xmluri.cpp

来自「IBM的解析xml的工具Xerces的源代码」· C++ 代码 · 共 2,222 行 · 第 1/5 页

        fQueryString = 0;
	}
	else if (!isGenericURI())
    {
        ThrowXMLwithMemMgr2(MalformedURLException
                , XMLExcepts::XMLNUM_URI_Component_for_GenURI_Only
                , errMsg_QUERY
                , newQueryString
                , fMemoryManager);
	}
	else if ( !getPath() )
    {
        ThrowXMLwithMemMgr2(MalformedURLException
                , XMLExcepts::XMLNUM_URI_NullPath
                , errMsg_QUERY
                , newQueryString
                , fMemoryManager);
	}
	else if (!isURIString(newQueryString))
    {
        ThrowXMLwithMemMgr2(MalformedURLException
               , XMLExcepts::XMLNUM_URI_Component_Invalid_Char
               , errMsg_QUERY
               , newQueryString
               , fMemoryManager);
	}
	else
    {
        if (getQueryString())
        {
            fMemoryManager->deallocate(fQueryString);//delete [] fQueryString;
        }

        fQueryString = XMLString::replicate(newQueryString, fMemoryManager);
	}
}

// ---------------------------------------------------------------------------
//  XMLUri: Public, static methods
// ---------------------------------------------------------------------------

//
//  scheme = alpha *( alpha | digit | "+" | "-" | "." )
//  alphanum = alpha | digit
//
bool XMLUri::isConformantSchemeName(const XMLCh* const scheme)
{
	if ( !scheme )
        return false;

    const XMLCh* tmpStr = scheme;
    if (!XMLString::isAlpha(*tmpStr))     // first: alpha
        return false;

    // second onwards: ( alpha | digit | "+" | "-" | "." )
    tmpStr++;
    while (*tmpStr)
    {
        if ( !XMLString::isAlphaNum(*tmpStr) &&
             (XMLString::indexOf(SCHEME_CHARACTERS, *tmpStr) == -1))
            return false;

        tmpStr++;
    }

    return true;
}

//
// userinfo = *( unreserved | escaped |
//              ";" | ":" | "&" | "=" | "+" | "$" | "," )
//
void XMLUri::isConformantUserInfo(const XMLCh* const userInfo
                                  , MemoryManager* const manager)
{
	if ( !userInfo )
        return;

    const XMLCh* tmpStr = userInfo;
    while (*tmpStr)
    {
        if ( isUnreservedCharacter(*tmpStr) ||
            (XMLString::indexOf(USERINFO_CHARACTERS, *tmpStr) != -1))
        {
            tmpStr++;
        }
        else if (*tmpStr == chPercent)               // '%'
        {
            if (XMLString::isHex(*(tmpStr+1)) &&     // 1st hex
                XMLString::isHex(*(tmpStr+2))  )     // 2nd hex
            {
                tmpStr+=3;
            }
            else
            {
                XMLCh value1[BUF_LEN+1];
                value1[0] = chPercent;
                value1[1] = *(tmpStr+1);
                value1[2] = *(tmpStr+2);
                value1[3] = chNull;

                ThrowXMLwithMemMgr2(MalformedURLException
                        , XMLExcepts::XMLNUM_URI_Component_Invalid_EscapeSequence
                        , errMsg_USERINFO
                        , value1
                        , manager);
            }
        }
        else
        {	
            ThrowXMLwithMemMgr2(MalformedURLException
                    , XMLExcepts::XMLNUM_URI_Component_Invalid_Char
                    , errMsg_USERINFO
                    , userInfo
                    , manager);
        }
    } //while

    return;
}

bool XMLUri::isValidServerBasedAuthority(const XMLCh* const host,
                                         const int hostLen,
                                         const int port,
                                         const XMLCh* const userinfo,
                                         const int userLen)
{
    // The order is important, do not change
    if (!isWellFormedAddress(host, hostLen))
        return false;

    // check port number
    if ((port > 65535) || (port < 0 && port != -1))
        return false;

