreeBiblIndices, and CDDCFilterWithBounds::m_SatisfiedValues.

Referenced by CQueryParser::ParseQueryOperators().

Here is the caller graph for this function:

bool CConcXml::LoadXmlAndReadBibliography	(	TiXmlDocument &	doc,
		const char *	pFileBuffer,
		CBibliography &	Bibl,
		string &	strError
	)

load xml file into TiXmlDocument& doc and load bibliographical fileds to CBibliography& Bibl

References CBibliography::CleanBibliography(), CBibliography::ConvertDateToInt(), TiXmlDocument::Error(), TiXmlDocument::ErrorCol(), TiXmlDocument::ErrorDesc(), TiXmlDocument::ErrorRow(), Format(), CBibliography::m_BiblAttribs, CBibliography::m_DateStr, m_DateXPath, m_FreeBiblIndices, CBibliography::m_OrigBibl, m_OrigXPath, CBibliography::m_ScanBibl, m_ScanXPath, CBibliography::m_StartPageInfo, m_StartPageXPath, TiXmlDocument::Parse(), ReadXmlField(), and UnknownPageNumber.

Referenced by CConcIndexator::IndexTable(), CConcIndexator::LoadXmlFile(), and ReadMorphXmlFileIntoGraTable().

Here is the call graph for this function:

Here is the caller graph for this function:

bool CConcXml::ReadMorphXmlFileIntoGraTable	(	string	FileName,
		const char *	pFileBuffer,
		vector< CXmlToken > &	GraTable,
		string &	strError,
		CBibliography &	Bibl
	)

load xml file under MorphXML_Index into vector<CXmlToken>& GraTable

References TiXmlNode::FirstChildElement(), Format(), GetTextAreaElements(), LoadXmlAndReadBibliography(), CXmlToken::m_Annots, CXmlMorphAnnot::m_GrammemsStr, CXmlMorphAnnot::m_Lemma, CXmlToken::m_Type, CXmlToken::m_WordStr, TiXmlNode::NextSiblingElement(), Trim(), and TiXmlNode::Value().

Referenced by CConcIndexator::IndexMorphXml().

Here is the call graph for this function:

Here is the caller graph for this function:

string CConcXml::GetVisibleFreeHeaderBiblAttributes	(	size_t	FileNo,
		string	Delim
	)			const

return values of all visible free bibliographical attributes for the given FileNo delimited by "Delim"

References CConcXml::CFreeBiblIndex::GetStringValue(), CConcXml::CFreeBiblIndex::m_bShowInHeader, and m_FreeBiblIndices.

Referenced by CConcHolder::ShowBibliographyForTextOrHtml().

Here is the call graph for this function:

Here is the caller graph for this function:

string CConcXml::GetFreeHeaderBiblAttributesWithNames	(	size_t	FileNo,
		char	Delim
	)			const

return names and values of all free bibliographical attributes for the given FileNo delimited by "Delim"

References CConcXml::CFreeBiblIndex::GetStringValue(), CConcXml::CFreeBiblIndex::m_bShowInHeader, m_FreeBiblIndices, and CConcXml::CFreeBiblIndex::m_Name.

Referenced by CConcHolder::ShowBibliographyForTable().

Here is the call graph for this function:

Here is the caller graph for this function:

string CConcXml::GetFreeHeaderBiblAttributesJson	(	size_t	FileNo,
		bool	assume_utf8 = true
	)			const

return names and values of all free bibliographical attributes for the given FileNo as JSON (without enclosing {})

References CConcXml::CFreeBiblIndex::GetStringValue(), jsonStr(), CConcXml::CFreeBiblIndex::m_bShowInHeader, m_FreeBiblIndices, and CConcXml::CFreeBiblIndex::m_Name.

Referenced by CConcHolder::GenerateOneHitStringJson().

Here is the call graph for this function:

Here is the caller graph for this function:

void CConcXml::SetFreeBiblAttribsEmpty

(

CBibliography &

Bibl

)

set all free bibliographical attributes to ""

References CBibliography::m_BiblAttribs, and m_FreeBiblIndices.

Referenced by CConcIndexator::LoadFileIntoGraphan().

Here is the caller graph for this function:

bool CConcXml::GetTextAreaElements	(	const TiXmlDocument &	doc,
		vector< TiXmlElement * > &	Result,
		string &	strError
	)			const

return all text area elements for this document ("doc")

References Format(), m_TextAreas, TiXmlDocument::RootElement(), TiXmlNode::ToElement(), and TinyXPath::XNp_xpath_node().

Referenced by CConcIndexator::IndexTable(), CConcIndexator::LoadXmlFile(), and ReadMorphXmlFileIntoGraTable().

Here is the call graph for this function:

Here is the caller graph for this function:

size_t CConcXml::GetTextAreasCount

(

)

const

return all text area names

References m_TextAreas.

Referenced by CQueryNode::ConvertOccurrencesToHits(), CQueryNode::ConvertOccurrencesToHitsForPatterns(), CConcIndexator::IndexTextOrHtmlFile(), and CConcIndexator::LoadXmlFile().

