Coverage Report

Created: 2020-02-25 14:32

/Users/buildslave/jenkins/workspace/coverage/llvm-project/clang/lib/Format/FormatTokenLexer.h
Line
Count
Source
1
//===--- FormatTokenLexer.h - Format C++ code ----------------*- C++ ----*-===//
2
//
3
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
4
// See https://llvm.org/LICENSE.txt for license information.
5
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
6
//
7
//===----------------------------------------------------------------------===//
8
///
9
/// \file
10
/// This file contains FormatTokenLexer, which tokenizes a source file
11
/// into a token stream suitable for ClangFormat.
12
///
13
//===----------------------------------------------------------------------===//
14
15
#ifndef LLVM_CLANG_LIB_FORMAT_FORMATTOKENLEXER_H
16
#define LLVM_CLANG_LIB_FORMAT_FORMATTOKENLEXER_H
17
18
#include "Encoding.h"
19
#include "FormatToken.h"
20
#include "clang/Basic/SourceLocation.h"
21
#include "clang/Basic/SourceManager.h"
22
#include "clang/Format/Format.h"
23
#include "llvm/ADT/MapVector.h"
24
#include "llvm/ADT/StringSet.h"
25
#include "llvm/Support/Regex.h"
26
27
#include <stack>
28
29
namespace clang {
30
namespace format {
31
32
enum LexerState {
33
  NORMAL,
34
  TEMPLATE_STRING,
35
  TOKEN_STASHED,
36
};
37
38
class FormatTokenLexer {
39
public:
40
  FormatTokenLexer(const SourceManager &SourceMgr, FileID ID, unsigned Column,
41
                   const FormatStyle &Style, encoding::Encoding Encoding);
42
43
  ArrayRef<FormatToken *> lex();
44
45
95.7k
  const AdditionalKeywords &getKeywords() { return Keywords; }
46
47
private:
48
  void tryMergePreviousTokens();
49
50
  bool tryMergeLessLess();
51
  bool tryMergeNSStringLiteral();
52
  bool tryMergeJSPrivateIdentifier();
53
  bool tryMergeCSharpStringLiteral();
54
  bool tryMergeCSharpKeywordVariables();
55
  bool tryMergeCSharpNullConditionals();
56
  bool tryMergeCSharpDoubleQuestion();
57
  bool tryTransformCSharpForEach();
58
  bool tryMergeCSharpAttributeAndTarget();
59
  bool tryMergeCSharpNamedArgument();
60
61
  bool tryMergeTokens(ArrayRef<tok::TokenKind> Kinds, TokenType NewType);
62
63
  // Returns \c true if \p Tok can only be followed by an operand in JavaScript.
64
  bool precedesOperand(FormatToken *Tok);
65
66
  bool canPrecedeRegexLiteral(FormatToken *Prev);
67
68
  // Tries to parse a JavaScript Regex literal starting at the current token,
69
  // if that begins with a slash and is in a location where JavaScript allows
70
  // regex literals. Changes the current token to a regex literal and updates
71
  // its text if successful.
72
  void tryParseJSRegexLiteral();
73
74
  // Handles JavaScript template strings.
75
  //
76
  // JavaScript template strings use backticks ('`') as delimiters, and allow
77
  // embedding expressions nested in ${expr-here}. Template strings can be
78
  // nested recursively, i.e. expressions can contain template strings in turn.
79
  //
80
  // The code below parses starting from a backtick, up to a closing backtick or
81
  // an opening ${. It also maintains a stack of lexing contexts to handle
82
  // nested template parts by balancing curly braces.
83
  void handleTemplateStrings();
84
85
  void handleCSharpVerbatimAndInterpolatedStrings();
86
87
  void tryParsePythonComment();
88
89
  bool tryMerge_TMacro();
90
91
  bool tryMergeConflictMarkers();
92
93
  FormatToken *getStashedToken();
94
95
  FormatToken *getNextToken();
96
97
  FormatToken *FormatTok;
98
  bool IsFirstToken;
99
  std::stack<LexerState> StateStack;
100
  unsigned Column;
101
  unsigned TrailingWhitespace;
102
  std::unique_ptr<Lexer> Lex;
103
  const SourceManager &SourceMgr;
104
  FileID ID;
105
  const FormatStyle &Style;
106
  IdentifierTable IdentTable;
107
  AdditionalKeywords Keywords;
108
  encoding::Encoding Encoding;
109
  llvm::SpecificBumpPtrAllocator<FormatToken> Allocator;
110
  // Index (in 'Tokens') of the last token that starts a new line.
111
  unsigned FirstInLineIndex;
112
  SmallVector<FormatToken *, 16> Tokens;
113
114
  llvm::SmallMapVector<IdentifierInfo *, TokenType, 8> Macros;
115
116
  bool FormattingDisabled;
117
118
  llvm::Regex MacroBlockBeginRegex;
119
  llvm::Regex MacroBlockEndRegex;
120
121
  // Targets that may appear inside a C# attribute.
122
  static const llvm::StringSet<> CSharpAttributeTargets;
123
124
  void readRawToken(FormatToken &Tok);
125
126
  void resetLexer(unsigned Offset);
127
};
128
129
} // namespace format
130
} // namespace clang
131
132
#endif