A support class for applications which parse various text formats. More...

#include <tsTextParser.h>

Classes
class	Position
	A class which describes a position in the document. More...

Public Member Functions
	TextParser (const UString &text, Report &report)
	Constructor.

	TextParser (const UStringList &lines, Report &report)
	Constructor.

	TextParser (Report &report)
	Constructor.

virtual	~TextParser ()
	Destructor.

virtual void	clear ()
	Clear the document in the parser.

bool	eof () const
	Check end of file.

bool	eol () const
	Check end of line.

virtual bool	isAtNumberStart () const
	Check if the parser is at the start of a number (digit or minus sign).

bool	isAtPosition (const Position &pos) const
	Check if we are at the specified position in the document.

virtual bool	isAtXMLNameStart () const
	Check if the parser is at the start of an XML name.

virtual bool	isXMLNameChar (UChar c) const
	Check if a character is suitable in the middle of an XML name.

virtual bool	isXMLNameStartChar (UChar c) const
	Check if a character is suitable for starting an XML name.

size_t	lineNumber () const
	Get the current line number.

void	loadDocument (const UString &text)
	Load the document to parse.

void	loadDocument (const UStringList &lines)
	Load the document to parse from a list of lines.

bool	loadFile (const fs::path &fileName)
	Load the document to parse from a text file.

bool	loadStream (std::istream &strm)
	Load the document to parse from a text stream.

bool	match (const UString &str, bool skipIfMatch, CaseSensitivity cs=CASE_SENSITIVE)
	Check if the current position in the document matches a string.

virtual bool	parseJSONStringLiteral (UString &str)
	Parse a JSON string literal.

virtual bool	parseNumericLiteral (UString &str, bool allowHexa=false, bool allowFloat=true)
	Parse a numeric literal.

virtual bool	parseStringLiteral (UString &str, UChar requiredQuote=CHAR_NULL)
	Parse a string literal.

virtual bool	parseText (UString &result, const UString endToken, bool skipIfMatch, bool translateEntities)
	Parse text up to a given token.

virtual bool	parseXMLName (UString &name)
	Parse an XML name.

Position	position () const
	Save the position in the document.

void	rewind ()
	Rewind to start of document.

bool	saveFile (const fs::path &fileName)
	Save the document to parse to a text file.

bool	saveStream (std::ostream &strm)
	Save the document to parse to a text stream.

bool	seek (const Position &pos)
	Restore a previous position in the document.

bool	skipLine ()
	Skip to next line.

bool	skipWhiteSpace ()
	Skip all whitespaces, including end of lines.

Detailed Description

A support class for applications which parse various text formats.

Constructor & Destructor Documentation

◆ TextParser() [1/3]

ts::TextParser::TextParser ( Report & report )

Constructor.

The document to parse is empty.

Parameters

[in,out] report Where to report errors.

◆ TextParser() [2/3]

ts::TextParser::TextParser	(	const UStringList &	lines,
		Report &	report
	)

Constructor.

Parameters

[in]	lines	Reference to a list of text lines forming the document. The lifetime of the referenced list must equals or exceeds the lifetime of the parser.
[in,out]	report	Where to report errors.

◆ TextParser() [3/3]

ts::TextParser::TextParser	(	const UString &	text,
		Report &	report
	)

Constructor.

Parameters

[in]	text	Document text to parse with embedded new-line characters.
[in,out]	report	Where to report errors.

Member Function Documentation

◆ loadDocument() [1/2]

void ts::TextParser::loadDocument ( const UStringList & lines )

Load the document to parse from a list of lines.

Parameters

[in] lines Reference to a list of text lines forming the document. The lifetime of the referenced list must equals or exceeds the lifetime of the parser.

◆ loadDocument() [2/2]

void ts::TextParser::loadDocument ( const UString & text )

Load the document to parse.

Parameters

[in] text Document text to parse with embedded new-line characters.

◆ loadFile()

bool ts::TextParser::loadFile ( const fs::path & fileName )

Load the document to parse from a text file.

Parameters

[in] fileName Name of the file to load.

Returns: True on success, false on failure.

◆ loadStream()

bool ts::TextParser::loadStream ( std::istream & strm )

Load the document to parse from a text stream.

Parameters

[in,out] strm A standard text stream in input mode.

Returns: True on success, false on error.

◆ saveFile()

bool ts::TextParser::saveFile ( const fs::path & fileName )

Save the document to parse to a text file.

Parameters

[in] fileName Name of the file to save.

Returns: True on success, false on failure.

◆ saveStream()

bool ts::TextParser::saveStream ( std::ostream & strm )

Save the document to parse to a text stream.

Parameters

[in,out] strm A standard text stream in output mode.

Returns: True on success, false on error.

◆ eof()

bool ts::TextParser::eof ( ) const

Check end of file.

Returns: True if the parser reached the end of file.

◆ eol()

bool ts::TextParser::eol ( ) const

Check end of line.

Returns: True if the parser reached the end of line.

◆ position()

Position ts::TextParser::position ( ) const

inline

Save the position in the document.

Returns: The current position in the document.

◆ seek()

bool ts::TextParser::seek ( const Position & pos )

Restore a previous position in the document.

Parameters

[in] pos Previous position to restore.

