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
|
//===--- BreakableToken.h - Format C++ code -------------------------------===//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
///
/// \file
/// \brief Declares BreakableToken, BreakableStringLiteral, and
/// BreakableBlockComment classes, that contain token type-specific logic to
/// break long lines in tokens.
///
//===----------------------------------------------------------------------===//
#ifndef LLVM_CLANG_FORMAT_BREAKABLETOKEN_H
#define LLVM_CLANG_FORMAT_BREAKABLETOKEN_H
#include "TokenAnnotator.h"
#include "WhitespaceManager.h"
#include <utility>
namespace clang {
namespace format {
class BreakableToken {
public:
BreakableToken(const SourceManager &SourceMgr, const FormatToken &Tok,
unsigned StartColumn)
: Tok(Tok), StartColumn(StartColumn),
TokenText(SourceMgr.getCharacterData(Tok.getStartOfNonWhitespace()),
Tok.TokenLength) {}
virtual ~BreakableToken() {}
virtual unsigned getLineCount() const = 0;
virtual unsigned getLineSize(unsigned Index) const = 0;
virtual unsigned getLineLengthAfterSplit(unsigned LineIndex,
unsigned TailOffset) const = 0;
// Contains starting character index and length of split.
typedef std::pair<StringRef::size_type, unsigned> Split;
virtual Split getSplit(unsigned LineIndex, unsigned TailOffset,
unsigned ColumnLimit) const = 0;
virtual void insertBreak(unsigned LineIndex, unsigned TailOffset, Split Split,
bool InPPDirective,
WhitespaceManager &Whitespaces) = 0;
virtual void trimLine(unsigned LineIndex, unsigned TailOffset,
unsigned InPPDirective,
WhitespaceManager &Whitespaces) {}
protected:
const FormatToken &Tok;
unsigned StartColumn;
StringRef TokenText;
};
class BreakableStringLiteral : public BreakableToken {
public:
BreakableStringLiteral(const SourceManager &SourceMgr, const FormatToken &Tok,
unsigned StartColumn)
: BreakableToken(SourceMgr, Tok, StartColumn) {
assert(TokenText.startswith("\"") && TokenText.endswith("\""));
}
virtual unsigned getLineCount() const { return 1; }
virtual unsigned getLineSize(unsigned Index) const {
return Tok.TokenLength - 2; // Should be in sync with getLine
}
virtual unsigned getLineLengthAfterSplit(unsigned LineIndex,
unsigned TailOffset) const {
return getDecorationLength() + getLine().size() - TailOffset;
}
virtual Split getSplit(unsigned LineIndex, unsigned TailOffset,
unsigned ColumnLimit) const {
StringRef Text = getLine().substr(TailOffset);
if (ColumnLimit <= getDecorationLength())
return Split(StringRef::npos, 0);
unsigned MaxSplit = ColumnLimit - getDecorationLength();
assert(MaxSplit < Text.size());
StringRef::size_type SpaceOffset = Text.rfind(' ', MaxSplit);
if (SpaceOffset != StringRef::npos && SpaceOffset != 0)
return Split(SpaceOffset + 1, 0);
StringRef::size_type SlashOffset = Text.rfind('/', MaxSplit);
if (SlashOffset != StringRef::npos && SlashOffset != 0)
return Split(SlashOffset + 1, 0);
StringRef::size_type SplitPoint = getStartOfCharacter(Text, MaxSplit);
if (SplitPoint != StringRef::npos && SplitPoint > 1)
// Do not split at 0.
return Split(SplitPoint, 0);
return Split(StringRef::npos, 0);
}
virtual void insertBreak(unsigned LineIndex, unsigned TailOffset, Split Split,
bool InPPDirective, WhitespaceManager &Whitespaces) {
unsigned WhitespaceStartColumn = StartColumn + Split.first + 2;
Whitespaces.breakToken(Tok, 1 + TailOffset + Split.first, Split.second,
"\"", "\"", InPPDirective, StartColumn,
WhitespaceStartColumn);
}
private:
StringRef getLine() const {
// Get string without quotes.
