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
|
//===--- TokenAnnotator.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 implements a token annotator, i.e. creates
/// \c AnnotatedTokens out of \c FormatTokens with required extra information.
///
//===----------------------------------------------------------------------===//
#ifndef LLVM_CLANG_FORMAT_TOKEN_ANNOTATOR_H
#define LLVM_CLANG_FORMAT_TOKEN_ANNOTATOR_H
#include "UnwrappedLineParser.h"
#include "clang/Basic/OperatorPrecedence.h"
#include "clang/Format/Format.h"
#include <string>
namespace clang {
class Lexer;
class SourceManager;
namespace format {
enum TokenType {
TT_BinaryOperator,
TT_BlockComment,
TT_CastRParen,
TT_ConditionalExpr,
TT_CtorInitializerColon,
TT_ImplicitStringLiteral,
TT_InheritanceColon,
TT_LineComment,
TT_ObjCArrayLiteral,
TT_ObjCBlockLParen,
TT_ObjCDecl,
TT_ObjCForIn,
TT_ObjCMethodExpr,
TT_ObjCMethodSpecifier,
TT_ObjCProperty,
TT_ObjCSelectorName,
TT_OverloadedOperatorLParen,
TT_PointerOrReference,
TT_PureVirtualSpecifier,
TT_RangeBasedForLoopColon,
TT_StartOfName,
TT_TemplateCloser,
TT_TemplateOpener,
TT_TrailingUnaryOperator,
TT_UnaryOperator,
TT_Unknown
};
enum LineType {
LT_Invalid,
LT_Other,
LT_BuilderTypeCall,
LT_PreprocessorDirective,
LT_VirtualFunctionDecl,
LT_ObjCDecl, // An @interface, @implementation, or @protocol line.
LT_ObjCMethodDecl,
LT_ObjCProperty // An @property line.
};
class AnnotatedToken {
public:
explicit AnnotatedToken(const FormatToken &FormatTok)
: FormatTok(FormatTok), Type(TT_Unknown), SpacesRequiredBefore(0),
CanBreakBefore(false), MustBreakBefore(false),
ClosesTemplateDeclaration(false), MatchingParen(NULL),
ParameterCount(0), BindingStrength(0), SplitPenalty(0),
LongestObjCSelectorName(0), Parent(NULL), FakeLParens(0),
FakeRParens(0) {
}
bool is(tok::TokenKind Kind) const { return FormatTok.Tok.is(Kind); }
bool isNot(tok::TokenKind Kind) const { return FormatTok.Tok.isNot(Kind); }
bool isObjCAtKeyword(tok::ObjCKeywordKind Kind) const {
return FormatTok.Tok.isObjCAtKeyword(Kind);
}
FormatToken FormatTok;
TokenType Type;
unsigned SpacesRequiredBefore;
bool CanBreakBefore;
bool MustBreakBefore;
bool ClosesTemplateDeclaration;
AnnotatedToken *MatchingParen;
/// \brief Number of parameters, if this is "(", "[" or "<".
///
/// This is initialized to 1 as we don't need to distinguish functions with
/// 0 parameters from functions with 1 parameter. Thus, we can simply count
/// the number of commas.
unsigned ParameterCount;
/// \brief The total length of the line up to and including this token.
unsigned TotalLength;
// FIXME: Come up with a 'cleaner' concept.
/// \brief The binding strength of a token. This is a combined value of
/// operator precedence, parenthesis nesting, etc.
unsigned BindingStrength;
/// \brief Penalty for inserting a line break before this token.
unsigned SplitPenalty;
/// \brief If this is the first ObjC selector name in an ObjC method
/// definition or call, this contains the length of the longest name.
unsigned LongestObjCSelectorName;
std::vector<AnnotatedToken> Children;
AnnotatedToken *Parent;
/// \brief Insert this many fake ( before this token for correct indentation.
unsigned FakeLParens;
/// \brief Insert this many fake ) after this token for correct indentation.
unsigned FakeRParens;
const AnnotatedToken *getPreviousNoneComment() const {
AnnotatedToken *Tok = Parent;
while (Tok != NULL && Tok->is(tok::comment))
Tok = Tok->Parent;
return Tok;
}
};
class AnnotatedLine {
public:
AnnotatedLine(const UnwrappedLine &Line)
: First(Line.Tokens.front()), Level(Line.Level),
InPPDirective(Line.InPPDirective),
MustBeDeclaration(Line.MustBeDeclaration) {
assert(!Line.Tokens.empty());
AnnotatedToken *Current = &First;
for (std::list<FormatToken>::const_iterator I = ++Line.Tokens.begin(),
E = Line.Tokens.end();
I != E; ++I) {
Current->Children.push_back(AnnotatedToken(*I));
Current->Children[0].Parent = Current;
Current = &Current->Children[0];
}
Last = Current;
}
AnnotatedLine(const AnnotatedLine &Other)
: First(Other.First), Type(Other.Type), Level(Other.Level),
InPPDirective(Other.InPPDirective),
MustBeDeclaration(Other.MustBeDeclaration) {
Last = &First;
while (!Last->Children.empty()) {
Last->Children[0].Parent = Last;
Last = &Last->Children[0];
}
}
AnnotatedToken First;
AnnotatedToken *Last;
LineType Type;
unsigned Level;
bool InPPDirective;
bool MustBeDeclaration;
};
inline prec::Level getPrecedence(const AnnotatedToken &Tok) {
return getBinOpPrecedence(Tok.FormatTok.Tok.getKind(), true, true);
}
/// \brief Determines extra information about the tokens comprising an
/// \c UnwrappedLine.
class TokenAnnotator {
public:
TokenAnnotator(const FormatStyle &Style, SourceManager &SourceMgr, Lexer &Lex,
IdentifierInfo &Ident_in)
: Style(Style), SourceMgr(SourceMgr), Lex(Lex), Ident_in(Ident_in) {
}
void annotate(AnnotatedLine &Line);
void calculateFormattingInformation(AnnotatedLine &Line);
private:
/// \brief Calculate the penalty for splitting before \c Tok.
unsigned splitPenalty(const AnnotatedLine &Line, const AnnotatedToken &Tok);
bool spaceRequiredBetween(const AnnotatedLine &Line,
const AnnotatedToken &Left,
const AnnotatedToken &Right);
bool spaceRequiredBefore(const AnnotatedLine &Line,
const AnnotatedToken &Tok);
bool canBreakBefore(const AnnotatedLine &Line, const AnnotatedToken &Right);
const FormatStyle &Style;
SourceManager &SourceMgr;
Lexer &Lex;
// Contextual keywords:
IdentifierInfo &Ident_in;
};
} // end namespace format
} // end namespace clang
#endif // LLVM_CLANG_FORMAT_TOKEN_ANNOTATOR_H
|
