Reader Class Reference

Reads and interprets text files. More...

#include <maxtextfile.h>

Inheritance diagram for Reader:

Public Types
enum	TextFileReaderEncoding { FAVOR_UTF8 = 0x10000000 , FOUND_BOM = 0x20000000 , FOUND_COOKIE = 0x40000000 , FLIPPED = 0x80000000 }
	Text file reading encoding. More...
enum	EOFCharacterHandling { DEFAULT_EOF_HANDLING , STOP_READING_AT_EOF , FILTEROUT_EOF_CHARACTER , IGNORE_EOF_CHARACTER }
	EOF character handling. More...

Public Member Functions
	Reader ()
	Default Constructor. More...
virtual	~Reader ()
	Destructor. More...
bool	Open (FILE *file, unsigned int encoding=0, LineEndMode mode=Text)
	Wrap ANSI C FILE pointer This service is used to allow a developer to access a file open with fopen but with the advantage to use the SDK API. More...
bool	Open (HANDLE fileHandle, unsigned int encoding=0, LineEndMode mode=Text)
	Wrap a Win32 file handle. More...
bool	Open (const MCHAR *fileName, unsigned int encoding=0, LineEndMode mode=Text)
	Open a file using a file name. More...
bool	Open (const MaxSDK::Util::MaxString &fileName, unsigned int encoding=0, LineEndMode mode=Text)
	Open a file using a file name. More...
void	Close ()
	Close the underlying stream and free any intermediate data. More...
MaxString	LastError () const
	Returns the last error return by the BinaryStream. More...
unsigned int	Encoding () const
	Returns the current encoding of this file. More...
LineEndMode	Mode () const
	Determine how this reader handles line ending. More...
void	SetReadBufferSize (size_t readSize)
	Set the read buffer size. More...
size_t	GetReadBufferSize () const
	Returns the read buffer size. More...
void	SetDetectSize (size_t detectSize)
	Set the default size of the buffer used to validate encoding. More...
size_t	GetDetectSize () const
	Returns the detect buffer size. More...
size_t	NumberOfChars () const
	Return the number of characters in the file. More...
size_t	NumberOfLines () const
	Calculate the total number of line feeds in the file. More...
void	SetEOFCharacterHandling (EOFCharacterHandling)
	Set the EOF character handling method and refilter the buffer. More...
EOFCharacterHandling	GetEOFCharacterHandling () const
	Get the EOF character handling method. More...
virtual Char	ReadChar (bool peek=false) const
	Reads a single char. More...
virtual unsigned int	ReadCharUTF32 (bool peek=false) const
	Reads a single char and returns it's UTF32 representation. More...
virtual MaxString	ReadChars (size_t nchars) const
	Reads characters from the file. More...
virtual MaxString	ReadLine (size_t nchars=(size_t) -1, bool dontReturnEOL=false) const
	Reads a line from the file (or nchars, depending on which one comes first.) More...
virtual MaxString	ReadChunk (size_t len, bool dontReturnLastEOL=false) const
	Reads up to "len" bytes from the file and convert it to a unicode-compliant string. More...
virtual MaxString	ReadFull () const
	Reads the file in a single operation and returns it in a single string object. More...
virtual size_t	PositionBytes () const
	Get the number of bytes read so far. More...
size_t	Position () const
	Get the number of characters read so far. More...
size_t	LineNumber () const
	Get the current line number. More...
virtual size_t	Seek (long offset, int origin)
	Seek inside the stream. More...
virtual bool	IsEndOfFile () const
	Returns true if file at the end. More...
virtual bool	IsFileOpen () const
	Returns true if file is open. More...
virtual size_t	UnreadChar (const Char &c)
	Unread a character. More...
Public Member Functions inherited from BaseTextReader
virtual	~BaseTextReader ()

