aboutsummaryrefslogtreecommitdiffstats
path: root/contrib/libs/clang16/lib/Format/UnwrappedLineParser.h
blob: f043e567eb73319328a5cc5fd668b78f1936666e (plain) (blame)
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
//===--- UnwrappedLineParser.h - Format C++ code ----------------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
///
/// \file
/// This file contains the declaration of the UnwrappedLineParser,
/// which turns a stream of tokens into UnwrappedLines.
///
//===----------------------------------------------------------------------===//

#ifndef LLVM_CLANG_LIB_FORMAT_UNWRAPPEDLINEPARSER_H
#define LLVM_CLANG_LIB_FORMAT_UNWRAPPEDLINEPARSER_H

#include "FormatToken.h"
#include "clang/Basic/IdentifierTable.h"
#include "clang/Format/Format.h"
#include "llvm/ADT/BitVector.h"
#include "llvm/Support/Regex.h"
#include <list>
#include <stack>
#include <vector>

namespace clang {
namespace format {

struct UnwrappedLineNode;

/// 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();

  /// The \c Tokens comprising this \c UnwrappedLine.
  std::list<UnwrappedLineNode> Tokens;

  /// The indent level of the \c UnwrappedLine.
  unsigned Level;

  /// The \c PPBranchLevel (adjusted for header guards) if this line is a
  /// \c InMacroBody line, and 0 otherwise.
  unsigned PPLevel;

  /// Whether this \c UnwrappedLine is part of a preprocessor directive.
  bool InPPDirective;
  /// Whether this \c UnwrappedLine is part of a pramga directive.
  bool InPragmaDirective;
  /// Whether it is part of a macro body.
  bool InMacroBody;

  bool MustBeDeclaration;

  /// \c True if this line should be indented by ContinuationIndent in
  /// addition to the normal indention level.
  bool IsContinuation = false;

  /// If this \c UnwrappedLine closes a block in a sequence of lines,
  /// \c MatchingOpeningBlockLineIndex stores the index of the corresponding
  /// opening line. Otherwise, \c MatchingOpeningBlockLineIndex must be
  /// \c kInvalidIndex.
  size_t MatchingOpeningBlockLineIndex = kInvalidIndex;

  /// If this \c UnwrappedLine opens a block, stores the index of the
  /// line with the corresponding closing brace.
  size_t MatchingClosingBlockLineIndex = kInvalidIndex;

  static const size_t kInvalidIndex = -1;

  unsigned FirstStartColumn = 0;
};

class UnwrappedLineConsumer {
public:
  virtual ~UnwrappedLineConsumer() {}
  virtual void consumeUnwrappedLine(const UnwrappedLine &Line) = 0;
  virtual void finishRun() = 0;
};

class FormatTokenSource;

class UnwrappedLineParser {
public:
  UnwrappedLineParser(const FormatStyle &Style,
                      const AdditionalKeywords &Keywords,
                      unsigned FirstStartColumn, ArrayRef<FormatToken *> Tokens,
                      UnwrappedLineConsumer &Callback);

  void parse();

private:
  enum class IfStmtKind {
    NotIf,   // Not an if statement.
    IfOnly,  // An if statement without the else clause.
    IfElse,  // An if statement followed by else but not else if.
    IfElseIf // An if statement followed by else if.
  };

