ACEXML_Parser Class Reference

A SAX based parser. More...

#include <ACEXML/parser/parser/Parser.h>

Inheritance diagram for ACEXML_Parser:

Collaboration diagram for ACEXML_Parser:

List of all members.

Public Member Functions

ACEXML_Parser (void)

Default constructor.

virtual ~ACEXML_Parser (void)

Destructor.

int initialize (ACEXML_InputSource *input)

virtual
ACEXML_ContentHandler * getContentHandler (void) const

virtual
ACEXML_DTDHandler * getDTDHandler (void) const

virtual
ACEXML_EntityResolver * getEntityResolver (void) const

virtual
ACEXML_ErrorHandler * getErrorHandler (void) const

virtual int getFeature (const ACEXML_Char *name ACEXML_ENV_ARG_DECL)

virtual void setFeature (const ACEXML_Char *name, int boolean_value ACEXML_ENV_ARG_DECL)

virtual void * getProperty (const ACEXML_Char *name ACEXML_ENV_ARG_DECL)

virtual void setProperty (const ACEXML_Char *name, void *value ACEXML_ENV_ARG_DECL)

virtual void parse (ACEXML_InputSource *input ACEXML_ENV_ARG_DECL)

virtual void parse (const ACEXML_Char *systemId ACEXML_ENV_ARG_DECL)

virtual void setContentHandler (ACEXML_ContentHandler *handler)

virtual void setDTDHandler (ACEXML_DTDHandler *handler)

virtual void setEntityResolver (ACEXML_EntityResolver *resolver)

virtual void setErrorHandler (ACEXML_ErrorHandler *handler)

Protected Member Functions

void parse_xml_prolog (ACEXML_ENV_SINGLE_ARG_DECL)

void parse_version_info (ACEXML_ENV_SINGLE_ARG_DECL)

void parse_encoding_decl (ACEXML_ENV_SINGLE_ARG_DECL)

void parse_xml_decl (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_text_decl (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_processing_instruction (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_doctypedecl (ACEXML_ENV_SINGLE_ARG_DECL)

void parse_element (int is_root ACEXML_ENV_ARG_DECL)

int parse_content (const ACEXML_Char *startname, const ACEXML_Char *&ns_uri, const ACEXML_Char *&ns_lname, int ns_flag ACEXML_ENV_ARG_DECL)

int parse_char_reference (ACEXML_Char *buf, size_t &len)

ACEXML_Char * parse_reference_name (void)

int parse_cdata (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_internal_dtd (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_comment (void)

int parse_element_decl (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_entity_decl (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_attlist_decl (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_atttype (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_notation_decl (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_external_id (ACEXML_Char *&publicId, ACEXML_Char *&systemId ACEXML_ENV_ARG_DECL)

int parse_external_dtd (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_external_subset (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_markup_decl (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_conditional_section (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_includesect (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_ignoresect (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_PE_reference (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_entity_reference (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_entity_value (ACEXML_Char *&str ACEXML_ENV_ARG_DECL)

int parse_defaultdecl (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_children_definition (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_child (int skip_open_paren ACEXML_ENV_ARG_DECL)

ACEXML_Char * parse_name (ACEXML_Char ch=0)

ACEXML_Char * parse_nmtoken (ACEXML_Char ch=0)

int parse_version (ACEXML_Char *&str)

int parse_version_num (ACEXML_Char *&str)

int parse_encname (ACEXML_Char *&str)

int parse_sddecl (ACEXML_Char *&str)

ACEXML_Char * parse_attname (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_attvalue (ACEXML_Char *&str ACEXML_ENV_ARG_DECL)

int parse_tokenized_type (ACEXML_ENV_SINGLE_ARG_DECL)

int parse_system_literal (ACEXML_Char *&str)

int parse_pubid_literal (ACEXML_Char *&str)

int is_whitespace (const ACEXML_Char c) const

int isChar (ACEXML_UCS4 c) const

int isCharRef (const ACEXML_Char c) const

int isBasechar (const ACEXML_Char c) const

int isIdeographic (const ACEXML_Char c) const

int isCombiningchar (const ACEXML_Char c) const

int isDigit (const ACEXML_Char c) const

int isExtender (const ACEXML_Char c) const

int isLetter (const ACEXML_Char c) const

int isNameChar (const ACEXML_Char c) const

int isPubidChar (const ACEXML_Char c) const

virtual ACEXML_Char get (void)

Get a character.

virtual ACEXML_Char peek (void)

Peek a character.

