#include <cXmlReader.h>

Inheritance diagram for GrayLib::cXmlReader:

Public Member Functions
	cXmlReader (const char *pszStart="", StrLen_t nLenMax=StrT::k_LEN_MAX, StrLen_t iTabSize=cStrConst::k_TabSize, CXML_ENCODING_TYPE eEncoding=CXML_ENCODING_UNKNOWN, bool bCondenseWhitespace=true)

	~cXmlReader ()

HRESULT	ReturnError (HRESULT hRes) const

void	put_CondenseWhitespace (bool bCondense) noexcept

bool	isCondensedWhitespace () const noexcept

HRESULT	Parse (cXmlReadVisitor *pVisitor, cXmlString sElementParent)

HRESULT	Parse (cXmlReadVisitor *pVisitor)

HRESULT	ParseText (const char pszText, cXmlReadVisitor pVisitor)

HRESULT	ParseStream (cStreamInput &rInp, cXmlReadVisitor *pVisitor)

HRESULT	ParseFile (const FILECHAR_t pszXMLFile, cXmlReadVisitor pVisitor)

Public Member Functions inherited from Gray::cTextReader
	cTextReader (const char *pszStart, StrLen_t nLenMax=StrT::k_LEN_MAX, StrLen_t nTabSize=cStrConst::k_TabSize)

StrLen_t	get_LenMax () const noexcept

StrLen_t	get_LenRemaining () const noexcept

bool	isValidIndex () const noexcept

bool	isValidPos () const noexcept

const char *	get_CursorPtr () const noexcept

char	get_CursorChar () const noexcept

void	IncToks (StrLen_t nLen=1)

void	IncTab (StrLen_t nLenChar=1)

StrLen_t	IncLineCR (StrLen_t nLenChar=1)

bool	isEOF () const

void	SetStartPtr (const char *pszStart, StrLen_t nLenMax=StrT::k_LEN_MAX)

Public Member Functions inherited from Gray::cTextPos
	cTextPos (STREAM_POS_t lOffset=(STREAM_POS_t) k_ITERATE_BAD, ITERATE_t iLineNum=k_ITERATE_BAD, StrLen_t iColNum=k_StrLen_UNK) noexcept

void	InitTop () noexcept

bool	isTopLine () const noexcept

bool	isValidPos () const noexcept

STREAM_POS_t	get_Offset () const noexcept

ITERATE_t	get_LineNum () const noexcept
	< Get 0 based line. More...

ITERATE_t	get_Line1 () const noexcept
	< Get 1 based line. More...

StrLen_t	get_Column1 () const noexcept
	< Get 1 based column. More...

void	IncOffset (StrLen_t nLenOffsetSrc) noexcept

void	IncOffset (StrLen_t nLenOffsetSrc, StrLen_t nLenCol) noexcept

void	IncChar (StrLen_t nLenChar=1) noexcept

void	IncLine (StrLen_t nLenChar=1) noexcept

StrLen_t	GetStr2 (OUT char *pszOut, StrLen_t nLenOut) const

Static Public Member Functions
static CXML_ENCODING_TYPE GRAYCALL	GetEncodingEnum (cXmlString sEncoding)

static StrLen_t GRAYCALL	FixNewLines (char *pszBuffer, StrLen_t nLenInp)

Static Public Member Functions inherited from GrayLib::cXml
static StrLen_t GRAYCALL	ParseMicrosoftBOM (const BYTE *pszData)

static bool GRAYCALL	IsXML (const IniChar_t *pszStr, StrLen_t iLenMax=StrT::k_LEN_MAX)

static cXmlString GRAYCALL	GetAttributeStr (const IniChar_t *pszName, const cXmlString &sValue)

static void	AddPathElement (cXmlString &sPath, const cXmlString &sElement)

static void	RemovePathElement (cXmlString &sPath, const cXmlString &sElement)

Public Attributes
cTextPos	m_PosNode
	The cursor at the start of current XMLNODE_TYPE m_Pos. as opposed to cTextReader is the current cursor. More...

CXML_ENCODING_TYPE	m_eEncoding
	current encoding. More...

bool	m_bCondenseWhitespace
	try to preserve Whitespace or not? More...

int	m_iDepth
	Indent depth of reader. More...

Public Attributes inherited from Gray::cTextReader
const StrLen_t	m_iTabSize
	for proper tracking of the column number on errors. and m_CursorPos. 0 = not used/don't care. More...