    // check userinfo
    int index = 0;
    while (index < userLen)
    {
        if (isUnreservedCharacter(userinfo[index]) ||
            (XMLString::indexOf(USERINFO_CHARACTERS, userinfo[index]) != -1))
        {
            index++;
        }
        else if (userinfo[index] == chPercent)               // '%'
        {
            if (XMLString::isHex(userinfo[index+1]) &&     // 1st hex
                XMLString::isHex(userinfo[index+2])  )     // 2nd hex
                index +=3;
            else
                return false;
        }
        else
            return false;
    } //while

    return true;
}

bool XMLUri::isValidServerBasedAuthority(const XMLCh* const host
                                         , const int port
                                         , const XMLCh* const userinfo
                                         , MemoryManager* const manager)
{
    // The order is important, do not change
    if (!isWellFormedAddress(host, manager))
        return false;

    // check port number
    if ((port > 65535) || (port < 0 && port != -1))
        return false;
    
    // check userinfo
    if (!userinfo)
        return true;
        
    const XMLCh* tmpStr = userinfo;
    while (*tmpStr)
    {
        if ( isUnreservedCharacter(*tmpStr) ||
            (XMLString::indexOf(USERINFO_CHARACTERS, *tmpStr) != -1))
        {
            tmpStr++;
        }
        else if (*tmpStr == chPercent)               // '%'
        {
            if (XMLString::isHex(*(tmpStr+1)) &&     // 1st hex
                XMLString::isHex(*(tmpStr+2))  )     // 2nd hex
            {
                tmpStr+=3;
            }
            else
                return false;
        }
        else
            return false;
    } //while
    
    return true;
}

bool XMLUri::isValidRegistryBasedAuthority(const XMLCh* const authority,
                                           const int authLen)
{
    // check authority
    int index = 0;
    while (index < authLen)
    {
        if (isUnreservedCharacter(authority[index]) ||
            (XMLString::indexOf(REG_NAME_CHARACTERS, authority[index]) != -1))
        {
            index++;
        }
        else if (authority[index] == chPercent)               // '%'
        {
            if (XMLString::isHex(authority[index+1]) &&     // 1st hex
                XMLString::isHex(authority[index+2])  )     // 2nd hex
                index +=3;
            else
                return false;
        }
        else
            return false;
    } //while

    return true;
}

bool XMLUri::isValidRegistryBasedAuthority(const XMLCh* const authority)
{
    // check authority
    if (!authority)
        return false;
        
    const XMLCh* tmpStr = authority;
    while (*tmpStr)
    {
        if (isUnreservedCharacter(*tmpStr) ||
            (XMLString::indexOf(REG_NAME_CHARACTERS, *tmpStr) != -1))
        {
            tmpStr++;
        }
        else if (*tmpStr == chPercent)               // '%'
        {
            if (XMLString::isHex(*(tmpStr+1)) &&     // 1st hex
                XMLString::isHex(*(tmpStr+2))  )     // 2nd hex
            {
                tmpStr+=3;
            }
            else
                return false;
        }
        else
            return false;
    } //while
    
    return true;
}

//
// uric     = reserved | unreserved | escaped
// escaped  = "%" hex hex
// hex      = digit | "A" | "B" | "C" | "D" | "E" | "F" |
//                    "a" | "b" | "c" | "d" | "e" | "f"
//
bool XMLUri::isURIString(const XMLCh* const uricString)
{
	if (!uricString || !*uricString)
        return false;

    const XMLCh* tmpStr = uricString;

    while (*tmpStr)
    {
        if (isReservedOrUnreservedCharacter(*tmpStr))            
        {
            tmpStr++;
        }
        else if (*tmpStr == chPercent)               // '%'
        {
            if (XMLString::isHex(*(tmpStr+1)) &&     // 1st hex
                XMLString::isHex(*(tmpStr+2))  )     // 2nd hex
            {
                tmpStr+=3;
            }
            else
            {
                return false;
            }
        }
        else
        {	
            return false;
        }
    }

    return true;
}

//
//  host          = hostname | IPv4address
//
//  hostname      = *( domainlabel "." ) toplabel [ "." ]
//  domainlabel   = alphanum | alphanum *( alphanum | "-" ) alphanum
//  toplabel      = alpha | alpha *( alphanum | "-" ) alphanum
//
//  IPv4address   = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT
//
bool XMLUri::isWellFormedAddress(const XMLCh* const addrString
                                 , MemoryManager* const manager)
{
    // Check that we have a non-zero length string.
    if (!addrString || !*addrString)
        return false;
        