Static Public Member Functions
static bool	Detect (void *data, size_t len, unsigned int &encoding, size_t *ignoreBytes)
	Detect the encoding of the passed buffer. More...
static size_t	NumberOfChars (const void *data, size_t len, unsigned int encoding=CP_ACP)
	Determine the number of chars inside a buffer. More...
static size_t	NumberOfLines (const void *data, size_t length, unsigned int encoding=CP_ACP)
	Determine the number of line feeds inside a buffer. More...
template<typename ChType , ChType ch>
static size_t	RemoveCharacter (ChType *data, size_t len)
	Remove ch character from the passed buffer. More...
template<typename ChType , ChType ch>
static size_t	TruncateAtCharacter (ChType *data, size_t len)
	Truncate buffer at ch character. More...
Static Public Member Functions inherited from MaxHeapOperators
static UtilExport void *	operator new (size_t size)
	Standard new operator used to allocate objects If there is insufficient memory, an exception will be thrown. More...
static UtilExport void *	operator new (size_t size, const std::nothrow_t &e)
	Standard new operator used to allocate objects if there is insufficient memory, NULL will be returned. More...
static UtilExport void *	operator new (size_t size, const char *filename, int line)
	New operator used to allocate objects that takes the filename and line number where the new was called If there is insufficient memory, an exception will be thrown. More...
static UtilExport void *	operator new (size_t size, int block_type, const char *filename, int line)
	New operator used to allocate objects that takes the type of memory, filename and line number where the new was called If there is insufficient memory, an exception will be thrown. More...
static UtilExport void *	operator new (size_t size, const std::nothrow_t &e, const char *filename, int line)
	New operator used to allocate objects that takes the filename and line number where the new was called If there is insufficient memory, NULL will be returned. More...
static UtilExport void *	operator new (size_t size, unsigned long flags)
	New operator used to allocate objects that takes extra flags to specify special operations If there is insufficient memory, an exception will be thrown. More...
static UtilExport void *	operator new (size_t size, const std::nothrow_t &e, unsigned long flags)
	New operator used to allocate objects that takes extra flags to specify special operations If there is insufficient memory, NULL will be returned. More...
static UtilExport void *	operator new[] (size_t size)
	New operator used to allocate arrays of objects If there is insufficient memory, an exception will be thrown. More...
static UtilExport void *	operator new[] (size_t size, const std::nothrow_t &e)
	New operator used to allocate arrays of objects If there is insufficient memory, NULL will be returned. More...
static UtilExport void *	operator new[] (size_t size, const char *filename, int line)
	New operator used to allocate arrays of objects If there is insufficient memory, an exception will be thrown. More...
static UtilExport void *	operator new[] (size_t size, int block_type, const char *filename, int line)
	New operator used to allocate arrays of objects. More...
static UtilExport void *	operator new[] (size_t size, const std::nothrow_t &e, const char *filename, int line)
	New operator used to allocate arrays of objects If there is insufficient memory, NULL will be returned. More...
static UtilExport void *	operator new[] (size_t size, unsigned long flags)
	New operator used to allocate arrays of objects If there is insufficient memory, an exception will be thrown. More...
static UtilExport void *	operator new[] (size_t size, const std::nothrow_t &e, unsigned long flags)
	New operator used to allocate arrays of objects If there is insufficient memory, NULL will be returned. More...
static UtilExport void	operator delete (void *ptr)
	Standard delete operator used to deallocate an object If the pointer is invalid, an exception will be thrown. More...
static UtilExport void	operator delete (void *ptr, const std::nothrow_t &e)
	Standard delete operator used to deallocate an object If the pointer is invalid, nothing will happen. More...
static UtilExport void	operator delete (void *ptr, const char *filename, int line)
	Delete operator used to deallocate an object that takes the filename and line number where the delete was called If the pointer is invalid, an exception will be thrown. More...
static UtilExport void	operator delete (void *ptr, int block_type, const char *filename, int line)
	Delete operator used to deallocate an object that takes the type of memory, filename and line number where the delete was called If the pointer is invalid, an exception will be thrown. More...
static UtilExport void	operator delete (void *ptr, const std::nothrow_t &e, const char *filename, int line)
	Delete operator used to deallocate an object that takes the filename and line number where the delete was called If the pointer is invalid, nothing will happen. More...
static UtilExport void	operator delete (void *ptr, unsigned long flags)
	Delete operator used to deallocate an object that takes extra flags to specify special operations If the pointer is invalid, an exception will be thrown. More...
static UtilExport void	operator delete (void *ptr, const std::nothrow_t &e, unsigned long flags)
	Delete operator used to deallocate an object that takes extra flags to specify special operations If the pointer is invalid, nothing will happen. More...
static UtilExport void	operator delete[] (void *ptr)
	Standard delete operator used to deallocate an array of objects If the pointer is invalid, an exception will be thrown. More...
static UtilExport void	operator delete[] (void *ptr, const std::nothrow_t &e)
	Standard delete operator used to deallocate an array of objects If the pointer is invalid, nothing will happen. More...
static UtilExport void	operator delete[] (void *ptr, const char *filename, int line)
	Delete operator used to deallocate an array of objects that takes the filename and line number where the delete was called If the pointer is invalid, an exception will be thrown. More...
static UtilExport void	operator delete[] (void *ptr, int block_type, const char *filename, int line)
	Delete operator used to deallocate an array of objects that takes the type of memory, filename and line number where the delete was called If the pointer is invalid, an exception will be thrown. More...
static UtilExport void	operator delete[] (void *ptr, const std::nothrow_t &e, const char *filename, int line)
	Delete operator used to deallocate an array of objects that takes the filename and line number where the delete was called If the pointer is invalid, nothing will happen. More...
static UtilExport void	operator delete[] (void *ptr, unsigned long flags)
	Delete operator used to deallocate an array of objects that takes extra flags to specify special operations If the pointer is invalid, an exception will be thrown. More...
static UtilExport void	operator delete[] (void *ptr, const std::nothrow_t &e, unsigned long flags)
	Delete operator used to deallocate an array of objects that takes extra flags to specify special operations If the pointer is invalid, an exception will be thrown. More...
static UtilExport void *	operator new (size_t size, void *placement_ptr)
	Placement new operator. More...
static UtilExport void	operator delete (void *ptr, void *placement_ptr)
	Placement delete operator. More...
static UtilExport void *	aligned_malloc (size_t size, size_t alignment)
	Allocates memory on a specified alignment boundary. More...
static UtilExport void *	aligned_realloc (void *ptr, size_t size, size_t alignment)
	Reallocates memory on a specified alignment boundary. More...
static UtilExport void	aligned_free (void *ptr)
	Frees a block of memory that was allocated with aligned_malloc/aligned_realloc. More...