Protected Member Functions
bool	IsAlpha (wchar_t anyByte) const

bool	IsAlphaNum (wchar_t anyByte) const

wchar_t	ToLower (wchar_t v) const

bool	IsStringEqual (const char pszData, const char pszEndTag, bool bIgnoreCase=false) const

bool	ReadWhitespace ()

HRESULT	ParseName (OUT cXmlString &rsName)

HRESULT	ParseStringTo (OUT cXmlString &rsText, const char *pszEndTag, bool bIgnoreWhitespace)

HRESULT	ParseAttrib (OUT cXmlString &sName, OUT cXmlString &sValue)

HRESULT	ParseAttribSet (OUT cXmlAttributeSet &Attribs)

HRESULT	ParseDeclaration (OUT cXmlAttributeSet &Attribs)

HRESULT	ParseUnknown (OUT cXmlString &sValue)

HRESULT	ParseComment (OUT cXmlString &sValue)

HRESULT	ParseText (OUT cXmlString &sValue, bool bCDATAExpected)

HRESULT	ParseNodeType ()

bool	ParseMicrosoftBOM ()

HRESULT	ParseElement (OUT cXmlString &sElement, OUT cXmlAttributeSet &Attribs)

HRESULT	ParseVisitType (cXmlReadVisitor *pVisitor, XMLNODE_TYPE eNodeType, bool bDoc, bool bCDATA)

Friends
class	cXmlNode

Additional Inherited Members
Public Types inherited from GrayLib::cXml
enum	XMLNODE_TYPE { XMLNODE_QTY }

Static Public Attributes inherited from Gray::cTextPos
static const cTextPos	k_Invalid
	Set to invalid values. More...

static const cTextPos	k_Zero
	Top of file. More...

Static Public Attributes inherited from GrayLib::cXml
static const char	k_xmlHeader [6] = "<?xml"
	"<?xml" // not case sensitive ! More...

static const char	k_xmlEnd [3] = "?>"
	"?>" More...

static const char	k_commentHeader [5] = "<!--"
	"<!--" // comments are not reentrant! More...

static const char	k_commentEnd [4] = "-->"
	"-->" More...

static const char	k_cdataHeader [10] = "<![CDATA["
	"<![CDATA[" More...

static const char	k_cdataEnd [4] = "]]>"
	"]]>" More...

static const char	k_dtdHeader [3] = "<!"
	"<!" More...

Protected Attributes inherited from Gray::cTextReader
const char *	m_pszStart
	starting read position in the data parsing stream/buffer. cTextPos cursor = m_pszStart + m_lOffset. More...

StrLen_t	m_nLenMax
	don't advance cTextPos::m_lOffset past this. More...

Protected Attributes inherited from Gray::cTextPos
STREAM_POS_t	m_lOffset
	byte offset into the file. 0 based More...

ITERATE_t	m_iLineNum
	0 based row/line, for debug purposes if there is an error. More...

StrLen_t	m_iColNum
	0 based column number. if used. # of characters, not bytes. UTF can have multi bytes per char. More...

Detailed Description

The state of XML reading/parsing at a given time. eXPat like generic XML loading. Similar to .Net XmlReader. Sort of similar to the JavaScript DOMParser Acts like cStreamInput ?

Constructor & Destructor Documentation

◆ cXmlReader()

GrayLib::cXmlReader::cXmlReader	(	const char *	pszStart = `""`,
		StrLen_t	nLenMax = `StrT::k_LEN_MAX`,
		StrLen_t	iTabSize = `cStrConst::k_TabSize`,
		CXML_ENCODING_TYPE	eEncoding = `CXML_ENCODING_UNKNOWN`,
		bool	bCondenseWhitespace = `true`
	)

◆ ~cXmlReader()

GrayLib::cXmlReader::~cXmlReader ( )

Member Function Documentation

◆ FixNewLines()

StrLen_t GRAYCALL GrayLib::cXmlReader::FixNewLines	(	char *	pszBuffer,
		StrLen_t	nLenInp
	)

static

Convert any "\r\n" or "\r" to just "\n" used by LoadFile.

◆ GetEncodingEnum()

CXML_ENCODING_TYPE GRAYCALL GrayLib::cXmlReader::GetEncodingEnum ( cXmlString sEncoding )

static

◆ IsAlpha()

bool GrayLib::cXmlReader::IsAlpha ( wchar_t anyByte ) const

protected

None of these methods are reliable for any language except English. Good for approximation, not great for accuracy.