// FIXME: Handle string prefixes.
return TokenText.substr(1, TokenText.size() - 2);
}
unsigned getDecorationLength() const { return StartColumn + 2; }
static StringRef::size_type getStartOfCharacter(StringRef Text,
StringRef::size_type Offset) {
StringRef::size_type NextEscape = Text.find('\\');
while (NextEscape != StringRef::npos && NextEscape < Offset) {
StringRef::size_type SequenceLength =
getEscapeSequenceLength(Text.substr(NextEscape));
if (Offset < NextEscape + SequenceLength)
return NextEscape;
NextEscape = Text.find('\\', NextEscape + SequenceLength);
}
return Offset;
}
static unsigned getEscapeSequenceLength(StringRef Text) {
assert(Text[0] == '\\');
if (Text.size() < 2)
return 1;
switch (Text[1]) {
case 'u':
return 6;
case 'U':
return 10;
case 'x':
return getHexLength(Text);
default:
if (Text[1] >= '0' && Text[1] <= '7')
return getOctalLength(Text);
return 2;
}
}
static unsigned getHexLength(StringRef Text) {
unsigned I = 2; // Point after '\x'.
while (I < Text.size() && ((Text[I] >= '0' && Text[I] <= '9') ||
(Text[I] >= 'a' && Text[I] <= 'f') ||
(Text[I] >= 'A' && Text[I] <= 'F'))) {
++I;
}
return I;
}
static unsigned getOctalLength(StringRef Text) {
unsigned I = 1;
while (I < Text.size() && I < 4 && (Text[I] >= '0' && Text[I] <= '7')) {
++I;
}
return I;
}
};
class BreakableComment : public BreakableToken {
public:
virtual unsigned getLineSize(unsigned Index) const {
return getLine(Index).size();
}
virtual unsigned getLineCount() const { return Lines.size(); }
virtual unsigned getLineLengthAfterSplit(unsigned LineIndex,
unsigned TailOffset) const {
return getContentStartColumn(LineIndex, TailOffset) +
getLine(LineIndex).size() - TailOffset;
}
virtual Split getSplit(unsigned LineIndex, unsigned TailOffset,
unsigned ColumnLimit) const;
virtual void insertBreak(unsigned LineIndex, unsigned TailOffset, Split Split,
bool InPPDirective, WhitespaceManager &Whitespaces);
protected:
BreakableComment(const SourceManager &SourceMgr, const FormatToken &Tok,
unsigned StartColumn)
: BreakableToken(SourceMgr, Tok, StartColumn) {}
// Get comment lines without /* */, common prefix and trailing whitespace.
// Last line is not trimmed, as it is terminated by */, so its trailing
// whitespace is not really trailing.
StringRef getLine(unsigned Index) const {
return Index < Lines.size() - 1 ? Lines[Index].rtrim() : Lines[Index];
}
unsigned getContentStartColumn(unsigned LineIndex,
unsigned TailOffset) const {
return (TailOffset == 0 && LineIndex == 0)
? StartColumn
: IndentAtLineBreak + Decoration.size();
}
unsigned IndentAtLineBreak;
StringRef Decoration;
SmallVector<StringRef, 16> Lines;
};
class BreakableBlockComment : public BreakableComment {
public:
BreakableBlockComment(const SourceManager &SourceMgr,
const AnnotatedToken &Token, unsigned StartColumn);
void alignLines(WhitespaceManager &Whitespaces);
virtual unsigned getLineLengthAfterSplit(unsigned LineIndex,
unsigned TailOffset) const {
return BreakableComment::getLineLengthAfterSplit(LineIndex, TailOffset) +
(LineIndex + 1 < Lines.size() ? 0 : 2);
}
virtual void trimLine(unsigned LineIndex, unsigned TailOffset,
unsigned InPPDirective, WhitespaceManager &Whitespaces);
private:
unsigned OriginalStartColumn;
unsigned CommonPrefixLength;
};
class BreakableLineComment : public BreakableComment {
public:
BreakableLineComment(const SourceManager &SourceMgr,
const AnnotatedToken &Token, unsigned StartColumn);
private:
static StringRef getLineCommentPrefix(StringRef Comment);
};
} // namespace format
} // namespace clang
#endif // LLVM_CLANG_FORMAT_BREAKABLETOKEN_H
|