    // Get address length.
    int addrStrLen = XMLString::stringLen(addrString);
    
    // Check if the host is a valid IPv6reference.
    if (*addrString == chOpenSquare)
    {
        return isWellFormedIPv6Reference(addrString, addrStrLen);
    }

    //
    // Cannot start with a '.', '-', or end with a '-'.
    //
    if (*addrString == chPeriod ||
        *addrString == chDash ||
        addrString[addrStrLen-1] == chDash)
        return false;

    // rightmost domain label starting with digit indicates IP address
    // since top level domain label can only start with an alpha
    // see RFC 2396 Section 3.2.2
    
    int lastPeriodPos = XMLString::lastIndexOf(addrString, chPeriod);

    // if the string ends with "."
    // get the second last "."
    if (lastPeriodPos + 1 == addrStrLen)
    {
        XMLCh* tmp2 = (XMLCh*) manager->allocate
        (
            addrStrLen * sizeof(XMLCh)
        );//new XMLCh[addrStrLen];
        XMLString::subString(tmp2, addrString, 0, lastPeriodPos, manager);
        lastPeriodPos = XMLString::lastIndexOf(tmp2, chPeriod);
        manager->deallocate(tmp2);//delete [] tmp2;

        if ( XMLString::isDigit(addrString[lastPeriodPos + 1]))
			return false;
    }

    if (XMLString::isDigit(addrString[lastPeriodPos + 1]))
    {
        return isWellFormedIPv4Address(addrString, addrStrLen);
    } // end of IPv4address
    else
    {
        //
        //  hostname      = *( domainlabel "." ) toplabel [ "." ]
        //  domainlabel   = alphanum | alphanum *( alphanum | "-" ) alphanum
        //  toplabel      = alpha | alpha *( alphanum | "-" ) alphanum
        
        // RFC 2396 states that hostnames take the form described in 
        // RFC 1034 (Section 3) and RFC 1123 (Section 2.1). According
        // to RFC 1034, hostnames are limited to 255 characters.
        if (addrStrLen > 255) {
            return false;
        }
        
        unsigned int labelCharCount = 0;
        
        // domain labels can contain alphanumerics and '-"
        // but must start and end with an alphanumeric
        for (int i = 0; i < addrStrLen; i++)
        {
            if (addrString[i] == chPeriod)
            {
              if (((i > 0)  &&
                   (!XMLString::isAlphaNum(addrString[i-1]))) ||
                  ((i + 1 < addrStrLen) &&
                   (!XMLString::isAlphaNum(addrString[i+1])))  )
                {
                    return false;
                }
                labelCharCount = 0;
            }
            else if (!XMLString::isAlphaNum(addrString[i]) &&
                      addrString[i] != chDash)
            {
                return false;
            }
            // RFC 1034: Labels must be 63 characters or less.
            else if (++labelCharCount > 63) {
                return false;
            }
        } //for
    }

    return true;
}

//
//  RFC 2732 amended RFC 2396 by replacing the definition 
//  of IPv4address with the one defined by RFC 2373.
//
//  IPv4address   = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT
//
bool XMLUri::isWellFormedIPv4Address(const XMLCh* const addr, const int length)
{
    int numDots = 0;
    int numDigits = 0;
    
    // IPv4address = 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT "." 1*3DIGIT
    //
    // make sure that
    // 1) we see only digits and dot separators,
    // 2) that any dot separator is preceded and followed by a digit
    // 3) that we find 3 dots
    // 4) that each segment contains 1 to 3 digits.
    // 5) that each segment is not greater than 255.    
    for (int i = 0; i < length; ++i)
    {
        if (addr[i] == chPeriod)
        {
            if ((i == 0) ||
                (i+1 == length) ||
                !XMLString::isDigit(addr[i+1]))
            {
               return false;
            }
            numDigits = 0;
            if (++numDots > 3)
                return false;
        }
        else if (!XMLString::isDigit(addr[i]))
        {
            return false;
        }
        // Check that that there are no more than three digits
        // in this segment.
        else if (++numDigits > 3)