[pseudo] Split greatergreater token.

For a >> token (a right shift operator, or a nested template?), the clang
lexer always returns a single greatergreater token, as a result,
the grammar-based GLR parser never try to parse the nested template
case.

We derive a token stream by always splitting the >> token, so that the
GLR parser is able to pursue both options during parsing (usually 1
path fails).

Reviewed By: sammccall

Differential Revision: https://reviews.llvm.org/D121678

clang-tools-extra/pseudo/include/clang-pseudo/Token.h

@@ -180,7 +180,8 @@ enum class LexFlags : uint8_t {
   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.

clang-tools-extra/pseudo/lib/Lex.cpp

@@ -98,9 +98,21 @@ TokenStream cook(const TokenStream &Code, const LangOptions &LangOpts) {
       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();
+    } 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));
   }
 

clang-tools-extra/pseudo/lib/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 := >>
+fold-operator := greatergreater
 fold-operator := +=
 fold-operator := -=
 fold-operator := *=
@@ -202,7 +205,7 @@ additive-expression := additive-expression - multiplicative-expression
 # 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 := >>
+operator-name := greatergreater
 operator-name := <<=
 operator-name := >>=
 operator-name := ++
@@ -737,3 +740,8 @@ 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 := > >

clang-tools-extra/pseudo/unittests/TokenTest.cpp

@@ -171,6 +171,25 @@ 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(