Private Member Functions

ACEXML_Char skip_whitespace (void)

int skip_whitespace_count (ACEXML_Char *peek=0)

int skip_equal (void)

int get_quoted_string (ACEXML_Char *&str)

int isNormalDigit (const ACEXML_Char c) const

void error (const ACEXML_Char *msg ACEXML_ENV_ARG_DECL)

void warning (const ACEXML_Char *msg ACEXML_ENV_ARG_DECL)

void fatal_error (const ACEXML_Char *msg ACEXML_ENV_ARG_DECL)

void prefix_mapping (const ACEXML_Char *prefix, const ACEXML_Char *uri, int start ACEXML_ENV_ARG_DECL)

int parse_token (const ACEXML_Char *keyword)

int push_context (ACEXML_Parser_Context *context)

size_t pop_context (int GE_ref ACEXML_ENV_ARG_DECL)

virtual int switch_input (ACEXML_CharStream *cstream, const ACEXML_Char *systemId, const ACEXML_Char *publicId=0)

virtual int switch_input (ACEXML_InputSource *input, const ACEXML_Char *systemId, const ACEXML_Char *publicId=0)

int check_for_PE_reference (ACEXML_ENV_SINGLE_ARG_DECL)

void reset (void)

ACEXML_Char * normalize_systemid (const ACEXML_Char *systemId)

Private Attributes

ACEXML_DTDHandler * dtd_handler_

ACEXML_EntityResolver * entity_resolver_

ACEXML_ContentHandler * content_handler_

ACEXML_ErrorHandler * error_handler_

ACEXML_Char * doctype_

Document Type.

ACEXML_Parser_Context * current_

Current parser context.

ACE_Unbounded_Stack
< ACEXML_Parser_Context * > ctx_stack_

Stack used to hold the Parser_Context.

ACE_Unbounded_Stack
< ACEXML_Char * > GE_reference_

Set used to hold the general entity references that are active.

ACE_Unbounded_Stack
< ACEXML_Char * > PE_reference_

Set used to hold the parameter entity references that are active.

ACE_Obstack_T
< ACEXML_Char > obstack_

Obstack used by the parser to hold all the strings parsed.

ACE_Obstack_T
< ACEXML_Char > alt_stack_

Alternative obstack used to hold any strings when the original is in use.

ACEXML_NamespaceSupport xml_namespace_

Namespace stack used by the parser to implement support for Namespaces.

int nested_namespace_

T => We are processing a nested namespace.

ACEXML_Entity_Manager internal_GE_

Set of internal parsed general entities in the document.

ACEXML_Entity_Manager external_GE_

Set of external parsed general entities in the document.

ACEXML_Entity_Manager unparsed_entities_

Set of unparsed entities in the document.

ACEXML_Entity_Manager predef_entities_

Set of predefined entities used by the parser.

ACEXML_Entity_Manager internal_PE_

Set of internal parsed parameter entities in the document.

ACEXML_Entity_Manager external_PE_

Set of external parsed parameter entities in the document.

ACEXML_Entity_Manager notations_

Set of notations declared in the document.

ACEXML_ParserInt::ReferenceState ref_state_

State of the parser when it encounters a reference.

int external_subset_

T => We are parsing an external subset.

int external_entity_

T => We are parsing an external entity value.

int has_pe_refs_

T => Internal DTD has parameter entity references.

int standalone_

If set, the document is a standalone XML document.

int external_dtd_

If set, the document has an external DTD subset.

int internal_dtd_

If set, the document has an internal DTD.

int simple_parsing_

int validate_

If set, the parser should also validate.

int namespaces_

If set, the parser should allow access by namespace qualified names.

int namespace_prefixes_

Static Private Attributes

static const ACEXML_Char simple_parsing_feature_ [] = ACE_TEXT ("Simple")

static const ACEXML_Char namespaces_feature_ [] = ACE_TEXT ("http://xml.org/sax/features/namespaces")

static const ACEXML_Char namespace_prefixes_feature_ [] = ACE_TEXT ("http://xml.org/sax/features/namespace-prefixes")

static const ACEXML_Char validation_feature_ [] = ACE_TEXT ("http://xml.org/sax/features/validation")

Detailed Description

A SAX based parser.

Constructor & Destructor Documentation

ACEXML_Parser::ACEXML_Parser ( void )

Default constructor.

ACEXML_Parser::~ACEXML_Parser ( void ) [virtual]

Destructor.

Member Function Documentation

int ACEXML_Parser::initialize ( ACEXML_InputSource * input )

Initialize the parser state.

Return values:

if parser was initialized correctly else -1.

ACEXML_INLINE ACEXML_ContentHandler * ACEXML_Parser::getContentHandler ( void ) const [virtual]

Return the current content handler.

Implements ACEXML_XMLReader.

ACEXML_INLINE ACEXML_DTDHandler * ACEXML_Parser::getDTDHandler ( void ) const [virtual]

Return the current DTD handler.

Implements ACEXML_XMLReader.

ACEXML_INLINE ACEXML_EntityResolver * ACEXML_Parser::getEntityResolver ( void ) const [virtual]

Return the current entity resolver.

Implements ACEXML_XMLReader.

ACEXML_INLINE ACEXML_ErrorHandler * ACEXML_Parser::getErrorHandler ( void ) const [virtual]

Return the current error handler.

Implements ACEXML_XMLReader.

int ACEXML_Parser::getFeature ( const ACEXML_Char *name ACEXML_ENV_ARG_DECL ) [virtual]

Look up the value of a feature. This method allows programmers to check whether a specific feature has been activated in the parser.

