[clang-format] Add a space between an overloaded operator and '>'

The token annotator doesn't annotate the template opener and closer
as such if they enclose an overloaded operator. This causes the
space between the operator and the closer to be removed, resulting
in invalid C++ code.

Fixes #58602.

Differential Revision: https://reviews.llvm.org/D143755
This commit is contained in:
Owen Pan 2023-02-10 08:50:49 -08:00
parent 7c9df77435
commit b05dc1b876
6 changed files with 126 additions and 17 deletions

View File

@ -743,8 +743,8 @@ public:
} }
/// Returns the next token ignoring comments. /// Returns the next token ignoring comments.
[[nodiscard]] const FormatToken *getNextNonComment() const { [[nodiscard]] FormatToken *getNextNonComment() const {
const FormatToken *Tok = Next; FormatToken *Tok = Next;
while (Tok && Tok->is(tok::comment)) while (Tok && Tok->is(tok::comment))
Tok = Tok->Next; Tok = Tok->Next;
return Tok; return Tok;

View File

@ -103,6 +103,8 @@ void FormatTokenLexer::tryMergePreviousTokens() {
return; return;
if (tryMergeLessLess()) if (tryMergeLessLess())
return; return;
if (tryMergeGreaterGreater())
return;
if (tryMergeForEach()) if (tryMergeForEach())
return; return;
if (Style.isCpp() && tryTransformTryUsageForC()) if (Style.isCpp() && tryTransformTryUsageForC())
@ -460,12 +462,11 @@ bool FormatTokenLexer::tryMergeLessLess() {
return false; return false;
auto X = Tokens.size() > 3 ? First[-1] : nullptr; auto X = Tokens.size() > 3 ? First[-1] : nullptr;
auto Y = First[2]; if (X && X->is(tok::less))
if ((X && X->is(tok::less)) || Y->is(tok::less))
return false; return false;
// Do not remove a whitespace between the two "<" e.g. "operator< <>". auto Y = First[2];
if (X && X->is(tok::kw_operator) && Y->is(tok::greater)) if ((!X || X->isNot(tok::kw_operator)) && Y->is(tok::less))
return false; return false;
First[0]->Tok.setKind(tok::lessless); First[0]->Tok.setKind(tok::lessless);
@ -475,6 +476,30 @@ bool FormatTokenLexer::tryMergeLessLess() {
return true; return true;
} }
bool FormatTokenLexer::tryMergeGreaterGreater() {
// Merge kw_operator,greater,greater into kw_operator,greatergreater.
if (Tokens.size() < 2)
return false;
auto First = Tokens.end() - 2;
if (First[0]->isNot(tok::greater) || First[1]->isNot(tok::greater))
return false;
// Only merge if there currently is no whitespace between the first two ">".
if (First[1]->hasWhitespaceBefore())
return false;
auto Tok = Tokens.size() > 2 ? First[-1] : nullptr;
if (Tok && Tok->isNot(tok::kw_operator))
return false;
First[0]->Tok.setKind(tok::greatergreater);
First[0]->TokenText = ">>";
First[0]->ColumnWidth += 1;
Tokens.erase(Tokens.end() - 1);
return true;
}
bool FormatTokenLexer::tryMergeTokens(ArrayRef<tok::TokenKind> Kinds, bool FormatTokenLexer::tryMergeTokens(ArrayRef<tok::TokenKind> Kinds,
TokenType NewType) { TokenType NewType) {
if (Tokens.size() < Kinds.size()) if (Tokens.size() < Kinds.size())

View File

@ -51,6 +51,7 @@ private:
void tryMergePreviousTokens(); void tryMergePreviousTokens();
bool tryMergeLessLess(); bool tryMergeLessLess();
bool tryMergeGreaterGreater();
bool tryMergeNSStringLiteral(); bool tryMergeNSStringLiteral();
bool tryMergeJSPrivateIdentifier(); bool tryMergeJSPrivateIdentifier();
bool tryMergeCSharpStringLiteral(); bool tryMergeCSharpStringLiteral();

View File

@ -1219,19 +1219,25 @@ private:
!CurrentToken->isOneOf(tok::l_paren, tok::semi, tok::r_paren)) { !CurrentToken->isOneOf(tok::l_paren, tok::semi, tok::r_paren)) {
if (CurrentToken->isOneOf(tok::star, tok::amp)) if (CurrentToken->isOneOf(tok::star, tok::amp))
CurrentToken->setType(TT_PointerOrReference); CurrentToken->setType(TT_PointerOrReference);
consumeToken(); auto Next = CurrentToken->getNextNonComment();
if (!CurrentToken) if (!Next)
continue;
if (CurrentToken->is(tok::comma) &&
CurrentToken->Previous->isNot(tok::kw_operator)) {
break; break;
} if (Next->is(tok::less))
if (CurrentToken->Previous->isOneOf(TT_BinaryOperator, TT_UnaryOperator, next();
tok::comma, tok::star, tok::arrow, else
tok::amp, tok::ampamp) || consumeToken();
assert(CurrentToken);
auto Previous = CurrentToken->getPreviousNonComment();
assert(Previous);
if (CurrentToken->is(tok::comma) && Previous->isNot(tok::kw_operator))
break;
if (Previous->isOneOf(TT_BinaryOperator, TT_UnaryOperator, tok::comma,
tok::star, tok::arrow, tok::amp, tok::ampamp) ||
// User defined literal. // User defined literal.
CurrentToken->Previous->TokenText.startswith("\"\"")) { Previous->TokenText.startswith("\"\"")) {
CurrentToken->Previous->setType(TT_OverloadedOperator); Previous->setType(TT_OverloadedOperator);
if (CurrentToken->isOneOf(tok::less, tok::greater))
break;
} }
} }
if (CurrentToken && CurrentToken->is(tok::l_paren)) if (CurrentToken && CurrentToken->is(tok::l_paren))
@ -3893,6 +3899,10 @@ bool TokenAnnotator::spaceRequiredBefore(const AnnotatedLine &Line,
return true; return true;
if (Style.isCpp()) { if (Style.isCpp()) {
if (Left.is(TT_OverloadedOperator) &&
Right.isOneOf(TT_TemplateOpener, TT_TemplateCloser)) {
return true;
}
// Space between UDL and dot: auto b = 4s .count(); // Space between UDL and dot: auto b = 4s .count();
if (Right.is(tok::period) && Left.is(tok::numeric_constant)) if (Right.is(tok::period) && Left.is(tok::numeric_constant))
return true; return true;

