1 | /* |
2 | * Copyright (C) 2010 Google Inc. All rights reserved. |
3 | * Copyright (C) 2016-2017 Apple Inc. All rights reserved. |
4 | * |
5 | * Redistribution and use in source and binary forms, with or without |
6 | * modification, are permitted provided that the following conditions |
7 | * are met: |
8 | * |
9 | * 1. Redistributions of source code must retain the above copyright |
10 | * notice, this list of conditions and the following disclaimer. |
11 | * 2. Redistributions in binary form must reproduce the above copyright |
12 | * notice, this list of conditions and the following disclaimer in the |
13 | * documentation and/or other materials provided with the distribution. |
14 | * |
15 | * THIS SOFTWARE IS PROVIDED BY APPLE AND ITS CONTRIBUTORS "AS IS" AND ANY |
16 | * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED |
17 | * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE |
18 | * DISCLAIMED. IN NO EVENT SHALL APPLE OR ITS CONTRIBUTORS BE LIABLE FOR ANY |
19 | * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES |
20 | * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; |
21 | * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND |
22 | * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT |
23 | * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF |
24 | * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
25 | */ |
26 | |
27 | #include "config.h" |
28 | |
29 | #if ENABLE(INDEXED_DATABASE) |
30 | #include "IDBKeyPath.h" |
31 | |
32 | #include <wtf/ASCIICType.h> |
33 | #include <wtf/dtoa.h> |
34 | #include <wtf/text/StringBuilder.h> |
35 | |
36 | namespace WebCore { |
37 | |
38 | class IDBKeyPathLexer { |
39 | public: |
40 | enum TokenType { |
41 | TokenIdentifier, |
42 | TokenDot, |
43 | TokenEnd, |
44 | TokenError |
45 | }; |
46 | |
47 | explicit IDBKeyPathLexer(const String& s) |
48 | : m_string(s) |
49 | , m_remainingText(s) |
50 | , m_currentTokenType(TokenError) |
51 | { |
52 | } |
53 | |
54 | TokenType currentTokenType() const { return m_currentTokenType; } |
55 | |
56 | TokenType nextTokenType() |
57 | { |
58 | m_currentTokenType = lex(m_currentElement); |
59 | return m_currentTokenType; |
60 | } |
61 | |
62 | const String& currentElement() { return m_currentElement; } |
63 | |
64 | private: |
65 | TokenType lex(String&); |
66 | TokenType lexIdentifier(String&); |
67 | |
68 | String m_currentElement; |
69 | const String m_string; |
70 | StringView m_remainingText; |
71 | TokenType m_currentTokenType; |
72 | }; |
73 | |
74 | IDBKeyPathLexer::TokenType IDBKeyPathLexer::lex(String& element) |
75 | { |
76 | if (m_remainingText.isEmpty()) |
77 | return TokenEnd; |
78 | |
79 | if (m_remainingText[0] == '.') { |
80 | m_remainingText = m_remainingText.substring(1); |
81 | return TokenDot; |
82 | } |
83 | |
84 | return lexIdentifier(element); |
85 | } |
86 | |
87 | namespace { |
88 | |
89 | // The following correspond to grammar in ECMA-262. |
90 | const uint32_t unicodeLetter = U_GC_L_MASK | U_GC_NL_MASK; |
91 | const uint32_t unicodeCombiningMark = U_GC_MN_MASK | U_GC_MC_MASK; |
92 | const uint32_t unicodeDigit = U_GC_ND_MASK; |
93 | const uint32_t unicodeConnectorPunctuation = U_GC_PC_MASK; |
94 | const UChar ZWNJ = 0x200C; |
95 | const UChar ZWJ = 0x200D; |
96 | |
97 | static inline bool isIdentifierStartCharacter(UChar c) |
98 | { |
99 | return (U_GET_GC_MASK(c) & unicodeLetter) || (c == '$') || (c == '_'); |
100 | } |
101 | |
102 | static inline bool isIdentifierCharacter(UChar c) |
103 | { |
104 | return (U_GET_GC_MASK(c) & (unicodeLetter | unicodeCombiningMark | unicodeDigit | unicodeConnectorPunctuation)) || (c == '$') || (c == '_') || (c == ZWNJ) || (c == ZWJ); |
105 | } |
106 | |
107 | } // namespace |
108 | |
109 | IDBKeyPathLexer::TokenType IDBKeyPathLexer::lexIdentifier(String& element) |
110 | { |
111 | StringView start = m_remainingText; |
112 | if (!m_remainingText.isEmpty() && isIdentifierStartCharacter(m_remainingText[0])) |
113 | m_remainingText = m_remainingText.substring(1); |
114 | else |
115 | return TokenError; |
116 | |
117 | while (!m_remainingText.isEmpty() && isIdentifierCharacter(m_remainingText[0])) |
118 | m_remainingText = m_remainingText.substring(1); |
119 | |
