|
1 /**************************************************************************** |
|
2 ** |
|
3 ** Copyright (C) 2009 Nokia Corporation and/or its subsidiary(-ies). |
|
4 ** All rights reserved. |
|
5 ** Contact: Nokia Corporation (qt-info@nokia.com) |
|
6 ** |
|
7 ** This file is part of the QtXmlPatterns module of the Qt Toolkit. |
|
8 ** |
|
9 ** $QT_BEGIN_LICENSE:LGPL$ |
|
10 ** No Commercial Usage |
|
11 ** This file contains pre-release code and may not be distributed. |
|
12 ** You may use this file in accordance with the terms and conditions |
|
13 ** contained in the Technology Preview License Agreement accompanying |
|
14 ** this package. |
|
15 ** |
|
16 ** GNU Lesser General Public License Usage |
|
17 ** Alternatively, this file may be used under the terms of the GNU Lesser |
|
18 ** General Public License version 2.1 as published by the Free Software |
|
19 ** Foundation and appearing in the file LICENSE.LGPL included in the |
|
20 ** packaging of this file. Please review the following information to |
|
21 ** ensure the GNU Lesser General Public License version 2.1 requirements |
|
22 ** will be met: http://www.gnu.org/licenses/old-licenses/lgpl-2.1.html. |
|
23 ** |
|
24 ** In addition, as a special exception, Nokia gives you certain additional |
|
25 ** rights. These rights are described in the Nokia Qt LGPL Exception |
|
26 ** version 1.1, included in the file LGPL_EXCEPTION.txt in this package. |
|
27 ** |
|
28 ** If you have questions regarding the use of this file, please contact |
|
29 ** Nokia at qt-info@nokia.com. |
|
30 ** |
|
31 ** |
|
32 ** |
|
33 ** |
|
34 ** |
|
35 ** |
|
36 ** |
|
37 ** |
|
38 ** $QT_END_LICENSE$ |
|
39 ** |
|
40 ****************************************************************************/ |
|
41 |
|
42 // |
|
43 // W A R N I N G |
|
44 // ------------- |
|
45 // |
|
46 // This file is not part of the Qt API. It exists purely as an |
|
47 // implementation detail. This header file may change from version to |
|
48 // version without notice, or even be removed. |
|
49 // |
|
50 // We mean it. |
|
51 |
|
52 #ifndef Patternist_DerivedString_H |
|
53 #define Patternist_DerivedString_H |
|
54 |
|
55 #include <QRegExp> |
|
56 |
|
57 #include "private/qxmlutils_p.h" |
|
58 #include "qbuiltintypes_p.h" |
|
59 #include "qpatternistlocale_p.h" |
|
60 #include "qvalidationerror_p.h" |
|
61 |
|
62 QT_BEGIN_HEADER |
|
63 |
|
64 QT_BEGIN_NAMESPACE |
|
65 |
|
66 namespace QPatternist |
|
67 { |
|
68 /** |
|
69 * @short Represents instances of derived @c xs:string types, such as @c |
|
70 * xs:normalizedString. |
|
71 * |
|
72 * Whitespace is a significant part for creating values from the lexical |
|
73 * space. Of course the specification is tricky here. Here's some pointers: |
|
74 * |
|
75 * - From <a href="4.3.6.1 The whiteSpace Schema Component">XML Schema Part 2: Datatypes |
|
76 * Second Edition, 4.3.6 whiteSpace</a>: |
|
77 * "For all atomic datatypes other than string (and types |
|
78 * derived by restriction from it) the value of whiteSpace is |
|
79 * collapse and cannot be changed by a schema author; for string the |
|
80 * value of whiteSpace is preserve; for any type derived by |
|
81 * restriction from string the value of whiteSpace can be any of the |
|
82 * three legal values." |
|
83 * - From <a href="http://www.w3.org/TR/xmlschema-1/#d0e1654">XML Schema Part 1: Structures |
|
84 * Second Edition, 3.1.4 White Space Normalization during Validation</a>: |
|
85 * "[Definition:] The normalized value of an element or attribute |
|
86 * information item is an initial value whose white space, if any, |
|
87 * has been normalized according to the value of the whiteSpace facet of |
|
88 * the simple type definition used in its validation." |
|
89 * |
|
90 * @author Frans Englich <frans.englich@nokia.com> |
|
91 * @ingroup Patternist_xdm |
|
