source: trunk/src/xmlpatterns/data/qderivedstring_p.h@ 615

/****************************************************************************
**
** Copyright (C) 2009 Nokia Corporation and/or its subsidiary(-ies).
** All rights reserved.
** Contact: Nokia Corporation ([email protected])
**
** This file is part of the QtXmlPatterns module of the Qt Toolkit.
**
** $QT_BEGIN_LICENSE:LGPL$
** Commercial Usage
** Licensees holding valid Qt Commercial licenses may use this file in
** accordance with the Qt Commercial License Agreement provided with the
** Software or, alternatively, in accordance with the terms contained in
** a written agreement between you and Nokia.
**
** GNU Lesser General Public License Usage
** Alternatively, this file may be used under the terms of the GNU Lesser
** General Public License version 2.1 as published by the Free Software
** Foundation and appearing in the file LICENSE.LGPL included in the
** packaging of this file.  Please review the following information to
** ensure the GNU Lesser General Public License version 2.1 requirements
** will be met: http://www.gnu.org/licenses/old-licenses/lgpl-2.1.html.
**
** In addition, as a special exception, Nokia gives you certain additional
** rights.  These rights are described in the Nokia Qt LGPL Exception
** version 1.1, included in the file LGPL_EXCEPTION.txt in this package.
**
** GNU General Public License Usage
** Alternatively, this file may be used under the terms of the GNU
** General Public License version 3.0 as published by the Free Software
** Foundation and appearing in the file LICENSE.GPL included in the
** packaging of this file.  Please review the following information to
** ensure the GNU General Public License version 3.0 requirements will be
** met: http://www.gnu.org/copyleft/gpl.html.
**
** If you have questions regarding the use of this file, please contact
** Nokia at [email protected].
** $QT_END_LICENSE$
**
****************************************************************************/

//
//  W A R N I N G
//  -------------
//
// This file is not part of the Qt API.  It exists purely as an
// implementation detail.  This header file may change from version to
// version without notice, or even be removed.
//
// We mean it.

#ifndef Patternist_DerivedString_H
#define Patternist_DerivedString_H

#include <QRegExp>

#include "private/qxmlutils_p.h"
#include "qbuiltintypes_p.h"
#include "qpatternistlocale_p.h"
#include "qvalidationerror_p.h"

QT_BEGIN_HEADER

QT_BEGIN_NAMESPACE

namespace QPatternist
{
    /**
     * @short Represents instances of derived @c xs:string types, such as @c
     * xs:normalizedString.
     *
     * Whitespace is a significant part for creating values from the lexical
     * space. Of course the specification is tricky here. Here's some pointers:
     *
     * - From <a href="4.3.6.1 The whiteSpace Schema Component">XML Schema Part 2: Datatypes
     *   Second Edition, 4.3.6 whiteSpace</a>:
     *   "For all atomic datatypes other than string (and types
     *   derived by restriction from it) the value of whiteSpace is
     *   collapse and cannot be changed by a schema author; for string the
     *   value of whiteSpace is preserve; for any type derived by
     *   restriction from string the value of whiteSpace can be any of the
     *   three legal values."
     * - From <a href="http://www.w3.org/TR/xmlschema-1/#d0e1654">XML Schema Part 1: Structures
     *   Second Edition, 3.1.4 White Space Normalization during Validation</a>:
     *   "[Definition:]  The normalized value of an element or attribute
     *   information item is an initial value whose white space, if any,
     *   has been normalized according to the value of the whiteSpace facet of
     *   the simple type definition used in its validation."
     *
     * @author Frans Englich <[email protected]>
     * @ingroup Patternist_xdm
     * @todo Documentation is missing
     */
    template<TypeOfDerivedString DerivedType>
    class DerivedString : public AtomicValue
    {
    private:
        static inline ItemType::Ptr itemType()
        {
            switch(DerivedType)
            {
                case TypeNormalizedString:  return BuiltinTypes::xsNormalizedString;
                case TypeToken:             return BuiltinTypes::xsToken;
                case TypeLanguage:          return BuiltinTypes::xsLanguage;
                case TypeNMTOKEN:           return BuiltinTypes::xsNMTOKEN;
                case TypeName:              return BuiltinTypes::xsName;
                case TypeNCName:            return BuiltinTypes::xsNCName;
                case TypeID:                return BuiltinTypes::xsID;
                case TypeIDREF:             return BuiltinTypes::xsIDREF;
                case TypeENTITY:            return BuiltinTypes::xsENTITY;
                case TypeString:            return BuiltinTypes::xsString;
            }

            Q_ASSERT_X(false, Q_FUNC_INFO, "This line is not supposed to be reached.");
            return ItemType::Ptr();
        }

        const QString m_value;

        inline DerivedString(const QString &value) : m_value(value)
        {
        }

        /**
         * @short This is an incomplete test for whether @p ch conforms to
         * the XML 1.0 NameChar production.
         */
        static inline bool isNameChar(const QChar &ch)
        {
            return ch.isLetter()            ||
                   ch.isDigit()             ||
                   ch == QLatin1Char('.')   ||
                   ch == QLatin1Char('-')   ||
                   ch == QLatin1Char('_')   ||
                   ch == QLatin1Char(':');
        }

        /**
         * @returns @c true if @p input is a valid @c xs:Name.
         * @see <a href="http://www.w3.org/TR/REC-xml/#NT-Name">Extensible
         * Markup Language (XML) 1.0 (Fourth Edition), [5] Name</a>
         */
        static inline bool isValidName(const QString &input)
        {
            if(input.isEmpty())
                return false;

            const QChar first(input.at(0));

            if(first.isLetter()             ||
               first == QLatin1Char('_')    ||
               first == QLatin1Char(':'))
            {
                const int len = input.length();

                if(len == 1)
                    return true;

                /* Since we've checked the first character above, we start at
                 * position 1. */
                for(int i = 1; i < len; ++i)
                {
                    if(!isNameChar(input.at(i)))
                        return false;
                }

                return true;
            }
            else
                return false;
        }

        /**
         * @returns @c true if @p input conforms to the XML 1.0 @c Nmtoken product.
         *
         * @see <a
         * href="http://www.w3.org/TR/2000/WD-xml-2e-20000814#NT-Nmtoken">Extensible
         * Markup Language (XML) 1.0 (Second Edition), [7] Nmtoken</a>
         */
        static inline bool isValidNMTOKEN(const QString &input)
        {
            const int len = input.length();

            if(len == 0)
                return false;

            for(int i = 0; i < len; ++i)
            {
                if(!isNameChar(input.at(i)))
                    return false;
            }

            return true;
        }

        /**
         * @short Performs attribute value normalization as if @p input was not
         * from a @c CDATA section.
         *
         * Each whitespace character in @p input that's not a space, such as tab
         * or new line character, is replaced with a space. This algorithm
         * differs from QString::simplified() in that it doesn't collapse
         * subsequent whitespace characters to a single one, or remove trailing
         * and leading space.
         *
         * @see <a href="http://www.w3.org/TR/REC-xml/#AVNormalize">Extensible