Protected Types
enum	TextFileReaderError {   ALL_OK , STREAM_INVALID_ARGUMENT , STREAM_ALREADY_OPEN , STREAM_NOT_OPEN ,   ERR_INVALID_FORMAT , STREAM_ERROR }
	Internal processing error code. More...

Protected Member Functions
void	Detect (size_t len) const
	Detect the opened file encoding by analyzing the first "len" bytes of the file. More...
size_t	FillBuffer (size_t len, bool force=false, bool binary=false, bool detecting_encoding=false) const
	Read and cache len bytes from stream. More...
size_t	Filter (size_t pos) const
	Apply the selected open mode on the internal cache buffer up to position. More...
size_t	Filter (size_t pos, bool processBufferBoundaryCRLF) const
	Apply the selected open mode on the internal cache buffer up to position. More...
size_t	EnsureBufferContains (size_t len) const
	Ensure buffer size can contains the passed length. More...
size_t	NumberOfChars (const void *data, size_t size) const
	Return the number of characters in the passed buffer depending on the current encoding. More...
size_t	ConvertNumUTF8CharsToNumBytes (const char *data, size_t num)
	Return the number of bytes corresponding to the num of UTF8 chars in passed buffer. More...
size_t	ConvertNumUTF16CharsToNumBytes (const MCHAR *data, size_t num)
	Return the number of bytes corresponding to the num of UTF16 chars in passed buffer. More...
size_t	ConvertNumCharsToNumBytes (const char *data, size_t num, unsigned int encoding)
	Return the number of bytes corresponding to the num of chars in passed buffer depending on the encoding. More...
size_t	NumberOfLines (const void *data, size_t size) const
	Calculate the total number of line feeds in the passed buffer. More...
template<typename ChType , typename CharLengthFunctor , int maxCharLength>
ChType *	ReadChar (size_t &charLengthT, bool peek, const CharLengthFunctor &CharLengthFunction) const
	INTERNAL FUNCTION. More...
template<typename ChType >
MaxString	MakeString (const ChType *data, size_t length, bool dontReturnEndingCRLF) const
size_t	Unread (const MaxString &string)
	Unread String. More...
size_t	SeekToEnd (long offset=0)
	INTERNAL FUNCTION. More...
size_t	SeekToAbsolute (long offset)
	Seek to an absolute point inside the text stream. More...
size_t	SeekFromCurrent (long offset)
	Advance "offset" characters. More...
bool	Open (BinaryStream *stream, unsigned int encoding=0, LineEndMode mode=Text, bool closeOnDelete=false)
	Open an abstract BinaryStream. More...