Returns: True on success, false on error.

◆ isAtPosition()

bool ts::TextParser::isAtPosition ( const Position & pos ) const

Check if we are at the specified position in the document.

Parameters

[in] pos Previous position to check.

Returns: True if still at this position.

◆ lineNumber()

size_t ts::TextParser::lineNumber ( ) const

inline

Get the current line number.

Returns: The current line number.

◆ skipWhiteSpace()

bool ts::TextParser::skipWhiteSpace ( )

Skip all whitespaces, including end of lines.

Note that the optional BOM at start of an UTF-8 file has already been removed by the UTF-16 conversion.

Returns: Always true.

◆ skipLine()

bool ts::TextParser::skipLine ( )

Skip to next line.

Returns: Always true.

◆ match()

bool ts::TextParser::match	(	const UString &	str,
		bool	skipIfMatch,
		CaseSensitivity	cs = `CASE_SENSITIVE`
	)

Check if the current position in the document matches a string.

Parameters

[in]	str	A string to check at the current position in the document.
[in]	skipIfMatch	If true and str matches the current position, skip it in the document.
[in]	cs	Case sensitivity of the comparision.

Returns: True if str matches the current position in the document.

◆ parseText()

virtual bool ts::TextParser::parseText	(	UString &	result,
		const UString	endToken,
		bool	skipIfMatch,
		bool	translateEntities
	)

virtual

Parse text up to a given token.

Parameters

[out]	result	Returned parsed text.
[in]	endToken	Stop when this token is found. Do not include endToken in returned string.
[in]	skipIfMatch	If true, skip endToken in the parser.
[in]	translateEntities	If true, translate HTML entities in the text.

Returns: True on success, false if endToken was not found.

◆ isXMLNameStartChar()

virtual bool ts::TextParser::isXMLNameStartChar ( UChar c ) const

virtual

Check if a character is suitable for starting an XML name.

An XML name starts with a letter, underscore or colon.

Parameters

[in] c The character to check.

Returns: True if c is suitable for starting an XML name.

◆ isXMLNameChar()

virtual bool ts::TextParser::isXMLNameChar ( UChar c ) const

virtual

Check if a character is suitable in the middle of an XML name.

An XML name contains letters, digits, underscores, colons, dots and dashes.

Parameters

[in] c The character to check.

Returns: True if c is suitable in the middle of an XML name.

◆ isAtXMLNameStart()

virtual bool ts::TextParser::isAtXMLNameStart ( ) const

virtual

Check if the parser is at the start of an XML name.

Returns: True if the parser is at the start of a name.

◆ parseXMLName()

virtual bool ts::TextParser::parseXMLName ( UString & name )

virtual

Parse an XML name.

Parameters

[out] name Returned parsed name.

Returns: True on success, false if no name was not found.

◆ isAtNumberStart()

virtual bool ts::TextParser::isAtNumberStart ( ) const

virtual

Check if the parser is at the start of a number (digit or minus sign).

Returns: True if the parser is at the start of a number.

◆ parseNumericLiteral()

virtual bool ts::TextParser::parseNumericLiteral	(	UString &	str,
		bool	allowHexa = `false`,
		bool	allowFloat = `true`
	)

virtual

Parse a numeric literal.

Parameters

[out]	str	Returned numeric literal
[in]	allowHexa	If true, hexadecimal integers "0x..." are allowed.
[in]	allowFloat	It true, floating point values "[-]digits[.digits][e\|E[+\|-]digits]" are allowed.

Returns: True on success, false if no string literal was not found.

◆ parseStringLiteral()

virtual bool ts::TextParser::parseStringLiteral	(	UString &	str,
		UChar	requiredQuote = `CHAR_NULL`
	)

virtual

Parse a string literal.

A string literal is enclosed in simple or double quotes. Any similar quotation mark is considered part of the string when it is preceded by a backslash character.

Parameters

[out]	str	Returned string literal, including the first and last quote. When the method returns true (success), it is consequently guaranteed that the length of the returned string is greater than or equal to 2.
[in]	requiredQuote	If defined as single or double quote, accept only that type of quote. Otherwise, accept any of the two.

Returns: True on success, false if no string literal was not found.

◆ parseJSONStringLiteral()

virtual bool ts::TextParser::parseJSONStringLiteral ( UString & str )

virtual

Parse a JSON string literal.

Parameters

[out] str Returned decoded value of the string literal.

Returns: True on success, false if no string literal was not found.

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

tsTextParser.h

Classes

Public Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ TextParser() [1/3]

◆ TextParser() [2/3]

◆ TextParser() [3/3]

Member Function Documentation

◆ loadDocument() [1/2]

◆ loadDocument() [2/2]

◆ loadFile()

◆ loadStream()

◆ saveFile()

◆ saveStream()

◆ eof()

◆ eol()

◆ position()

◆ seek()

◆ isAtPosition()

◆ lineNumber()

◆ skipWhiteSpace()

◆ skipLine()

◆ match()

◆ parseText()

◆ isXMLNameStartChar()

◆ isXMLNameChar()

◆ isAtXMLNameStart()

◆ parseXMLName()

◆ isAtNumberStart()

◆ parseNumericLiteral()

◆ parseStringLiteral()

◆ parseJSONStringLiteral()