BracesAroundStatementsCheck.cpp
9.99 KB
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
//===--- BracesAroundStatementsCheck.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 "BracesAroundStatementsCheck.h"
#include "clang/AST/ASTContext.h"
#include "clang/ASTMatchers/ASTMatchers.h"
#include "clang/Lex/Lexer.h"
using namespace clang::ast_matchers;
namespace clang {
namespace tidy {
namespace readability {
namespace {
tok::TokenKind getTokenKind(SourceLocation Loc, const SourceManager &SM,
const ASTContext *Context) {
Token Tok;
SourceLocation Beginning =
Lexer::GetBeginningOfToken(Loc, SM, Context->getLangOpts());
const bool Invalid =
Lexer::getRawToken(Beginning, Tok, SM, Context->getLangOpts());
assert(!Invalid && "Expected a valid token.");
if (Invalid)
return tok::NUM_TOKENS;
return Tok.getKind();
}
SourceLocation forwardSkipWhitespaceAndComments(SourceLocation Loc,
const SourceManager &SM,
const ASTContext *Context) {
assert(Loc.isValid());
for (;;) {
while (isWhitespace(*SM.getCharacterData(Loc)))
Loc = Loc.getLocWithOffset(1);
tok::TokenKind TokKind = getTokenKind(Loc, SM, Context);
if (TokKind == tok::NUM_TOKENS || TokKind != tok::comment)
return Loc;
// Fast-forward current token.
Loc = Lexer::getLocForEndOfToken(Loc, 0, SM, Context->getLangOpts());
}
}
SourceLocation findEndLocation(SourceLocation LastTokenLoc,
const SourceManager &SM,
const ASTContext *Context) {
SourceLocation Loc =
Lexer::GetBeginningOfToken(LastTokenLoc, SM, Context->getLangOpts());
// Loc points to the beginning of the last (non-comment non-ws) token
// before end or ';'.
assert(Loc.isValid());
bool SkipEndWhitespaceAndComments = true;
tok::TokenKind TokKind = getTokenKind(Loc, SM, Context);
if (TokKind == tok::NUM_TOKENS || TokKind == tok::semi ||
TokKind == tok::r_brace) {
// If we are at ";" or "}", we found the last token. We could use as well
// `if (isa<NullStmt>(S))`, but it wouldn't work for nested statements.
SkipEndWhitespaceAndComments = false;
}
Loc = Lexer::getLocForEndOfToken(Loc, 0, SM, Context->getLangOpts());
// Loc points past the last token before end or after ';'.
if (SkipEndWhitespaceAndComments) {
Loc = forwardSkipWhitespaceAndComments(Loc, SM, Context);
tok::TokenKind TokKind = getTokenKind(Loc, SM, Context);
if (TokKind == tok::semi)
Loc = Lexer::getLocForEndOfToken(Loc, 0, SM, Context->getLangOpts());
}
for (;;) {
assert(Loc.isValid());
while (isHorizontalWhitespace(*SM.getCharacterData(Loc))) {
Loc = Loc.getLocWithOffset(1);
}
if (isVerticalWhitespace(*SM.getCharacterData(Loc))) {
// EOL, insert brace before.
break;
}
tok::TokenKind TokKind = getTokenKind(Loc, SM, Context);
if (TokKind != tok::comment) {
// Non-comment token, insert brace before.
break;
}
SourceLocation TokEndLoc =
Lexer::getLocForEndOfToken(Loc, 0, SM, Context->getLangOpts());
SourceRange TokRange(Loc, TokEndLoc);
StringRef Comment = Lexer::getSourceText(
CharSourceRange::getTokenRange(TokRange), SM, Context->getLangOpts());
if (Comment.startswith("/*") && Comment.find('\n') != StringRef::npos) {
// Multi-line block comment, insert brace before.
break;
}
// else: Trailing comment, insert brace after the newline.
// Fast-forward current token.
Loc = TokEndLoc;
}
return Loc;
}
} // namespace
BracesAroundStatementsCheck::BracesAroundStatementsCheck(
StringRef Name, ClangTidyContext *Context)
: ClangTidyCheck(Name, Context),
// Always add braces by default.
ShortStatementLines(Options.get("ShortStatementLines", 0U)) {}
void BracesAroundStatementsCheck::storeOptions(
ClangTidyOptions::OptionMap &Opts) {
Options.store(Opts, "ShortStatementLines", ShortStatementLines);
}
void BracesAroundStatementsCheck::registerMatchers(MatchFinder *Finder) {
Finder->addMatcher(
ifStmt(unless(allOf(isConstexpr(), isInTemplateInstantiation())))
.bind("if"),
this);
Finder->addMatcher(whileStmt().bind("while"), this);
Finder->addMatcher(doStmt().bind("do"), this);
Finder->addMatcher(forStmt().bind("for"), this);
Finder->addMatcher(cxxForRangeStmt().bind("for-range"), this);
}
void BracesAroundStatementsCheck::check(
const MatchFinder::MatchResult &Result) {
const SourceManager &SM = *Result.SourceManager;
const ASTContext *Context = Result.Context;
// Get location of closing parenthesis or 'do' to insert opening brace.
