[clang-format] Add basic support for formatting C# files
Summary:
This revision adds basic support for formatting C# files with clang-format, I know the barrier to entry is high here so I'm sending this revision in to test the water as to whether this might be something we'd consider landing.
Tracking in Bugzilla as:
https://bugs.llvm.org/show_bug.cgi?id=40850
Justification:
C# code just looks ugly in comparison to the C++ code in our source tree which is clang-formatted.
I've struggled with Visual Studio reformatting to get a clean and consistent style, I want to format our C# code on saving like I do now for C++ and i want it to have the same style as defined in our .clang-format file, so it consistent as it can be with C++. (Braces/Breaking/Spaces/Indent etc..)
Using clang format without this patch leaves the code in a bad state, sometimes when the BreakStringLiterals is set, it fails to compile.
Mostly the C# is similar to Java, except instead of JavaAnnotations I try to reuse the TT_AttributeSquare.
Almost the most valuable portion is to have a new Language in order to partition the configuration for C# within a common .clang-format file, with the auto detection on the .cs extension. But there are other C# specific styles that could be added later if this is accepted. in particular how `{ set;get }` is formatted.
Reviewers: djasper, klimek, krasimir, benhamilton, JonasToth
Reviewed By: klimek
Subscribers: llvm-commits, mgorny, jdoerfert, cfe-commits
Tags: #clang, #clang-tools-extra
Differential Revision: https://reviews.llvm.org/D58404
llvm-svn: 356662
diff --git a/clang/lib/Format/FormatToken.h b/clang/lib/Format/FormatToken.h
index a5daf8a..461e070 100644
--- a/clang/lib/Format/FormatToken.h
+++ b/clang/lib/Format/FormatToken.h
@@ -96,6 +96,8 @@
TYPE(TrailingReturnArrow) \
TYPE(TrailingUnaryOperator) \
TYPE(UnaryOperator) \
+ TYPE(CSharpStringLiteral) \
+ TYPE(CSharpNullCoalescing) \
TYPE(Unknown)
enum TokenType {
@@ -723,7 +725,36 @@
kw_slots = &IdentTable.get("slots");
kw_qslots = &IdentTable.get("Q_SLOTS");
- // Keep this at the end of the constructor to make sure everything here is
+ // C# keywords
+ kw_dollar = &IdentTable.get("dollar");
+ kw_base = &IdentTable.get("base");
+ kw_byte = &IdentTable.get("byte");
+ kw_checked = &IdentTable.get("checked");
+ kw_decimal = &IdentTable.get("decimal");
+ kw_delegate = &IdentTable.get("delegate");
+ kw_event = &IdentTable.get("event");
+ kw_fixed = &IdentTable.get("fixed");
+ kw_foreach = &IdentTable.get("foreach");
+ kw_implicit = &IdentTable.get("implicit");
+ kw_internal = &IdentTable.get("internal");
+ kw_lock = &IdentTable.get("lock");
+ kw_null = &IdentTable.get("null");
+ kw_object = &IdentTable.get("object");
+ kw_out = &IdentTable.get("out");
+ kw_params = &IdentTable.get("params");
+ kw_ref = &IdentTable.get("ref");
+ kw_string = &IdentTable.get("string");
+ kw_stackalloc = &IdentTable.get("stackalloc");
+ kw_sbyte = &IdentTable.get("sbyte");
+ kw_sealed = &IdentTable.get("sealed");
+ kw_uint = &IdentTable.get("uint");
+ kw_ulong = &IdentTable.get("ulong");
+ kw_unchecked = &IdentTable.get("unchecked");
+ kw_unsafe = &IdentTable.get("unsafe");
+ kw_ushort = &IdentTable.get("ushort");
+
+ // Keep this at the end of the constructor to make sure everything here
+ // is
// already initialized.
JsExtraKeywords = std::unordered_set<IdentifierInfo *>(
{kw_as, kw_async, kw_await, kw_declare, kw_finally, kw_from,
@@ -731,6 +762,19 @@
kw_set, kw_type, kw_typeof, kw_var, kw_yield,
// Keywords from the Java section.
kw_abstract, kw_extends, kw_implements, kw_instanceof, kw_interface});
+
+ CSharpExtraKeywords = std::unordered_set<IdentifierInfo *>(
+ {kw_base, kw_byte, kw_checked, kw_decimal, kw_delegate, kw_event,
+ kw_fixed, kw_foreach, kw_implicit, kw_in, kw_interface, kw_internal,
+ kw_is, kw_lock, kw_null, kw_object, kw_out, kw_override, kw_params,
+ kw_readonly, kw_ref, kw_string, kw_stackalloc, kw_sbyte, kw_sealed,
+ kw_uint, kw_ulong, kw_unchecked, kw_unsafe, kw_ushort,
+ // Keywords from the JavaScript section.