Protected Attributes
BinaryStream *	_stream
bool	_streamDelete
bool	_readCR
bool	_readLF
LineEndMode	_endOfLineMode
size_t	_detectSize
size_t	_readSize
EOFCharacterHandling	_eofCharacterHandling
TextFileReaderError	_error
unsigned int	_encoding
bool	_encodingDetected
BinaryStreamMemory *	_backbuffer
size_t	_ignoreBytes
size_t	_positionBytes
size_t	_positionChars
size_t	_line

Friends
class	ReaderWriter
class	CharBinaryStream
class	BinaryStreamMemory

Detailed Description

Reads and interprets text files.

This class was designed to perform file and stream I/O in a code page neutral way.

It was designed to perform resolve the following problems:

• Reads and interprets correctly the BOM (an invisible character at the beginning of unicode files.)
• Detect correctly UTF-8 and UTF-16 files. (even if it's not signed.)
• Detect encoding cookies. XML files usually begins with "<?xml encoding='????'>". The detection algorithm will interpret this directive correctly.
• Prevent from splitting a character. In UTF-16, UTF-8 and some ANSI codepage, characters can be stored on 1 to 6 bytes. All the operations of this object are designed to avoid to returns a partial character.

Plugin developer should consider using this class to perform File I/O to ensure that the files they generate remain compatible to previous version of Max.

See also

ReaderWriter class when file IO requirements are for reading and writing.

Member Enumeration Documentation

TextFileReaderEncoding

enum TextFileReaderEncoding

Text file reading encoding.

Enumerator
FAVOR_UTF8
FOUND_BOM
FOUND_COOKIE
FLIPPED

                                {
        /* If the file's encoding cannot be detected, favor UTF-8.
           By default, we favor ACP encoding. */
        FAVOR_UTF8 = 0x10000000,
 
        /* Found a BOM at the beginning of the file. */
        FOUND_BOM = 0x20000000,
 
        /* Found a cookie at the beginning of the file. */
        FOUND_COOKIE = 0x40000000,
 
        /* Found flipped UTF-16 data. */
        FLIPPED = 0x80000000
    };

EOFCharacterHandling

enum EOFCharacterHandling

EOF character handling.

Enumerator
DEFAULT_EOF_HANDLING
STOP_READING_AT_EOF	Used by ReaderWriter to override default value.
FILTEROUT_EOF_CHARACTER	Reading of file terminate at EOF character - this is Reader in text mode.
IGNORE_EOF_CHARACTER	EOF character are filter out - this is the ReaderWriter preferred mode. EOF character are read as regular character - this is Reader in binary mode.

                              {
        DEFAULT_EOF_HANDLING,       
        STOP_READING_AT_EOF,            
        FILTEROUT_EOF_CHARACTER,    
        IGNORE_EOF_CHARACTER        
    };

TextFileReaderError

enum TextFileReaderError

protected

Internal processing error code.

Used by LastError to determine the proper message to generate.

Enumerator
ALL_OK
STREAM_INVALID_ARGUMENT	No errors.
STREAM_ALREADY_OPEN	Invalid argument error.
STREAM_NOT_OPEN	Stream already open.
ERR_INVALID_FORMAT	Stream not open.
STREAM_ERROR	Invalid. Stream error

                             {
        ALL_OK,                     
        STREAM_INVALID_ARGUMENT,    
        STREAM_ALREADY_OPEN,        
        STREAM_NOT_OPEN,            
        ERR_INVALID_FORMAT,         
        STREAM_ERROR                
    };

Constructor & Destructor Documentation

Reader()

Reader

(

)

Default Constructor.