Implements ACEXML_XMLReader.

void ACEXML_Parser::setFeature	(	const ACEXML_Char *	name,
		int boolean_value	ACEXML_ENV_ARG_DECL
	)			`[virtual]`

Activating or deactivating a feature.

Implements ACEXML_XMLReader.

void * ACEXML_Parser::getProperty ( const ACEXML_Char *name ACEXML_ENV_ARG_DECL ) [virtual]

Look up the value of a property.

Implements ACEXML_XMLReader.

void ACEXML_Parser::setProperty	(	const ACEXML_Char *	name,
		void *value	ACEXML_ENV_ARG_DECL
	)			`[virtual]`

Set the value of a property.

Implements ACEXML_XMLReader.

void ACEXML_Parser::parse ( ACEXML_InputSource *input ACEXML_ENV_ARG_DECL ) [virtual]

Parse an XML document.

Implements ACEXML_XMLReader.

void ACEXML_Parser::parse ( const ACEXML_Char *systemId ACEXML_ENV_ARG_DECL ) [virtual]

Parse an XML document from a system identifier (URI).

Implements ACEXML_XMLReader.

ACEXML_INLINE void ACEXML_Parser::setContentHandler ( ACEXML_ContentHandler * handler ) [virtual]

Allow an application to register a content event handler.

Implements ACEXML_XMLReader.

ACEXML_INLINE void ACEXML_Parser::setDTDHandler ( ACEXML_DTDHandler * handler ) [virtual]

Allow an application to register a DTD event handler.

Implements ACEXML_XMLReader.

ACEXML_INLINE void ACEXML_Parser::setEntityResolver ( ACEXML_EntityResolver * resolver ) [virtual]

Allow an application to register an entity resolver.

Implements ACEXML_XMLReader.

ACEXML_INLINE void ACEXML_Parser::setErrorHandler ( ACEXML_ErrorHandler * handler ) [virtual]

Allow an application to register an error event handler.

Implements ACEXML_XMLReader.

void ACEXML_Parser::parse_xml_prolog ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse XML Prolog.

void ACEXML_Parser::parse_version_info ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse VersionInfo declaration.

void ACEXML_Parser::parse_encoding_decl ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse a EncodingDecl declaration.

void ACEXML_Parser::parse_xml_decl ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse a XMLDecl declaration.

int ACEXML_Parser::parse_text_decl ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse a TextDecl declaration.

int ACEXML_Parser::parse_processing_instruction ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse a PI statement. The first character encountered should always be '?' in the PI prefix "@<?".

Return values:

on success, -1 otherwise.

int ACEXML_Parser::parse_doctypedecl ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse the DOCTYPE declaration. The first character encountered should always be 'D' in doctype prefix: "@<@!DOCTYPE".

void ACEXML_Parser::parse_element ( int is_root ACEXML_ENV_ARG_DECL ) [protected]

Parse an XML element. The first character encountered should be the first character of the element "Name".

Parameters:

is_root

If not 0, then we are expecting to see the "root" element now, and the next element's name need to match the name defined in DOCTYPE definition, i.e., this->doctype_.

Todo:: Instead of simply checking for the root element based on the argument is_root, we should instead either pass in some sort of validator or allow the function to return the element name so it can be used in a validator.

int ACEXML_Parser::parse_content	(	const ACEXML_Char *	startname,
		const ACEXML_Char *&	ns_uri,
		const ACEXML_Char *&	ns_lname,
		int ns_flag	ACEXML_ENV_ARG_DECL
	)			`[protected]`

Parse a content declaration.

int ACEXML_Parser::parse_char_reference	(	ACEXML_Char *	buf,
		size_t &	len
	)			`[protected]`

Parse a character reference, i.e., " " or "". The first character encountered should be the '#' char.

Parameters:

	buf	points to a character buffer for the result.
	len	In/out argument which initially specifies the size of the buffer and is later set to the no. of characters in the reference.

Return values:

on success and -1 otherwise.

ACEXML_Char * ACEXML_Parser::parse_reference_name ( void ) [protected]

Parse a reference name, i.e., foo in "&foo;" or "%foo;". The first character encountered should be the character following '&' or ''. Effectively the same as

See also:: parse_name but we don't use the parser's obstack. Caller is responsible for deleting the memory.

Return values:

pointer to name of reference, 0 otherwise.

int ACEXML_Parser::parse_cdata ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse a CDATA section. The first character should always be the first '[' in CDATA definition.

Return values:

	0	on success.
	-1	if fail.

int ACEXML_Parser::parse_internal_dtd ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse a "markupdecl" section, this includes both "markupdecl" and "DeclSep" sections in XML specification

int ACEXML_Parser::parse_comment ( void ) [protected]

Skip over a comment. The first character encountered should always be the first '-' in the comment prefix "@<@!--".

int ACEXML_Parser::parse_element_decl ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse an "ELEMENT" decl. The first character this method expects is always the 'L' (the second char) in the word "ELEMENT".

