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
|
// Copyright (c) 2008 Roberto Raggi <roberto.raggi@gmail.com>
//
// Permission is hereby granted, free of charge, to any person obtaining a copy
// of this software and associated documentation files (the "Software"), to deal
// in the Software without restriction, including without limitation the rights
// to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
// copies of the Software, and to permit persons to whom the Software is
// furnished to do so, subject to the following conditions:
//
// The above copyright notice and this permission notice shall be included in
// all copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
// AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
// THE SOFTWARE.
#pragma once
#include "CPlusPlusForwardDeclarations.h"
#include "Token.h"
#include <QByteArray>
namespace CPlusPlus {
class CPLUSPLUS_EXPORT Lexer
{
Lexer(const Lexer &other);
void operator =(const Lexer &other);
public:
Lexer(TranslationUnit *unit);
Lexer(const char *firstChar, const char *lastChar);
~Lexer();
Control *control() const { return _control; }
void scan(Token *tok);
inline void operator()(Token *tok)
{ scan(tok); }
bool scanCommentTokens() const;
void setScanCommentTokens(bool onoff);
bool scanKeywords() const;
void setScanKeywords(bool onoff);
bool scanAngleStringLiteralTokens() const;
void setScanAngleStringLiteralTokens(bool onoff);
void setStartWithNewline(bool enabled);
int state() const;
void setState(int state);
LanguageFeatures languageFeatures() const { return _languageFeatures; }
void setLanguageFeatures(LanguageFeatures features) { _languageFeatures = features; }
void setPreprocessorMode(bool onoff)
{ f._ppMode = onoff; }
QByteArray expectedRawStringSuffix() const { return _expectedRawStringSuffix; }
void setExpectedRawStringSuffix(const QByteArray &suffix)
{ _expectedRawStringSuffix = suffix; }
public:
static void yyinp_utf8(const char *¤tSourceChar, unsigned char &yychar,
unsigned &utf16charCounter)
{
++utf16charCounter;
// Process multi-byte UTF-8 code point (non-latin1)
if (CPLUSPLUS_UNLIKELY(isByteOfMultiByteCodePoint(yychar))) {
unsigned trailingBytesCurrentCodePoint = 1;
for (unsigned char c = yychar << 2; isByteOfMultiByteCodePoint(c); c <<= 1)
++trailingBytesCurrentCodePoint;
// Code points >= 0x00010000 are represented by two UTF-16 code units
if (trailingBytesCurrentCodePoint >= 3)
++utf16charCounter;
yychar = *(currentSourceChar += trailingBytesCurrentCodePoint + 1);
// Process single-byte UTF-8 code point (latin1)
} else {
yychar = *++currentSourceChar;
}
}
private:
void pushLineStartOffset();
void scan_helper(Token *tok);
void setSource(const char *firstChar, const char *lastChar);
static int classify(const char *string, int length, LanguageFeatures features);
static int classifyObjCAtKeyword(const char *s, int n);
static int classifyOperator(const char *string, int length);
void scanStringLiteral(Token *tok, unsigned char hint = 0);
void scanRawStringLiteral(Token *tok, unsigned char hint = 0);
bool scanUntilRawStringLiteralEndPrecise();
bool scanUntilRawStringLiteralEndSimple();
void scanCharLiteral(Token *tok, unsigned char hint = 0);
void scanUntilQuote(Token *tok, unsigned char quote);
bool scanDigitSequence();
bool scanExponentPart();
bool scanOptionalFloatingSuffix();
bool scanOptionalIntegerSuffix(bool allowU = true);
void scanOptionalUserDefinedLiteral(Token *tok);
void scanNumericLiteral(Token *tok);
void scanPreprocessorNumber(Token *tok, bool dotAlreadySkipped);
void scanIdentifier(Token *tok, unsigned extraProcessedChars = 0);
void scanBackslash(Kind type);
void scanCppComment(Kind type);
static bool isByteOfMultiByteCodePoint(unsigned char byte)
{ return byte & 0x80; } // Check if most significant bit is set
void yyinp()
{
yyinp_utf8(_currentChar, _yychar, _currentCharUtf16);
if (CPLUSPLUS_UNLIKELY(_yychar == '\n'))
pushLineStartOffset();
}
private:
struct Flags {
unsigned _scanCommentTokens: 1;
unsigned _scanKeywords: 1;
unsigned _scanAngleStringLiteralTokens: 1;
unsigned _ppMode: 1;
unsigned _ignoreTrigraph : 1;
};
struct State {
unsigned char _tokenKind : 7;
unsigned char _newlineExpected : 1;
};
TranslationUnit *_translationUnit;
Control *_control;
QByteArray _expectedRawStringSuffix;
const char *_firstChar;
const char *_currentChar;
const char *_lastChar;
const char *_tokenStart;
unsigned char _yychar;
unsigned _currentCharUtf16;
unsigned _tokenStartUtf16;
union {
unsigned char _state;
State s;
};
union {
unsigned _flags;
Flags f;
};
unsigned _currentLine;
LanguageFeatures _languageFeatures;
};
} // namespace CPlusPlus
|
