| 1 | /**************************************************************************** |
| 2 | ** |
| 3 | ** Copyright (C) 2016 The Qt Company Ltd. |
| 4 | ** Contact: https://www.qt.io/licensing/ |
| 5 | ** |
| 6 | ** This file is part of the QtXmlPatterns module of the Qt Toolkit. |
| 7 | ** |
| 8 | ** $QT_BEGIN_LICENSE:LGPL$ |
| 9 | ** Commercial License Usage |
| 10 | ** Licensees holding valid commercial Qt licenses may use this file in |
| 11 | ** accordance with the commercial license agreement provided with the |
| 12 | ** Software or, alternatively, in accordance with the terms contained in |
| 13 | ** a written agreement between you and The Qt Company. For licensing terms |
| 14 | ** and conditions see https://www.qt.io/terms-conditions. For further |
| 15 | ** information use the contact form at https://www.qt.io/contact-us. |
| 16 | ** |
| 17 | ** GNU Lesser General Public License Usage |
| 18 | ** Alternatively, this file may be used under the terms of the GNU Lesser |
| 19 | ** General Public License version 3 as published by the Free Software |
| 20 | ** Foundation and appearing in the file LICENSE.LGPL3 included in the |
| 21 | ** packaging of this file. Please review the following information to |
| 22 | ** ensure the GNU Lesser General Public License version 3 requirements |
| 23 | ** will be met: https://www.gnu.org/licenses/lgpl-3.0.html. |
| 24 | ** |
| 25 | ** GNU General Public License Usage |
| 26 | ** Alternatively, this file may be used under the terms of the GNU |
| 27 | ** General Public License version 2.0 or (at your option) the GNU General |
| 28 | ** Public license version 3 or any later version approved by the KDE Free |
| 29 | ** Qt Foundation. The licenses are as published by the Free Software |
| 30 | ** Foundation and appearing in the file LICENSE.GPL2 and LICENSE.GPL3 |
| 31 | ** included in the packaging of this file. Please review the following |
| 32 | ** information to ensure the GNU General Public License requirements will |
| 33 | ** be met: https://www.gnu.org/licenses/gpl-2.0.html and |
| 34 | ** https://www.gnu.org/licenses/gpl-3.0.html. |
| 35 | ** |
| 36 | ** $QT_END_LICENSE$ |
| 37 | ** |
| 38 | ****************************************************************************/ |
| 39 | |
| 40 | #include "qabstractfloat_p.h" |
| 41 | #include "qatomicstring_p.h" |
| 42 | #include "qcommonsequencetypes_p.h" |
| 43 | #include "qcommonvalues_p.h" |
| 44 | #include "qinteger_p.h" |
| 45 | #include "qliteral_p.h" |
| 46 | #include "qpatternistlocale_p.h" |
| 47 | #include "qschemanumeric_p.h" |
| 48 | |
| 49 | #include "qstringvaluefns_p.h" |
| 50 | |
| 51 | QT_BEGIN_NAMESPACE |
| 52 | |
| 53 | using namespace QPatternist; |
| 54 | |
| 55 | Item ConcatFN::evaluateSingleton(const DynamicContext::Ptr &context) const |
| 56 | { |
| 57 | const Expression::List::const_iterator end(m_operands.constEnd()); |
| 58 | Expression::List::const_iterator it(m_operands.constBegin()); |
| 59 | QString result; |
| 60 | |
| 61 | for(; it != end; ++it) |
| 62 | { |
| 63 | Item item((*it)->evaluateSingleton(context)); |
| 64 | |
| 65 | if(item) |
| 66 | result += item.stringValue(); |
| 67 | } |
| 68 | |
| 69 | return AtomicString::fromValue(value: result); |
| 70 | } |
| 71 | |
| 72 | Item StringJoinFN::evaluateSingleton(const DynamicContext::Ptr &context) const |
| 73 | { |
| 74 | Item::Iterator::Ptr it(m_operands.first()->evaluateSequence(context)); |
| 75 | Q_ASSERT(it); |
| 76 | Item current(it->next()); |
| 77 | |
| 78 | if(!current) /* Exit early, don't evaluate the separator. */ |
