xmlparser.cpp

xml文件解析器 解析所有的xml文件 支持unicode

    FILE *f=xfopen(filename,_X("rb"));
    if (f)
    {
        char bb[205];
        int l=(int)fread(bb,1,200,f);
        setGlobalOptions(guessCharEncoding(bb,l),guessWideCharChars,dropWhiteSpace);
        fclose(f);
    }

    // parse the file
    XMLResults pResults;
    XMLNode xnode=XMLNode::parseFile(filename,tag,&pResults);

    // display error message (if any)
    if (pResults.error != eXMLErrorNone)
    {
        // create message
        char message[2000],*s1=(char*)"",*s3=(char*)""; XMLCSTR s2=_X("");
        if (pResults.error==eXMLErrorFirstTagNotFound) { s1=(char*)"First Tag should be '"; s2=tag; s3=(char*)"'.\n"; }
        sprintf(message,
#ifdef _XMLWIDECHAR
            "XML Parsing error inside file '%S'.\n%S\nAt line %i, column %i.\n%s%S%s"
#else
            "XML Parsing error inside file '%s'.\n%s\nAt line %i, column %i.\n%s%s%s"
#endif
            ,filename,XMLNode::getError(pResults.error),pResults.nLine,pResults.nColumn,s1,s2,s3);

        // display message
#if defined(_XMLWINDOWS) && !defined(UNDER_CE) && !defined(_XMLPARSER_NO_MESSAGEBOX_)
        MessageBoxA(NULL,message,"XML Parsing error",MB_OK|MB_ICONERROR|MB_TOPMOST);
#else
        printf("%s",message);
#endif
        exit(255);
    }
    return xnode;
}

/////////////////////////////////////////////////////////////////////////
//      Here start the core implementation of the XMLParser library    //
/////////////////////////////////////////////////////////////////////////

// You should normally not change anything below this point.

#ifndef _XMLWIDECHAR
// If "characterEncoding=ascii" then we assume that all characters have the same length of 1 byte.
// If "characterEncoding=UTF8" then the characters have different lengths (from 1 byte to 4 bytes).
// If "characterEncoding=ShiftJIS" then the characters have different lengths (from 1 byte to 2 bytes).
// This table is used as lookup-table to know the length of a character (in byte) based on the
// content of the first byte of the character.
// (note: if you modify this, you must always have XML_utf8ByteTable[0]=0 ).
static const char XML_utf8ByteTable[256] =
{
    //  0 1 2 3 4 5 6 7 8 9 a b c d e f
    0,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,// 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,// 0x70End 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
};
static const char XML_asciiByteTable[256] =
{
    0,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1
};
static const char XML_sjisByteTable[256] =
{
    //  0 1 2 3 4 5 6 7 8 9 a b c d e f
    0,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,// 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
    1,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,// 0x80 0x81 to 0x9F 2 bytes
    2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,// 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
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,// 0xc0 
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,// 0xd0
    2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,// 0xe0 0xe0 to 0xef 2 bytes
    1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1 // 0xf0
};
static const char *XML_ByteTable=(const char *)XML_utf8ByteTable; // the default is "characterEncoding=XMLNode::encoding_UTF8"
#endif


XMLNode XMLNode::emptyXMLNode;
XMLClear XMLNode::emptyXMLClear={ NULL, NULL, NULL};
XMLAttribute XMLNode::emptyXMLAttribute={ NULL, NULL};

// Enumeration used to decipher what type a token is
typedef enum XMLTokenTypeTag
{
    eTokenText = 0,
    eTokenQuotedText,
    eTokenTagStart,         /* "<"            */
    eTokenTagEnd,           /* "</"           */
    eTokenCloseTag,         /* ">"            */
    eTokenEquals,           /* "="            */
    eTokenDeclaration,      /* "<?"           */
    eTokenShortHandClose,   /* "/>"           */
    eTokenClear,
    eTokenError
} XMLTokenType;

// Main structure used for parsing XML
typedef struct XML
{
    XMLCSTR                lpXML;
    XMLCSTR                lpszText;
    int                    nIndex,nIndexMissigEndTag;
    enum XMLError          error;
    XMLCSTR                lpEndTag;
    int                    cbEndTag;
    XMLCSTR                lpNewElement;
    int                    cbNewElement;
    int                    nFirst;
} XML;

typedef struct
{
    ALLXMLClearTag *pClr;
    XMLCSTR     pStr;
} NextToken;

// Enumeration used when parsing attributes
typedef enum Attrib
{
    eAttribName = 0,
    eAttribEquals,
    eAttribValue
} Attrib;

// Enumeration used when parsing elements to dictate whether we are currently
// inside a tag
typedef enum Status
{
    eInsideTag = 0,
    eOutsideTag
} Status;

XMLError XMLNode::writeToFile(XMLCSTR filename, const char *encoding, char nFormat) const
{
    if (!d) return eXMLErrorNone;
    FILE *f=xfopen(filename,_X("wb"));
    if (!f) return eXMLErrorCannotOpenWriteFile;
#ifdef _XMLWIDECHAR
    unsigned char h[2]={ 0xFF, 0xFE };
    if (!fwrite(h,2,1,f)) return eXMLErrorCannotWriteFile;
    if ((!isDeclaration())&&((d->lpszName)||(!getChildNode().isDeclaration())))
    {
        if (!fwrite(_X("<?xml version=\"1.0\" encoding=\"utf-16\"?>\n"),sizeof(wchar_t)*40,1,f))
            return eXMLErrorCannotWriteFile;
    }
#else
    if ((!isDeclaration())&&((d->lpszName)||(!getChildNode().isDeclaration())))
    {
        if (characterEncoding==encoding_UTF8)
        {
            // header so that windows recognize the file as UTF-8:
            unsigned char h[3]={0xEF,0xBB,0xBF}; if (!fwrite(h,3,1,f)) return eXMLErrorCannotWriteFile;
            encoding="utf-8";
        } else if (characterEncoding==encoding_ShiftJIS) encoding="SHIFT-JIS";
        
