pegasus/src/Pegasus/Common/XmlParser.cpp - diff

Return to XmlParser.cpp CVS log

Up to [Pegasus] / pegasus / src / Pegasus / Common

Diff for /pegasus/src/Pegasus/Common/XmlParser.cpp between version 1.1.1.1 and 1.35

version 1.1.1.1, 2001/01/14 19:53:23

version 1.35, 2005/11/07 23:20:01

Line 1

//BEGIN_LICENSE

//%2005////////////////////////////////////////////////////////////////////////

// Company, L.P.; IBM Corp.; The Open Group; Tivoli Systems.

// IBM Corp.; EMC Corporation, The Open Group.

// IBM Corp.; EMC Corporation; VERITAS Software Corporation; The Open Group.

// EMC Corporation; VERITAS Software Corporation; The Open Group.

// Permission is hereby granted, free of charge, to any person obtaining a copy

// of this software and associated documentation files (the "Software"), to

// deal in the Software without restriction, including without limitation the

// rights to use, copy, modify, merge, publish, distribute, sublicense, and/or

// sell copies of the Software, and to permit persons to whom the Software is

// furnished to do so, subject to the following conditions:

// THE ABOVE COPYRIGHT NOTICE AND THIS PERMISSION NOTICE SHALL BE INCLUDED IN

// ALL COPIES OR SUBSTANTIAL PORTIONS OF THE SOFTWARE. THE SOFTWARE IS PROVIDED

// "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT

// LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR

// PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT

// HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN

// ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION

// WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

// Permission is hereby granted, free of charge, to any person obtaining a

//==============================================================================

// copy of this software and associated documentation files (the "Software"),

// to deal in the Software without restriction, including without limitation

// the rights to use, copy, modify, merge, publish, distribute, sublicense,

// and/or sell copies of the Software, and to permit persons to whom the

// Software is furnished to do so, subject to the following conditions:

// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR

// Author: Mike Brasher (mbrasher@bmc.com)

// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,

// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL

// THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER

// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING

// FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER

// DEALINGS IN THE SOFTWARE.

//END_LICENSE

// Modified By: David Dillard, VERITAS Software Corp.

//BEGIN_HISTORY

// (david.dillard@veritas.com)

// Author:

//%/////////////////////////////////////////////////////////////////////////////

// $Log$

// Revision 1.1.1.1 2001/01/14 19:53:23 mike

// Pegasus import

//END_HISTORY

////////////////////////////////////////////////////////////////////////////////

Line 52

Line 57

// &quot - full quote

// &apos - apostrophe

// as well as character (numeric) references:

// 1 - decimal reference for character '1'

// 1 - hexadecimal reference for character '1'

// 4. Element names and attribute names take the following form:

// [A-Za-z_][A-Za-z_0-9-.:]

Line 71

Line 81

// TODO:

// Handle <!DOCTYPE...> sections which are complicated (containing

// ATTN: KS P1 4 Mar 2002. Review the following TODOs to see if there is

// work. Handle <!DOCTYPE...> sections which are complicated (containing

// rules rather than references to files).

// Handle reference of this form: "Α"

// Remove newlines from string literals:

// Example: <xyz x="hello

Line 83

Line 92

////////////////////////////////////////////////////////////////////////////////

#include <Pegasus/Common/Config.h>

#include <cctype>

#include <cassert>

#include <cstdio>

#include <cstdlib>

#include <cstring>

#include "XmlParser.h"

#include "Logger.h"

#include "ExceptionRep.h"

#include "CharSet.h"

PEGASUS_NAMESPACE_BEGIN

#define PEGASUS_ARRAY_T XmlEntry

# include "ArrayImpl.h"

#undef PEGASUS_ARRAY_T

////////////////////////////////////////////////////////////////////////////////

// Static helper functions

Line 103

Line 120

for (; *p; p++)

{

if (*p == '\n')

std::cout << "\\n";

PEGASUS_STD(cout) << "\\n";

else if (*p == '\r')

std::cout << "\\r";

PEGASUS_STD(cout) << "\\r";

else if (*p == '\t')

std::cout << "\\t";

PEGASUS_STD(cout) << "\\t";

else

std::cout << *p;

PEGASUS_STD(cout) << *p;

}

Line 120

Line 137

char replacement;

};

// ATTN: Add support for more entity references

static EntityReference _references[] =

{

{ "&", 5, '&' },

Line 129

Line 147

{ "'", 6, '\'' }

};

// Implements a check for a whitespace character, without calling

// isspace( ). The isspace( ) function is locale-sensitive,

// and incorrectly flags some chars above 0x7f as whitespace. This

// causes the XmlParser to incorrectly parse UTF-8 data.