Here is the caller graph for this function:

int CConcXml::ProcessTextAreaNoInQueryStr

(

string &

Query

)

const

return text area index, which is specified in the input query (if nothing is specified, it returns UnknownTextAreaNo)

References GetTextAreaByName(), Trim(), and UnknownTextAreaNo.

Referenced by CQueryParser::ParseQuery().

Here is the call graph for this function:

Here is the caller graph for this function:

void CConcXml::InitLessByDate

(

vector< CHit > &

Hits

)

const

References m_Dates, CHit::m_FileNo, and CHit::m_OrderId.

Referenced by CConcHolder::InitOrderIDForHits().

Here is the caller graph for this function:

void CConcXml::InitGreaterByDate

(

vector< CHit > &

Hits

)

const

References m_Dates, CHit::m_FileNo, and CHit::m_OrderId.

Referenced by CConcHolder::InitOrderIDForHits().

Here is the caller graph for this function:

void CConcXml::InitLessByBiblIntegerField	(	string	FreeBiblAttribName,
		vector< CHit > &	Hits
	)			const

References CConcXml::CFreeBiblIndex::GetIntegerValue(), InitNoSort(), CHit::m_FileNo, m_FreeBiblIndices, and CHit::m_OrderId.

Referenced by CConcHolder::InitLessByRank(), and CConcHolder::InitOrderIDForHits().

Here is the call graph for this function:

Here is the caller graph for this function:

void CConcXml::InitGreaterByBiblIntegerField	(	string	FreeBiblAttribName,
		vector< CHit > &	Hits
	)			const

References CConcXml::CFreeBiblIndex::GetIntegerValue(), InitNoSort(), CHit::m_FileNo, m_FreeBiblIndices, and CHit::m_OrderId.

Referenced by CConcHolder::InitOrderIDForHits().

Here is the call graph for this function:

Here is the caller graph for this function:

void CConcXml::InitNoSort

(

vector< CHit > &

Hits

)

const

References CHit::m_OrderId.

Referenced by InitGreaterByBiblIntegerField(), and InitLessByBiblIntegerField().

Here is the caller graph for this function:

bool CConcXml::IsRegisteredBiblField

(

string

FreeBiblAttribName

)

const

References m_FreeBiblIndices.

Referenced by CConcHolder::InitLessByRank().

Here is the caller graph for this function:

---

Member Data Documentation

FreeBiblStringMap CConcXml::m_FreeBiblIndices [private]

Referenced by AddIndexItem(), DeleteFiles(), FinalSaveBibliography(), FreeBiblIndices(), GetFreeBibiAttributesDescr(), GetFreeHeaderBiblAttributesJson(), GetFreeHeaderBiblAttributesWithNames(), GetValueFromBiblSet(), GetVisibleFreeHeaderBiblAttributes(), InitGreaterByBiblIntegerField(), InitLessByBiblIntegerField(), IsRegisteredBiblField(), LoadBibl(), LoadXmlAndReadBibliography(), RegisterFreeBiblAttributes(), SetFreeBiblAttribsEmpty(), Start(), and UniteBibliography().

vector<file_off_t> CConcXml::m_EndOffsetsInBiblFile [private]

Referenced by AddIndexItem(), CheckBibl(), FinalSaveBibliography(), GetFullBibliographyOfHit(), LoadBibl(), Start(), and UniteBibliography().

vector<int> CConcXml::m_Dates [private]

Referenced by AddIndexItem(), FinalSaveBibliography(), InitGreaterByDate(), InitLessByDate(), LoadBibl(), Start(), and UniteBibliography().

FILE* CConcXml::m_BiblBodyFile [private]

Referenced by AddIndexItem(), CConcXml(), ExitWithoutSave(), FinalSaveBibliography(), GetFullBibliographyOfHit(), LoadBibl(), Start(), and ~CConcXml().

string CConcXml::m_Path [private]

Referenced by DeleteFiles(), FinalSaveBibliography(), GetBiblDateIndexFileName(), GetBiblFileName(), GetBiblIndexFileName(), LoadBibl(), SetPath(), and UniteBibliography().

size_t CConcXml::m_BiblBodyFileSize [private]

Referenced by AddIndexItem(), ExitWithoutSave(), FinalSaveBibliography(), and Start().

string CConcXml::m_OrigXPath [private]

Referenced by GetFreeBibiAttributesDescr(), LoadXmlAndReadBibliography(), and RegisterFreeBiblAttributes().

string CConcXml::m_ScanXPath [private]

Referenced by GetFreeBibiAttributesDescr(), LoadXmlAndReadBibliography(), and RegisterFreeBiblAttributes().

string CConcXml::m_DateXPath [private]

Referenced by GetFreeBibiAttributesDescr(), LoadXmlAndReadBibliography(), and RegisterFreeBiblAttributes().

string CConcXml::m_StartPageXPath [private]

Referenced by GetFreeBibiAttributesDescr(), LoadXmlAndReadBibliography(), and RegisterFreeBiblAttributes().

vector<CTextArea> CConcXml::m_TextAreas [private]

Referenced by GetTextAreaByName(), GetTextAreaElements(), GetTextAreasCount(), GetTextAreasDescr(), and RegisterTextAreas().

---

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

• Bibliography.h
• Bibliography.cpp