| 79 | return CommonValues::EmptyString; |
| 80 | |
| 81 | QString result; |
| 82 | QString separator; |
| 83 | const Item isep(m_operands.at(i: 1)->evaluateSingleton(context)); |
| 84 | |
| 85 | if(isep) |
| 86 | separator = isep.stringValue(); |
| 87 | |
| 88 | while(true) |
| 89 | { |
| 90 | result += current.stringValue(); |
| 91 | current = it->next(); |
| 92 | |
| 93 | if(!current) |
| 94 | break; |
| 95 | |
| 96 | result += separator; |
| 97 | } |
| 98 | |
| 99 | return result.isEmpty() |
| 100 | ? toItem(atomicValue: CommonValues::EmptyString) |
| 101 | : toItem(atomicValue: AtomicString::fromValue(value: result)); |
| 102 | } |
| 103 | |
| 104 | Expression::Ptr StringJoinFN::compress(const StaticContext::Ptr &context) |
| 105 | { |
| 106 | if(m_operands.first()->staticType()->cardinality().allowsMany()) |
| 107 | return FunctionCall::compress(context); |
| 108 | else |
| 109 | { |
| 110 | if(m_operands.first()->is(i: IDEmptySequence)) |
| 111 | return wrapLiteral(item: CommonValues::EmptyString, context, r: this); |
| 112 | else |
| 113 | return m_operands.first()->compress(context); |
| 114 | } |
| 115 | } |
| 116 | |
| 117 | Item SubstringFN::evaluateSingleton(const DynamicContext::Ptr &context) const |
| 118 | { |
| 119 | Item item(m_operands.first()->evaluateSingleton(context)); |
| 120 | |
| 121 | if(!item) |
| 122 | return CommonValues::EmptyString; |
| 123 | |
| 124 | const QString str(item.stringValue()); |
| 125 | |
| 126 | const xsDouble dblStart = m_operands.at(i: 1)->evaluateSingleton(context).as<Numeric>() |
| 127 | ->round()->toDouble(); |
| 128 | if(qIsNaN(d: dblStart)) |
| 129 | return CommonValues::EmptyString; |
| 130 | |
| 131 | /* XPath starts from 1, but C++ starts from 0. */ |
| 132 | xsInteger startingLoc = Double::fromValue(num: dblStart)->round()->toInteger() - 1; |
| 133 | |
| 134 | xsInteger length = 0; |
| 135 | if(m_operands.count() == 2) |
| 136 | length = str.length() - startingLoc; |
| 137 | else |
| 138 | { |
| 139 | const xsDouble dblLen = m_operands.at(i: 2)->evaluateSingleton(context).as<Numeric>() |
| 140 | ->round()->toDouble(); |
| 141 | |
| 142 | if(qIsNaN(d: dblLen)) |
| 143 | return CommonValues::EmptyString; |
| 144 | |
| 145 | length = Double::fromValue(num: dblLen)->round()->toInteger(); |
| 146 | if(startingLoc > startingLoc + length) |
| 147 | return CommonValues::EmptyString; |
| 148 | } |
| 149 | |
| 150 | if(startingLoc < 0) |
| 151 | { |
| 152 | length = length + startingLoc; |
| 153 | startingLoc = 0; |
| 154 | } |
| 155 | |
| 156 | return AtomicString::fromValue(value: str.mid(position: startingLoc, n: length)); |
| 157 | } |
| 158 | |
| 159 | Item StringLengthFN::evaluateSingleton(const DynamicContext::Ptr &context) const |
| 160 | { |
| 161 | const Item item(m_operands.first()->evaluateSingleton(context)); |
| 162 | |
| 163 | /* fn:string() is re-implemented "inline" here. */ |
| 164 | if(item) |
| 165 | return Integer::fromValue(num: item.stringValue().length()); |
| 166 | else |
| 167 | return CommonValues::IntegerZero; |
| 168 | } |
| 169 | |
| 170 | NormalizeUnicodeFN::NormalizeUnicodeFN() : m_normForm(QString::NormalizationForm_C) |
| 171 | { |
| 172 | } |
| 173 | |
| 174 | Item NormalizeSpaceFN::evaluateSingleton(const DynamicContext::Ptr &context) const |
| 175 | { |
| 176 | const Item arg(m_operands.first()->evaluateSingleton(context)); |
| 177 | |
| 178 | if(!arg) |
| 179 | return CommonValues::EmptyString; |
| 180 | |
| 181 | return toItem(atomicValue: AtomicString::fromValue(value: arg.stringValue().simplified())); |
