[clang-tools-extra] 217f267 - Revert "[pseudo] Split greatergreater token."

[Zequan Wu via cfe-commits]

Author: Zequan Wu
Date: 2022-03-18T10:15:48-07:00
New Revision: 217f267efe3082438e698e2f08566b9df8c530fa

URL: https://github.com/llvm/llvm-project/commit/217f267efe3082438e698e2f08566b9df8c530fa
DIFF: https://github.com/llvm/llvm-project/commit/217f267efe3082438e698e2f08566b9df8c530fa.diff

LOG: Revert "[pseudo] Split greatergreater token."

This reverts commit f66d3758bda99e9f57bfdad168212feda18792ae.

It breaks windows bot.

Added: 
    

Modified: 
    clang-tools-extra/pseudo/include/clang-pseudo/Token.h
    clang-tools-extra/pseudo/lib/Lex.cpp
    clang-tools-extra/pseudo/lib/cxx.bnf
    clang-tools-extra/pseudo/unittests/TokenTest.cpp

Removed: 
    


################################################################################
diff  --git a/clang-tools-extra/pseudo/include/clang-pseudo/Token.h b/clang-tools-extra/pseudo/include/clang-pseudo/Token.h
index 4563477b2c4fe..24b6729151e61 100644
--- a/clang-tools-extra/pseudo/include/clang-pseudo/Token.h
+++ b/clang-tools-extra/pseudo/include/clang-pseudo/Token.h
@@ -180,8 +180,7 @@ enum class LexFlags : uint8_t {
   NeedsCleaning = 1 << 1,
 };
 
-/// Derives a token stream by decoding escapes, interpreting raw_identifiers and
-/// splitting the greatergreater token.
+/// Derives a token stream by decoding escapes and interpreting raw_identifiers.
 ///
 /// Tokens containing UCNs, escaped newlines, trigraphs etc are decoded and
 /// their backing data is owned by the returned stream.

diff  --git a/clang-tools-extra/pseudo/lib/Lex.cpp b/clang-tools-extra/pseudo/lib/Lex.cpp
index e99bf3a63e5e1..f5a239533c532 100644
--- a/clang-tools-extra/pseudo/lib/Lex.cpp
+++ b/clang-tools-extra/pseudo/lib/Lex.cpp
@@ -98,21 +98,9 @@ TokenStream cook(const TokenStream &Code, const LangOptions &LangOpts) {
       Tok.Length = Text.size();
       Tok.Flags &= ~static_cast<decltype(Tok.Flags)>(LexFlags::NeedsCleaning);
     }
-
-    if (Tok.Kind == tok::raw_identifier) {
-      // Cook raw_identifiers into identifier, keyword, etc.
+    // Cook raw_identifiers into identifier, keyword, etc.
+    if (Tok.Kind == tok::raw_identifier)
       Tok.Kind = Identifiers.get(Tok.text()).getTokenID();
-    } 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(std::move(Tok));
   }
 

diff  --git a/clang-tools-extra/pseudo/lib/cxx.bnf b/clang-tools-extra/pseudo/lib/cxx.bnf
index cf664b8e13e55..48bf4621eefe5 100644
--- a/clang-tools-extra/pseudo/lib/cxx.bnf
+++ b/clang-tools-extra/pseudo/lib/cxx.bnf
@@ -13,9 +13,6 @@
 #  - 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:
 #   - nonterminals are lower_case; terminals (aka tokens) correspond to
@@ -99,7 +96,7 @@ fold-operator := %
 fold-operator := ^
 fold-operator := |
 fold-operator := <<
-fold-operator := greatergreater
+fold-operator := >>
 fold-operator := +=
 fold-operator := -=
 fold-operator := *=
@@ -205,7 +202,7 @@ additive-expression := additive-expression - multiplicative-expression
 # expr.shift
 shift-expression := additive-expression
 shift-expression := shift-expression << additive-expression
-shift-expression := shift-expression greatergreater additive-expression
+shift-expression := shift-expression >> additive-expression
 # expr.spaceship
 compare-expression := shift-expression
 compare-expression := compare-expression <=> shift-expression
@@ -618,7 +615,7 @@ operator-name := <=>
 operator-name := ^^
 operator-name := ||
 operator-name := <<
-operator-name := greatergreater
+operator-name := >>
 operator-name := <<=
 operator-name := >>=
 operator-name := ++
@@ -740,8 +737,3 @@ contextual-zero := NUMERIC_CONSTANT
 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 := > >

diff  --git a/clang-tools-extra/pseudo/unittests/TokenTest.cpp b/clang-tools-extra/pseudo/unittests/TokenTest.cpp
index b17f8c93c1763..1357d23501193 100644
--- a/clang-tools-extra/pseudo/unittests/TokenTest.cpp
+++ b/clang-tools-extra/pseudo/unittests/TokenTest.cpp
@@ -171,25 +171,6 @@ no_indent \
                             }));
 }
 
-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(