path: root/src/contrib/xml/tinyxmlparser.cpp

/*:*
 *: File: ./src/contrib/xml/tinyxmlparser.cpp
 *: 
 *: yChat; Homepage: www.yChat.org; Version 0.8.3-CURRENT
 *: 
 *: Copyright (C) 2003 Paul C. Buetow, Volker Richter
 *: Copyright (C) 2004 Paul C. Buetow
 *: Copyright (C) 2005 EXA Digital Solutions GbR
 *: 
 *: This program is free software; you can redistribute it and/or
 *: modify it under the terms of the GNU General Public License
 *: as published by the Free Software Foundation; either version 2
 *: of the License, or (at your option) any later version.
 *: 
 *: This program is distributed in the hope that it will be useful,
 *: but WITHOUT ANY WARRANTY; without even the implied warranty of
 *: MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *: GNU General Public License for more details.
 *: 
 *: You should have received a copy of the GNU General Public License
 *: along with this program; if not, write to the Free Software
 *: Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
 *:*/

/*
www.sourceforge.net/projects/tinyxml
Original code (2.0 and earlier )copyright (c) 2000-2002 Lee Thomason (www.grinninglizard.com)
 
This software is provided 'as-is', without any express or implied 
warranty. In no event will the authors be held liable for any 
damages arising from the use of this software.
 
Permission is granted to anyone to use this software for any 
purpose, including commercial applications, and to alter it and 
redistribute it freely, subject to the following restrictions:
 
1. The origin of this software must not be misrepresented; you must 
not claim that you wrote the original software. If you use this
software in a product, an acknowledgment in the product documentation
would be appreciated but is not required.
 
2. Altered source versions must be plainly marked as such, and 
must not be misrepresented as being the original software.
 
3. This notice may not be removed or altered from any source 
distribution.
*/

#include "tinyxml.h"
#include <ctype.h>

//#define DEBUG_PARSER

// Note tha "PutString" hardcodes the same list. This
// is less flexible than it appears. Changing the entries
// or order will break putstring.
TiXmlBase::Entity TiXmlBase::entity[ NUM_ENTITY ] =
  {
    { "&amp;",  5, '&' },
    { "&lt;",   4, '<' },
    { "&gt;",   4, '>' },
    { "&quot;", 6, '\"' },
    { "&apos;", 6, '\'' }
  };

// Bunch of unicode info at:
//		http://www.unicode.org/faq/utf_bom.html
// Including the basic of this table, which determines the #bytes in the
// sequence from the lead byte. 1 placed for invalid sequences --
// although the result will be junk, pass it through as much as possible.
// Beware of the non-characters in UTF-8:
//				ef bb bf (Microsoft "lead bytes")
//				ef bf be
//				ef bf bf



const int TiXmlBase::utf8ByteTable[256] =
  {
    //	0	1	2	3	4	5	6	7	8	9	a	b	c	d	e	f
    1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	// 0x00
    1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	// 0x10
    1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	// 0x20
    1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	// 0x30
    1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	// 0x40
    1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	// 0x50
    1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	// 0x60
    1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	// 0x70	End of ASCII range
    1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	// 0x80 0x80 to 0xc1 invalid
    1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	// 0x90
    1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	// 0xa0
    1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	// 0xb0
    1,	1,	2,	2,	2,	2,	2,	2,	2,	2,	2,	2,	2,	2,	2,	2,	// 0xc0 0xc2 to 0xdf 2 byte
    2,	2,	2,	2,	2,	2,	2,	2,	2,	2,	2,	2,	2,	2,	2,	2,	// 0xd0
    3,	3,	3,	3,	3,	3,	3,	3,	3,	3,	3,	3,	3,	3,	3,	3,	// 0xe0 0xe0 to 0xef 3 byte
    4,	4,	4,	4,	4,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1,	1	// 0xf0 0xf0 to 0xf4 4 byte, 0xf5 and higher invalid
  };


void TiXmlBase::ConvertUTF32ToUTF8( unsigned long input, char* output, int* length )
{
  const unsigned long BYTE_MASK = 0xBF;
  const unsigned long BYTE_MARK = 0x80;
  const unsigned long FIRST_BYTE_MARK[7] =
    {
      0x00, 0x00, 0xC0, 0xE0, 0xF0, 0xF8, 0xFC
    };

  if (input < 0x80)
    *length = 1;
  else if ( input < 0x800 )
    *length = 2;
  else if ( input < 0x10000 )
    *length = 3;
  else if ( input < 0x200000 )
    *length = 4;
  else
  {
    *length = 0;
    return;
  }	// This code won't covert this correctly anyway.

  output += *length;

  // Scary scary fall throughs.
  switch (*length)
  {
  case 4:
    --output;
    *output = (char)((input | BYTE_MARK) & BYTE_MASK);
    input >>= 6;
  case 3:
    --output;
    *output = (char)((input | BYTE_MARK) & BYTE_MASK);
    input >>= 6;
  case 2:
    --output;
    *output = (char)((input | BYTE_MARK) & BYTE_MASK);
    input >>= 6;
  case 1:
    --output;
    *output = (char)(input | FIRST_BYTE_MARK[*length]);
  }
}


/*static*/ int TiXmlBase::IsAlpha( unsigned char anyByte, TiXmlEncoding encoding )
{
  // 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 alhabetical vs. not across encoding. So take a very
  // conservative approach.

  //	if ( encoding == TIXML_ENCODING_UTF8 )
  //	{
  if ( anyByte < 127 )
    return isalpha( anyByte );
  else
    return 1;	// What else to do? The unicode set is huge...get the english ones right.
  //	}
  //	else
  //	{
  //		return isalpha( anyByte );
  //	}
}


/*static*/ int TiXmlBase::IsAlphaNum( unsigned char anyByte, TiXmlEncoding encoding )
{
  // 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 alhabetical vs. not across encoding. So take a very
  // conservative approach.

  //	if ( encoding == TIXML_ENCODING_UTF8 )
  //	{
  if ( anyByte < 127 )
    return isalnum( anyByte );
  else
    return 1;	// What else to do? The unicode set is huge...get the english ones right.
  //	}
  //	else
  //	{
  //		return isalnum( anyByte );
  //	}
}


class TiXmlParsingData
{
  friend class TiXmlDocument;
public:
  void Stamp( const char* now, TiXmlEncoding encoding );

  const TiXmlCursor& Cursor()
  {
    return cursor;
  }

private:
  // Only used by the document!
  TiXmlParsingData( const char* start, int _tabsize, int row, int col )
  {
    assert( start );
    stamp = start;
    tabsize = _tabsize;
    cursor.r