Experimental XML writer class for use with expat-parsed XML or vanilla input.

Inheritance diagram for moot::TokenWriterExpat:

Collaboration diagram for moot::TokenWriterExpat:

[legend]

Public Member Functions
Constructors and Such
	TokenWriterExpat (int fmt=tiofXML, bool got_raw_xml=false, const std::string &encoding="", const std::string &name="TokenWriterExpat")

void	setEncoding (const std::string &encoding="")

virtual	~TokenWriterExpat (void)

Output Selection
virtual void	to_mstream (mootio::mostream *os)

virtual void	close (void)

Overrides
virtual void	put_token (const mootToken &token)

virtual void	put_tokens (const mootSentence &tokens)

virtual void	put_sentence (const mootSentence &sentence)

virtual void	put_comment_block_begin (void)

virtual void	put_comment_block_end (void)

virtual void	put_raw_buffer (const char *buf, size_t len)

Output Utilities
void	_put_token_raw (const mootToken &token, mootio::mostream *os)

void	_put_token_gen (const mootToken &token, mootio::mostream *os)

void	_put_token (const mootToken &token, mootio::mostream *os)

void	_put_tokens (const mootSentence &tokens, mootio::mostream *os)

void	_put_sentence (const mootSentence &sentence, mootio::mostream *os)

void	_put_comment_block_begin (mootio::mostream *os)

void	_put_comment_block_end (mootio::mostream *os)

void	_put_raw_buffer (const char buf, size_t len, mootio::mostream os)

Public Member Functions inherited from moot::TokenWriter
	TokenWriter (int fmt=tiofWellDone, const std::string &name="TokenWriter")

virtual	~TokenWriter (void)

virtual void	to_mstream (mootio::mostream &mos)

virtual void	to_filename (const char *filename)

virtual void	to_file (FILE *file)

virtual void	to_fd (int fd)

virtual void	to_cxxstream (std::ostream &os)

virtual bool	opened (void)

virtual bool	flush (void)

bool	autoflush (mootio::mostream *os)

virtual void	put_comment_buffer (const char *buf, size_t len)

virtual void	put_comment (const char *s)

virtual void	put_comment_buffer (const std::string &s)

virtual void	printf_comment (const char *fmt,...)

virtual void	put_raw (const char *s)

virtual void	put_raw (const std::string &s)

virtual void	printf_raw (const char *fmt,...)

virtual void	writer_name (const std::string &myname)

virtual void	carp (const char *fmt,...)

Public Attributes
Output Parameters
bool	use_raw_xml

std::string	root_elt
	Default name of root element. Default="doc". More...

std::string	eos_elt
	Default name of 'eos' element (sentence boundary). Default="eos". More...

std::string	token_elt
	Default name of 'token' element. Default="token". More...

std::string	text_elt
	Default name of 'text' element. Default="text". More...

std::string	analysis_elt
	Default name of 'analysis' element. Default="analysis". More...

std::string	postag_attr
	Default name of 'pos' attribute (of 'analysis' elt) Default="pos". More...

std::string	besttag_elt
	Name of 'best tag' element. Default="moot.tag". More...

std::string	location_elt
	Name of 'best tag' element. Default="moot.loc". More...

std::string	offset_attr
	Name of 'location' element 'offset' attribute. Default="offset". More...

std::string	length_attr
	Name of 'location' element 'length' attribute. Default="length". More...

Internal Data
std::string	twx_encoding

mootXMLRecoder	twx_recoder

int	lastc

Public Attributes inherited from moot::TokenWriter
int	tw_format

std::string	tw_name

mootio::mostream *	tw_ostream

bool	tw_ostream_created

bool	tw_is_comment_block

void *	tw_data

Additional Inherited Members
Static Public Member Functions inherited from moot::TokenIO
static int	parse_format_string (const std::string &fmtString)

static int	guess_filename_format (const char *filename)

static bool	is_empty_format (int fmt)

static int	sanitize_format (int fmt, int fmt_implied=tiofNone, int fmt_default=tiofNone)