92 * @todo Documentation is missing |
|
93 */ |
|
94 template<TypeOfDerivedString DerivedType> |
|
95 class DerivedString : public AtomicValue |
|
96 { |
|
97 private: |
|
98 static inline ItemType::Ptr itemType() |
|
99 { |
|
100 switch(DerivedType) |
|
101 { |
|
102 case TypeNormalizedString: return BuiltinTypes::xsNormalizedString; |
|
103 case TypeToken: return BuiltinTypes::xsToken; |
|
104 case TypeLanguage: return BuiltinTypes::xsLanguage; |
|
105 case TypeNMTOKEN: return BuiltinTypes::xsNMTOKEN; |
|
106 case TypeName: return BuiltinTypes::xsName; |
|
107 case TypeNCName: return BuiltinTypes::xsNCName; |
|
108 case TypeID: return BuiltinTypes::xsID; |
|
109 case TypeIDREF: return BuiltinTypes::xsIDREF; |
|
110 case TypeENTITY: return BuiltinTypes::xsENTITY; |
|
111 case TypeString: return BuiltinTypes::xsString; |
|
112 } |
|
113 |
|
114 Q_ASSERT_X(false, Q_FUNC_INFO, "This line is not supposed to be reached."); |
|
115 return ItemType::Ptr(); |
|
116 } |
|
117 |
|
118 const QString m_value; |
|
119 |
|
120 inline DerivedString(const QString &value) : m_value(value) |
|
121 { |
|
122 } |
|
123 |
|
124 /** |
|
125 * @short This is an incomplete test for whether @p ch conforms to |
|
126 * the XML 1.0 NameChar production. |
|
127 */ |
|
128 static inline bool isNameChar(const QChar &ch) |
|
129 { |
|
130 return ch.isLetter() || |
|
131 ch.isDigit() || |
|
132 ch == QLatin1Char('.') || |
|
133 ch == QLatin1Char('-') || |
|
134 ch == QLatin1Char('_') || |
|
135 ch == QLatin1Char(':'); |
|
136 } |
|
137 |
|
138 /** |
|
139 * @returns @c true if @p input is a valid @c xs:Name. |
|
140 * @see <a href="http://www.w3.org/TR/REC-xml/#NT-Name">Extensible |
|
141 * Markup Language (XML) 1.0 (Fourth Edition), [5] Name</a> |
|
142 */ |
|
143 static inline bool isValidName(const QString &input) |
|
144 { |
|
145 if(input.isEmpty()) |
|
146 return false; |
|
147 |
|
148 const QChar first(input.at(0)); |
|
149 |
|
150 if(first.isLetter() || |
|
151 first == QLatin1Char('_') || |
|
152 first == QLatin1Char(':')) |
|
153 { |
|
154 const int len = input.length(); |
|
155 |
|
156 if(len == 1) |
|
157 return true; |
|
158 |
|
159 /* Since we've checked the first character above, we start at |
|
160 * position 1. */ |
|
161 for(int i = 1; i < len; ++i) |
|
162 { |
|
163 if(!isNameChar(input.at(i))) |
|
164 return false; |
|
165 } |
|
166 |
|
167 return true; |
|
168 } |
|
169 else |
|
170 return false; |
|
171 } |
|
172 |
|
173 /** |
|
174 * @returns @c true if @p input conforms to the XML 1.0 @c Nmtoken product. |
|
175 * |
|
176 * @see <a |
|
177 * href="http://www.w3.org/TR/2000/WD-xml-2e-20000814#NT-Nmtoken">Extensible |
|
178 * Markup Language (XML) 1.0 (Second Edition), [7] Nmtoken</a> |
|
179 */ |
|
180 static inline bool isValidNMTOKEN(const QString &input) |
|
181 { |
|
182 const int len = input.length(); |
|
183 |
|
184 if(len == 0) |
|
185 return false; |
|
186 |
|
187 for(int i = 0; i < len; ++i) |
|
188 { |
|
189 if(!isNameChar(input.at(i))) |
|
190 return false; |
|
191 } |
|
192 |
|
193 return true; |
|
194 } |
|
195 |
|
196 /** |
|
197 * @short Performs attribute value normalization as if @p input was not |
|
198 * from a @c CDATA section. |
|
199 * |
|
200 * Each whitespace character in @p input that's not a space, such as tab |
|
201 * or new line character, is replaced with a space. This algorithm |
|
202 * differs from QString::simplified() in that it doesn't collapse |
|
203 * subsequent whitespace characters to a single one, or remove trailing |
|
204 * and leading space. |
|
205 * |
|
206 * @see <a href="http://www.w3.org/TR/REC-xml/#AVNormalize">Extensible |
|
207 * Markup Language (XML) 1.0 (Second Edition), 3.3.3 [E70]Attribute-Value Normalization</a> |
|
208 */ |
|
209 static QString attributeNormalize(const QString &input) |
|
210 { |
|
211 QString retval(input); |
|
212 const int len = retval.length(); |