  void reset();
  void parseFile();
  bool precededByCommentOrPPDirective() const;
  bool parseLevel(const FormatToken *OpeningBrace = nullptr,
                  bool CanContainBracedList = true,
                  TokenType NextLBracesType = TT_Unknown,
                  IfStmtKind *IfKind = nullptr,
                  FormatToken **IfLeftBrace = nullptr);
  bool mightFitOnOneLine(UnwrappedLine &Line,
                         const FormatToken *OpeningBrace = nullptr) const;
  FormatToken *parseBlock(bool MustBeDeclaration = false,
                          unsigned AddLevels = 1u, bool MunchSemi = true,
                          bool KeepBraces = true, IfStmtKind *IfKind = nullptr,
                          bool UnindentWhitesmithsBraces = false,
                          bool CanContainBracedList = true,
                          TokenType NextLBracesType = TT_Unknown);
  void parseChildBlock(bool CanContainBracedList = true,
                       TokenType NextLBracesType = TT_Unknown);
  void parsePPDirective();
  void parsePPDefine();
  void parsePPIf(bool IfDef);
  void parsePPElse();
  void parsePPEndIf();
  void parsePPPragma();
  void parsePPUnknown();
  void readTokenWithJavaScriptASI();
  void parseStructuralElement(bool IsTopLevel = false,
                              TokenType NextLBracesType = TT_Unknown,
                              IfStmtKind *IfKind = nullptr,
                              FormatToken **IfLeftBrace = nullptr,
                              bool *HasDoWhile = nullptr,
                              bool *HasLabel = nullptr);
  bool tryToParseBracedList();
  bool parseBracedList(bool ContinueOnSemicolons = false, bool IsEnum = false,
                       tok::TokenKind ClosingBraceKind = tok::r_brace);
  void parseParens(TokenType AmpAmpTokenType = TT_Unknown);
  void parseSquare(bool LambdaIntroducer = false);
  void keepAncestorBraces();
  void parseUnbracedBody(bool CheckEOF = false);
  void handleAttributes();
  bool handleCppAttributes();
  bool isBlockBegin(const FormatToken &Tok) const;
  FormatToken *parseIfThenElse(IfStmtKind *IfKind, bool KeepBraces = false);
  void parseTryCatch();
  void parseLoopBody(bool KeepBraces, bool WrapRightBrace);
  void parseForOrWhileLoop();
  void parseDoWhile();
  void parseLabel(bool LeftAlignLabel = false);
  void parseCaseLabel();
  void parseSwitch();
  void parseNamespace();
  bool parseModuleImport();
  void parseNew();
  void parseAccessSpecifier();
  bool parseEnum();
  bool parseStructLike();
  bool parseRequires();
  void parseRequiresClause(FormatToken *RequiresToken);
  void parseRequiresExpression(FormatToken *RequiresToken);
  void parseConstraintExpression();
  void parseJavaEnumBody();
  // Parses a record (aka class) as a top level element. If ParseAsExpr is true,
  // parses the record as a child block, i.e. if the class declaration is an
  // expression.
  void parseRecord(bool ParseAsExpr = false);
  void parseObjCLightweightGenerics();
  void parseObjCMethod();
  void parseObjCProtocolList();
  void parseObjCUntilAtEnd();
  void parseObjCInterfaceOrImplementation();
  bool parseObjCProtocol();
  void parseJavaScriptEs6ImportExport();
  void parseStatementMacro();
  void parseCSharpAttribute();
  // Parse a C# generic type constraint: `where T : IComparable<T>`.
  // See:
  // https://docs.microsoft.com/en-us/dotnet/csharp/language-reference/keywords/where-generic-type-constraint
  void parseCSharpGenericTypeConstraint();
  bool tryToParseLambda();
  bool tryToParseChildBlock();
  bool tryToParseLambdaIntroducer();
  bool tryToParsePropertyAccessor();
  void tryToParseJSFunction();
  bool tryToParseSimpleAttribute();
  void parseVerilogHierarchyIdentifier();
  void parseVerilogSensitivityList();
  // Returns the number of levels of indentation in addition to the normal 1
  // level for a block, used for indenting case labels.
  unsigned parseVerilogHierarchyHeader();
  void parseVerilogTable();
  void parseVerilogCaseLabel();

  // Used by addUnwrappedLine to denote whether to keep or remove a level
  // when resetting the line state.
  enum class LineLevel { Remove, Keep };

  void addUnwrappedLine(LineLevel AdjustLevel = LineLevel::Remove);
  bool eof() const;
  // LevelDifference is the difference of levels after and before the current
  // token. For example:
  // - if the token is '{' and opens a block, LevelDifference is 1.
  // - if the token is '}' and closes a block, LevelDifference is -1.
  void nextToken(int LevelDifference = 0);
  void readToken(int LevelDifference = 0);

  // Decides which comment tokens should be added to the current line and which
  // should be added as comments before the next token.
  //
  // Comments specifies the sequence of comment tokens to analyze. They get
  // either pushed to the current line or added to the comments before the next
  // token.
  //
  // NextTok specifies the next token. A null pointer NextTok is supported, and
  // signifies either the absence of a next token, or that the next token
  // shouldn't be taken into account for the analysis.
  void distributeComments(const SmallVectorImpl<FormatToken *> &Comments,
                          const FormatToken *NextTok);

  // Adds the comment preceding the next token to unwrapped lines.
  void flushComments(bool NewlineBeforeNext);
  void pushToken(FormatToken *Tok);
  void calculateBraceTypes(bool ExpectClassBody = false);

  // Marks a conditional compilation edge (for example, an '#if', '#ifdef',
  // '#else' or merge conflict marker). If 'Unreachable' is true, assumes
  // this branch either cannot be taken (for example '#if false'), or should
  // not be taken in this round.
  void conditionalCompilationCondition(bool Unreachable);
  void conditionalCompilationStart(bool Unreachable);
  void conditionalCompilationAlternative();
  void conditionalCompilationEnd();

  bool isOnNewLine(const FormatToken &FormatTok);

  // Compute hash of the current preprocessor branch.
  // This is used to identify the different branches, and thus track if block
  // open and close in the same branch.
  size_t computePPHash() const;

  // 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.
  std::unique_ptr<UnwrappedLine> Line;