Return values:

on success, -1 otherwise.

int ACEXML_Parser::parse_entity_decl ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse an "ENTITY" decl. The first character this method expects is always the 'N' (the second char) in the word "ENTITY".

Return values:

on success, -1 otherwise.

int ACEXML_Parser::parse_attlist_decl ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse an "ATTLIST" decl. Thse first character this method expects is always the 'A' (the first char) in the word "ATTLIST".

Return values:

on success, -1 otherwise.

int ACEXML_Parser::parse_atttype ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse a AttType declaration.

EnumeratedType ::= NotationType | Enumeration NotationType ::= 'NOTATION' S '(' S? Name (S? '|' S? Name)* S? ')' [VC: Notation Attributes] [VC: One Notation Per Element Type] [VC: No Notation on Empty Element] Enumeration ::= '(' S? Nmtoken (S? '|' S? Nmtoken)* S? ')' [VC: Enumeration]

int ACEXML_Parser::parse_notation_decl ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse a "NOTATION" decl. The first character this method expects is always the 'N' (the first char) in the word "NOTATION".

Return values:

on success, -1 otherwise.

int ACEXML_Parser::parse_external_id	(	ACEXML_Char *&	publicId,
		ACEXML_Char *&systemId	ACEXML_ENV_ARG_DECL
	)			`[protected]`

Parse an ExternalID or a reference to PUBLIC ExternalID. Possible cases are in the forms of:

SYSTEM 'quoted string representing system resource' PUBLIC 'quoted name of public ID' 'quoted resource' PUBLIC 'quoted name we are referring to'

The first character this function sees must be either 'S' or 'P'. When the function finishes parsing, the input stream points at the first non-whitespace character.

Parameters:

	publicId	returns the unquoted publicId read. If none is available, it will be reset to 0.
	systemId	returns the unquoted systemId read. If none is available, it will be reset to 0.

Return values:

on success, -1 otherwise.

int ACEXML_Parser::parse_external_dtd ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse an external DTD.

int ACEXML_Parser::parse_external_subset ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse an external subset. This does the actual parsing of an external subset and is called by

See also:: parse_external_dtd.

int ACEXML_Parser::parse_markup_decl ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse a markupDecl section.

int ACEXML_Parser::parse_conditional_section ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse a conditionalSect declaration.

int ACEXML_Parser::parse_includesect ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse a includeSect declaration.

int ACEXML_Parser::parse_ignoresect ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse a ignoreSect declaration.

int ACEXML_Parser::parse_PE_reference ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse a PEReference.

int ACEXML_Parser::parse_entity_reference ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse a Reference.

int ACEXML_Parser::parse_entity_value ( ACEXML_Char *&str ACEXML_ENV_ARG_DECL ) [protected]

Parse an entityValue.

int ACEXML_Parser::parse_defaultdecl ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse a DefaultDecl specification.

int ACEXML_Parser::parse_children_definition ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse the "children" and "Mixed" non-terminals in contentspec.

The first character this function sees must be the first open paren '(' in children.

Return values:

on success, -1 otherwise.

int ACEXML_Parser::parse_child ( int skip_open_paren ACEXML_ENV_ARG_DECL ) [protected]

Parse a cp non-terminal. cp can either be a seq or a choice. This function calls itself recursively.

Parameters:

skip_open_paren when non-zero, it indicates that the open paren of the seq or choice has already been removed from the input stream.

Return values:

on success, -1 otherwise.

ACEXML_Char * ACEXML_Parser::parse_name ( ACEXML_Char ch = 0 ) [protected]

Parse a name from the input CharStream. If ch @!= 0, then we have already consumed the first name character from the input CharStream, otherwise, parse_name will use this->get() to acquire the initial character.

Returns:: A pointer to the string in the obstack, 0 if it's not a valid name.

ACEXML_Char * ACEXML_Parser::parse_nmtoken ( ACEXML_Char ch = 0 ) [protected]

Parse a NMTOKEN from the input stream.

Returns:: A pointer to the string in the obstack, 0 if it's not a valid NMTOKEN.

int ACEXML_Parser::parse_version ( ACEXML_Char *& str ) [protected]

Parse the version string in an XML Prolog section.

Parameters:

str

String containing the version number if successful.

Returns:: 0 if the string was read successfully, 0 otherwise.

int ACEXML_Parser::parse_version_num ( ACEXML_Char *& str ) [protected]

Parse the version number in a VersionInfo declaration.

int ACEXML_Parser::parse_encname ( ACEXML_Char *& str ) [protected]

Parse the encoding name in an XML Prolog section.

Parameters:

str

String containing the encoding name if successful.

Returns:: 0 if the string was read successfully, 0 otherwise.

int ACEXML_Parser::parse_sddecl ( ACEXML_Char *& str ) [protected]

Parse a SDDecl string.

Parameters:

str

String containing the encoding name if successful.

Returns:: 0 if the string was read successfully, -1 otherwise.

ACEXML_Char * ACEXML_Parser::parse_attname ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse an attribute name.

Return values:

	str	String containing the value of the attribute name if successful.
	0	otherwise.

int ACEXML_Parser::parse_attvalue ( ACEXML_Char *&str ACEXML_ENV_ARG_DECL ) [protected]

Parse an attribute value.