static int	parse_format_request (const char request, const char filename=__null, int fmt_implied=tiofNone, int fmt_default=tiofNone)

static std::string	format_canonical_string (int fmt)

static class TokenReader *	new_reader (int fmt)

static class TokenWriter *	new_writer (int fmt)

static class TokenReader *	file_reader (const char filename, const char fmt_request=__null, int fmt_implied=tiofNone, int fmt_default=tiofNone)

static class TokenWriter *	file_writer (const char filename, const char fmt_request=__null, int fmt_implied=tiofNone, int fmt_default=tiofNone)

static size_t	pipe_tokens (class TokenReader reader, class TokenWriter writer)

static size_t	pipe_sentences (class TokenReader reader, class TokenWriter writer)

Constructor & Destructor Documentation

◆ TokenWriterExpat()

moot::TokenWriterExpat::TokenWriterExpat	(	int	fmt = `tiofXML`,
		bool	got_raw_xml = `false`,
		const std::string &	encoding = `""`,
		const std::string &	name = `"TokenWriterExpat"`
	)

Default constructor:

Parameters

fmt	output format, a bitmask of TokenIOFormat flags
got_raw_xml	whether this object is part of a lossless XML I/O chain: useful but cryptic – see `use_raw_xml` for details.
encoding	destination encoding. still somewhat buggy.

◆ ~TokenWriterExpat()

virtual moot::TokenWriterExpat::~TokenWriterExpat ( void )

inlinevirtual

Default destructor

Member Function Documentation

◆ setEncoding()

void moot::TokenWriterExpat::setEncoding ( const std::string & encoding = "" )

inline

Set default output encoding. Still somewhat buggy

References moot::mootXMLRecoder::scan_request().

◆ to_mstream()

virtual void moot::TokenWriterExpat::to_mstream ( mootio::mostream * os )

virtual

Select output to a mootio::mostream

Reimplemented from moot::TokenWriter.

◆ close()

virtual void moot::TokenWriterExpat::close ( void )

virtual

Close currently selected output sink

Reimplemented from moot::TokenWriter.

◆ put_token()

virtual void moot::TokenWriterExpat::put_token ( const mootToken & token )

inlinevirtual

Write a single token to the current output sink.

Reimplemented from moot::TokenWriter.

◆ put_tokens()

virtual void moot::TokenWriterExpat::put_tokens ( const mootSentence & tokens )

inlinevirtual

Write a partial sentence to the current output sink.

Reimplemented from moot::TokenWriter.

◆ put_sentence()

virtual void moot::TokenWriterExpat::put_sentence ( const mootSentence & sentence )

inlinevirtual

Write a whole sentence to the current output sink.

Reimplemented from moot::TokenWriter.

◆ put_comment_block_begin()

virtual void moot::TokenWriterExpat::put_comment_block_begin ( void )

inlinevirtual

Begin a comment block.

Reimplemented from moot::TokenWriter.

◆ put_comment_block_end()

virtual void moot::TokenWriterExpat::put_comment_block_end ( void )

inlinevirtual

End a comment block, if one is active.

Reimplemented from moot::TokenWriter.

◆ put_raw_buffer()

virtual void moot::TokenWriterExpat::put_raw_buffer	(	const char *	buf,
		size_t	len
	)

inlinevirtual

Write some raw data to the current sink. No recoding is performed.

Reimplemented from moot::TokenWriter.

◆ _put_token_raw()

void moot::TokenWriterExpat::_put_token_raw	(	const mootToken &	token,
		mootio::mostream *	os
	)

Write a single token to a mootio::mostream, raw mode

◆ _put_token_gen()

void moot::TokenWriterExpat::_put_token_gen	(	const mootToken &	token,
		mootio::mostream *	os
	)

Write a single token to a mootio::mostream, gen mode

◆ _put_token()

void moot::TokenWriterExpat::_put_token	(	const mootToken &	token,
		mootio::mostream *	os
	)

inline

Write a single token to a mootio::mostream

◆ _put_tokens()

void moot::TokenWriterExpat::_put_tokens	(	const mootSentence &	tokens,
		mootio::mostream *	os
	)

inline

Write a partial sentence to a C stream, obeying use_raw_xml flag

References moot::tiofNone, and mootio::mstream::valid().

