/*
Original code by 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 "tinyxml2.h"

#include 		// yes, this one new style header, is in the Android SDK.
#   ifdef ANDROID_NDK
#   include 
#else
#   include 
#endif

static const char LINE_FEED				= (char)0x0a;			// all line endings are normalized to LF
static const char LF = LINE_FEED;
static const char CARRIAGE_RETURN		= (char)0x0d;			// CR gets filtered out
static const char CR = CARRIAGE_RETURN;
static const char SINGLE_QUOTE			= '\'';
static const char DOUBLE_QUOTE			= '\"';

// Bunch of unicode info at:
//		http://www.unicode.org/faq/utf_bom.html
//	ef bb bf (Microsoft "lead bytes") - designates UTF-8

static const unsigned char TIXML_UTF_LEAD_0 = 0xefU;
static const unsigned char TIXML_UTF_LEAD_1 = 0xbbU;
static const unsigned char TIXML_UTF_LEAD_2 = 0xbfU;

namespace tinyxml2
{

struct Entity {
    const char* pattern;
    int length;
    char value;
};

static const int NUM_ENTITIES = 5;
static const Entity entities[NUM_ENTITIES] = {
    { "quot", 4,	DOUBLE_QUOTE },
    { "amp", 3,		'&'  },
    { "apos", 4,	SINGLE_QUOTE },
    { "lt",	2, 		''	 }
};


StrPair::~StrPair()
{
    Reset();
}


void StrPair::Reset()
{
    if ( _flags & NEEDS_DELETE ) {
        delete [] _start;
    }
    _flags = 0;
    _start = 0;
    _end = 0;
}


void StrPair::SetStr( const char* str, int flags )
{
    Reset();
    size_t len = strlen( str );
    _start = new char[ len+1 ];
    memcpy( _start, str, len+1 );
    _end = _start + len;
    _flags = flags | NEEDS_DELETE;
}


char* StrPair::ParseText( char* p, const char* endTag, int strFlags )
{
    TIXMLASSERT( endTag && *endTag );

    char* start = p;
    char  endChar = *endTag;
    size_t length = strlen( endTag );

    // Inner loop of text parsing.
    while ( *p ) {
        if ( *p == endChar && strncmp( p, endTag, length ) == 0 ) {
            Set( start, p, strFlags );
            return p + length;
        }
        ++p;
    }
    return 0;
}


char* StrPair::ParseName( char* p )
{
    if ( !p || !(*p) ) {
        return 0;
    }

    char* const start = p;

    while( *p && ( p == start ? XMLUtil::IsNameStartChar( *p ) : XMLUtil::IsNameChar( *p ) )) {
        ++p;
    }

    if ( p > start ) {
        Set( start, p, 0 );
        return p;
    }
    return 0;
}


void StrPair::CollapseWhitespace()
{
    // Adjusting _start would cause undefined behavior on delete[]
    TIXMLASSERT( ( _flags & NEEDS_DELETE ) == 0 );
    // Trim leading space.
    _start = XMLUtil::SkipWhiteSpace( _start );

    if ( _start && *_start ) {
        char* p = _start;	// the read pointer
        char* q = _start;	// the write pointer

        while( *p ) {
            if ( XMLUtil::IsWhiteSpace( *p )) {
                p = XMLUtil::SkipWhiteSpace( p );
                if ( *p == 0 ) {
                    break;    // don't write to q; this trims the trailing space.
                }
                *q = ' ';
                ++q;
            }
            *q = *p;
            ++q;
            ++p;
        }
        *q = 0;
    }
}


const char* StrPair::GetStr()
{
    if ( _flags & NEEDS_FLUSH ) {
        *_end = 0;
        _flags ^= NEEDS_FLUSH;

        if ( _flags ) {
            char* p = _start;	// the read pointer
            char* q = _start;	// the write pointer

            while( p < _end ) {
                if ( (_flags & NEEDS_NEWLINE_NORMALIZATION) && *p == CR ) {
                    // CR-LF pair becomes LF
                    // CR alone becomes LF
                    // LF-CR becomes LF
                    if ( *(p+1) == LF ) {
                        p += 2;
                    }
                    else {
                        ++p;
                    }
                    *q++ = LF;
                }
                else if ( (_flags & NEEDS_NEWLINE_NORMALIZATION) && *p == LF ) {
                    if ( *(p+1) == CR ) {
                        p += 2;
                    }
                    else {
                        ++p;
                    }
                    *q++ = LF;
                }
                else if ( (_flags & NEEDS_ENTITY_PROCESSING) && *p == '&' ) {
                    // Entities handled by tinyXML2:
                    // - special entities in the entity table [in/out]
                    // - numeric character reference [in]
                    //   中 or 中

                    if ( *(p+1) == '#' ) {
                        const int buflen = 10;
                        char buf[buflen] = { 0 };
                        int len = 0;
                        p = const_cast( XMLUtil::GetCharacterRef( p, buf, &len ) );
                        TIXMLASSERT( 0