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 QtQml 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 "qv4regexp_p.h" |
41 | #include "qv4engine_p.h" |
42 | #include "qv4scopedvalue_p.h" |
43 | #include <private/qv4mm_p.h> |
44 | #include <runtime/VM.h> |
45 | |
46 | using namespace QV4; |
47 | |
48 | static JSC::RegExpFlags jscFlags(uint flags) |
49 | { |
50 | JSC::RegExpFlags jscFlags = JSC::NoFlags; |
51 | if (flags & CompiledData::RegExp::RegExp_Global) |
52 | jscFlags = static_cast<JSC::RegExpFlags>(flags | JSC::FlagGlobal); |
53 | if (flags & CompiledData::RegExp::RegExp_IgnoreCase) |
54 | jscFlags = static_cast<JSC::RegExpFlags>(flags | JSC::FlagIgnoreCase); |
55 | if (flags & CompiledData::RegExp::RegExp_Multiline) |
56 | jscFlags = static_cast<JSC::RegExpFlags>(flags | JSC::FlagMultiline); |
57 | if (flags & CompiledData::RegExp::RegExp_Unicode) |
58 | jscFlags = static_cast<JSC::RegExpFlags>(flags | JSC::FlagUnicode); |
59 | if (flags & CompiledData::RegExp::RegExp_Sticky) |
60 | jscFlags = static_cast<JSC::RegExpFlags>(flags | JSC::FlagSticky); |
61 | return jscFlags; |
62 | } |
63 | |
64 | RegExpCache::~RegExpCache() |
65 | { |
66 | for (RegExpCache::Iterator it = begin(), e = end(); it != e; ++it) { |
67 | if (RegExp *re = it.value().as<RegExp>()) |
68 | re->d()->cache = nullptr; |
69 | } |
70 | } |
71 | |
72 | DEFINE_MANAGED_VTABLE(RegExp); |
73 | |
74 | uint RegExp::match(const QString &string, int start, uint *matchOffsets) |
75 | { |
76 | if (!isValid()) |
77 | return JSC::Yarr::offsetNoMatch; |
78 | |
79 | WTF::String s(string); |
80 | |
81 | #if ENABLE(YARR_JIT) |
82 | static const uint offsetJITFail = std::numeric_limits<unsigned>::max() - 1; |
83 | auto *priv = d(); |
84 | if (priv->hasValidJITCode()) { |
85 | uint ret = JSC::Yarr::offsetNoMatch; |
86 | #if ENABLE(YARR_JIT_ALL_PARENS_EXPRESSIONS) |
87 | char buffer[8192]; |
88 | ret = uint(priv->jitCode->execute(input: s.characters16(), start, length: s.length(), |
89 | output: (int*)matchOffsets, freeParenContext: buffer, parenContextSize: 8192).start); |
90 | #else |
91 | ret = uint(priv->jitCode->execute(s.characters16(), start, s.length(), |
92 | (int*)matchOffsets).start); |
93 | #endif |
94 | if (ret != offsetJITFail) |
95 | return ret; |
96 | |
97 | // JIT failed. We need byteCode to run the interpreter. |
98 | if (!priv->byteCode) { |
99 | JSC::Yarr::ErrorCode error = JSC::Yarr::ErrorCode::NoError; |
100 | JSC::Yarr::YarrPattern yarrPattern(WTF::String(*priv->pattern), jscFlags(flags: priv->flags), |
101 | error); |
102 | |
103 | // As we successfully parsed the pattern before, we should still be able to. |
104 | Q_ASSERT(error == JSC::Yarr::ErrorCode::NoError); |
105 | |
106 | priv->byteCode = JSC::Yarr::byteCompile( |
107 | yarrPattern, |
108 | priv->internalClass->engine->bumperPointerAllocator).release(); |
109 | } |
110 | } |
111 | #endif // ENABLE(YARR_JIT) |
112 | |
113 | return JSC::Yarr::interpret(byteCode(), input: s.characters16(), length: string.length(), start, output: matchOffsets); |
114 | } |
115 | |
116 | QString RegExp::getSubstitution(const QString &matched, const QString &str, int position, const Value *captures, int nCaptures, const QString &replacement) |
117 | { |
118 | QString result; |
119 | |
120 | int matchedLength = matched.length(); |
121 | Q_ASSERT(position >= 0 && position <= str.length()); |
122 | int tailPos = position + matchedLength; |
123 | int seenDollar = -1; |
124 | for (int i = 0; i < replacement.length(); ++i) { |
125 | QChar ch = replacement.at(i); |
126 | if (seenDollar >= 0) { |
127 | if (ch.unicode() == '$') { |
128 | result += QLatin1Char('$'); |
129 | } else if (ch.unicode() == '&') { |
130 | result += matched; |
131 | } else if (ch.unicode() == '`') { |
132 | result += str.left(n: position); |