Parameters:

str

String containing the value of the attribute if successful.

Returns:: 0 if attribute value was read successfully, -1 otherwise.

int ACEXML_Parser::parse_tokenized_type ( ACEXML_ENV_SINGLE_ARG_DECL ) [protected]

Parse a tokenized type attribute.

Returns:: 0 if attribute type was read successfully, -1 otherwise.

int ACEXML_Parser::parse_system_literal ( ACEXML_Char *& str ) [protected]

Parse a SystemLiteral.

Parameters:

str

String containing the SystemLiteral if successful.

Returns:: 0 if the string was read successfully, 0 otherwise.

int ACEXML_Parser::parse_pubid_literal ( ACEXML_Char *& str ) [protected]

Parse a PubidLiteral.

Parameters:

str

String containing the PubidLiteral if successful.

Returns:: 0 if the string was read successfully, 0 otherwise.

ACEXML_INLINE int ACEXML_Parser::is_whitespace ( const ACEXML_Char c ) const [protected]

Check if a character c is a whitespace.

Return values:

if c is a valid white space character. 0 otherwise.

ACEXML_INLINE int ACEXML_Parser::isChar ( ACEXML_UCS4 c ) const [protected]

Check if a character c is a valid Char.

Return values:

if c is a valid character. 0 otherwise.

ACEXML_INLINE int ACEXML_Parser::isCharRef ( const ACEXML_Char c ) const [protected]

Check if a character c is a valid CharRef character.

Return values:

if c is a valid character reference character, 0 otherwise.

ACEXML_INLINE int ACEXML_Parser::isBasechar ( const ACEXML_Char c ) const [protected]

Check if a character c is a BaseChar.

Return values:

if c is a valid BaseChar character, 0 otherwise.

ACEXML_INLINE int ACEXML_Parser::isIdeographic ( const ACEXML_Char c ) const [protected]

Check if a character c is a Ideographic.

Return values:

if c is a valid Ideographic character, 0 otherwise.

ACEXML_INLINE int ACEXML_Parser::isCombiningchar ( const ACEXML_Char c ) const [protected]

Check if a character c is a CombiningChar.

Return values:

if c is a valid CombiningChar character, 0 otherwise.

ACEXML_INLINE int ACEXML_Parser::isDigit ( const ACEXML_Char c ) const [protected]

Check if a character c is a Digit.

Return values:

if c is a valid Digit character, 0 otherwise.

ACEXML_INLINE int ACEXML_Parser::isExtender ( const ACEXML_Char c ) const [protected]

Check if a character c is an Extender.

Return values:

if c is a valid Extender character, 0 otherwise.

ACEXML_INLINE int ACEXML_Parser::isLetter ( const ACEXML_Char c ) const [protected]

Check if a character c is a Letter.

Return values:

if c is a valid Letter character, 0 otherwise.

ACEXML_INLINE int ACEXML_Parser::isNameChar ( const ACEXML_Char c ) const [protected]

Check if a character is an acceptable NameChar.

Return values:

if c is a valid NameChar character, 0 otherwise.

ACEXML_INLINE int ACEXML_Parser::isPubidChar ( const ACEXML_Char c ) const [protected]

Check if a character is a PubidChar.

Return values:

if c is a valid PubidChar character, 0 otherwise.

ACEXML_INLINE ACEXML_Char ACEXML_Parser::get ( void ) [protected, virtual]

Get a character.

ACEXML_INLINE ACEXML_Char ACEXML_Parser::peek ( void ) [protected, virtual]

Peek a character.

ACEXML_INLINE ACEXML_Char ACEXML_Parser::skip_whitespace ( void ) [private]

Skip any whitespaces encountered until the first non-whitespace character is encountered.

Returns:: The next non-whitespace character from the CharStream.

See also:: skip_whitespace_count

ACEXML_INLINE int ACEXML_Parser::skip_whitespace_count ( ACEXML_Char * peek = 0 ) [private]

Skip any whitespaces encountered until the first non-whitespace character. The first non-whitespace character is not consumed. This method does peek into the input CharStream and therefore is more expensive than skip_whitespace.

Parameters:

peek

If non-null, peek points to a ACEXML_Char where skip_whitespace_count stores the first non-whitespace character it sees (character is not removed from the stream.)

Returns:: The number of whitespace characters consumed.

See also:: skip_whitespace

ACEXML_INLINE int ACEXML_Parser::skip_equal ( void ) [private]

Skip an equal sign.

Return values:

when succeeds, -1 if no equal sign is found.

int ACEXML_Parser::get_quoted_string ( ACEXML_Char *& str ) [private]

Get a quoted string. Quoted strings are used to specify attribute values and this routine will replace character and entity references on-the-fly. Parameter entities are not allowed (or replaced) in this function. (But regular entities are.)

Parameters:

str

returns the un-quoted string.

Return values:

on success, -1 otherwise.