// Section 2.3 of XML 1.0 Standard (http://www.w3.org/TR/REC-xml)

// defines white space as:

// S ::= (#x20 | #x9 | #xD | #xA)+

static inline int _isspace(char c)

{

return CharSet::isSpace((Uint8)c);

}

static Uint32 _REFERENCES_SIZE = (sizeof(_references) / sizeof(_references[0]));

// Remove all redundant spaces from the given string:

static void _normalize(char* text)

{

Uint32 length = strlen(text);

char* p = text;

char* end = p + length;

char* end = p + strlen(text);

// Remove leading spaces:

while (isspace(*p))

while (_isspace(*p))

p++;

if (p != text)

Line 155

Line 186

{

// Advance to the next space:

while (*p && !isspace(*p))

while (*p && !_isspace(*p))

p++;

if (!*p)

Line 165

Line 196

char* q = p++;

while (isspace(*p))

while (_isspace(*p))

p++;

// Discard trailing spaces (if we are at the end):

Line 178

Line 209

// Remove the redundant spaces:

Uint32 n = p - q;

const size_t n = p - q;

if (n > 1)

{

Line 195

Line 226

////////////////////////////////////////////////////////////////////////////////

static char* _xmlMessages[] =

static const char* _xmlMessages[] =

{

"Bad opening element",

"Bad closing element",

Line 216

Line 247

"Semantic error"

};

static const char* _xmlKeys[] =

{

"Common.XmlParser.BAD_START_TAG",

"Common.XmlParser.BAD_END_TAG",

"Common.XmlParser.BAD_ATTRIBUTE_NAME",

"Common.XmlParser.EXPECTED_EQUAL_SIGN",

"Common.XmlParser.BAD_ATTRIBUTE_VALUE",

"Common.XmlParser.MINUS_MINUS_IN_COMMENT",

"Common.XmlParser.UNTERMINATED_COMMENT",

"Common.XmlParser.UNTERMINATED_CDATA",

"Common.XmlParser.UNTERMINATED_DOCTYPE",

"Common.XmlParser.TOO_MANY_ATTRIBUTES",

"Common.XmlParser.MALFORMED_REFERENCE",

"Common.XmlParser.EXPECTED_COMMENT_OR_CDATA",

"Common.XmlParser.START_END_MISMATCH",

"Common.XmlParser.UNCLOSED_TAGS",

"Common.XmlParser.MULTIPLE_ROOTS",

"Common.XmlParser.VALIDATION_ERROR",

"Common.XmlParser.SEMANTIC_ERROR"

};

// l10n replace _formMessage (comment out the old one)

static String _formMessage(Uint32 code, Uint32 line, const String& message)

{

String result = _xmlMessages[Uint32(code) - 1];

Line 225

Line 279

result.append(": on line ");

result.append(buffer);

if (message.getLength())

if (message.size())

{

result.append(": ");

result.append(message);

Line 233

Line 287

return result;

}

static MessageLoaderParms _formMessage(Uint32 code, Uint32 line, const String& message)

{

String dftMsg = _xmlMessages[Uint32(code) - 1];

String key = _xmlKeys[Uint32(code) - 1];

String msg = message;

dftMsg.append(": on line $0");

if (message.size())

{

msg = ": " + msg;

dftMsg.append("$1");

}

return MessageLoaderParms(key, dftMsg, line ,msg);

}

static MessageLoaderParms _formPartialMessage(Uint32 code, Uint32 line)

{

String dftMsg = _xmlMessages[Uint32(code) - 1];

String key = _xmlKeys[Uint32(code) - 1];

dftMsg.append(": on line $0");

return MessageLoaderParms(key, dftMsg, line);

}

XmlException::XmlException(

XmlException::Code code,

Line 243

Line 325

}

XmlException::XmlException(

XmlException::Code code,

Uint32 lineNumber,

MessageLoaderParms& msgParms)

: Exception(_formPartialMessage(code, lineNumber))

{

if (msgParms.default_msg.size())

{

msgParms.default_msg = ": " + msgParms.default_msg;

