hokein updated this revision to Diff 415387.
hokein marked 4 inline comments as done.
hokein added a comment.
address comments
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D121678/new/
https://reviews.llvm.org/D121678
Files:
clang/include/clang/Tooling/Syntax/Pseudo/Token.h
clang/lib/Tooling/Syntax/Pseudo/Lex.cpp
clang/lib/Tooling/Syntax/Pseudo/Token.cpp
clang/lib/Tooling/Syntax/Pseudo/cxx.bnf
clang/unittests/Tooling/Syntax/Pseudo/TokenTest.cpp
Index: clang/unittests/Tooling/Syntax/Pseudo/TokenTest.cpp
===================================================================
--- clang/unittests/Tooling/Syntax/Pseudo/TokenTest.cpp
+++ clang/unittests/Tooling/Syntax/Pseudo/TokenTest.cpp
@@ -172,6 +172,25 @@
}));
}
+TEST(TokenTest, SplitGreaterGreater) {
+ LangOptions Opts;
+ std::string Code = R"cpp(
+>> // split
+// >> with an escaped newline in the middle, split
+>\
+>
+>>= // not split
+)cpp";
+ TokenStream Split = stripComments(cook(lex(Code, Opts), Opts));
+ EXPECT_THAT(Split.tokens(), ElementsAreArray({
+ token(">", tok::greater),
+ token(">", tok::greater),
+ token(">", tok::greater),
+ token(">", tok::greater),
+ token(">>=", tok::greatergreaterequal),
+ }));
+}
+
TEST(TokenTest, DropComments) {
LangOptions Opts;
std::string Code = R"cpp(
Index: clang/lib/Tooling/Syntax/Pseudo/cxx.bnf
===================================================================
--- clang/lib/Tooling/Syntax/Pseudo/cxx.bnf
+++ clang/lib/Tooling/Syntax/Pseudo/cxx.bnf
@@ -13,6 +13,9 @@
# - the file merely describes the core C++ grammar. Preprocessor directives and
# lexical conversions are omitted as we reuse clang's lexer and run a fake
# preprocessor;
+# - grammar rules with the >> token are adjusted, the greatergreater token is
+# split into two > tokens, to make the GLR parser aware of nested templates
+# and right shift operator.
#
# Guidelines:
# - non-terminals are lower_case; terminals (aka tokens) correspond to
@@ -96,7 +99,7 @@
fold-operator := ^
fold-operator := |
fold-operator := <<
-fold-operator := >>
+fold-operator := greatergreater
fold-operator := +=
fold-operator := -=
fold-operator := *=
@@ -202,7 +205,7 @@
# expr.shift
shift-expression := additive-expression
shift-expression := shift-expression << additive-expression
-shift-expression := shift-expression >> additive-expression
+shift-expression := shift-expression greatergreater additive-expression
# expr.spaceship
compare-expression := shift-expression
compare-expression := compare-expression <=> shift-expression
@@ -615,7 +618,7 @@
operator-name := ^^
operator-name := ||
operator-name := <<
-operator-name := >>
+operator-name := greatergreater
operator-name := <<=
operator-name := >>=
operator-name := ++
@@ -737,3 +740,8 @@
module-keyword := IDENTIFIER
import-keyword := IDENTIFIER
export-keyword := IDENTIFIER
+
+#! greatergreater token -- clang lexer always lexes it as a single token, we
+#! split it into two tokens to make the GLR parser aware of the nested-template
+#! case.
+greatergreater := > >
Index: clang/lib/Tooling/Syntax/Pseudo/Token.cpp
===================================================================
--- clang/lib/Tooling/Syntax/Pseudo/Token.cpp
+++ clang/lib/Tooling/Syntax/Pseudo/Token.cpp
@@ -7,6 +7,7 @@
//===----------------------------------------------------------------------===//
#include "clang/Tooling/Syntax/Pseudo/Token.h"
+#include "clang/Basic/TokenKinds.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/Support/Format.h"
#include "llvm/Support/FormatVariadic.h"
Index: clang/lib/Tooling/Syntax/Pseudo/Lex.cpp
===================================================================
--- clang/lib/Tooling/Syntax/Pseudo/Lex.cpp
+++ clang/lib/Tooling/Syntax/Pseudo/Lex.cpp
@@ -99,10 +99,21 @@
Tok.Length = Text.size();
Tok.Flags &= ~static_cast<decltype(Tok.Flags)>(LexFlags::NeedsCleaning);
}
- // Cook raw_identifiers into identifier, keyword, etc.
- if (Tok.Kind == tok::raw_identifier)
+
+ if (Tok.Kind == tok::raw_identifier) {
+ // Cook raw_identifiers into identifier, keyword, etc.
Tok.Kind = Identifiers.get(Tok.text()).getTokenID();
- Result.push(std::move(Tok));
+ } else if (Tok.Kind == tok::greatergreater) {
+ // Split the greatergreater token.
+ // FIXME: split lessless token to support Cuda triple angle brackets <<<.
+ assert(Tok.text() == ">>");
+ Tok.Kind = tok::greater;
+ Tok.Length = 1;
+ Result.push(Tok);
+ // Line is wrong if the first greater is followed by an escaped newline!
+ Tok.Data = Tok.text().data() + 1;
+ }
+ Result.push((Tok));
}
Result.finalize();
Index: clang/include/clang/Tooling/Syntax/Pseudo/Token.h
===================================================================
--- clang/include/clang/Tooling/Syntax/Pseudo/Token.h
+++ clang/include/clang/Tooling/Syntax/Pseudo/Token.h
@@ -181,7 +181,8 @@
NeedsCleaning = 1 << 1,
};
-/// Derives a token stream by decoding escapes and interpreting raw_identifiers.
+/// Derives a token stream by decoding escapes, interpreting raw_identifiers and
+/// splitting the greatergreater token.
///
/// Tokens containing UCNs, escaped newlines, trigraphs etc are decoded and
/// their backing data is owned by the returned stream.
_______________________________________________
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