ACEXML_INLINE int ACEXML_Parser::isNormalDigit ( const ACEXML_Char c ) const [private]

Check if a character c is a Digit.

Return values:

if c is a valid Digit character, 0 otherwise.

void ACEXML_Parser::error ( const ACEXML_Char *msg ACEXML_ENV_ARG_DECL ) [private]

Dispatch errors to ErrorHandler.

void ACEXML_Parser::warning ( const ACEXML_Char *msg ACEXML_ENV_ARG_DECL ) [private]

Dispatch warnings to ErrorHandler.

void ACEXML_Parser::fatal_error ( const ACEXML_Char *msg ACEXML_ENV_ARG_DECL ) [private]

Dispatch fatal errors to ErrorHandler.

void ACEXML_Parser::prefix_mapping	(	const ACEXML_Char *	prefix,
		const ACEXML_Char *	uri,
		int start	ACEXML_ENV_ARG_DECL
	)			`[private]`

Dispatch prefix mapping calls to the ContentHandler.

Parameters:

	prefix	Namespace prefix
	uri	Namespace URI
	name	Local name
	start	1 => startPrefixMapping 0 => endPrefixMapping

ACEXML_INLINE int ACEXML_Parser::parse_token ( const ACEXML_Char * keyword ) [private]

Parse a keyword.

int ACEXML_Parser::push_context ( ACEXML_Parser_Context * context ) [private]

Push the current context on to the stack.

size_t ACEXML_Parser::pop_context ( int GE_ref ACEXML_ENV_ARG_DECL ) [private]

Pop the top element in the stack and replace current context with that.

int ACEXML_Parser::switch_input	(	ACEXML_CharStream *	cstream,
		const ACEXML_Char *	systemId,
		const ACEXML_Char *	publicId = `0`
	)			`[private, virtual]`

Create a new ACEXML_CharStream from systemId and publicId and replace the current input stream with the newly created stream.

int ACEXML_Parser::switch_input	(	ACEXML_InputSource *	input,
		const ACEXML_Char *	systemId,
		const ACEXML_Char *	publicId = `0`
	)			`[private, virtual]`

Create a new ACEXML_InputSource from systemId and publicId and replace the current input source with the newly created InputSource.

int ACEXML_Parser::check_for_PE_reference ( ACEXML_ENV_SINGLE_ARG_DECL ) [private]

Check for a parameter entity reference. This is used to check for the occurence of a PE Reference withing markupDecl. Additionally this function consumes any leading or trailing whitespace around the PE Reference.

Return values:

Number

of whitespace characters skipped.

void ACEXML_Parser::reset ( void ) [private]

Reset the parser state.

ACEXML_Char * ACEXML_Parser::normalize_systemid ( const ACEXML_Char * systemId ) [private]

Very trivial, non-conformant normalization of a systemid.

Member Data Documentation

ACEXML_DTDHandler* ACEXML_Parser::dtd_handler_ [private]

Keeping track of the handlers. We do not manage the memory for handlers.

ACEXML_EntityResolver* ACEXML_Parser::entity_resolver_ [private]

ACEXML_ContentHandler* ACEXML_Parser::content_handler_ [private]

ACEXML_ErrorHandler* ACEXML_Parser::error_handler_ [private]

ACEXML_Char* ACEXML_Parser::doctype_ [private]

Document Type.

ACEXML_Parser_Context* ACEXML_Parser::current_ [private]

Current parser context.

ACE_Unbounded_Stack<ACEXML_Parser_Context*> ACEXML_Parser::ctx_stack_ [private]

Stack used to hold the Parser_Context.

ACE_Unbounded_Stack<ACEXML_Char*> ACEXML_Parser::GE_reference_ [private]

Set used to hold the general entity references that are active.

ACE_Unbounded_Stack<ACEXML_Char*> ACEXML_Parser::PE_reference_ [private]

Set used to hold the parameter entity references that are active.

ACE_Obstack_T<ACEXML_Char> ACEXML_Parser::obstack_ [private]

Obstack used by the parser to hold all the strings parsed.

ACE_Obstack_T<ACEXML_Char> ACEXML_Parser::alt_stack_ [private]

Alternative obstack used to hold any strings when the original is in use.

ACEXML_NamespaceSupport ACEXML_Parser::xml_namespace_ [private]

Namespace stack used by the parser to implement support for Namespaces.

int ACEXML_Parser::nested_namespace_ [private]

T => We are processing a nested namespace.

ACEXML_Entity_Manager ACEXML_Parser::internal_GE_ [private]

Set of internal parsed general entities in the document.

ACEXML_Entity_Manager ACEXML_Parser::external_GE_ [private]

Set of external parsed general entities in the document.

ACEXML_Entity_Manager ACEXML_Parser::unparsed_entities_ [private]

Set of unparsed entities in the document.

ACEXML_Entity_Manager ACEXML_Parser::predef_entities_ [private]

Set of predefined entities used by the parser.

ACEXML_Entity_Manager ACEXML_Parser::internal_PE_ [private]

Set of internal parsed parameter entities in the document.