This will only work for low-ASCII, everything else is assumed to be a valid letter. I'm not sure this is the best approach, but it is quite tricky trying to figure out alphabetical vs. not across encoding. So take a very conservative approach.

◆ IsAlphaNum()

bool GrayLib::cXmlReader::IsAlphaNum ( wchar_t anyByte ) const

protected

This will only work for low-ASCII, everything else is assumed to be a valid letter. I'm not sure this is the best approach, but it is quite tricky trying to figure out alphabetical vs. not across encoding. So take a very conservative approach.

◆ isCondensedWhitespace()

bool GrayLib::cXmlReader::isCondensedWhitespace ( ) const

inlinenoexcept

Return the current white space setting.

◆ IsStringEqual()

bool GrayLib::cXmlReader::IsStringEqual	(	const char *	pszData,
		const char *	pszEndTag,
		bool	bIgnoreCase = `false`
	)		const

protected

Return true if the next characters in the stream are any of the endTag sequences. Ignore case only works for English, and should only be relied on when comparing to English words: IsStringEqual( pszData, "version", true ) is fine.

bIgnoreCase = false = default.

◆ Parse() [1/2]

HRESULT GrayLib::cXmlReader::Parse ( cXmlReadVisitor * pVisitor )

Parse a buffer/document into pVisitor

◆ Parse() [2/2]

HRESULT GrayLib::cXmlReader::Parse	(	cXmlReadVisitor *	pVisitor,
		cXmlString	sElementParent
	)

Parse a element node.

◆ ParseAttrib()

HRESULT GrayLib::cXmlReader::ParseAttrib	(	OUT cXmlString &	sName,
		OUT cXmlString &	sValue
	)

protected

Attribute parsing starts: first letter of the name

Returns: the next char after the value end quote

Parse a single attribute. e.g. name="value".

◆ ParseAttribSet()

HRESULT GrayLib::cXmlReader::ParseAttribSet ( OUT cXmlAttributeSet & Attribs )

protected

Parse a set of attributes.

◆ ParseComment()

HRESULT GrayLib::cXmlReader::ParseComment ( OUT cXmlString & sValue )

protected

from the XML spec: [Definition: Comments may appear anywhere in a document outside other markup; in addition, they may appear within the document type declaration at places allowed by the grammar. They are not part of the document's character data; an XML processor MAY, but need not, make it possible for an application to retrieve the text of comments. For compatibility, the string "--" (double-hyphen) MUST NOT occur within comments.] Parameter entity references MUST NOT be recognized within comments.

An example of a comment:

//! <!-- declarations for <head> & <body> -->
//!

◆ ParseDeclaration()

HRESULT GrayLib::cXmlReader::ParseDeclaration ( OUT cXmlAttributeSet & Attribs )

protected

◆ ParseElement()

HRESULT GrayLib::cXmlReader::ParseElement	(	OUT cXmlString &	sElement,
		OUT cXmlAttributeSet &	Attribs
	)

protected

Parse an "<element>" or "<element />"

Returns: S_FALSE = Closed "<element />" S_OK = open tag must look for "</element>" close.

◆ ParseFile()

HRESULT GrayLib::cXmlReader::ParseFile	(	const FILECHAR_t *	pszXMLFile,
		cXmlReadVisitor *	pVisitor
	)

◆ ParseMicrosoftBOM()

bool GrayLib::cXmlReader::ParseMicrosoftBOM ( )

protected

Check for the Microsoft UTF-8 lead bytes.

◆ ParseName()

HRESULT GrayLib::cXmlReader::ParseName ( OUT cXmlString & rsName )

protected

Reads an XML name into the string provided. Returns a pointer just past the last character of the name, or 0 if the function has an error.

Names start with letters or underscores. Of course, in unicode, cXml has no idea what a letter is. The algorithm is generous.

After that, they can be letters, underscores, numbers, hyphens, or colons. (Colons are valid only for namespaces, but cXml can't tell namespaces from names.)

Returns: pointer to pszData after name.

◆ ParseNodeType()

HRESULT GrayLib::cXmlReader::ParseNodeType ( )

protected

Determine the XMLNODE_Type on the next data.