~Reader()

virtual ~Reader ( )

virtual

Destructor.

Member Function Documentation

Detect() [1/2]

void Detect ( size_t  len ) const

protected

Detect the opened file encoding by analyzing the first "len" bytes of the file.

Parameters

len	Size of the buffer to use to detect the encoding

Returns

.

FillBuffer()

size_t FillBuffer ( size_t  len, bool  force = false, bool  binary = false, bool  detecting_encoding = false  ) const

protected

Read and cache len bytes from stream.

Parameters

len
force
binary
detecting_encoding

Filter() [1/2]

size_t Filter ( size_t  pos ) const

protected

Apply the selected open mode on the internal cache buffer up to position.

Parameters

pos	Position to stop filtering

Returns

Size of the buffer filtered

Filter() [2/2]

size_t Filter ( size_t  pos, bool  processBufferBoundaryCRLF  ) const

protected

Apply the selected open mode on the internal cache buffer up to position.

Parameters

pos	Position to stop filtering
processBufferBoundaryCRLF	if true, take care of the CR or LF which is read in the last FillBuffer call

Returns

Size of the buffer filtered

EnsureBufferContains()

size_t EnsureBufferContains ( size_t  len ) const

protected

Ensure buffer size can contains the passed length.

Parameters

len	The minimum size of the cache buffer

Returns

The remaining buffer size

NumberOfChars() [1/3]

size_t NumberOfChars ( const void *  data, size_t  size  ) const

protected

Return the number of characters in the passed buffer depending on the current encoding.

Parameters

data	Buffer to evaluate
size	The size of the buffer in bytes

Returns

The total number of chars.

ConvertNumUTF8CharsToNumBytes()

size_t ConvertNumUTF8CharsToNumBytes ( const char *  data, size_t  num  )

protected

Return the number of bytes corresponding to the num of UTF8 chars in passed buffer.

Parameters

data	- Buffer to evaluate
num	- num of chars in the passed buffer

Returns

The total number of bytes.

ConvertNumUTF16CharsToNumBytes()

size_t ConvertNumUTF16CharsToNumBytes ( const MCHAR *  data, size_t  num  )

protected

Return the number of bytes corresponding to the num of UTF16 chars in passed buffer.

Parameters

data	Buffer to evaluate
num	num of chars in the passed buffer

Returns

The total number of bytes.

ConvertNumCharsToNumBytes()

size_t ConvertNumCharsToNumBytes ( const char *  data, size_t  num, unsigned int  encoding  )

protected

Return the number of bytes corresponding to the num of chars in passed buffer depending on the encoding.

Parameters

data	Buffer to evaluate
num	number of chars in the passed buffer
encoding

Returns

The total number of bytes.

NumberOfLines() [1/3]

size_t NumberOfLines ( const void *  data, size_t  size  ) const

protected

Calculate the total number of line feeds in the passed buffer.

Parameters

data	The buffer to evaluate the number of line
size	The size of the buffer in bytes

Returns

The total number of lines.

ReadChar() [1/2]

ChType* ReadChar ( size_t &  charLengthT, bool  peek, const CharLengthFunctor &  CharLengthFunction  ) const

protected

INTERNAL FUNCTION.

Used in the implementation of ReadChar() and ReadCharUTF32().

MakeString()

MaxString MakeString ( const ChType *  data, size_t  length, bool  dontReturnEndingCRLF  ) const

protected

Unread()

size_t Unread ( const MaxString &  string )

protected

Unread String.

Put back a sequence of character inside the buffer. The data will be re-read next time you call read. This is used internally when parsing max scripts.

Parameters

string

String to put back in the buffer

Returns

Unread size in number of characters.

SeekToEnd()

size_t SeekToEnd ( long  offset = 0 )

protected

INTERNAL FUNCTION.

Used by Seek Seek inside this text stream with the end as the reference point.

Parameters

offset

Offset characters from end of file to seek to

Returns

Returns the absolute position of the text file. (in chars)

SeekToAbsolute()

size_t SeekToAbsolute ( long  offset )

protected

Seek to an absolute point inside the text stream.

