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
|
// Copyright (C) 2016 The Qt Company Ltd.
// SPDX-License-Identifier: LicenseRef-Qt-Commercial OR GPL-3.0-only WITH Qt-GPL-exception-1.0
#ifndef RE2NFA_H
#define RE2NFA_H
#include "nfa.h"
#include <QSet>
class RE2NFA
{
public:
RE2NFA(const QMap<QString, NFA> ¯os, const QSet<InputType> &maxInputSet, Qt::CaseSensitivity cs);
NFA parse(const QString &expression, int *errorColumn = 0);
private:
NFA parseExpr();
NFA parseBranch();
NFA parsePiece();
NFA parseAtom();
NFA parseMaybeQuantifier(const NFA &nfa);
NFA parseSet();
NFA parseSet2();
NFA createCharNFA();
private:
friend class RegExpTokenizer;
enum Token {
TOK_INVALID,
TOK_STRING,
TOK_LBRACE, // {
TOK_RBRACE, // }
TOK_LBRACKET, // [
TOK_RBRACKET, // ]
TOK_LPAREN, // (
TOK_RPAREN, // )
TOK_COMMA,
TOK_STAR,
TOK_OR,
TOK_QUESTION,
TOK_DOT,
TOK_PLUS,
TOK_SEQUENCE,
TOK_QUOTED_STRING
};
struct Symbol
{
inline Symbol() : token(TOK_INVALID), column(-1) {}
inline Symbol(Token t, const QString &l = QString()) : token(t), lexem(l), column(-1) {}
Token token;
QString lexem;
int column;
};
inline bool hasNext() const { return index < symbols.count(); }
inline Token next() { return symbols.at(index++).token; }
bool next(Token t);
bool test(Token t);
inline void prev() { index--; }
inline const Symbol &symbol() const { return symbols.at(index - 1); }
QString lexemUntil(Token t);
void tokenize(const QString &input);
QMap<QString, NFA> macros;
QList<Symbol> symbols;
int index;
int errorColumn;
const QSet<InputType> maxInputSet;
Qt::CaseSensitivity caseSensitivity;
};
#endif // RE2NFA_H
|