  // Comments are sorted into unwrapped lines by whether they are in the same
  // line as the previous token, or not. If not, they belong to the next token.
  // Since the next token might already be in a new unwrapped line, we need to
  // store the comments belonging to that token.
  SmallVector<FormatToken *, 1> CommentsBeforeNextToken;
  FormatToken *FormatTok;
  bool MustBreakBeforeNextToken;

  // The parsed lines. Only added to through \c CurrentLines.
  SmallVector<UnwrappedLine, 8> Lines;

  // Preprocessor directives are parsed out-of-order from other unwrapped lines.
  // Thus, we need to keep a list of preprocessor directives to be reported
  // after an unwrapped line that has been started was finished.
  SmallVector<UnwrappedLine, 4> PreprocessorDirectives;

  // New unwrapped lines are added via CurrentLines.
  // Usually points to \c &Lines. While parsing a preprocessor directive when
  // there is an unfinished previous unwrapped line, will point to
  // \c &PreprocessorDirectives.
  SmallVectorImpl<UnwrappedLine> *CurrentLines;

  // We store for each line whether it must be a declaration depending on
  // whether we are in a compound statement or not.
  llvm::BitVector DeclarationScopeStack;

  const FormatStyle &Style;
  const AdditionalKeywords &Keywords;

  llvm::Regex CommentPragmasRegex;

  FormatTokenSource *Tokens;
  UnwrappedLineConsumer &Callback;

  // FIXME: This is a temporary measure until we have reworked the ownership
  // of the format tokens. The goal is to have the actual tokens created and
  // owned outside of and handed into the UnwrappedLineParser.
  ArrayRef<FormatToken *> AllTokens;

  // Keeps a stack of the states of nested control statements (true if the
  // statement contains more than some predefined number of nested statements).
  SmallVector<bool, 8> NestedTooDeep;

  // Represents preprocessor branch type, so we can find matching
  // #if/#else/#endif directives.
  enum PPBranchKind {
    PP_Conditional, // Any #if, #ifdef, #ifndef, #elif, block outside #if 0
    PP_Unreachable  // #if 0 or a conditional preprocessor block inside #if 0
  };

  struct PPBranch {
    PPBranch(PPBranchKind Kind, size_t Line) : Kind(Kind), Line(Line) {}
    PPBranchKind Kind;
    size_t Line;
  };

  // Keeps a stack of currently active preprocessor branching directives.
  SmallVector<PPBranch, 16> PPStack;

  // The \c UnwrappedLineParser re-parses the code for each combination
  // of preprocessor branches that can be taken.
  // To that end, we take the same branch (#if, #else, or one of the #elif
  // branches) for each nesting level of preprocessor branches.
  // \c PPBranchLevel stores the current nesting level of preprocessor
  // branches during one pass over the code.
  int PPBranchLevel;

  // Contains the current branch (#if, #else or one of the #elif branches)
  // for each nesting level.
  SmallVector<int, 8> PPLevelBranchIndex;

  // Contains the maximum number of branches at each nesting level.
  SmallVector<int, 8> PPLevelBranchCount;

  // Contains the number of branches per nesting level we are currently
  // in while parsing a preprocessor branch sequence.
  // This is used to update PPLevelBranchCount at the end of a branch
  // sequence.
  std::stack<int> PPChainBranchIndex;

  // Include guard search state. Used to fixup preprocessor indent levels
  // so that include guards do not participate in indentation.
  enum IncludeGuardState {
    IG_Inited,   // Search started, looking for #ifndef.
    IG_IfNdefed, // #ifndef found, IncludeGuardToken points to condition.
    IG_Defined,  // Matching #define found, checking other requirements.
    IG_Found,    // All requirements met, need to fix indents.
    IG_Rejected, // Search failed or never started.
  };

  // Current state of include guard search.
  IncludeGuardState IncludeGuard;

  // Points to the #ifndef condition for a potential include guard. Null unless
  // IncludeGuardState == IG_IfNdefed.
  FormatToken *IncludeGuardToken;

  // Contains the first start column where the source begins. This is zero for
  // normal source code and may be nonzero when formatting a code fragment that
  // does not start at the beginning of the file.
  unsigned FirstStartColumn;

  friend class ScopedLineState;
  friend class CompoundStatementIndenter;
};

struct UnwrappedLineNode {
  UnwrappedLineNode() : Tok(nullptr) {}
  UnwrappedLineNode(FormatToken *Tok) : Tok(Tok) {}

  FormatToken *Tok;
  SmallVector<UnwrappedLine, 0> Children;
};

inline UnwrappedLine::UnwrappedLine()
    : Level(0), PPLevel(0), InPPDirective(false), InPragmaDirective(false),
      InMacroBody(false), MustBeDeclaration(false),
      MatchingOpeningBlockLineIndex(kInvalidIndex) {}

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

#endif