Parameters

offset

Offset characters from end of file to seek to

Returns

Returns the absolute position of the text file. (in chars)

SeekFromCurrent()

size_t SeekFromCurrent ( long  offset )

protected

Advance "offset" characters.

Parameters

offset

Offset characters from end of file to seek to

Returns

Returns the absolute position of the text file. (in chars)

Open() [1/5]

bool Open ( BinaryStream *  stream, unsigned int  encoding = 0, LineEndMode  mode = Text, bool  closeOnDelete = false  )

protected

Open an abstract BinaryStream.

Parameters

stream	Opened stream the Reader uses
encoding	This parameter can contains hint to the detection algorithm. Acceptable values are all codepages numbers that are recognized by Windows.

In addition to that, you can also specify FAVOR_UTF8. It can be used to cascade the detection of the codepage. For example, if you specify "CP_ACP | FAVOR_UTF8", the detection algorithm will treat any non-UTF8 data as ACP.

See also

TextFileReaderEncoding

Parameters

mode

See also

LineEndMode - default Text

Parameters

closeOnDelete

Delete the "stream" at the same time of this object.

Open() [2/5]

bool Open	(	FILE *	file,
		unsigned int	encoding = 0,
		LineEndMode	mode = Text
	)

Wrap ANSI C FILE pointer This service is used to allow a developer to access a file open with fopen but with the advantage to use the SDK API.

Using this service allows the developer to not worry about character encoding The developer is responsible to close the file once he is done.

Parameters

file	ANSI C FILE pointer
encoding	This parameter can contains hint to the detection algorithm. Acceptable values are all codepages numbers that are recognized by Windows.

In addition to that, you can also specify FAVOR_UTF8. It can be used to cascade the detection of the codepage. For example, if you specify "CP_ACP | FAVOR_UTF8", the detection algorithm will treat any non-UTF8 data as ACP.

See also

TextFileReaderEncoding The flag is only used when no BOM is present or if the file is a new file.
If the file has been open with css=<encoding>, a BOM is present and this parameter is ignored.

Parameters

mode

See also

LineEndMode - default Text

Returns

true if successful, false otherwise

Open() [3/5]

bool Open	(	HANDLE	fileHandle,
		unsigned int	encoding = 0,
		LineEndMode	mode = Text
	)

Wrap a Win32 file handle.

Parameters

fileHandle	File Handle
encoding	This parameter can contains hint to the detection algorithm. Acceptable values are all codepages numbers that are recognized by Windows.

In addition to that, you can also specify FAVOR_UTF8. It can be used to cascade the detection of the codepage. For example, if you specify "CP_ACP | FAVOR_UTF8", the detection algorithm will treat any non-UTF8 data as ACP.

See also

TextFileReaderEncoding

Parameters

mode

See also

LineEndMode - default Text

Returns

true if successful, false otherwise

Open() [4/5]

bool Open	(	const MCHAR *	fileName,
		unsigned int	encoding = 0,
		LineEndMode	mode = Text
	)

Open a file using a file name.

Parameters

fileName	File name to open. If file does not exist, it will be created.
encoding	This parameter can contains hint to the detection algorithm. Acceptable values are all codepages numbers that are recognized by Windows.

In addition to that, you can also specify FAVOR_UTF8. It can be used to cascade the detection of the codepage. For example, if you specify "CP_ACP | FAVOR_UTF8", the detection algorithm will treat any non-UTF8 data as ACP.

See also

TextFileReaderEncoding

Parameters

mode

See also

LineEndMode - default Text

Returns

true if successful, false otherwise

Open() [5/5]

bool Open	(	const MaxSDK::Util::MaxString &	fileName,
		unsigned int	encoding = 0,
		LineEndMode	mode = Text
	)

Open a file using a file name.

Parameters

fileName	File name to open. If file does not exist, it will be created.
encoding	This parameter can contains hint to the detection algorithm. Acceptable values are all codepages numbers that are recognized by Windows.