}

_rep->message.append(MessageLoader::getMessage(msgParms));

}

////////////////////////////////////////////////////////////////////////////////

// XmlValidationError

Line 257

Line 354

}

XmlValidationError::XmlValidationError(

Uint32 lineNumber,

MessageLoaderParms& msgParms)

: XmlException(XmlException::VALIDATION_ERROR, lineNumber, msgParms)

{

}

////////////////////////////////////////////////////////////////////////////////

// XmlSemanticError

Line 266

Line 373

XmlSemanticError::XmlSemanticError(

Uint32 lineNumber,

const String& message)

: XmlException(XmlException::VALIDATION_ERROR, lineNumber, message)

: XmlException(XmlException::SEMANTIC_ERROR, lineNumber, message)

{

}

XmlSemanticError::XmlSemanticError(

Uint32 lineNumber,

MessageLoaderParms& msgParms)

: XmlException(XmlException::SEMANTIC_ERROR, lineNumber, msgParms)

{

}

////////////////////////////////////////////////////////////////////////////////

// XmlParser

Line 283

Line 400

}

inline void _skipWhitespace(Uint32& line, char*& p)

{

while (*p && _isspace(*p))

{

if (*p == '\n')

line++;

p++;

}

Boolean XmlParser::next(XmlEntry& entry)

{

if (!_putBackStack.isEmpty())

Line 307

Line 435

// Skip over any whitespace:

_skipWhitespace(_current);

_skipWhitespace(_line, _current);

if (!*_current)

{

Line 379

Line 507

// Nothing to do!

}

void XmlParser::_skipWhitespace(char*& p)

// A-Za-z0-9_-:.

{

static unsigned char _isInnerElementChar[] =

while (*p && isspace(*p))

{

if (*p == '\n')

0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,

_line++;

0,0,0,0,0,0,0,0,1,1,0,1,1,1,1,1,1,1,1,1,1,1,0,0,0,0,0,0,1,1,1,1,1,1,1,1,1,

1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,0,0,0,0,1,0,1,1,1,1,1,1,1,1,1,1,1,1,1,1,

p++;

1,1,1,1,1,1,1,1,1,1,1,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,

}

0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,

}

0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,

0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,

};

Boolean XmlParser::_getElementName(char*& p)

{

if (!isalpha(*p) && *p != '_')

if (!CharSet::isAlNumUnder(Uint8(*p)))

{

std::cout << __LINE__ << std::endl;

throw XmlException(XmlException::BAD_START_TAG, _line);

}

while (*p &&

p++;

(isalnum(*p) || *p == '_' || *p == '-' || *p == ':' || *p == '.'))

while (*p && _isInnerElementChar[Uint8(*p)])

p++;

// The next character must be a space:

if (isspace(*p))

if (_isspace(*p))

{

*p++ = '\0';

_skipWhitespace(p);

_skipWhitespace(_line, p);

}

if (*p == '>')

Line 423

Line 550

{

openCloseElement = false;

if (!isalpha(*p) && *p != '_')

if (!CharSet::isAlNumUnder(Uint8(*p)))

{

std::cout << __LINE__ << std::endl;

throw XmlException(XmlException::BAD_START_TAG, _line);

}

while (*p &&

p++;

(isalnum(*p) || *p == '_' || *p == '-' || *p == ':' || *p == '.'))

while (*p && _isInnerElementChar[Uint8(*p)])

p++;

// The next character must be a space:

if (isspace(*p))

if (_isspace(*p))

{

*p++ = '\0';

_skipWhitespace(p);

_skipWhitespace(_line, p);

}

if (*p == '>')

Line 460

Line 585

void XmlParser::_getAttributeNameAndEqual(char*& p)

{

if (!isalpha(*p) && *p != '_')

if (!CharSet::isAlNumUnder((Uint8)*p))

{

std::cout << __LINE__ << std::endl;

throw XmlException(XmlException::BAD_ATTRIBUTE_NAME, _line);

}

while (*p &&

p++;

(isalnum(*p) || *p == '_' || *p == '-' || *p == ':' || *p == '.'))

while (*p && _isInnerElementChar[Uint8(*p)])

p++;

char* term = p;

_skipWhitespace(p);

_skipWhitespace(_line, p);

if (*p != '=')

{

std::cout << __LINE__ << std::endl;

throw XmlException(XmlException::BAD_ATTRIBUTE_NAME, _line);

