The class which parses text zones in a mac MS Works document v4. More...

#include <MsWks4Text.hxx>

Classes
struct	DataFOD
	structure which retrieves data information which correspond to a text position More...
Public Member Functions
	MsWks4Text (MsWksDocument &document)
	constructor
	~MsWks4Text ()
	destructor
void	setDefault (MWAWFont &font)
	sets the default font
int	numPages () const
	returns the number of pages
void	flushExtra (MWAWInputStreamPtr)
	sends the data which have not been sent: actually do nothing
Protected Types
typedef bool(MsWks4Text::*	FDPParser )(MWAWInputStreamPtr &input, long endPos, int &id, std::string &mess)
	callback when a new attribute is found in an FDPP/FDPC entry
typedef bool(MsWks4Text::*	DataParser )(MWAWInputStreamPtr input, long endPos, long bot, long eot, int id, std::string &mess)
	definition of the plc data parser (low level)
Protected Member Functions
bool	readStructures (MWAWInputStreamPtr input, bool mainOle)
	finds and parses all structures which correspond to the text
bool	readText (MWAWInputStreamPtr input, MWAWEntry const &entry, bool mainOle)
	reads a text section and send it to the listener
bool	readFootNote (MWAWInputStreamPtr input, int id)
	sends the text which corresponds to footnote id to the listner
bool	readPLC (MWAWInputStreamPtr input, MWAWEntry const &entry, std::vector< long > &textPtrs, std::vector< long > &listValues, DataParser parser=&MsWks4Text::defDataParser)
	reads a PLC (Pointer List Composant ?) in zone entry
bool	readSimplePLC (MWAWInputStreamPtr &input, MWAWEntry const &entry, std::vector< long > &textPtrs, std::vector< long > &listValues)
	reads a PLC (Pointer List Composant ?) in zone entry
bool	defDataParser (MWAWInputStreamPtr input, long endPos, long bot, long eot, int id, std::string &mess)
	the default parser (does nothing)
bool	readFontNames (MWAWInputStreamPtr input, MWAWEntry const &entry)
	reads the font names entry : FONT
bool	readFont (MWAWInputStreamPtr &input, long endPos, int &id, std::string &mess)
	reads a font properties
void	setProperty (MsWks4TextInternal::Paragraph const &tabs)
	sends a paragraph properties to the listener
bool	readParagraph (MWAWInputStreamPtr &input, long endPos, int &id, std::string &mess)
	reads a paragraph properties
bool	ftntDataParser (MWAWInputStreamPtr input, long endPos, long bot, long eot, int id, std::string &mess)
	parses the footnote position : FTNT
bool	eobjDataParser (MWAWInputStreamPtr input, long endPos, long bot, long eot, int id, std::string &mess)
	parses the object position : EOBJ
bool	toknDataParser (MWAWInputStreamPtr input, long endPos, long bot, long eot, int id, std::string &mess)
	parses the field properties entries : TOKN.
bool	pgdDataParser (MWAWInputStreamPtr input, long endPos, long, long, int id, std::string &mess)
	parses the pagebreak positin entries : PGD
void	flushNote (int noteId)
	sends to the listener the text which corresponds to noteId
std::vector< DataFOD >	mergeSortedLists (std::vector< DataFOD > const &lst1, std::vector< DataFOD > const &lst2) const
	function which takes two sorted list of attribute (by text position).
bool	readFDP (MWAWInputStreamPtr &input, MWAWEntry const &entry, std::vector< DataFOD > &fods, FDPParser parser)
	parses a FDPP or a FDPC entry (which contains a list of ATTR_TEXT/ATTR_PARAG with their definition ) and adds found data in listFODs
bool	findFDPStructures (MWAWInputStreamPtr &input, int which)
	Fills the vector of (FDPCs/FDPPs) paragraph/characters strutures.
bool	findFDPStructuresByHand (MWAWInputStreamPtr &input, int which)
	Fills the vector of (FDPCs/FDPPs) paragraph/characters strutures, a function to call when the normal ways fails.
Protected Attributes
MWAWParser *	m_mainParser
	the main parser;
MWAWParserStatePtr	m_parserState
	the parser state
MsWksDocument &	m_document
	the main document
MWAWEntry	m_textPositions
	an entry which corresponds to the complete text zone
shared_ptr < MsWks4TextInternal::State >	m_state
	the internal state
std::vector< DataFOD >	m_FODsList
	the list of a FOD
std::vector< MWAWEntry const * >	m_FDPCs
	the list of FDPC entries
std::vector< MWAWEntry const * >	m_FDPPs
	the list of FDPP entries
Private Member Functions
	MsWks4Text (MsWks4Text const &orig)
MsWks4Text &	operator= (MsWks4Text const &orig)
Friends
class	MsWks4Zone

Detailed Description

The class which parses text zones in a mac MS Works document v4.

This class must be associated with a MsWks4Zone. It reads the entries:

TEXT : the text strings
FONT : the fonts name
FDPC, BTEC : the fonts properties
FDPP, BTEP : the paragraph properties
FTNT : the footnote definition
PGD : the page break (only parsed)
TOKN : the field properties (pagenumber, date, ...)