In addition to that, you can also specify FAVOR_UTF8. It can be used to cascade the detection of the codepage. For example, if you specify "CP_ACP | FAVOR_UTF8", the detection algorithm will treat any non-UTF8 data as ACP.

See also

TextFileReaderEncoding

Parameters

mode

See also

LineEndMode - default Text

Returns

true if successful, false otherwise

Close()

void Close

(

)

Close the underlying stream and free any intermediate data.

LastError()

MaxString LastError

(

)

const

Returns the last error return by the BinaryStream.

Returns

Error string

Encoding()

unsigned int Encoding

(

)

const

Returns the current encoding of this file.

See also

TextFileReaderEncoding The actual code page can be retrieved this way : "Encoding() & MSDE_CP_MASK"

Returns

Returns the actual encoding found

Mode()

LineEndMode Mode

(

)

const

Determine how this reader handles line ending.

Returns

LineEndMode

SetReadBufferSize()

void SetReadBufferSize

(

size_t

readSize

)

Set the read buffer size.

The larger the buffer is, the better read performance is.

Parameters

readSize

Size of the buffer to read. Default 4096

GetReadBufferSize()

size_t GetReadBufferSize

(

)

const

Returns the read buffer size.

SetDetectSize()

void SetDetectSize

(

size_t

detectSize

)

Set the default size of the buffer used to validate encoding.

This parameter is used internally when calling Detect.

Parameters

detectSize

Size of the buffer used when detecting the current character type. Default 65536

GetDetectSize()

size_t GetDetectSize

(

)

const

Returns the detect buffer size.

NumberOfChars() [2/3]

size_t NumberOfChars

(

)

const

Return the number of characters in the file.

Returns

The total number of chars.

NumberOfLines() [2/3]

size_t NumberOfLines

(

)

const

Calculate the total number of line feeds in the file.

Returns

The total number of lines.

SetEOFCharacterHandling()

void SetEOFCharacterHandling

(

EOFCharacterHandling

)

Set the EOF character handling method and refilter the buffer.

See also

EOFCharacterHandling

GetEOFCharacterHandling()

EOFCharacterHandling GetEOFCharacterHandling

(

)

const

Get the EOF character handling method.

See also

EOFCharacterHandling

ReadChar() [2/2]

virtual Char ReadChar ( bool  peek = false ) const

virtual

Reads a single char.

Parameters

peek	Read a char but does not move the internal pointer to next char. Default is false so we move to next character

Returns

The character read.

Implements BaseTextReader.

ReadCharUTF32()

virtual unsigned int ReadCharUTF32 ( bool  peek = false ) const

virtual

Reads a single char and returns it's UTF32 representation.

Parameters

peek	Read a char but does not move the internal pointer to next char. Default is false so we move to next character

Returns

The UTF32 char representation

Implements BaseTextReader.

ReadChars()

virtual MaxString ReadChars ( size_t  nchars ) const

virtual

Reads characters from the file.

Parameters

nchars

Stop reading after 'nchars' characters.

Returns

Line read.

Implements BaseTextReader.

ReadLine()

virtual MaxString ReadLine ( size_t  nchars = (size_t) -1, bool  dontReturnEOL = false  ) const

virtual

Reads a line from the file (or nchars, depending on which one comes first.)

Parameters

nchars	Stop reading after 'nchars' characters even if the EOL was not found.
dontReturnEOL	By default, this function will returns the line including it's end-of-line character(s) unless you set "dontReturnEOL" to true.

Implements BaseTextReader.

ReadChunk()

virtual MaxString ReadChunk ( size_t  len, bool  dontReturnLastEOL = false  ) const

virtual

Reads up to "len" bytes from the file and convert it to a unicode-compliant string.

Parameters

len	Number of bytes to take out of the underlying stream.
dontReturnLastEOL	Determine if this function will trim the last EOL sequence.

ReadFull()

virtual MaxString ReadFull ( ) const

virtual

Reads the file in a single operation and returns it in a single string object.

Returns

The full stream content

PositionBytes()

virtual size_t PositionBytes ( ) const

virtual

Get the number of bytes read so far.

Position()

size_t Position ( ) const

virtual

Get the number of characters read so far.

Implements BaseTextReader.

LineNumber()

size_t LineNumber ( ) const

virtual

Get the current line number.