| 182 | } |
| 183 | |
| 184 | Item NormalizeUnicodeFN::evaluateSingleton(const DynamicContext::Ptr &context) const |
| 185 | { |
| 186 | const Item arg(m_operands.first()->evaluateSingleton(context)); |
| 187 | |
| 188 | if(!arg) |
| 189 | return CommonValues::EmptyString; |
| 190 | |
| 191 | int normForm; |
| 192 | |
| 193 | /* The second argument has been removed, if we've already determined the form. */ |
| 194 | if(m_operands.count() == 1) |
| 195 | normForm = m_normForm; |
| 196 | else |
| 197 | { |
| 198 | normForm = determineNormalizationForm(context); |
| 199 | if(normForm == -1) |
| 200 | return toItem(atomicValue: AtomicString::fromValue(value: arg.stringValue())); |
| 201 | } |
| 202 | |
| 203 | return AtomicString::fromValue(value: arg.stringValue().normalized( |
| 204 | mode: static_cast<QString::NormalizationForm>(normForm))); |
| 205 | } |
| 206 | |
| 207 | Expression::Ptr NormalizeUnicodeFN::compress(const StaticContext::Ptr &context) |
| 208 | { |
| 209 | const Expression::Ptr me(FunctionCall::compress(context)); |
| 210 | if(me != this) |
| 211 | return me; |
| 212 | |
| 213 | Q_ASSERT(m_operands.count() == 1 || m_operands.count() == 2); |
| 214 | |
| 215 | if(m_operands.count() == 1) |
| 216 | m_normForm = QString::NormalizationForm_C; |
| 217 | else if(m_operands.last()->is(i: IDStringValue)) |
| 218 | { |
| 219 | m_normForm = static_cast<QString::NormalizationForm>( |
| 220 | determineNormalizationForm(context: context->dynamicContext())); |
| 221 | |
| 222 | if (int(m_normForm) == -1) |
| 223 | return m_operands.first(); |
| 224 | |
| 225 | /* Remove the operand since we don't need it anymore. */ |
| 226 | m_operands.removeLast(); |
| 227 | } |
| 228 | |
| 229 | return me; |
| 230 | } |
| 231 | |
| 232 | int NormalizeUnicodeFN::determineNormalizationForm(const DynamicContext::Ptr &context) const |
| 233 | { |
| 234 | const QString strRepr(m_operands.last()->evaluateSingleton(context).stringValue().trimmed().toUpper()); |
| 235 | |
| 236 | /* TODO. Put these values in a QHash for faster lookup. Keep thread safety in mind. */ |
| 237 | if(strRepr.isEmpty()) |
| 238 | return -1; |
| 239 | else if(strRepr == QLatin1String("NFC" )) |
| 240 | return QString::NormalizationForm_C; |
| 241 | else if(strRepr == QLatin1String("NFD" )) |
| 242 | return QString::NormalizationForm_D; |
| 243 | else if(strRepr == QLatin1String("NFKC" )) |
| 244 | return QString::NormalizationForm_KC; |
| 245 | else if(strRepr == QLatin1String("NFKD" )) |
| 246 | return QString::NormalizationForm_KD; |
| 247 | else |
| 248 | { |
| 249 | /* What form is FULLY_NORMALIZED? Is a code path available for that somewhere? */ |
| 250 | context->error(message: QtXmlPatterns::tr(sourceText: "The normalization form %1 is " |
| 251 | "unsupported. The supported forms are " |
| 252 | "%2, %3, %4, and %5, and none, i.e. " |
| 253 | "the empty string (no normalization)." ) |
| 254 | .arg(a: formatKeyword(keyword: strRepr)) |
| 255 | .arg(a: formatKeyword(keyword: "NFC" )) |
| 256 | .arg(a: formatKeyword(keyword: "NFD" )) |
| 257 | .arg(a: formatKeyword(keyword: "NFKC" )) |
| 258 | .arg(a: formatKeyword(keyword: "NFKD" )), |
| 259 | errorCode: ReportContext::FOCH0003, |
| 260 | reflection: this); |
| 261 | return QString::NormalizationForm_C; /* Silence compiler warning. */ |
| 262 | } |
| 263 | } |
| 264 | |
| 265 | Item UpperCaseFN::evaluateSingleton(const DynamicContext::Ptr &context) const |
| 266 | { |
| 267 | const Item item(m_operands.first()->evaluateSingleton(context)); |
| 268 | |