}

p++;

_skipWhitespace(p);

_skipWhitespace(_line, p);

*term = '\0';

}

Line 492

Line 612

// ATTN-B: handle values contained in semiquotes:

if (*p != '"' && *p != '\'')

{

std::cout << __LINE__ << std::endl;

throw XmlException(XmlException::BAD_ATTRIBUTE_VALUE, _line);

}

char startChar = *p++;

Line 503

Line 620

p++;

if (*p != startChar)

{

std::cout << __LINE__ << std::endl;

throw XmlException(XmlException::BAD_ATTRIBUTE_VALUE, _line);

}

*p++ = '\0';

}

Line 588

Line 702

void XmlParser::_substituteReferences(char* text)

{

Uint32 rem = strlen(text);

size_t rem = strlen(text);

for (char* p = text; *p; p++, rem--)

{

if (*p == '&')

{

// Look for predefined entity reference:

// Process character or entity reference

Boolean found = false;

Uint16 referenceChar = 0;

Uint32 referenceLength = 0;

XmlException::Code code = XmlException::MALFORMED_REFERENCE;

for (Uint32 i = 0; i < _REFERENCES_SIZE; i++)

if (*(p+1) == '#')

{

Uint32 length = _references[i].length;

// Found a character (numeric) reference

const char* match = _references[i].match;

// Determine whether it is decimal or hex

if (*(p+2) == 'x')

{

// Decode a hexadecimal character reference

char* q = p+3;

if (strncmp(p, _references[i].match, length) == 0)

// At most four digits are allowed, plus trailing ';'

Uint32 numDigits;

for (numDigits = 0; numDigits < 5; numDigits++, q++)

{

found = true;

if (isdigit(*q))

*p = _references[i].replacement;

{

char* q = p + length;

referenceChar = (referenceChar << 4);

rem = rem - length + 1;

referenceChar += (*q - '0');

memmove(p + 1, q, rem);

}

else if ((*q >= 'A') && (*q <= 'F'))

{

referenceChar = (referenceChar << 4);

referenceChar += (*q - 'A' + 10);

}

else if ((*q >= 'a') && (*q <= 'f'))

{

referenceChar = (referenceChar << 4);

referenceChar += (*q - 'a' + 10);

}

else if (*q == ';')

{

break;

}

else

{

throw XmlException(code, _line);

}

// If not found, then at least make sure it is well formed:

// Hex number must be 1 - 4 digits

if ((numDigits == 0) || (numDigits > 4))

{

throw XmlException(code, _line);

}

if (!found)

// ATTN: Currently do not support 16-bit characters

if (referenceChar > 0xff)

{

char* start = p;

// ATTN: Is there a good way to say "unsupported"?

p++;

throw XmlException(code, _line);

}

XmlException::Code code = XmlException::MALFORMED_REFERENCE;

referenceLength = numDigits + 4;

}

else

{

// Decode a decimal character reference

Uint32 newChar = 0;

char* q = p+2;

if (isalpha(*p) || *p == '_')

// At most five digits are allowed, plus trailing ';'

Uint32 numDigits;

for (numDigits = 0; numDigits < 6; numDigits++, q++)

{

for (p++; *p && *p != ';'; p++)

if (isdigit(*q))

{

newChar = (newChar * 10);

newChar += (*q - '0');

}

else if (*q == ';')

{

break;

}

else

{

if (!isalnum(*p) && *p != '_')

throw XmlException(code, _line);

}

else if (*p == '#')

// Decimal number must be 1 - 5 digits and fit in 16 bits

if ((numDigits == 0) || (numDigits > 5) ||

(newChar > 0xffff))

{

for (p++ ; *p && *p != ';'; p++)

throw XmlException(code, _line);

}

// ATTN: Currently do not support 16-bit characters

if (newChar > 0xff)

{

if (!isdigit(*p))

// ATTN: Is there a good way to say "unsupported"?

throw XmlException(code, _line);

}

referenceChar = Uint16(newChar);

referenceLength = numDigits + 3;

}

else

{

// Check for entity reference

// ATTN: Inefficient if many entity references are supported

Uint32 i;

for (i = 0; i < _REFERENCES_SIZE; i++)

{

Uint32 length = _references[i].length;

const char* match = _references[i].match;

if (*p != ';')

if (strncmp(p, _references[i].match, length) == 0)

throw XmlException(code, _line);