133 | } else if (ch.unicode() == '\'') { |
134 | result += str.mid(position: tailPos); |
135 | } else if (ch.unicode() >= '0' && ch.unicode() <= '9') { |
136 | int n = ch.unicode() - '0'; |
137 | if (i + 1 < replacement.length()) { |
138 | ch = replacement.at(i: i + 1); |
139 | if (ch.unicode() >= '0' && ch.unicode() <= '9') { |
140 | n = n*10 + (ch.unicode() - '0'); |
141 | ++i; |
142 | } |
143 | } |
144 | if (n > 0 && n <= nCaptures) { |
145 | String *s = captures[n].stringValue(); |
146 | if (s) |
147 | result += s->toQString(); |
148 | } else { |
149 | for (int j = seenDollar; j <= i; ++j) |
150 | result += replacement.at(i: j); |
151 | } |
152 | } else { |
153 | result += QLatin1Char('$'); |
154 | result += ch; |
155 | } |
156 | seenDollar = -1; |
157 | } else { |
158 | if (ch == QLatin1Char('$')) { |
159 | seenDollar = i; |
160 | continue; |
161 | } |
162 | result += ch; |
163 | } |
164 | } |
165 | if (seenDollar >= 0) |
166 | result += QLatin1Char('$'); |
167 | return result; |
168 | } |
169 | |
170 | QString Heap::RegExp::flagsAsString() const |
171 | { |
172 | QString result; |
173 | if (flags & CompiledData::RegExp::RegExp_Global) |
174 | result += QLatin1Char('g'); |
175 | if (flags & CompiledData::RegExp::RegExp_IgnoreCase) |
176 | result += QLatin1Char('i'); |
177 | if (flags & CompiledData::RegExp::RegExp_Multiline) |
178 | result += QLatin1Char('m'); |
179 | if (flags & CompiledData::RegExp::RegExp_Unicode) |
180 | result += QLatin1Char('u'); |
181 | if (flags & CompiledData::RegExp::RegExp_Sticky) |
182 | result += QLatin1Char('y'); |
183 | return result; |
184 | } |
185 | |
186 | Heap::RegExp *RegExp::create(ExecutionEngine* engine, const QString& pattern, uint flags) |
187 | { |
188 | RegExpCacheKey key(pattern, flags); |
189 | |
190 | RegExpCache *cache = engine->regExpCache; |
191 | if (!cache) |
192 | cache = engine->regExpCache = new RegExpCache; |
193 | |
194 | QV4::WeakValue &cachedValue = (*cache)[key]; |
195 | if (QV4::RegExp *result = cachedValue.as<RegExp>()) |
196 | return result->d(); |
197 | |
198 | Scope scope(engine); |
199 | Scoped<RegExp> result(scope, engine->memoryManager->alloc<RegExp>(args: engine, args: pattern, args: flags)); |
200 | |
201 | result->d()->cache = cache; |
202 | cachedValue.set(engine, value: result); |
203 | |
204 | return result->d(); |
205 | } |
206 | |
207 | void Heap::RegExp::init(ExecutionEngine *engine, const QString &pattern, uint flags) |
208 | { |
209 | Base::init(); |
210 | this->pattern = new QString(pattern); |
211 | this->flags = flags; |
212 | |
213 | valid = false; |
214 | |
215 | JSC::Yarr::ErrorCode error = JSC::Yarr::ErrorCode::NoError; |
216 | JSC::Yarr::YarrPattern yarrPattern(WTF::String(pattern), jscFlags(flags), error); |
217 | if (error != JSC::Yarr::ErrorCode::NoError) |
218 | return; |
219 | subPatternCount = yarrPattern.m_numSubpatterns; |
220 | #if ENABLE(YARR_JIT) |
221 | if (!yarrPattern.m_containsBackreferences && engine->canJIT()) { |
222 | jitCode = new JSC::Yarr::YarrCodeBlock; |
223 | JSC::VM *vm = static_cast<JSC::VM *>(engine); |
224 | JSC::Yarr::jitCompile(yarrPattern, JSC::Yarr::Char16, vm, jitObject&: *jitCode); |
225 | } |
226 | #else |
227 | Q_UNUSED(engine) |
228 | #endif |
229 | if (hasValidJITCode()) { |
230 | valid = true; |
231 | return; |
232 | } |
233 | byteCode = JSC::Yarr::byteCompile(yarrPattern, internalClass->engine->bumperPointerAllocator).release(); |
234 | if (byteCode) |
235 | valid = true; |
236 | } |
237 | |
238 | void Heap::RegExp::destroy() |
239 | { |
240 | if (cache) { |
241 | RegExpCacheKey key(this); |
242 | cache->remove(akey: key); |
243 | } |
244 | #if ENABLE(YARR_JIT) |
245 | delete jitCode; |
246 | #endif |
247 | delete byteCode; |
248 | delete pattern; |
249 | Base::destroy(); |
250 | } |
251 | |