        if (!encoding) encoding="ISO-8859-1";
        if (fprintf(f,"<?xml version=\"1.0\" encoding=\"%s\"?>\n",encoding)<0) return eXMLErrorCannotWriteFile;
    } else
    {
        if (characterEncoding==encoding_UTF8) 
        {
            unsigned char h[3]={0xEF,0xBB,0xBF}; if (!fwrite(h,3,1,f)) return eXMLErrorCannotWriteFile;
        }
    }
#endif
    int i;
    XMLSTR t=createXMLString(nFormat,&i);
    if (!fwrite(t,sizeof(XMLCHAR)*i,1,f)) return eXMLErrorCannotWriteFile;
    if (fclose(f)!=0) return eXMLErrorCannotWriteFile;
    free(t);
    return eXMLErrorNone;
}

// Duplicate a given string.
XMLSTR stringDup(XMLCSTR lpszData, int cbData)
{
    if (lpszData==NULL) return NULL;

    XMLSTR lpszNew;
    if (cbData==0) cbData=(int)xstrlen(lpszData);
    lpszNew = (XMLSTR)malloc((cbData+1) * sizeof(XMLCHAR));
    if (lpszNew)
    {
        memcpy(lpszNew, lpszData, (cbData) * sizeof(XMLCHAR));
        lpszNew[cbData] = (XMLCHAR)NULL;
    }
    return lpszNew;
}

XMLSTR toXMLStringUnSafe(XMLSTR dest,XMLCSTR source)
{
    XMLSTR dd=dest;
    XMLCHAR ch;
    XMLCharacterEntity *entity;
    while ((ch=*source))
    {
        entity=XMLEntities;
        do
        {
            if (ch==entity->c) {xstrcpy(dest,entity->s); dest+=entity->l; source++; goto out_of_loop1; }
            entity++;
        } while(entity->s);
#ifdef _XMLWIDECHAR
        *(dest++)=*(source++);
#else
        switch(XML_ByteTable[(unsigned char)ch])
        {
        case 4: *(dest++)=*(source++);
        case 3: *(dest++)=*(source++);
        case 2: *(dest++)=*(source++);
        case 1: *(dest++)=*(source++);
        }
#endif
out_of_loop1:
        ;
    }
    *dest=0;
    return dd;
}

// private (used while rendering):
int lengthXMLString(XMLCSTR source)
{
    int r=0;
    XMLCharacterEntity *entity;
    XMLCHAR ch;
    while ((ch=*source))
    {
        entity=XMLEntities;
        do
        {
            if (ch==entity->c) { r+=entity->l; source++; goto out_of_loop1; }
            entity++;
        } while(entity->s);
#ifdef _XMLWIDECHAR
        r++; source++;
#else
        ch=XML_ByteTable[(unsigned char)ch]; r+=ch; source+=ch;
#endif
out_of_loop1:
        ;
    }
    return r;
}

ToXMLStringTool::~ToXMLStringTool(){ freeBuffer(); }
void ToXMLStringTool::freeBuffer(){ if (buf) free(buf); buf=NULL; buflen=0; }
XMLSTR ToXMLStringTool::toXML(XMLCSTR source)
{
    int l=lengthXMLString(source)+1;
    if (l>buflen) { buflen=l; buf=(XMLSTR)realloc(buf,l*sizeof(XMLCHAR)); }
    return toXMLStringUnSafe(buf,source);
}

// private:
XMLSTR fromXMLString(XMLCSTR s, int lo, XML *pXML)
{
    // This function is the opposite of the function "toXMLString". It decodes the escape
    // sequences &amp;, &quot;, &apos;, &lt;, &gt; and replace them by the characters
    // &,",',<,>. This function is used internally by the XML Parser. All the calls to
    // the XML library will always gives you back "decoded" strings.
    //
    // in: string (s) and length (lo) of string
    // out:  new allocated string converted from xml
    if (!s) return NULL;

    int ll=0,j;
    XMLSTR d;
    XMLCSTR ss=s;
    XMLCharacterEntity *entity;
    while ((lo>0)&&(*s))
    {
        if (*s==_X('&'))
        {
            if ((lo>2)&&(s[1]==_X('#')))
            {
                s+=2; lo-=2;
                if ((*s==_X('X'))||(*s==_X('x'))) { s++; lo--; }
                while ((*s)&&(*s!=_X(';'))&&((lo--)>0)) s++;
                if (*s!=_X(';'))
                {
                    pXML->error=eXMLErrorUnknownCharacterEntity;
                    return NULL;
                }
                s++; lo--;
            } else
            {
                entity=XMLEntities;
                do
                {
                    if ((lo>=entity->l)&&(xstrnicmp(s,entity->s,entity->l)==0)) { s+=entity->l; lo-=entity->l; break; }
                    entity++;
                } while(entity->s);
                if (!entity->s)
                {
                    pXML->error=eXMLErrorUnknownCharacterEntity;
                    return NULL;
                }
            }
        } else
        {
#ifdef _XMLWIDECHAR
            s++; lo--;
#else
            j=XML_ByteTable[(unsigned char)*s]; s+=j; lo-=j; ll+=j-1;
#endif
        }
        ll++;
    }

    d=(XMLSTR)malloc((ll+1)*sizeof(XMLCHAR));
    s=d;
    while (ll-->0)
    {
        if (*ss==_X('&'))
        {
            if (ss[1]==_X('#'))
            {
                ss+=2; j=0;
                if ((*ss==_X('X'))||(*ss==_X('x')))
                {