120 | element = start.substring(0, start.length() - m_remainingText.length()).toString(); |
121 | return TokenIdentifier; |
122 | } |
123 | |
124 | static bool IDBIsValidKeyPath(const String& keyPath) |
125 | { |
126 | IDBKeyPathParseError error; |
127 | Vector<String> keyPathElements; |
128 | IDBParseKeyPath(keyPath, keyPathElements, error); |
129 | return error == IDBKeyPathParseError::None; |
130 | } |
131 | |
132 | void IDBParseKeyPath(const String& keyPath, Vector<String>& elements, IDBKeyPathParseError& error) |
133 | { |
134 | // IDBKeyPath ::= EMPTY_STRING | identifier ('.' identifier)* |
135 | // The basic state machine is: |
136 | // Start => {Identifier, End} |
137 | // Identifier => {Dot, End} |
138 | // Dot => {Identifier} |
139 | // It bails out as soon as it finds an error, but doesn't discard the bits it managed to parse. |
140 | enum ParserState { Identifier, Dot, End }; |
141 | |
142 | IDBKeyPathLexer lexer(keyPath); |
143 | IDBKeyPathLexer::TokenType tokenType = lexer.nextTokenType(); |
144 | ParserState state; |
145 | if (tokenType == IDBKeyPathLexer::TokenIdentifier) |
146 | state = Identifier; |
147 | else if (tokenType == IDBKeyPathLexer::TokenEnd) |
148 | state = End; |
149 | else { |
150 | error = IDBKeyPathParseError::Start; |
151 | return; |
152 | } |
153 | |
154 | while (1) { |
155 | switch (state) { |
156 | case Identifier : { |
157 | IDBKeyPathLexer::TokenType tokenType = lexer.currentTokenType(); |
158 | ASSERT(tokenType == IDBKeyPathLexer::TokenIdentifier); |
159 | |
160 | String element = lexer.currentElement(); |
161 | elements.append(element); |
162 | |
163 | tokenType = lexer.nextTokenType(); |
164 | if (tokenType == IDBKeyPathLexer::TokenDot) |
165 | state = Dot; |
166 | else if (tokenType == IDBKeyPathLexer::TokenEnd) |
167 | state = End; |
168 | else { |
169 | error = IDBKeyPathParseError::Identifier; |
170 | return; |
171 | } |
172 | break; |
173 | } |
174 | case Dot: { |
175 | IDBKeyPathLexer::TokenType tokenType = lexer.currentTokenType(); |
176 | ASSERT(tokenType == IDBKeyPathLexer::TokenDot); |
177 | |
178 | tokenType = lexer.nextTokenType(); |
179 | if (tokenType == IDBKeyPathLexer::TokenIdentifier) |
180 | state = Identifier; |
181 | else { |
182 | error = IDBKeyPathParseError::Dot; |
183 | return; |
184 | } |
185 | break; |
186 | } |
187 | case End: { |
188 | error = IDBKeyPathParseError::None; |
189 | return; |
190 | } |
191 | } |
192 | } |
193 | } |
194 | |
195 | bool isIDBKeyPathValid(const IDBKeyPath& keyPath) |
196 | { |
197 | auto visitor = WTF::makeVisitor([](const String& string) { |
198 | return IDBIsValidKeyPath(string); |
199 | }, [](const Vector<String>& vector) { |
200 | if (vector.isEmpty()) |
201 | return false; |
202 | for (auto& key : vector) { |
203 | if (!IDBIsValidKeyPath(key)) |
204 | return false; |
205 | } |
206 | return true; |
207 | }); |
208 | return WTF::visit(visitor, keyPath); |
209 | } |
210 | |
211 | IDBKeyPath isolatedCopy(const IDBKeyPath& keyPath) |
212 | { |
213 | auto visitor = WTF::makeVisitor([](const String& string) -> IDBKeyPath { |
214 | return string.isolatedCopy(); |
215 | }, [](const Vector<String>& vector) -> IDBKeyPath { |
216 | Vector<String> vectorCopy; |
217 | vectorCopy.reserveInitialCapacity(vector.size()); |
218 | for (auto& string : vector) |
219 | vectorCopy.uncheckedAppend(string.isolatedCopy()); |
220 | return vectorCopy; |
221 | }); |
222 | |
223 | return WTF::visit(visitor, keyPath); |
224 | } |
225 | |
226 | #if !LOG_DISABLED |
227 | String loggingString(const IDBKeyPath& path) |
228 | { |
229 | auto visitor = WTF::makeVisitor([](const String& string) { |
230 | return makeString("< " , string, " >" ); |
231 | }, [](const Vector<String>& strings) { |
232 | if (strings.isEmpty()) |
233 | return "< >"_str ; |
234 | |
235 | StringBuilder builder; |
236 | builder.append("< " ); |
237 | for (size_t i = 0; i < strings.size() - 1; ++i) { |
238 | builder.append(strings[i]); |
239 | builder.append(", " ); |
240 | } |
241 | builder.append(strings.last()); |
242 | builder.append(" >" ); |
243 | |
244 | return builder.toString(); |
245 | }); |
246 | |
247 | return WTF::visit(visitor, path); |
248 | } |
249 | #endif |
250 | |
251 | } // namespace WebCore |
252 | |
253 | #endif // ENABLE(INDEXED_DATABASE) |
254 | |