|
213 const QLatin1Char space(' '); |
|
214 |
|
215 for(int i = 0; i < len; ++i) |
|
216 { |
|
217 const QChar ati(retval.at(i)); |
|
218 |
|
219 if(ati.isSpace() && ati != space) |
|
220 retval[i] = space; |
|
221 } |
|
222 |
|
223 return retval; |
|
224 } |
|
225 |
|
226 static AtomicValue::Ptr error(const NamePool::Ptr &np, const QString &invalidValue) |
|
227 { |
|
228 return ValidationError::createError(QString::fromLatin1("%1 is not a valid value for " |
|
229 "type %2.").arg(formatData(invalidValue)) |
|
230 .arg(formatType(np, itemType()))); |
|
231 } |
|
232 |
|
233 public: |
|
234 |
|
235 /** |
|
236 * @note This function doesn't perform any cleanup/normalizaiton of @p |
|
237 * value. @p value must be a canonical value space of the type. |
|
238 * |
|
239 * If you want cleanup to be performed and/or the lexical space |
|
240 * checked, use fromLexical(). |
|
241 */ |
|
242 static AtomicValue::Ptr fromValue(const QString &value) |
|
243 { |
|
244 return AtomicValue::Ptr(new DerivedString(value)); |
|
245 } |
|
246 |
|
247 /** |
|
248 * Constructs an instance from the lexical |
|
249 * representation @p lexical. |
|
250 */ |
|
251 static AtomicValue::Ptr fromLexical(const NamePool::Ptr &np, const QString &lexical) |
|
252 { |
|
253 switch(DerivedType) |
|
254 { |
|
255 case TypeString: |
|
256 return AtomicValue::Ptr(new DerivedString(lexical)); |
|
257 case TypeNormalizedString: |
|
258 return AtomicValue::Ptr(new DerivedString(attributeNormalize(lexical))); |
|
259 case TypeToken: |
|
260 return AtomicValue::Ptr(new DerivedString(lexical.simplified())); |
|
261 case TypeLanguage: |
|
262 { |
|
263 const QString simplified(lexical.trimmed()); |
|
264 |
|
265 const QRegExp validate(QLatin1String("[a-zA-Z]{1,8}(-[a-zA-Z0-9]{1,8})*")); |
|
266 Q_ASSERT(validate.isValid()); |
|
267 |
|
268 if(validate.exactMatch(simplified)) |
|
269 return AtomicValue::Ptr(new DerivedString(lexical.simplified())); |
|
270 else |
|
271 return error(np, simplified); |
|
272 } |
|
273 case TypeNMTOKEN: |
|
274 { |
|
275 const QString trimmed(lexical.trimmed()); |
|
276 |
|
277 if(isValidNMTOKEN(trimmed)) |
|
278 return AtomicValue::Ptr(new DerivedString(trimmed)); |
|
279 else |
|
280 return error(np, trimmed); |
|
281 } |
|
282 case TypeName: |
|
283 { |
|
284 const QString simplified(lexical.simplified()); |
|
285 |
|
286 if(isValidName(simplified)) |
|
287 return AtomicValue::Ptr(new DerivedString(simplified)); |
|
288 else |
|
289 return error(np, simplified); |
|
290 } |
|
291 case TypeID: |
|
292 /* Fallthrough. */ |
|
293 case TypeIDREF: |
|
294 /* Fallthrough. */ |
|
295 case TypeENTITY: |
|
296 /* Fallthrough. */ |
|
297 case TypeNCName: |
|
298 { |
|
299 /* We treat xs:ID, xs:ENTITY, xs:IDREF and xs:NCName in the exact same |
|
300 * way, except for the type annotation. |
|
301 * |
|
302 * We use trimmed() instead of simplified() because it's |
|
303 * faster and whitespace isn't allowed between |
|
304 * non-whitespace characters anyway, for these types. */ |
|
305 const QString trimmed(lexical.trimmed()); |
|
306 |
|
307 if(QXmlUtils::isNCName(trimmed)) |
|
308 return AtomicValue::Ptr(new DerivedString(trimmed)); |
|
309 else |
|
310 return error(np, trimmed); |
|
311 } |
|
312 default: |
|
313 { |
|
314 Q_ASSERT_X(false, Q_FUNC_INFO, "This line is not supposed to be reached."); |
|
315 return AtomicValue::Ptr(); |
|
316 } |
|
317 } |
|
318 } |
|
319 |
|
320 virtual QString stringValue() const |
|
321 { |
|
322 return m_value; |
|
323 } |
|
324 |
|
325 virtual bool evaluateEBV(const QExplicitlySharedDataPointer<DynamicContext> &) const |
|
326 { |
|
327 return m_value.length() > 0; |
|
328 } |
|
329 |
|
330 virtual ItemType::Ptr type() const |
|
331 { |
|
332 return itemType(); |
|
333 } |
|
334 }; |
|
335 } |
|
336 |
|
337 QT_END_NAMESPACE |
|
338 |
|
339 QT_END_HEADER |
|
340 |
|
341 #endif |