ACEXML_Entity_Manager ACEXML_Parser::external_PE_ [private]

Set of external parsed parameter entities in the document.

ACEXML_Entity_Manager ACEXML_Parser::notations_ [private]

Set of notations declared in the document.

ACEXML_ParserInt::ReferenceState ACEXML_Parser::ref_state_ [private]

State of the parser when it encounters a reference.

int ACEXML_Parser::external_subset_ [private]

T => We are parsing an external subset.

int ACEXML_Parser::external_entity_ [private]

T => We are parsing an external entity value.

int ACEXML_Parser::has_pe_refs_ [private]

T => Internal DTD has parameter entity references.

int ACEXML_Parser::standalone_ [private]

If set, the document is a standalone XML document.

int ACEXML_Parser::external_dtd_ [private]

If set, the document has an external DTD subset.

int ACEXML_Parser::internal_dtd_ [private]

If set, the document has an internal DTD.

int ACEXML_Parser::simple_parsing_ [private]

Feature flags If set, the parser should parse a document without a prolog

int ACEXML_Parser::validate_ [private]

If set, the parser should also validate.

int ACEXML_Parser::namespaces_ [private]

If set, the parser should allow access by namespace qualified names.

int ACEXML_Parser::namespace_prefixes_ [private]

If set, the parser should include namespace declarations in the list of attributes of an element.