if (auto S = Result.Nodes.getNodeAs<ForStmt>("for")) {
checkStmt(Result, S->getBody(), S->getRParenLoc());
} else if (auto S = Result.Nodes.getNodeAs<CXXForRangeStmt>("for-range")) {
checkStmt(Result, S->getBody(), S->getRParenLoc());
} else if (auto S = Result.Nodes.getNodeAs<DoStmt>("do")) {
checkStmt(Result, S->getBody(), S->getDoLoc(), S->getWhileLoc());
} else if (auto S = Result.Nodes.getNodeAs<WhileStmt>("while")) {
SourceLocation StartLoc = findRParenLoc(S, SM, Context);
if (StartLoc.isInvalid())
return;
checkStmt(Result, S->getBody(), StartLoc);
} else if (auto S = Result.Nodes.getNodeAs<IfStmt>("if")) {
SourceLocation StartLoc = findRParenLoc(S, SM, Context);
if (StartLoc.isInvalid())
return;
if (ForceBracesStmts.erase(S))
ForceBracesStmts.insert(S->getThen());
bool BracedIf = checkStmt(Result, S->getThen(), StartLoc, S->getElseLoc());
const Stmt *Else = S->getElse();
if (Else && BracedIf)
ForceBracesStmts.insert(Else);
if (Else && !isa<IfStmt>(Else)) {
// Omit 'else if' statements here, they will be handled directly.
checkStmt(Result, Else, S->getElseLoc());
}
} else {
llvm_unreachable("Invalid match");
}
}
/// Find location of right parenthesis closing condition.
template <typename IfOrWhileStmt>
SourceLocation
BracesAroundStatementsCheck::findRParenLoc(const IfOrWhileStmt *S,
const SourceManager &SM,
const ASTContext *Context) {
// Skip macros.
if (S->getBeginLoc().isMacroID())
return SourceLocation();
SourceLocation CondEndLoc = S->getCond()->getEndLoc();
if (const DeclStmt *CondVar = S->getConditionVariableDeclStmt())
CondEndLoc = CondVar->getEndLoc();
if (!CondEndLoc.isValid()) {
return SourceLocation();
}
SourceLocation PastCondEndLoc =
Lexer::getLocForEndOfToken(CondEndLoc, 0, SM, Context->getLangOpts());
if (PastCondEndLoc.isInvalid())
return SourceLocation();
SourceLocation RParenLoc =
forwardSkipWhitespaceAndComments(PastCondEndLoc, SM, Context);
if (RParenLoc.isInvalid())
return SourceLocation();
tok::TokenKind TokKind = getTokenKind(RParenLoc, SM, Context);
if (TokKind != tok::r_paren)
return SourceLocation();
return RParenLoc;
}
/// Determine if the statement needs braces around it, and add them if it does.
/// Returns true if braces where added.
bool BracesAroundStatementsCheck::checkStmt(
const MatchFinder::MatchResult &Result, const Stmt *S,
SourceLocation InitialLoc, SourceLocation EndLocHint) {
// 1) If there's a corresponding "else" or "while", the check inserts "} "
// right before that token.
// 2) If there's a multi-line block comment starting on the same line after
// the location we're inserting the closing brace at, or there's a non-comment
// token, the check inserts "\n}" right before that token.
// 3) Otherwise the check finds the end of line (possibly after some block or
// line comments) and inserts "\n}" right before that EOL.
if (!S || isa<CompoundStmt>(S)) {
// Already inside braces.
return false;
}
if (!InitialLoc.isValid())
return false;
const SourceManager &SM = *Result.SourceManager;
const ASTContext *Context = Result.Context;
// Treat macros.
CharSourceRange FileRange = Lexer::makeFileCharRange(
CharSourceRange::getTokenRange(S->getSourceRange()), SM,
Context->getLangOpts());
if (FileRange.isInvalid())
return false;
// Convert InitialLoc to file location, if it's on the same macro expansion
// level as the start of the statement. We also need file locations for
// Lexer::getLocForEndOfToken working properly.
InitialLoc = Lexer::makeFileCharRange(
CharSourceRange::getCharRange(InitialLoc, S->getBeginLoc()),
SM, Context->getLangOpts())
.getBegin();
if (InitialLoc.isInvalid())
return false;
SourceLocation StartLoc =
Lexer::getLocForEndOfToken(InitialLoc, 0, SM, Context->getLangOpts());
// StartLoc points at the location of the opening brace to be inserted.
SourceLocation EndLoc;
std::string ClosingInsertion;
if (EndLocHint.isValid()) {
EndLoc = EndLocHint;
ClosingInsertion = "} ";
} else {
const auto FREnd = FileRange.getEnd().getLocWithOffset(-1);
EndLoc = findEndLocation(FREnd, SM, Context);
ClosingInsertion = "\n}";
}
assert(StartLoc.isValid());
assert(EndLoc.isValid());
// Don't require braces for statements spanning less than certain number of
// lines.
if (ShortStatementLines && !ForceBracesStmts.erase(S)) {
unsigned StartLine = SM.getSpellingLineNumber(StartLoc);
unsigned EndLine = SM.getSpellingLineNumber(EndLoc);
if (EndLine - StartLine < ShortStatementLines)
return false;
}
auto Diag = diag(StartLoc, "statement should be inside braces");
Diag << FixItHint::CreateInsertion(StartLoc, " {")
<< FixItHint::CreateInsertion(EndLoc, ClosingInsertion);
return true;
}
void BracesAroundStatementsCheck::onEndOfTranslationUnit() {
ForceBracesStmts.clear();
}
} // namespace readability
} // namespace tidy
} // namespace clang