View File

@ -10663,6 +10663,14 @@ TEST_F(FormatTest, UnderstandsOverloadedOperators) {
verifyFormat("foo() { ::operator new(n * sizeof(foo)); }"); verifyFormat("foo() { ::operator new(n * sizeof(foo)); }");
} }
TEST_F(FormatTest, SpaceBeforeTemplateCloser) {
verifyFormat("C<&operator- > minus;");
verifyFormat("C<&operator> > gt;");
verifyFormat("C<&operator>= > ge;");
verifyFormat("C<&operator<= > le;");
verifyFormat("C<&operator< <X>> lt;");
}
TEST_F(FormatTest, UnderstandsFunctionRefQualification) { TEST_F(FormatTest, UnderstandsFunctionRefQualification) {
verifyFormat("void A::b() && {}"); verifyFormat("void A::b() && {}");
verifyFormat("void A::b() && noexcept {}"); verifyFormat("void A::b() && noexcept {}");

View File

@ -574,6 +574,71 @@ TEST_F(TokenAnnotatorTest, UnderstandsOverloadedOperators) {
EXPECT_TOKEN(Tokens[4], tok::l_paren, TT_OverloadedOperatorLParen); EXPECT_TOKEN(Tokens[4], tok::l_paren, TT_OverloadedOperatorLParen);
} }
TEST_F(TokenAnnotatorTest, OverloadedOperatorInTemplate) {
struct {
const char *Text;
tok::TokenKind Kind;
} Operators[] = {{"+", tok::plus},
{"-", tok::minus},
// FIXME:
// {"*", tok::star},
{"/", tok::slash},
{"%", tok::percent},
{"^", tok::caret},
// FIXME:
// {"&", tok::amp},
{"|", tok::pipe},
{"~", tok::tilde},
{"!", tok::exclaim},
{"=", tok::equal},
// FIXME:
// {"<", tok::less},
{">", tok::greater},
{"+=", tok::plusequal},
{"-=", tok::minusequal},
{"*=", tok::starequal},
{"/=", tok::slashequal},
{"%=", tok::percentequal},
{"^=", tok::caretequal},
{"&=", tok::ampequal},
{"|=", tok::pipeequal},
{"<<", tok::lessless},
{">>", tok::greatergreater},
{">>=", tok::greatergreaterequal},
{"<<=", tok::lesslessequal},
{"==", tok::equalequal},
{"!=", tok::exclaimequal},
{"<=", tok::lessequal},
{">=", tok::greaterequal},
{"<=>", tok::spaceship},
{"&&", tok::ampamp},
{"||", tok::pipepipe},
{"++", tok::plusplus},
{"--", tok::minusminus},
{",", tok::comma},
{"->*", tok::arrowstar},
{"->", tok::arrow}};
for (const auto &Operator : Operators) {
std::string Input("C<&operator");
Input += Operator.Text;
Input += " > a;";
auto Tokens = annotate(std::string(Input));
ASSERT_EQ(Tokens.size(), 9u) << Tokens;
EXPECT_TOKEN(Tokens[1], tok::less, TT_TemplateOpener);
EXPECT_TOKEN(Tokens[4], Operator.Kind, TT_OverloadedOperator);
EXPECT_TOKEN(Tokens[5], tok::greater, TT_TemplateCloser);
}
auto Tokens = annotate("C<&operator< <X>> lt;");
ASSERT_EQ(Tokens.size(), 12u) << Tokens;
EXPECT_TOKEN(Tokens[1], tok::less, TT_TemplateOpener);
EXPECT_TOKEN(Tokens[4], tok::less, TT_OverloadedOperator);
EXPECT_TOKEN(Tokens[5], tok::less, TT_TemplateOpener);
EXPECT_TOKEN(Tokens[7], tok::greater, TT_TemplateCloser);
EXPECT_TOKEN(Tokens[8], tok::greater, TT_TemplateCloser);
}
TEST_F(TokenAnnotatorTest, UnderstandsRequiresClausesAndConcepts) { TEST_F(TokenAnnotatorTest, UnderstandsRequiresClausesAndConcepts) {
auto Tokens = annotate("template <typename T>\n" auto Tokens = annotate("template <typename T>\n"
"concept C = (Foo && Bar) && (Bar && Baz);"); "concept C = (Foo && Bar) && (Bar && Baz);");