◆ _put_sentence()

void moot::TokenWriterExpat::_put_sentence	(	const mootSentence &	sentence,
		mootio::mostream *	os
	)

inline

Write a single sentence to a C stream, obeying use_raw_xml flag

References moot::tiofNone, moot::TokTypeEOS, and mootio::mstream::valid().

◆ _put_comment_block_begin()

void moot::TokenWriterExpat::_put_comment_block_begin ( mootio::mostream * os )

Begin a comment block.

◆ _put_comment_block_end()

void moot::TokenWriterExpat::_put_comment_block_end ( mootio::mostream * os )

End a comment block, if one is active.

◆ _put_raw_buffer()

void moot::TokenWriterExpat::_put_raw_buffer	(	const char *	buf,
		size_t	len,
		mootio::mostream *	os
	)

Write some raw data to the current sink. No recoding is performed.

Member Data Documentation

◆ use_raw_xml

bool moot::TokenWriterExpat::use_raw_xml

Whether the data to write contains raw XML as generated by TokenReaderExpat with save_raw_xml=true. Useful for lossless XML I/O.

Warning: If this flag is set, arguments to put_* methods must provide tokens of type TokTypeXMLRaw for all document content except the following:

sentence boundary markers (TokTypeEOS)
'vanilla' tokens (TokTypeVanilla) In 'use_raw_xml' mode, only the 'besttag' element will be written for 'vanilla' tokens – in other words, TokTypeXMLRaw tokens are expected for token start- and end- elements, as well as for text, analyses, etc., although no checking is performed for the presence of such elements.

If the flag is false (the default), a document will be generated with a default structure (see root_elt, eos_elt, token_elt, etc.), which should be compatible with the default behavior of TokenReaderExpat.

◆ root_elt

std::string moot::TokenWriterExpat::root_elt

◆ eos_elt

std::string moot::TokenWriterExpat::eos_elt

◆ token_elt

std::string moot::TokenWriterExpat::token_elt

◆ text_elt

std::string moot::TokenWriterExpat::text_elt

◆ analysis_elt

std::string moot::TokenWriterExpat::analysis_elt

◆ postag_attr

std::string moot::TokenWriterExpat::postag_attr

◆ besttag_elt

std::string moot::TokenWriterExpat::besttag_elt

◆ location_elt

std::string moot::TokenWriterExpat::location_elt

◆ offset_attr

std::string moot::TokenWriterExpat::offset_attr

◆ length_attr

std::string moot::TokenWriterExpat::length_attr

◆ twx_encoding

std::string moot::TokenWriterExpat::twx_encoding

Name of destination encoding. See setEncoding()

◆ twx_recoder

mootXMLRecoder moot::TokenWriterExpat::twx_recoder

Recoder object: handles text (re-)coding

◆ lastc

int moot::TokenWriterExpat::lastc

Last character written

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

mootTokenExpatIO.h

Public Member Functions

Public Attributes

Additional Inherited Members

Constructor & Destructor Documentation

◆ TokenWriterExpat()

◆ ~TokenWriterExpat()

Member Function Documentation

◆ setEncoding()

◆ to_mstream()

◆ close()

◆ put_token()

◆ put_tokens()

◆ put_sentence()

◆ put_comment_block_begin()

◆ put_comment_block_end()

◆ put_raw_buffer()

◆ _put_token_raw()

◆ _put_token_gen()

◆ _put_token()

◆ _put_tokens()

◆ _put_sentence()

◆ _put_comment_block_begin()

◆ _put_comment_block_end()

◆ _put_raw_buffer()

Member Data Documentation

◆ use_raw_xml

◆ root_elt

◆ eos_elt

◆ token_elt

◆ text_elt

◆ analysis_elt

◆ postag_attr

◆ besttag_elt

◆ location_elt

◆ offset_attr

◆ length_attr

◆ twx_encoding

◆ twx_recoder

◆ lastc