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
|
//===--- LexerUtils.cpp - clang-tidy---------------------------------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
#include "LexerUtils.h"
#include "clang/AST/AST.h"
#include "clang/Basic/SourceManager.h"
#include <optional>
namespace clang::tidy::utils::lexer {
Token getPreviousToken(SourceLocation Location, const SourceManager &SM,
const LangOptions &LangOpts, bool SkipComments) {
Token Token;
Token.setKind(tok::unknown);
Location = Location.getLocWithOffset(-1);
if (Location.isInvalid())
return Token;
auto StartOfFile = SM.getLocForStartOfFile(SM.getFileID(Location));
while (Location != StartOfFile) {
Location = Lexer::GetBeginningOfToken(Location, SM, LangOpts);
if (!Lexer::getRawToken(Location, Token, SM, LangOpts) &&
(!SkipComments || !Token.is(tok::comment))) {
break;
}
Location = Location.getLocWithOffset(-1);
}
return Token;
}
SourceLocation findPreviousTokenStart(SourceLocation Start,
const SourceManager &SM,
const LangOptions &LangOpts) {
if (Start.isInvalid() || Start.isMacroID())
return SourceLocation();
SourceLocation BeforeStart = Start.getLocWithOffset(-1);
if (BeforeStart.isInvalid() || BeforeStart.isMacroID())
return SourceLocation();
return Lexer::GetBeginningOfToken(BeforeStart, SM, LangOpts);
}
SourceLocation findPreviousTokenKind(SourceLocation Start,
const SourceManager &SM,
const LangOptions &LangOpts,
tok::TokenKind TK) {
if (Start.isInvalid() || Start.isMacroID())
return SourceLocation();
while (true) {
SourceLocation L = findPreviousTokenStart(Start, SM, LangOpts);
if (L.isInvalid() || L.isMacroID())
return SourceLocation();
Token T;
if (Lexer::getRawToken(L, T, SM, LangOpts, /*IgnoreWhiteSpace=*/true))
return SourceLocation();
if (T.is(TK))
return T.getLocation();
Start = L;
}
}
SourceLocation findNextTerminator(SourceLocation Start, const SourceManager &SM,
const LangOptions &LangOpts) {
return findNextAnyTokenKind(Start, SM, LangOpts, tok::comma, tok::semi);
}
std::optional<Token>
findNextTokenSkippingComments(SourceLocation Start, const SourceManager &SM,
const LangOptions &LangOpts) {
std::optional<Token> CurrentToken;
do {
CurrentToken = Lexer::findNextToken(Start, SM, LangOpts);
} while (CurrentToken && CurrentToken->is(tok::comment));
return CurrentToken;
}
bool rangeContainsExpansionsOrDirectives(SourceRange Range,
const SourceManager &SM,
const LangOptions &LangOpts) {
assert(Range.isValid() && "Invalid Range for relexing provided");
SourceLocation Loc = Range.getBegin();
while (Loc < Range.getEnd()) {
if (Loc.isMacroID())
return true;
std::optional<Token> Tok = Lexer::findNextToken(Loc, SM, LangOpts);
if (!Tok)
return true;
if (Tok->is(tok::hash))
return true;
Loc = Lexer::getLocForEndOfToken(Loc, 0, SM, LangOpts).getLocWithOffset(1);
}
return false;
}
std::optional<Token> getQualifyingToken(tok::TokenKind TK,
CharSourceRange Range,
const ASTContext &Context,
const SourceManager &SM) {
assert((TK == tok::kw_const || TK == tok::kw_volatile ||
TK == tok::kw_restrict) &&
"TK is not a qualifier keyword");
std::pair<FileID, unsigned> LocInfo = SM.getDecomposedLoc(Range.getBegin());
StringRef File = SM.getBufferData(LocInfo.first);
Lexer RawLexer(SM.getLocForStartOfFile(LocInfo.first), Context.getLangOpts(),
File.begin(), File.data() + LocInfo.second, File.end());
std::optional<Token> LastMatchBeforeTemplate;
std::optional<Token> LastMatchAfterTemplate;
bool SawTemplate = false;
Token Tok;
while (!RawLexer.LexFromRawLexer(Tok) &&
Range.getEnd() != Tok.getLocation() &&
!SM.isBeforeInTranslationUnit(Range.getEnd(), Tok.getLocation())) {
if (Tok.is(tok::raw_identifier)) {
IdentifierInfo &Info = Context.Idents.get(
StringRef(SM.getCharacterData(Tok.getLocation()), Tok.getLength()));
Tok.setIdentifierInfo(&Info);
Tok.setKind(Info.getTokenID());
}
if (Tok.is(tok::less))
SawTemplate = true;
else if (Tok.isOneOf(tok::greater, tok::greatergreater))
LastMatchAfterTemplate = std::nullopt;
else if (Tok.is(TK)) {
if (SawTemplate)
LastMatchAfterTemplate = Tok;
else
LastMatchBeforeTemplate = Tok;
}
}
return LastMatchAfterTemplate != std::nullopt ? LastMatchAfterTemplate
: LastMatchBeforeTemplate;
}
static bool breakAndReturnEnd(const Stmt &S) {
return isa<CompoundStmt, DeclStmt, NullStmt>(S);
}
static bool breakAndReturnEndPlus1Token(const Stmt &S) {
return isa<Expr, DoStmt, ReturnStmt, BreakStmt, ContinueStmt, GotoStmt, SEHLeaveStmt>(S);
}
// Given a Stmt which does not include it's semicolon this method returns the
// SourceLocation of the semicolon.
static SourceLocation getSemicolonAfterStmtEndLoc(const SourceLocation &EndLoc,
const SourceManager &SM,
const LangOptions &LangOpts) {
if (EndLoc.isMacroID()) {
// Assuming EndLoc points to a function call foo within macro F.
// This method is supposed to return location of the semicolon within
// those macro arguments:
// F ( foo() ; )
// ^ EndLoc ^ SpellingLoc ^ next token of SpellingLoc
const SourceLocation SpellingLoc = SM.getSpellingLoc(EndLoc);
std::optional<Token> NextTok =
findNextTokenSkippingComments(SpellingLoc, SM, LangOpts);
// Was the next token found successfully?
// All macro issues are simply resolved by ensuring it's a semicolon.
if (NextTok && NextTok->is(tok::TokenKind::semi)) {
// Ideally this would return `F` with spelling location `;` (NextTok)
// following the example above. For now simply return NextTok location.
return NextTok->getLocation();
}
// Fallthrough to 'normal handling'.
// F ( foo() ) ;
// ^ EndLoc ^ SpellingLoc ) ^ next token of EndLoc
}
std::optional<Token> NextTok =
findNextTokenSkippingComments(EndLoc, SM, LangOpts);
// Testing for semicolon again avoids some issues with macros.
if (NextTok && NextTok->is(tok::TokenKind::semi))
return NextTok->getLocation();
return SourceLocation();
}
SourceLocation getUnifiedEndLoc(const Stmt &S, const SourceManager &SM,
const LangOptions &LangOpts) {
const Stmt *LastChild = &S;
while (!LastChild->children().empty() && !breakAndReturnEnd(*LastChild) &&
!breakAndReturnEndPlus1Token(*LastChild)) {
for (const Stmt *Child : LastChild->children())
LastChild = Child;
}
if (!breakAndReturnEnd(*LastChild) &&
breakAndReturnEndPlus1Token(*LastChild))
return getSemicolonAfterStmtEndLoc(S.getEndLoc(), SM, LangOpts);
return S.getEndLoc();
}
} // namespace clang::tidy::utils::lexer
|
