Training courses

Kernel and Embedded Linux

Bootlin training courses

Embedded Linux, kernel,
Yocto Project, Buildroot, real-time,
graphics, boot time, debugging...

Bootlin logo

Elixir Cross Referencer

  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
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
//===--- ContinuationIndenter.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
/// This file implements an indenter that manages the indentation of
/// continuations.
///
//===----------------------------------------------------------------------===//

#ifndef LLVM_CLANG_LIB_FORMAT_CONTINUATIONINDENTER_H
#define LLVM_CLANG_LIB_FORMAT_CONTINUATIONINDENTER_H

#include "Encoding.h"
#include "FormatToken.h"
#include "clang/Format/Format.h"
#include "llvm/Support/Regex.h"
#include <map>
#include <tuple>

namespace clang {
class SourceManager;

namespace format {

class AnnotatedLine;
class BreakableToken;
struct FormatToken;
struct LineState;
struct ParenState;
struct RawStringFormatStyleManager;
class WhitespaceManager;

struct RawStringFormatStyleManager {
  llvm::StringMap<FormatStyle> DelimiterStyle;
  llvm::StringMap<FormatStyle> EnclosingFunctionStyle;

  RawStringFormatStyleManager(const FormatStyle &CodeStyle);

  llvm::Optional<FormatStyle> getDelimiterStyle(StringRef Delimiter) const;

  llvm::Optional<FormatStyle>
  getEnclosingFunctionStyle(StringRef EnclosingFunction) const;
};

class ContinuationIndenter {
public:
  /// Constructs a \c ContinuationIndenter to format \p Line starting in
  /// column \p FirstIndent.
  ContinuationIndenter(const FormatStyle &Style,
                       const AdditionalKeywords &Keywords,
                       const SourceManager &SourceMgr,
                       WhitespaceManager &Whitespaces,
                       encoding::Encoding Encoding,
                       bool BinPackInconclusiveFunctions);

  /// Get the initial state, i.e. the state after placing \p Line's
  /// first token at \p FirstIndent. When reformatting a fragment of code, as in
  /// the case of formatting inside raw string literals, \p FirstStartColumn is
  /// the column at which the state of the parent formatter is.
  LineState getInitialState(unsigned FirstIndent, unsigned FirstStartColumn,
                            const AnnotatedLine *Line, bool DryRun);

  // FIXME: canBreak and mustBreak aren't strictly indentation-related. Find a
  // better home.
  /// Returns \c true, if a line break after \p State is allowed.
  bool canBreak(const LineState &State);

  /// Returns \c true, if a line break after \p State is mandatory.
  bool mustBreak(const LineState &State);

  /// Appends the next token to \p State and updates information
  /// necessary for indentation.
  ///
  /// Puts the token on the current line if \p Newline is \c false and adds a
  /// line break and necessary indentation otherwise.
  ///
  /// If \p DryRun is \c false, also creates and stores the required
  /// \c Replacement.
  unsigned addTokenToState(LineState &State, bool Newline, bool DryRun,
                           unsigned ExtraSpaces = 0);

  /// Get the column limit for this line. This is the style's column
  /// limit, potentially reduced for preprocessor definitions.
  unsigned getColumnLimit(const LineState &State) const;

private:
  /// Mark the next token as consumed in \p State and modify its stacks
  /// accordingly.
  unsigned moveStateToNextToken(LineState &State, bool DryRun, bool Newline);

  /// Update 'State' according to the next token's fake left parentheses.
  void moveStatePastFakeLParens(LineState &State, bool Newline);
  /// Update 'State' according to the next token's fake r_parens.
  void moveStatePastFakeRParens(LineState &State);

  /// Update 'State' according to the next token being one of "(<{[".
  void moveStatePastScopeOpener(LineState &State, bool Newline);
  /// Update 'State' according to the next token being one of ")>}]".
  void moveStatePastScopeCloser(LineState &State);
  /// Update 'State' with the next token opening a nested block.
  void moveStateToNewBlock(LineState &State);

  /// Reformats a raw string literal.
  /// 
  /// \returns An extra penalty induced by reformatting the token.
  unsigned reformatRawStringLiteral(const FormatToken &Current,
                                    LineState &State,
                                    const FormatStyle &RawStringStyle,
                                    bool DryRun);

