blob: 27c11020554b7f221b21ba5dace9505158868b4a (
plain)
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
|
//===--- UnwrappedLineParser.h - Format C++ code ----------------*- C++ -*-===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
///
/// \file
/// \brief This file contains the declaration of the UnwrappedLineParser,
/// which turns a stream of tokens into UnwrappedLines.
///
/// This is EXPERIMENTAL code under heavy development. It is not in a state yet,
/// where it can be used to format real code.
///
//===----------------------------------------------------------------------===//
#ifndef LLVM_CLANG_FORMAT_UNWRAPPED_LINE_PARSER_H
#define LLVM_CLANG_FORMAT_UNWRAPPED_LINE_PARSER_H
#include "clang/Basic/IdentifierTable.h"
#include "clang/Basic/SourceManager.h"
#include "clang/Format/Format.h"
#include "clang/Lex/Lexer.h"
namespace clang {
namespace format {
/// \brief A wrapper around a \c Token storing information about the
/// whitespace characters preceeding it.
struct FormatToken {
FormatToken()
: NewlinesBefore(0), HasUnescapedNewline(false), WhiteSpaceLength(0),
TokenLength(0), IsFirst(false) {
}
/// \brief The \c Token.
Token Tok;
/// \brief The number of newlines immediately before the \c Token.
///
/// This can be used to determine what the user wrote in the original code
/// and thereby e.g. leave an empty line between two function definitions.
unsigned NewlinesBefore;
/// \brief Whether there is at least one unescaped newline before the \c
/// Token.
bool HasUnescapedNewline;
/// \brief The location of the start of the whitespace immediately preceeding
/// the \c Token.
///
/// Used together with \c WhiteSpaceLength to create a \c Replacement.
SourceLocation WhiteSpaceStart;
/// \brief The length in characters of the whitespace immediately preceeding
/// the \c Token.
unsigned WhiteSpaceLength;
/// \brief The length of the non-whitespace parts of the token. This is
/// necessary because we need to handle escaped newlines that are stored
/// with the token.
unsigned TokenLength;
/// \brief Indicates that this is the first token.
bool IsFirst;
};
/// \brief An unwrapped line is a sequence of \c Token, that we would like to
/// put on a single line if there was no column limit.
///
/// This is used as a main interface between the \c UnwrappedLineParser and the
/// \c UnwrappedLineFormatter. The key property is that changing the formatting
/// within an unwrapped line does not affect any other unwrapped lines.
struct UnwrappedLine {
UnwrappedLine() : Level(0), InPPDirective(false) {
}
/// \brief The \c Token comprising this \c UnwrappedLine.
SmallVector<FormatToken, 16> Tokens;
/// \brief The indent level of the \c UnwrappedLine.
unsigned Level;
/// \brief Whether this \c UnwrappedLine is part of a preprocessor directive.
bool InPPDirective;
};
class UnwrappedLineConsumer {
public:
virtual ~UnwrappedLineConsumer() {
}
virtual void consumeUnwrappedLine(const UnwrappedLine &Line) = 0;
};
class FormatTokenSource {
public:
virtual ~FormatTokenSource() {
}
virtual FormatToken getNextToken() = 0;
};
class UnwrappedLineParser {
public:
UnwrappedLineParser(const FormatStyle &Style, FormatTokenSource &Tokens,
UnwrappedLineConsumer &Callback);
/// Returns true in case of a structural error.
bool parse();
private:
bool parseFile();
bool parseLevel(bool HasOpeningBrace);
bool parseBlock(unsigned AddLevels = 1);
void parsePPDirective();
void parsePPDefine();
void parsePPUnknown();
void parseComments();
void parseStructuralElement();
void parseParens();
void parseIfThenElse();
void parseForOrWhileLoop();
void parseDoWhile();
void parseLabel();
void parseCaseLabel();
void parseSwitch();
void parseNamespace();
void parseAccessSpecifier();
void parseEnum();
void addUnwrappedLine();
bool eof() const;
void nextToken();
void readToken();
// FIXME: We are constantly running into bugs where Line.Level is incorrectly
// subtracted from beyond 0. Introduce a method to subtract from Line.Level
// and use that everywhere in the Parser.
UnwrappedLine Line;
FormatToken FormatTok;
const FormatStyle &Style;
FormatTokenSource *Tokens;
UnwrappedLineConsumer &Callback;
};
} // end namespace format
} // end namespace clang
#endif // LLVM_CLANG_FORMAT_UNWRAPPED_LINE_PARSER_H
|
