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
|
//===--- FormatTokenLexer.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 contains FormatTokenLexer, which tokenizes a source file
/// into a token stream suitable for ClangFormat.
///
//===----------------------------------------------------------------------===//
#ifndef LLVM_CLANG_LIB_FORMAT_FORMATTOKENLEXER_H
#define LLVM_CLANG_LIB_FORMAT_FORMATTOKENLEXER_H
#include "Encoding.h"
#include "FormatToken.h"
#include "clang/Basic/SourceLocation.h"
#include "clang/Basic/SourceManager.h"
#include "clang/Format/Format.h"
#include "llvm/Support/Regex.h"
#include <stack>
namespace clang {
namespace format {
enum LexerState {
NORMAL,
TEMPLATE_STRING,
TOKEN_STASHED,
};
class FormatTokenLexer {
public:
FormatTokenLexer(const SourceManager &SourceMgr, FileID ID, unsigned Column,
const FormatStyle &Style, encoding::Encoding Encoding);
ArrayRef<FormatToken *> lex();
const AdditionalKeywords &getKeywords() { return Keywords; }
private:
void tryMergePreviousTokens();
bool tryMergeLessLess();
bool tryMergeNSStringLiteral();
bool tryMergeTokens(ArrayRef<tok::TokenKind> Kinds, TokenType NewType);
// Returns \c true if \p Tok can only be followed by an operand in JavaScript.
bool precedesOperand(FormatToken *Tok);
bool canPrecedeRegexLiteral(FormatToken *Prev);
// Tries to parse a JavaScript Regex literal starting at the current token,
// if that begins with a slash and is in a location where JavaScript allows
// regex literals. Changes the current token to a regex literal and updates
// its text if successful.
void tryParseJSRegexLiteral();
// Handles JavaScript template strings.
//
// JavaScript template strings use backticks ('`') as delimiters, and allow
// embedding expressions nested in ${expr-here}. Template strings can be
// nested recursively, i.e. expressions can contain template strings in turn.
//
// The code below parses starting from a backtick, up to a closing backtick or
// an opening ${. It also maintains a stack of lexing contexts to handle
// nested template parts by balancing curly braces.
void handleTemplateStrings();
void tryParsePythonComment();
bool tryMerge_TMacro();
bool tryMergeConflictMarkers();
FormatToken *getStashedToken();
FormatToken *getNextToken();
FormatToken *FormatTok;
bool IsFirstToken;
std::stack<LexerState> StateStack;
unsigned Column;
unsigned TrailingWhitespace;
std::unique_ptr<Lexer> Lex;
const SourceManager &SourceMgr;
FileID ID;
const FormatStyle &Style;
IdentifierTable IdentTable;
AdditionalKeywords Keywords;
encoding::Encoding Encoding;
llvm::SpecificBumpPtrAllocator<FormatToken> Allocator;
// Index (in 'Tokens') of the last token that starts a new line.
unsigned FirstInLineIndex;
SmallVector<FormatToken *, 16> Tokens;
SmallVector<IdentifierInfo *, 8> ForEachMacros;
bool FormattingDisabled;
llvm::Regex MacroBlockBeginRegex;
llvm::Regex MacroBlockEndRegex;
void readRawToken(FormatToken &Tok);
void resetLexer(unsigned Offset);
};
} // namespace format
} // namespace clang
#endif
|