  /// If the current token is at the end of the current line, handle
  /// the transition to the next line.
  unsigned handleEndOfLine(const FormatToken &Current, LineState &State,
                           bool DryRun, bool AllowBreak);

  /// If \p Current is a raw string that is configured to be reformatted,
  /// return the style to be used.
  llvm::Optional<FormatStyle> getRawStringStyle(const FormatToken &Current,
                                                const LineState &State);

  /// If the current token sticks out over the end of the line, break
  /// it if possible.
  ///
  /// \returns A pair (penalty, exceeded), where penalty is the extra penalty
  /// when tokens are broken or lines exceed the column limit, and exceeded
  /// indicates whether the algorithm purposefully left lines exceeding the
  /// column limit.
  ///
  /// The returned penalty will cover the cost of the additional line breaks
  /// and column limit violation in all lines except for the last one. The
  /// penalty for the column limit violation in the last line (and in single
  /// line tokens) is handled in \c addNextStateToQueue.
  ///
  /// \p Strict indicates whether reflowing is allowed to leave characters
  /// protruding the column limit; if true, lines will be split strictly within
  /// the column limit where possible; if false, words are allowed to protrude
  /// over the column limit as long as the penalty is less than the penalty
  /// of a break.
  std::pair<unsigned, bool> breakProtrudingToken(const FormatToken &Current,
                                                 LineState &State,
                                                 bool AllowBreak, bool DryRun,
                                                 bool Strict);

  /// Returns the \c BreakableToken starting at \p Current, or nullptr
  /// if the current token cannot be broken.
  std::unique_ptr<BreakableToken>
  createBreakableToken(const FormatToken &Current, LineState &State,
                       bool AllowBreak);

  /// Appends the next token to \p State and updates information
  /// necessary for indentation.
  ///
  /// Puts the token on the current line.
  ///
  /// If \p DryRun is \c false, also creates and stores the required
  /// \c Replacement.
  void addTokenOnCurrentLine(LineState &State, bool DryRun,
                             unsigned ExtraSpaces);

  /// Appends the next token to \p State and updates information
  /// necessary for indentation.
  ///
  /// Adds a line break and necessary indentation.
  ///
  /// If \p DryRun is \c false, also creates and stores the required
  /// \c Replacement.
  unsigned addTokenOnNewLine(LineState &State, bool DryRun);

  /// Calculate the new column for a line wrap before the next token.
  unsigned getNewLineColumn(const LineState &State);

  /// Adds a multiline token to the \p State.
  ///
  /// \returns Extra penalty for the first line of the literal: last line is
  /// handled in \c addNextStateToQueue, and the penalty for other lines doesn't
  /// matter, as we don't change them.
  unsigned addMultilineToken(const FormatToken &Current, LineState &State);

  /// Returns \c true if the next token starts a multiline string
  /// literal.
  ///
  /// This includes implicitly concatenated strings, strings that will be broken
  /// by clang-format and string literals with escaped newlines.
  bool nextIsMultilineString(const LineState &State);

  FormatStyle Style;
  const AdditionalKeywords &Keywords;
  const SourceManager &SourceMgr;
  WhitespaceManager &Whitespaces;
  encoding::Encoding Encoding;
  bool BinPackInconclusiveFunctions;
  llvm::Regex CommentPragmasRegex;
  const RawStringFormatStyleManager RawStringFormats;
};

struct ParenState {
  ParenState(const FormatToken *Tok, unsigned Indent, unsigned LastSpace,
             bool AvoidBinPacking, bool NoLineBreak)
      : Tok(Tok), Indent(Indent), LastSpace(LastSpace),
        NestedBlockIndent(Indent), BreakBeforeClosingBrace(false),
        AvoidBinPacking(AvoidBinPacking), BreakBeforeParameter(false),
        NoLineBreak(NoLineBreak), NoLineBreakInOperand(false),
        LastOperatorWrapped(true), ContainsLineBreak(false),
        ContainsUnwrappedBuilder(false), AlignColons(true),
        ObjCSelectorNameFound(false), HasMultipleNestedBlocks(false),
        NestedBlockInlined(false), IsInsideObjCArrayLiteral(false) {}

  /// \brief The token opening this parenthesis level, or nullptr if this level
  /// is opened by fake parenthesis.
  ///
  /// Not considered for memoization as it will always have the same value at
  /// the same token.
  const FormatToken *Tok;