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

Generated on Mon Sep 3 04:03:19 2007 for ACEXML by

1.5.3


Public Member Functions
	ACEXML_Parser (void)
	Default constructor.
virtual	~ACEXML_Parser (void)
	Destructor.
int	initialize (ACEXML_InputSource *input)
virtual ACEXML_ContentHandler *	getContentHandler (void) const
virtual ACEXML_DTDHandler *	getDTDHandler (void) const
virtual ACEXML_EntityResolver *	getEntityResolver (void) const
virtual ACEXML_ErrorHandler *	getErrorHandler (void) const
virtual int	getFeature (const ACEXML_Char *name ACEXML_ENV_ARG_DECL)
virtual void	setFeature (const ACEXML_Char *name, int boolean_value ACEXML_ENV_ARG_DECL)
virtual void *	getProperty (const ACEXML_Char *name ACEXML_ENV_ARG_DECL)
virtual void	setProperty (const ACEXML_Char name, void value ACEXML_ENV_ARG_DECL)
virtual void	parse (ACEXML_InputSource *input ACEXML_ENV_ARG_DECL)
virtual void	parse (const ACEXML_Char *systemId ACEXML_ENV_ARG_DECL)
virtual void	setContentHandler (ACEXML_ContentHandler *handler)
virtual void	setDTDHandler (ACEXML_DTDHandler *handler)
virtual void	setEntityResolver (ACEXML_EntityResolver *resolver)
virtual void	setErrorHandler (ACEXML_ErrorHandler *handler)
Protected Member Functions
void	parse_xml_prolog (ACEXML_ENV_SINGLE_ARG_DECL)
void	parse_version_info (ACEXML_ENV_SINGLE_ARG_DECL)
void	parse_encoding_decl (ACEXML_ENV_SINGLE_ARG_DECL)
void	parse_xml_decl (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_text_decl (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_processing_instruction (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_doctypedecl (ACEXML_ENV_SINGLE_ARG_DECL)
void	parse_element (int is_root ACEXML_ENV_ARG_DECL)
int	parse_content (const ACEXML_Char startname, const ACEXML_Char &ns_uri, const ACEXML_Char *&ns_lname, int ns_flag ACEXML_ENV_ARG_DECL)
int	parse_char_reference (ACEXML_Char *buf, size_t &len)
ACEXML_Char *	parse_reference_name (void)
int	parse_cdata (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_internal_dtd (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_comment (void)
int	parse_element_decl (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_entity_decl (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_attlist_decl (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_atttype (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_notation_decl (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_external_id (ACEXML_Char &publicId, ACEXML_Char &systemId ACEXML_ENV_ARG_DECL)
int	parse_external_dtd (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_external_subset (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_markup_decl (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_conditional_section (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_includesect (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_ignoresect (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_PE_reference (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_entity_reference (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_entity_value (ACEXML_Char *&str ACEXML_ENV_ARG_DECL)
int	parse_defaultdecl (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_children_definition (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_child (int skip_open_paren ACEXML_ENV_ARG_DECL)
ACEXML_Char *	parse_name (ACEXML_Char ch=0)
ACEXML_Char *	parse_nmtoken (ACEXML_Char ch=0)
int	parse_version (ACEXML_Char *&str)
int	parse_version_num (ACEXML_Char *&str)
int	parse_encname (ACEXML_Char *&str)
int	parse_sddecl (ACEXML_Char *&str)
ACEXML_Char *	parse_attname (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_attvalue (ACEXML_Char *&str ACEXML_ENV_ARG_DECL)
int	parse_tokenized_type (ACEXML_ENV_SINGLE_ARG_DECL)
int	parse_system_literal (ACEXML_Char *&str)
int	parse_pubid_literal (ACEXML_Char *&str)
int	is_whitespace (const ACEXML_Char c) const
int	isChar (ACEXML_UCS4 c) const
int	isCharRef (const ACEXML_Char c) const
int	isBasechar (const ACEXML_Char c) const
int	isIdeographic (const ACEXML_Char c) const
int	isCombiningchar (const ACEXML_Char c) const
int	isDigit (const ACEXML_Char c) const
int	isExtender (const ACEXML_Char c) const
int	isLetter (const ACEXML_Char c) const
int	isNameChar (const ACEXML_Char c) const
int	isPubidChar (const ACEXML_Char c) const
virtual ACEXML_Char	get (void)
	Get a character.
virtual ACEXML_Char	peek (void)
	Peek a character.
Private Member Functions
ACEXML_Char	skip_whitespace (void)
int	skip_whitespace_count (ACEXML_Char *peek=0)
int	skip_equal (void)
int	get_quoted_string (ACEXML_Char *&str)
int	isNormalDigit (const ACEXML_Char c) const
void	error (const ACEXML_Char *msg ACEXML_ENV_ARG_DECL)
void	warning (const ACEXML_Char *msg ACEXML_ENV_ARG_DECL)
void	fatal_error (const ACEXML_Char *msg ACEXML_ENV_ARG_DECL)
void	prefix_mapping (const ACEXML_Char prefix, const ACEXML_Char uri, int start ACEXML_ENV_ARG_DECL)
int	parse_token (const ACEXML_Char *keyword)
int	push_context (ACEXML_Parser_Context *context)
size_t	pop_context (int GE_ref ACEXML_ENV_ARG_DECL)
virtual int	switch_input (ACEXML_CharStream cstream, const ACEXML_Char systemId, const ACEXML_Char *publicId=0)
virtual int	switch_input (ACEXML_InputSource input, const ACEXML_Char systemId, const ACEXML_Char *publicId=0)
int	check_for_PE_reference (ACEXML_ENV_SINGLE_ARG_DECL)
void	reset (void)
ACEXML_Char *	normalize_systemid (const ACEXML_Char *systemId)
Private Attributes
ACEXML_DTDHandler *	dtd_handler_
ACEXML_EntityResolver *	entity_resolver_
ACEXML_ContentHandler *	content_handler_
ACEXML_ErrorHandler *	error_handler_
ACEXML_Char *	doctype_
	Document Type.
ACEXML_Parser_Context *	current_
	Current parser context.
ACE_Unbounded_Stack < ACEXML_Parser_Context * >	ctx_stack_
	Stack used to hold the Parser_Context.
ACE_Unbounded_Stack < ACEXML_Char * >	GE_reference_
	Set used to hold the general entity references that are active.
ACE_Unbounded_Stack < ACEXML_Char * >	PE_reference_
	Set used to hold the parameter entity references that are active.
ACE_Obstack_T < ACEXML_Char >	obstack_
	Obstack used by the parser to hold all the strings parsed.
ACE_Obstack_T < ACEXML_Char >	alt_stack_
	Alternative obstack used to hold any strings when the original is in use.
ACEXML_NamespaceSupport	xml_namespace_
	Namespace stack used by the parser to implement support for Namespaces.
int	nested_namespace_
	T => We are processing a nested namespace.
ACEXML_Entity_Manager	internal_GE_
	Set of internal parsed general entities in the document.
ACEXML_Entity_Manager	external_GE_
	Set of external parsed general entities in the document.
ACEXML_Entity_Manager	unparsed_entities_
	Set of unparsed entities in the document.
ACEXML_Entity_Manager	predef_entities_
	Set of predefined entities used by the parser.
ACEXML_Entity_Manager	internal_PE_
	Set of internal parsed parameter entities in the document.
ACEXML_Entity_Manager	external_PE_
	Set of external parsed parameter entities in the document.
ACEXML_Entity_Manager	notations_
	Set of notations declared in the document.
ACEXML_ParserInt::ReferenceState	ref_state_
	State of the parser when it encounters a reference.
int	external_subset_
	T => We are parsing an external subset.
int	external_entity_
	T => We are parsing an external entity value.
int	has_pe_refs_
	T => Internal DTD has parameter entity references.
int	standalone_
	If set, the document is a standalone XML document.
int	external_dtd_
	If set, the document has an external DTD subset.
int	internal_dtd_
	If set, the document has an internal DTD.
int	simple_parsing_
int	validate_
	If set, the parser should also validate.
int	namespaces_
	If set, the parser should allow access by namespace qualified names.
int	namespace_prefixes_
Static Private Attributes
static const ACEXML_Char	simple_parsing_feature_ [] = ACE_TEXT ("Simple")
static const ACEXML_Char	namespaces_feature_ [] = ACE_TEXT ("http://xml.org/sax/features/namespaces")
static const ACEXML_Char	namespace_prefixes_feature_ [] = ACE_TEXT ("http://xml.org/sax/features/namespace-prefixes")
static const ACEXML_Char	validation_feature_ [] = ACE_TEXT ("http://xml.org/sax/features/validation")