Member Typedef Documentation

typedef bool(MsWks4Text::* MsWks4Text::DataParser)(MWAWInputStreamPtr input, long endPos, long bot, long eot, int id, std::string &mess) [protected]

definition of the plc data parser (low level)

Parameters:

endPos	the end of the properties' definition,
bot	defined the begin of the text zone corresponding to these properties
eot	defined the end of the text zone corresponding to these properties
id	the number of this properties
mess	a string which can be filled to indicate unparsed data

typedef bool(MsWks4Text::* MsWks4Text::FDPParser)(MWAWInputStreamPtr &input, long endPos, int &id, std::string &mess) [protected]

callback when a new attribute is found in an FDPP/FDPC entry

Parameters:

input	defines the input
endPos	the last position in the input

Returns:: true and filled id if this attribute can be parsed

Note:: mess can be filled to add a message in debugFile

Constructor & Destructor Documentation

MsWks4Text::MsWks4Text ( MsWksDocument & document )

constructor

MsWks4Text::~MsWks4Text ( )

destructor

MsWks4Text::MsWks4Text ( MsWks4Text const & orig ) [private]

Member Function Documentation

bool MsWks4Text::defDataParser	(	MWAWInputStreamPtr	input,
		long	endPos,
		long	bot,
		long	eot,
		int	id,
		std::string &	mess
	)		`[protected]`

the default parser (does nothing)

bool MsWks4Text::eobjDataParser	(	MWAWInputStreamPtr	input,
		long	endPos,
		long	bot,
		long	eot,
		int	id,
		std::string &	mess
	)		`[protected]`

parses the object position : EOBJ

Referenced by readStructures().

bool MsWks4Text::findFDPStructures	(	MWAWInputStreamPtr &	input,
		int	which
	)		`[protected]`

Fills the vector of (FDPCs/FDPPs) paragraph/characters strutures.

Uses the entry BTEC/BTEP : the normal ways, and calls readSimplePLC on each entry to check that the parsing is correct

Parameters:

input	the file input
which	set to 0 for paragraphs structures and to 1 for characters structures

Referenced by readStructures().

bool MsWks4Text::findFDPStructuresByHand	(	MWAWInputStreamPtr &	input,
		int	which
	)		`[protected]`

Fills the vector of (FDPCs/FDPPs) paragraph/characters strutures, a function to call when the normal ways fails.

Uses all entries FDPCs/FDPPs and calls readSimplePLC on each entry to check that the parsing is correct.

Parameters:

input	the file input
which	set to 0 for paragraphs structures and to 1 for characters structures

Referenced by readStructures().

void MsWks4Text::flushExtra ( MWAWInputStreamPtr ) [inline]

sends the data which have not been sent: actually do nothing

void MsWks4Text::flushNote ( int noteId ) [protected]

sends to the listener the text which corresponds to noteId

bool MsWks4Text::ftntDataParser	(	MWAWInputStreamPtr	input,
		long	endPos,
		long	bot,
		long	eot,
		int	id,
		std::string &	mess
	)		`[protected]`

parses the footnote position : FTNT

Referenced by readStructures().

std::vector< MsWks4Text::DataFOD > MsWks4Text::mergeSortedLists	(	std::vector< DataFOD > const &	lst1,
		std::vector< DataFOD > const &	lst2
	)		const `[protected]`

function which takes two sorted list of attribute (by text position).

Returns:: a list of attribute

Referenced by readPLC(), and readStructures().

int MsWks4Text::numPages ( ) const

returns the number of pages

MsWks4Text& MsWks4Text::operator= ( MsWks4Text const & orig ) [private]

bool MsWks4Text::pgdDataParser	(	MWAWInputStreamPtr	input,
		long	endPos,
		long	,
		long	,
		int	id,
		std::string &	mess
	)		`[protected]`

parses the pagebreak positin entries : PGD

Note:: the read data are not used to create the document

Referenced by readStructures().

bool MsWks4Text::readFDP	(	MWAWInputStreamPtr &	input,
		MWAWEntry const &	entry,
		std::vector< DataFOD > &	fods,
		MsWks4Text::FDPParser	parser
	)		`[protected]`

parses a FDPP or a FDPC entry (which contains a list of ATTR_TEXT/ATTR_PARAG with their definition ) and adds found data in listFODs

Referenced by readStructures().

bool MsWks4Text::readFont	(	MWAWInputStreamPtr &	input,
		long	endPos,
		int &	id,
		std::string &	mess
	)		`[protected]`

reads a font properties

Referenced by readStructures().

bool MsWks4Text::readFontNames	(	MWAWInputStreamPtr	input,
		MWAWEntry const &	entry
	)		`[protected]`

reads the font names entry : FONT

Referenced by readStructures().

bool MsWks4Text::readFootNote	(	MWAWInputStreamPtr	input,
		int	id
	)		`[protected]`

sends the text which corresponds to footnote id to the listner

bool MsWks4Text::readParagraph	(	MWAWInputStreamPtr &	input,
		long	endPos,
		int &	id,
		std::string &	mess
	)		`[protected]`

reads a paragraph properties

Referenced by readStructures().

bool MsWks4Text::readPLC	(	MWAWInputStreamPtr	input,
		MWAWEntry const &	entry,
		std::vector< long > &	textPtrs,
		std::vector< long > &	listValues,
		MsWks4Text::DataParser	parser = `&MsWks4Text::defDataParser`
	)		`[protected]`

reads a PLC (Pointer List Composant ?) in zone entry

Parameters:

input	the file's input
entry	the zone which contains the plc
textPtrs	lists of offset in text zones where properties changes
listValues	lists of properties values (filled only if values are simple types: int, ..)
parser	the parser to use to read the values

Referenced by readSimplePLC(), and readStructures().

bool MsWks4Text::readSimplePLC	(	MWAWInputStreamPtr &	input,
		MWAWEntry const &	entry,
		std::vector< long > &	textPtrs,
		std::vector< long > &	listValues
	)		`[inline, protected]`

reads a PLC (Pointer List Composant ?) in zone entry

Parameters:

input	the file's input
entry	the zone which contains the plc
textPtrs	lists of offset in text zones where properties changes
listValues	lists of properties values (filled only if values are simple types: int, ..)

Referenced by findFDPStructures().