+ kw_as, kw_async, kw_await, kw_declare, kw_finally, kw_from,
+ kw_function, kw_get, kw_import, kw_is, kw_let, kw_module, kw_readonly,
+ kw_set, kw_type, kw_typeof, kw_var, kw_yield,
+ // Keywords from the Java section.
+ kw_abstract, kw_extends, kw_implements, kw_instanceof, kw_interface});
}
// Context sensitive keywords.
@@ -796,6 +840,37 @@
IdentifierInfo *kw_slots;
IdentifierInfo *kw_qslots;
+ // C# keywords
+ IdentifierInfo *kw_dollar;
+ IdentifierInfo *kw_base;
+ IdentifierInfo *kw_byte;
+ IdentifierInfo *kw_checked;
+ IdentifierInfo *kw_decimal;
+ IdentifierInfo *kw_delegate;
+ IdentifierInfo *kw_event;
+ IdentifierInfo *kw_fixed;
+ IdentifierInfo *kw_foreach;
+ IdentifierInfo *kw_implicit;
+ IdentifierInfo *kw_internal;
+
+ IdentifierInfo *kw_lock;
+ IdentifierInfo *kw_null;
+ IdentifierInfo *kw_object;
+ IdentifierInfo *kw_out;
+
+ IdentifierInfo *kw_params;
+
+ IdentifierInfo *kw_ref;
+ IdentifierInfo *kw_string;
+ IdentifierInfo *kw_stackalloc;
+ IdentifierInfo *kw_sbyte;
+ IdentifierInfo *kw_sealed;
+ IdentifierInfo *kw_uint;
+ IdentifierInfo *kw_ulong;
+ IdentifierInfo *kw_unchecked;
+ IdentifierInfo *kw_unsafe;
+ IdentifierInfo *kw_ushort;
+
/// Returns \c true if \p Tok is a true JavaScript identifier, returns
/// \c false if it is a keyword or a pseudo keyword.
bool IsJavaScriptIdentifier(const FormatToken &Tok) const {
@@ -804,9 +879,68 @@
JsExtraKeywords.end();
}
+ /// Returns \c true if \p Tok is a C# keyword, returns
+ /// \c false if it is a anything else.
+ bool isCSharpKeyword(const FormatToken &Tok) const {
+ switch (Tok.Tok.getKind()) {
+ case tok::kw_bool:
+ case tok::kw_break:
+ case tok::kw_case:
+ case tok::kw_catch:
+ case tok::kw_char:
+ case tok::kw_class:
+ case tok::kw_const:
+ case tok::kw_continue:
+ case tok::kw_default:
+ case tok::kw_do:
+ case tok::kw_double:
+ case tok::kw_else:
+ case tok::kw_enum:
+ case tok::kw_explicit:
+ case tok::kw_extern:
+ case tok::kw_false:
+ case tok::kw_float:
+ case tok::kw_for:
+ case tok::kw_goto:
+ case tok::kw_if:
+ case tok::kw_int:
+ case tok::kw_long:
+ case tok::kw_namespace:
+ case tok::kw_new:
+ case tok::kw_operator:
+ case tok::kw_private:
+ case tok::kw_protected:
+ case tok::kw_public:
+ case tok::kw_return:
+ case tok::kw_short:
+ case tok::kw_sizeof:
+ case tok::kw_static:
+ case tok::kw_struct:
+ case tok::kw_switch:
+ case tok::kw_this:
+ case tok::kw_throw:
+ case tok::kw_true:
+ case tok::kw_try:
+ case tok::kw_typeof:
+ case tok::kw_using:
+ case tok::kw_virtual:
+ case tok::kw_void:
+ case tok::kw_volatile:
+ case tok::kw_while:
+ return true;
+ default:
+ return Tok.is(tok::identifier) &&
+ CSharpExtraKeywords.find(Tok.Tok.getIdentifierInfo()) ==
+ CSharpExtraKeywords.end();
+ }
+ }
+
private:
/// The JavaScript keywords beyond the C++ keyword set.
std::unordered_set<IdentifierInfo *> JsExtraKeywords;
+
+ /// The C# keywords beyond the C++ keyword set
+ std::unordered_set<IdentifierInfo *> CSharpExtraKeywords;
};
} // namespace format