{

referenceChar = _references[i].replacement;

referenceLength = length;

break;

}

rem -= p - start;

if (i == _REFERENCES_SIZE)

{

// Didn't recognize the entity reference

// ATTN: Is there a good way to say "unsupported"?

throw XmlException(code, _line);

}

// Replace the reference with the correct character

*p = (char)referenceChar;

char* q = p + referenceLength;

rem = rem - referenceLength + 1;

memmove(p + 1, q, rem);

}

Line 705

Line 902

entry.text = ++p;

if (!_getElementName(p))

{

std::cout << __LINE__ << std::endl;

throw(XmlException(XmlException::BAD_END_TAG, _line));

}

return;

}

else if (isalpha(*p) || *p == '_')

else if ((((*p >= 'A') && (*p <= 'Z')) ||

((*p >= 'a') && (*p <= 'z')) ||

(*p == '_')))

{

entry.type = XmlEntry::START_TAG;

entry.text = p;

Line 727

Line 923

}

else

{

std::cout << __LINE__ << std::endl;

throw XmlException(XmlException::BAD_START_TAG, _line);

}

//--------------------------------------------------------------------------

// Grab all the attributes:

Line 763

Line 956

_getAttributeNameAndEqual(p);

if (*p != '"' && *p != '\'')

{

std::cout << __LINE__ << std::endl;

throw XmlException(XmlException::BAD_ATTRIBUTE_VALUE, _line);

}

attr.value = p + 1;

_getAttributeValue(p);

Line 775

Line 965

{

// The next thing must a space or a "?>":

if (!(p[0] == '?' && p[1] == '>') && !isspace(*p))

if (!(p[0] == '?' && p[1] == '>') && !_isspace(*p))

{

std::cout << __LINE__ << std::endl;

throw XmlException(

XmlException::BAD_ATTRIBUTE_VALUE, _line);

}

else if (!(*p == '>' || (p[0] == '/' && p[1] == '>') || isspace(*p)))

else if (!(*p == '>' || (p[0] == '/' && p[1] == '>') || _isspace(*p)))

{

// The next thing must be a space or a '>':

std::cout << __LINE__ << std::endl;

throw XmlException(XmlException::BAD_ATTRIBUTE_VALUE, _line);

}

_skipWhitespace(p);

_skipWhitespace(_line, p);

if (entry.attributeCount == XmlEntry::MAX_ATTRIBUTES)

throw XmlException(XmlException::TOO_MANY_ATTRIBUTES, _line);

Line 814

Line 1002

void XmlEntry::print() const

{

std::cout << "=== " << _typeStrings[type] << " ";

PEGASUS_STD(cout) << "=== " << _typeStrings[type] << " ";

Boolean needQuotes = type == XmlEntry::CDATA || type == XmlEntry::CONTENT;

if (needQuotes)

std::cout << "\"";

PEGASUS_STD(cout) << "\"";

_printValue(text);

if (needQuotes)

std::cout << "\"";

PEGASUS_STD(cout) << "\"";

std::cout << '\n';

PEGASUS_STD(cout) << '\n';

for (Uint32 i = 0; i < attributeCount; i++)

{

std::cout << " " << attributes[i].name << "=\"";

PEGASUS_STD(cout) << " " << attributes[i].name << "=\"";

_printValue(attributes[i].value);

std::cout << "\"" << std::endl;

PEGASUS_STD(cout) << "\"" << PEGASUS_STD(endl);

}

Line 863

Line 1051

{

first = str;

while (isspace(*first))

while (_isspace(*first))

first++;

if (!*first)

Line 874

Line 1062

last = first + strlen(first);

while (last != first && isspace(last[-1]))

while (last != first && _isspace(last[-1]))

last--;

}

Line 920

Line 1108

if (!end || end != last)

return false;

value = Uint32(tmp);

value = static_cast<Real32>(tmp);

return true;

}

Line 944

Line 1132

if (!getAttributeValue(name, tmp))

return false;

value = tmp;

value = String(tmp);

return true;

}

void XmlAppendCString(Buffer& out, const char* str)

{

out.append(str, static_cast<Uint32>(strlen(str)));

}

PEGASUS_NAMESPACE_END

Legend:

Removed from v.1.1.1.1
changed lines
	Added in v.1.35

No CVS admin address has been configured