Implements BaseTextReader.

Seek()

virtual size_t Seek ( long  offset, int  origin  )

virtual

Seek inside the stream.

Parameters

offset	The seeks operations are done in number of characters (not bytes).
origin	The direction to move. Origin can be one of the following SEEK_CUR Current position of file pointer. SEEK_END End of file. SEEK_SET Beginning of file.

Returns

Returns the absolute position of the text file. (in chars)

Implements BaseTextReader.

IsEndOfFile()

virtual bool IsEndOfFile ( ) const

virtual

Returns true if file at the end.

Implements BaseTextReader.

IsFileOpen()

virtual bool IsFileOpen ( ) const

virtual

Returns true if file is open.

Implements BaseTextReader.

UnreadChar()

virtual size_t UnreadChar ( const Char &  c )

virtual

Unread a character.

Put back a character inside the buffer. The data will be re-read next time you call read.

Parameters

c	Char to put back in the buffer

Returns

Number of character written.

Implements BaseTextReader.

Detect() [2/2]

static bool Detect ( void *  data, size_t  len, unsigned int &  encoding, size_t *  ignoreBytes  )

static

Detect the encoding of the passed buffer.

Parameters

data	Buffer to detect the encoding
len	Size of the passed buffer
encoding	(in/out) In input, tell the detector what to expect. On output it contains what the detector found.
ignoreBytes	(out) On output, tell the caller how much bytes it must ignore at the beginning of the file because of the BOM.

Returns

Returns true if the encoding was formally detected. Or false, if it was guessed.

NumberOfChars() [3/3]

static size_t NumberOfChars ( const void *  data, size_t  len, unsigned int  encoding = CP_ACP  )

static

Determine the number of chars inside a buffer.

It's more complex than just strlen or wcslen. Those two functions will returns the number of char or WCHAR entries. This function will returns the number of of characters (or symbol).

Parameters

data	Buffer containing a string to count the number of symbols
len	The size of the buffer in bytes
encoding	Encoding to use to count the number of symbols

Returns

Number of symbols

NumberOfLines() [3/3]

static size_t NumberOfLines ( const void *  data, size_t  length, unsigned int  encoding = CP_ACP  )

static

Determine the number of line feeds inside a buffer.

Parameters

data	Buffer in which ' ' are counted.
length	The size of the buffer in bytes
encoding	Encoding of "data". Can be any valid encoding. ie. MSDE_CP_UTF16, CP_UTF8, CP_ACP, etc.

Returns

Number of line feed detected

RemoveCharacter()

static size_t RemoveCharacter ( ChType *  data, size_t  len  )

static

Remove ch character from the passed buffer.

Parameters

data	Buffer in which ch are to be removed.
len	Length of data (in MCHAR)

TruncateAtCharacter()

static size_t TruncateAtCharacter ( ChType *  data, size_t  len  )

static

Truncate buffer at ch character.

Parameters

data	Buffer to validate.
len	Length of data (in MCHAR)

Friends And Related Function Documentation

ReaderWriter

friend class ReaderWriter

friend

CharBinaryStream

friend class CharBinaryStream

friend

BinaryStreamMemory

friend class BinaryStreamMemory

friend

Member Data Documentation

_stream

BinaryStream* _stream

protected

_streamDelete

bool _streamDelete

protected

_readCR

bool _readCR

mutableprotected

_readLF

bool _readLF

mutableprotected

_endOfLineMode

LineEndMode _endOfLineMode

protected

_detectSize

size_t _detectSize

protected

_readSize

size_t _readSize

protected

_eofCharacterHandling

EOFCharacterHandling _eofCharacterHandling

mutableprotected

_error

TextFileReaderError _error

mutableprotected

_encoding

unsigned int _encoding

mutableprotected

_encodingDetected

bool _encodingDetected

mutableprotected

_backbuffer

BinaryStreamMemory* _backbuffer

mutableprotected

_ignoreBytes

size_t _ignoreBytes

mutableprotected

_positionBytes

size_t _positionBytes

mutableprotected

_positionChars

size_t _positionChars

mutableprotected

_line

size_t _line

mutableprotected