Returns: XMLNODE_TYPE

Elements start with a letter or underscore, but XML is reserved. Comments:

◆ ParseStream()

HRESULT GrayLib::cXmlReader::ParseStream	(	cStreamInput &	rInp,
		cXmlReadVisitor *	pVisitor
	)

◆ ParseStringTo()

HRESULT GrayLib::cXmlReader::ParseStringTo	(	OUT cXmlString &	rsText,
		const char *	pszEndTag,
		bool	bIgnoreWhitespace
	)

protected

Reads text. Returns a pointer past the given end tag. Wickedly complex options, but it keeps the (sensitive) code in one place.

Read text up to pszEndTag. substitute entities. But DONT read pszEndTag.

rsText = the string read
pszEndTag = read up to this. ignore case in the end tag
bTrimWhitespace = whether to keep the white space. certain tags always keep Whitespace

◆ ParseText() [1/2]

HRESULT GrayLib::cXmlReader::ParseText	(	const char *	pszText,
		cXmlReadVisitor *	pVisitor
	)

◆ ParseText() [2/2]

HRESULT GrayLib::cXmlReader::ParseText	(	OUT cXmlString &	sValue,
		bool	bCDATAExpected
	)

protected

Read in text chunk. Might use CDATA style.

Returns: S_FALSE = CDATA used.

◆ ParseUnknown()

HRESULT GrayLib::cXmlReader::ParseUnknown ( OUT cXmlString & sValue )

protected

read some unknown block enclosed in "<unknowntag>"

◆ ParseVisitType()

HRESULT GrayLib::cXmlReader::ParseVisitType	(	cXmlReadVisitor *	pVisitor,
		XMLNODE_TYPE	eNodeType,
		bool	bDoc,
		bool	bCDATA
	)

protected

◆ put_CondenseWhitespace()

void GrayLib::cXmlReader::put_CondenseWhitespace ( bool bCondense )

inlinenoexcept

The world does not agree on whether white space should be kept or not. In order to make everyone happy, these global, static functions are provided to set whether or not cXml will condense all white space into a single space or not. The default is to condense.

◆ ReadWhitespace()

bool GrayLib::cXmlReader::ReadWhitespace ( )

protected

skip whitespace.

Returns: false = no Whitespace found.

◆ ReturnError()

HRESULT GrayLib::cXmlReader::ReturnError ( HRESULT hRes ) const

◆ ToLower()

wchar_t GrayLib::cXmlReader::ToLower ( wchar_t v ) const

protected

Friends And Related Function Documentation

◆ cXmlNode

friend class cXmlNode

friend

Member Data Documentation

◆ m_bCondenseWhitespace

bool GrayLib::cXmlReader::m_bCondenseWhitespace

try to preserve Whitespace or not?

◆ m_eEncoding

CXML_ENCODING_TYPE GrayLib::cXmlReader::m_eEncoding

current encoding.

◆ m_iDepth

int GrayLib::cXmlReader::m_iDepth

Indent depth of reader.

◆ m_PosNode

cTextPos GrayLib::cXmlReader::m_PosNode

The cursor at the start of current XMLNODE_TYPE m_Pos. as opposed to cTextReader is the current cursor.

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

c:/Dennis/Source/Gray/GrayLib/include/Xml/cXmlReader.h
c:/Dennis/Source/Gray/GrayLib/src/Xml/cXmlReader.cpp

Public Member Functions

Static Public Member Functions

Public Attributes

Protected Member Functions

Friends

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ cXmlReader()

◆ ~cXmlReader()

Member Function Documentation

◆ FixNewLines()

◆ GetEncodingEnum()

◆ IsAlpha()

◆ IsAlphaNum()

◆ isCondensedWhitespace()

◆ IsStringEqual()

◆ Parse() [1/2]

◆ Parse() [2/2]

◆ ParseAttrib()

◆ ParseAttribSet()

◆ ParseComment()

◆ ParseDeclaration()

◆ ParseElement()

◆ ParseFile()

◆ ParseMicrosoftBOM()

◆ ParseName()

◆ ParseNodeType()

◆ ParseStream()

◆ ParseStringTo()

◆ ParseText() [1/2]

◆ ParseText() [2/2]

◆ ParseUnknown()

◆ ParseVisitType()

◆ put_CondenseWhitespace()

◆ ReadWhitespace()

◆ ReturnError()

◆ ToLower()

Friends And Related Function Documentation

◆ cXmlNode

Member Data Documentation

◆ m_bCondenseWhitespace

◆ m_eEncoding

◆ m_iDepth

◆ m_PosNode