Fixes https://github.com/llvm/llvm-project/issues/31592.
This commits enables lexing of digraphs in C++11 and onwards.
Enabling them in C++03 is error-prone, as it would unconditionally treat sequences like "<:" as digraphs, even if they are followed by a single colon, e.g. "<::" would be treated as "[:" instead of "<" followed by "::". Lexing in C++11 doesn't have this problem as it looks ahead the following token.
The relevant excerpt from Lexer::LexTokenInternal:
```
// C++0x [lex.pptoken]p3:
// Otherwise, if the next three characters are <:: and the subsequent
// character is neither : nor >, the < is treated as a preprocessor
// token by itself and not as the first character of the alternative
// token <:.
```
Also, note that both clang and gcc turn on digraphs by default (-fdigraphs), so clang-format should match this behaviour.
Reviewed By: MyDeveloperDay, HazardyKnusperkeks, owenpan
Differential Revision: https://reviews.llvm.org/D118706
LangOpts.CPlusPlus17 = LexingStd >= FormatStyle::LS_Cpp17;
LangOpts.CPlusPlus20 = LexingStd >= FormatStyle::LS_Cpp20;
LangOpts.Char8 = LexingStd >= FormatStyle::LS_Cpp20;
+ // Turning on digraphs in standards before C++0x is error-prone, because e.g.
+ // the sequence "<::" will be unconditionally treated as "[:".
+ // Cf. Lexer::LexTokenInternal.
+ LangOpts.Digraphs = LexingStd >= FormatStyle::LS_Cpp11;
LangOpts.LineComment = 1;
bool AlternativeOperators = Style.isCpp();
Style);
}
+TEST_F(FormatTest, UnderstandsDigraphs) {
+ verifyFormat("int arr<:5:> = {};");
+ verifyFormat("int arr[5] = <%%>;");
+ verifyFormat("int arr<:::qualified_variable:> = {};");
+ verifyFormat("int arr[::qualified_variable] = <%%>;");
+ verifyFormat("%:include <header>");
+ verifyFormat("%:define A x##y");
+ verifyFormat("#define A x%:%:y");
+}
+
} // namespace
} // namespace format
} // namespace clang