  /// The position to which a specific parenthesis level needs to be
  /// indented.
  unsigned Indent;

  /// The position of the last space on each level.
  ///
  /// Used e.g. to break like:
  /// functionCall(Parameter, otherCall(
  ///                             OtherParameter));
  unsigned LastSpace;

  /// If a block relative to this parenthesis level gets wrapped, indent
  /// it this much.
  unsigned NestedBlockIndent;

  /// The position the first "<<" operator encountered on each level.
  ///
  /// Used to align "<<" operators. 0 if no such operator has been encountered
  /// on a level.
  unsigned FirstLessLess = 0;

  /// The column of a \c ? in a conditional expression;
  unsigned QuestionColumn = 0;

  /// The position of the colon in an ObjC method declaration/call.
  unsigned ColonPos = 0;

  /// The start of the most recent function in a builder-type call.
  unsigned StartOfFunctionCall = 0;

  /// Contains the start of array subscript expressions, so that they
  /// can be aligned.
  unsigned StartOfArraySubscripts = 0;

  /// If a nested name specifier was broken over multiple lines, this
  /// contains the start column of the second line. Otherwise 0.
  unsigned NestedNameSpecifierContinuation = 0;

  /// If a call expression was broken over multiple lines, this
  /// contains the start column of the second line. Otherwise 0.
  unsigned CallContinuation = 0;

  /// The column of the first variable name in a variable declaration.
  ///
  /// Used to align further variables if necessary.
  unsigned VariablePos = 0;

  /// Whether a newline needs to be inserted before the block's closing
  /// brace.
  ///
  /// We only want to insert a newline before the closing brace if there also
  /// was a newline after the beginning left brace.
  bool BreakBeforeClosingBrace : 1;

  /// Avoid bin packing, i.e. multiple parameters/elements on multiple
  /// lines, in this context.
  bool AvoidBinPacking : 1;

  /// Break after the next comma (or all the commas in this context if
  /// \c AvoidBinPacking is \c true).
  bool BreakBeforeParameter : 1;

  /// Line breaking in this context would break a formatting rule.
  bool NoLineBreak : 1;

  /// Same as \c NoLineBreak, but is restricted until the end of the
  /// operand (including the next ",").
  bool NoLineBreakInOperand : 1;

  /// True if the last binary operator on this level was wrapped to the
  /// next line.
  bool LastOperatorWrapped : 1;

  /// \c true if this \c ParenState already contains a line-break.
  ///
  /// The first line break in a certain \c ParenState causes extra penalty so
  /// that clang-format prefers similar breaks, i.e. breaks in the same
  /// parenthesis.
  bool ContainsLineBreak : 1;

  /// \c true if this \c ParenState contains multiple segments of a
  /// builder-type call on one line.
  bool ContainsUnwrappedBuilder : 1;

  /// \c true if the colons of the curren ObjC method expression should
  /// be aligned.
  ///
  /// Not considered for memoization as it will always have the same value at
  /// the same token.
  bool AlignColons : 1;

  /// \c true if at least one selector name was found in the current
  /// ObjC method expression.
  ///
  /// Not considered for memoization as it will always have the same value at
  /// the same token.
  bool ObjCSelectorNameFound : 1;

  /// \c true if there are multiple nested blocks inside these parens.
  ///
  /// Not considered for memoization as it will always have the same value at
  /// the same token.
  bool HasMultipleNestedBlocks : 1;

  /// The start of a nested block (e.g. lambda introducer in C++ or
  /// "function" in JavaScript) is not wrapped to a new line.
  bool NestedBlockInlined : 1;

  /// \c true if the current \c ParenState represents an Objective-C
  /// array literal.
  bool IsInsideObjCArrayLiteral : 1;

