1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
|
/*
This file is part of solidity.
solidity is free software: you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
solidity is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
You should have received a copy of the GNU General Public License
along with solidity. If not, see <http://www.gnu.org/licenses/>.
This file is derived from the file "scanner.h", which was part of the
V8 project. The original copyright header follows:
Copyright 2006-2012, the V8 project authors. All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are
met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above
copyright notice, this list of conditions and the following
disclaimer in the documentation and/or other materials provided
with the distribution.
* Neither the name of Google Inc. nor the names of its
contributors may be used to endorse or promote products derived
from this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
/**
* @author Christian <c@ethdev.com>
* @date 2014
* Solidity scanner.
*/
#pragma once
#include <libdevcore/Common.h>
#include <libdevcore/CommonData.h>
#include <libevmasm/SourceLocation.h>
#include <libsolidity/parsing/Token.h>
namespace dev
{
namespace solidity
{
class AstRawString;
class AstValueFactory;
class ParserRecorder;
class CharStream
{
public:
CharStream(): m_position(0) {}
explicit CharStream(std::string const& _source): m_source(_source), m_position(0) {}
int position() const { return m_position; }
bool isPastEndOfInput(size_t _charsForward = 0) const { return (m_position + _charsForward) >= m_source.size(); }
char get(size_t _charsForward = 0) const { return m_source[m_position + _charsForward]; }
char advanceAndGet(size_t _chars = 1);
char rollback(size_t _amount);
void reset() { m_position = 0; }
std::string const& source() const { return m_source; }
///@{
///@name Error printing helper functions
/// Functions that help pretty-printing parse errors
/// Do only use in error cases, they are quite expensive.
std::string lineAtPosition(int _position) const;
std::tuple<int, int> translatePositionToLineColumn(int _position) const;
///@}
private:
std::string m_source;
size_t m_position;
};
class Scanner
{
friend class LiteralScope;
public:
explicit Scanner(CharStream const& _source = CharStream(), std::string const& _sourceName = "") { reset(_source, _sourceName); }
std::string source() const { return m_source.source(); }
/// Resets the scanner as if newly constructed with _source and _sourceName as input.
void reset(CharStream const& _source, std::string const& _sourceName);
/// Resets scanner to the start of input.
void reset();
/// @returns the next token and advances input
Token::Value next();
///@{
///@name Information about the current token
/// @returns the current token
Token::Value currentToken() const
{
return m_currentToken.token;
}
ElementaryTypeNameToken currentElementaryTypeNameToken() const
{
unsigned firstSize;
unsigned secondSize;
std::tie(firstSize, secondSize) = m_currentToken.extendedTokenInfo;
return ElementaryTypeNameToken(m_currentToken.token, firstSize, secondSize);
}
SourceLocation currentLocation() const { return m_currentToken.location; }
std::string const& currentLiteral() const { return m_currentToken.literal; }
std::tuple<unsigned, unsigned> const& currentTokenInfo() const { return m_currentToken.extendedTokenInfo; }
///@}
///@{
///@name Information about the current comment token
SourceLocation currentCommentLocation() const { return m_skippedComment.location; }
std::string const& currentCommentLiteral() const { return m_skippedComment.literal; }
/// Called by the parser during FunctionDefinition parsing to clear the current comment
void clearCurrentCommentLiteral() { m_skippedComment.literal.clear(); }
///@}
///@{
///@name Information about the next token
/// @returns the next token without advancing input.
Token::Value peekNextToken() const { return m_nextToken.token; }
SourceLocation peekLocation() const { return m_nextToken.location; }
std::string const& peekLiteral() const { return m_nextToken.literal; }
///@}
std::shared_ptr<std::string const> const& sourceName() const { return m_sourceName; }
///@{
///@name Error printing helper functions
/// Functions that help pretty-printing parse errors
/// Do only use in error cases, they are quite expensive.
std::string lineAtPosition(int _position) const { return m_source.lineAtPosition(_position); }
std::tuple<int, int> translatePositionToLineColumn(int _position) const { return m_source.translatePositionToLineColumn(_position); }
///@}
private:
/// Used for the current and look-ahead token and comments
struct TokenDesc
{
Token::Value token;
SourceLocation location;
std::string literal;
std::tuple<unsigned, unsigned> extendedTokenInfo;
};
///@{
///@name Literal buffer support
inline void addLiteralChar(char c) { m_nextToken.literal.push_back(c); }
inline void addCommentLiteralChar(char c) { m_nextSkippedComment.literal.push_back(c); }
inline void addLiteralCharAndAdvance() { addLiteralChar(m_char); advance(); }
void addUnicodeAsUTF8(unsigned codepoint);
///@}
bool advance() { m_char = m_source.advanceAndGet(); return !m_source.isPastEndOfInput(); }
void rollback(int _amount) { m_char = m_source.rollback(_amount); }
inline Token::Value selectToken(Token::Value _tok) { advance(); return _tok; }
/// If the next character is _next, advance and return _then, otherwise return _else.
inline Token::Value selectToken(char _next, Token::Value _then, Token::Value _else);
bool scanHexByte(char& o_scannedByte);
bool scanUnicode(unsigned& o_codepoint);
/// Scans a single Solidity token.
void scanToken();
/// Skips all whitespace and @returns true if something was skipped.
bool skipWhitespace();
/// Skips all whitespace that are neither '\r' nor '\n'.
void skipWhitespaceExceptUnicodeLinebreak();
Token::Value skipSingleLineComment();
Token::Value skipMultiLineComment();
void scanDecimalDigits();
Token::Value scanNumber(char _charSeen = 0);
std::tuple<Token::Value, unsigned, unsigned> scanIdentifierOrKeyword();
Token::Value scanString();
Token::Value scanHexString();
Token::Value scanSingleLineDocComment();
Token::Value scanMultiLineDocComment();
/// Scans a slash '/' and depending on the characters returns the appropriate token
Token::Value scanSlash();
/// Scans an escape-sequence which is part of a string and adds the
/// decoded character to the current literal. Returns true if a pattern
/// is scanned.
bool scanEscape();
/// @returns true iff we are currently positioned at a unicode line break.
bool isUnicodeLinebreak();
/// Return the current source position.
int sourcePos() const { return m_source.position(); }
bool isSourcePastEndOfInput() const { return m_source.isPastEndOfInput(); }
TokenDesc m_skippedComment; // desc for current skipped comment
TokenDesc m_nextSkippedComment; // desc for next skipped comment
TokenDesc m_currentToken; // desc for current token (as returned by Next())
TokenDesc m_nextToken; // desc for next token (one token look-ahead)
CharStream m_source;
std::shared_ptr<std::string const> m_sourceName;
/// one character look-ahead, equals 0 at end of input
char m_char;
};
}
}
|