| 269 | if(!item) |
| 270 | return CommonValues::EmptyString; |
| 271 | |
| 272 | return AtomicString::fromValue(value: item.stringValue().toUpper()); |
| 273 | } |
| 274 | |
| 275 | Item LowerCaseFN::evaluateSingleton(const DynamicContext::Ptr &context) const |
| 276 | { |
| 277 | const Item item(m_operands.first()->evaluateSingleton(context)); |
| 278 | |
| 279 | if(!item) |
| 280 | return CommonValues::EmptyString; |
| 281 | |
| 282 | return AtomicString::fromValue(value: item.stringValue().toLower()); |
| 283 | } |
| 284 | |
| 285 | Item TranslateFN::evaluateSingleton(const DynamicContext::Ptr &context) const |
| 286 | { |
| 287 | const Item item(m_operands.first()->evaluateSingleton(context)); |
| 288 | |
| 289 | if(!item) |
| 290 | return CommonValues::EmptyString; |
| 291 | |
| 292 | const QString mapString(m_operands.at(i: 1)->evaluateSingleton(context).stringValue()); |
| 293 | const QString arg(item.stringValue()); |
| 294 | |
| 295 | if(mapString.isEmpty()) |
| 296 | return AtomicString::fromValue(value: arg); |
| 297 | |
| 298 | const QString transString(m_operands.at(i: 2)->evaluateSingleton(context).stringValue()); |
| 299 | const int transLen = transString.length(); |
| 300 | const int argLen = arg.length(); |
| 301 | |
| 302 | QString result; |
| 303 | result.reserve(asize: argLen); |
| 304 | int outI = 0; |
| 305 | |
| 306 | for(int i = 0; i < argLen; ++i) |
| 307 | { |
| 308 | const QChar argCh(arg.at(i)); |
| 309 | const int mapPos = mapString.indexOf(c: argCh); |
| 310 | |
| 311 | if(mapPos == -1) |
| 312 | { |
| 313 | result[outI] = argCh; |
| 314 | ++outI; |
| 315 | continue; |
| 316 | } |
| 317 | else if(mapPos >= transLen) |
| 318 | continue; |
| 319 | |
| 320 | const QChar transCh(transString.at(i: mapPos)); |
| 321 | |
| 322 | if(transCh.isNull()) |
| 323 | continue; |
| 324 | |
| 325 | result[outI] = transCh; |
| 326 | ++outI; |
| 327 | } |
| 328 | |
| 329 | result.truncate(pos: outI); |
| 330 | return AtomicString::fromValue(value: result); |
| 331 | } |
| 332 | |
| 333 | EncodeString::EncodeString(const QByteArray &excludeChars, |
| 334 | const QByteArray &includeChars) : m_excludeChars(excludeChars), |
| 335 | m_includeChars(includeChars) |
| 336 | { |
| 337 | } |
| 338 | |
| 339 | Item EncodeString::evaluateSingleton(const DynamicContext::Ptr &context) const |
| 340 | { |
| 341 | const Item item(m_operands.first()->evaluateSingleton(context)); |
| 342 | |
| 343 | if(!item) |
| 344 | return CommonValues::EmptyString; |
| 345 | |
| 346 | const QByteArray value = item.stringValue().toUtf8().toPercentEncoding(exclude: m_excludeChars, include: m_includeChars); |
| 347 | return AtomicString::fromValue(value: QLatin1String(value)); |
| 348 | } |
| 349 | |
| 350 | const char *const EncodeForURIFN::include = "#!*'()" ; |
| 351 | |
| 352 | EncodeForURIFN::EncodeForURIFN() : EncodeString(QByteArray(), QByteArray::fromRawData(include, size: 6)) |
| 353 | { |
| 354 | } |
| 355 | |
| 356 | const char *const IriToURIFN::exclude = "#-_!~*'();?@&=+$,[]/:%" ; |
| 357 | |
| 358 | IriToURIFN::IriToURIFN() : EncodeString(QByteArray::fromRawData(exclude, size: 22), QByteArray()) |
| 359 | { |
| 360 | } |
| 361 | |
| 362 | const char *const EscapeHtmlURIFN::include = "?&[]%" ; |
| 363 | const char *const EscapeHtmlURIFN::exclude = " :;=@!./+*()-,#$'" ; |
| 364 | |
| 365 | EscapeHtmlURIFN::EscapeHtmlURIFN() : EncodeString(QByteArray::fromRawData(exclude, size: 17), |
| 366 | QByteArray::fromRawData(include, size: 6)) |
| 367 | { |
| 368 | } |
| 369 | |
| 370 | QT_END_NAMESPACE |
| 371 | |