  bool operator<(const ParenState &Other) const {
    if (Indent != Other.Indent)
      return Indent < Other.Indent;
    if (LastSpace != Other.LastSpace)
      return LastSpace < Other.LastSpace;
    if (NestedBlockIndent != Other.NestedBlockIndent)
      return NestedBlockIndent < Other.NestedBlockIndent;
    if (FirstLessLess != Other.FirstLessLess)
      return FirstLessLess < Other.FirstLessLess;
    if (BreakBeforeClosingBrace != Other.BreakBeforeClosingBrace)
      return BreakBeforeClosingBrace;
    if (QuestionColumn != Other.QuestionColumn)
      return QuestionColumn < Other.QuestionColumn;
    if (AvoidBinPacking != Other.AvoidBinPacking)
      return AvoidBinPacking;
    if (BreakBeforeParameter != Other.BreakBeforeParameter)
      return BreakBeforeParameter;
    if (NoLineBreak != Other.NoLineBreak)
      return NoLineBreak;
    if (LastOperatorWrapped != Other.LastOperatorWrapped)
      return LastOperatorWrapped;
    if (ColonPos != Other.ColonPos)
      return ColonPos < Other.ColonPos;
    if (StartOfFunctionCall != Other.StartOfFunctionCall)
      return StartOfFunctionCall < Other.StartOfFunctionCall;
    if (StartOfArraySubscripts != Other.StartOfArraySubscripts)
      return StartOfArraySubscripts < Other.StartOfArraySubscripts;
    if (CallContinuation != Other.CallContinuation)
      return CallContinuation < Other.CallContinuation;
    if (VariablePos != Other.VariablePos)
      return VariablePos < Other.VariablePos;
    if (ContainsLineBreak != Other.ContainsLineBreak)
      return ContainsLineBreak;
    if (ContainsUnwrappedBuilder != Other.ContainsUnwrappedBuilder)
      return ContainsUnwrappedBuilder;
    if (NestedBlockInlined != Other.NestedBlockInlined)
      return NestedBlockInlined;
    return false;
  }
};

/// The current state when indenting a unwrapped line.
///
/// As the indenting tries different combinations this is copied by value.
struct LineState {
  /// The number of used columns in the current line.
  unsigned Column;

  /// The token that needs to be next formatted.
  FormatToken *NextToken;

  /// \c true if this line contains a continued for-loop section.
  bool LineContainsContinuedForLoopSection;

  /// \c true if \p NextToken should not continue this line.
  bool NoContinuation;

  /// The \c NestingLevel at the start of this line.
  unsigned StartOfLineLevel;

  /// The lowest \c NestingLevel on the current line.
  unsigned LowestLevelOnLine;

  /// The start column of the string literal, if we're in a string
  /// literal sequence, 0 otherwise.
  unsigned StartOfStringLiteral;

  /// A stack keeping track of properties applying to parenthesis
  /// levels.
  std::vector<ParenState> Stack;

  /// Ignore the stack of \c ParenStates for state comparison.
  ///
  /// In long and deeply nested unwrapped lines, the current algorithm can
  /// be insufficient for finding the best formatting with a reasonable amount
  /// of time and memory. Setting this flag will effectively lead to the
  /// algorithm not analyzing some combinations. However, these combinations
  /// rarely contain the optimal solution: In short, accepting a higher
  /// penalty early would need to lead to different values in the \c
  /// ParenState stack (in an otherwise identical state) and these different
  /// values would need to lead to a significant amount of avoided penalty
  /// later.
  ///
  /// FIXME: Come up with a better algorithm instead.
  bool IgnoreStackForComparison;

  /// The indent of the first token.
  unsigned FirstIndent;

  /// The line that is being formatted.
  ///
  /// Does not need to be considered for memoization because it doesn't change.
  const AnnotatedLine *Line;

  /// Comparison operator to be able to used \c LineState in \c map.
  bool operator<(const LineState &Other) const {
    if (NextToken != Other.NextToken)
      return NextToken < Other.NextToken;
    if (Column != Other.Column)
      return Column < Other.Column;
    if (LineContainsContinuedForLoopSection !=
        Other.LineContainsContinuedForLoopSection)
      return LineContainsContinuedForLoopSection;
    if (NoContinuation != Other.NoContinuation)
      return NoContinuation;
    if (StartOfLineLevel != Other.StartOfLineLevel)
      return StartOfLineLevel < Other.StartOfLineLevel;
    if (LowestLevelOnLine != Other.LowestLevelOnLine)
      return LowestLevelOnLine < Other.LowestLevelOnLine;
    if (StartOfStringLiteral != Other.StartOfStringLiteral)
      return StartOfStringLiteral < Other.StartOfStringLiteral;
    if (IgnoreStackForComparison || Other.IgnoreStackForComparison)
      return false;
    return Stack < Other.Stack;
  }
};

} // end namespace format
} // end namespace clang

#endif