(Incomplete)Add support for id-expression

[eduucaldas]

Summary

• TODO: Differ between NameQualifiers
• TODO: Box all operators
• Done: Treat NestedNameSpecifiers
• Done: [Try] Unbox all operators

[eduucaldas]

Add support for DeclRefExpr in SyntaxTree, by generating IdExpression

clang/include/clang/Tooling/Syntax/Nodes.h

enum class NodeKind : uint16_t {
 
   // Expressions.
   UnknownExpression,
   PrefixUnaryOperatorExpression,
   PostfixUnaryOperatorExpression,
   BinaryOperatorExpression,
   CxxNullPtrExpression,
   IntegerLiteralExpression,
+  IdExpression,
 
   // Statements.
   UnknownStatement,
   DeclarationStatement,
   EmptyStatement,
   SwitchStatement,
   CaseStatement,
   DefaultStatement,
enum class NodeKind : uint16_t {
 
   // Declarators.
   SimpleDeclarator,
   ParenDeclarator,
 
   ArraySubscript,
   TrailingReturnType,
   ParametersAndQualifiers,
-  MemberPointer
+  MemberPointer,
+  Operator,
+  NestedNameSpecifier,
+  NameQualifier
 };
 /// For debugging purposes.
 llvm::raw_ostream &operator<<(llvm::raw_ostream &OS, NodeKind K);
 
 /// A relation between a parent and child node, e.g. 'left-hand-side of
 /// a binary expression'. Used for implementing accessors.
 ///
 /// Some roles describe parent/child relations that occur multiple times in
enum class NodeRole : uint8_t {
   StaticAssertDeclaration_condition,
   StaticAssertDeclaration_message,
   SimpleDeclaration_declarator,
   TemplateDeclaration_declaration,
   ExplicitTemplateInstantiation_declaration,
   ArraySubscript_sizeExpression,
   TrailingReturnType_declarator,
   ParametersAndQualifiers_parameter,
-  ParametersAndQualifiers_trailingReturn
+  ParametersAndQualifiers_trailingReturn,
+  IdExpression_unqualifiedId,
+  IdExpression_qualifier
 };
 /// For debugging purposes.
 llvm::raw_ostream &operator<<(llvm::raw_ostream &OS, NodeRole R);
 
 class SimpleDeclarator;
 
 /// A root node for a translation unit. Parent is always null.
 class TranslationUnit final : public Tree {

 public:
   Expression(NodeKind K) : Tree(K) {}
   static bool classof(const Node *N) {
     return NodeKind::UnknownExpression <= N->kind() &&
            N->kind() <= NodeKind::UnknownExpression;
   }
 };
 
+class NameQualifier final : public Tree {
+public:
+  NameQualifier() : Tree(NodeKind::NameQualifier) {}
+  static bool classof(const Node *N) {
+    return N->kind() == NodeKind::NameQualifier;
+  }
+};
+
+class NestedNameSpecifier final : public Tree {
+public:
+  NestedNameSpecifier() : Tree(NodeKind::NestedNameSpecifier) {}
+  static bool classof(const Node *N) {
+    return N->kind() <= NodeKind::NestedNameSpecifier;
+  }
+
+  std::vector<syntax::NameQualifier *> specifiers();
+};
+
 /// An expression of an unknown kind, i.e. one not currently handled by the
 /// syntax tree.
 class UnknownExpression final : public Expression {
 public:
   UnknownExpression() : Expression(NodeKind::UnknownExpression) {}
   static bool classof(const Node *N) {
     return N->kind() == NodeKind::UnknownExpression;
   }
 };
 
+/// An identifier expression, e.g. `n::S::a`. Modeled according to the grammar
+class IdExpression final : public Expression {
+public:
+  IdExpression() : Expression(NodeKind::IdExpression) {}
+  static bool classof(const Node *N) {
+    return N->kind() == NodeKind::IdExpression;
+  }
+
+  syntax::Leaf *unqualifiedId();
+  syntax::Leaf *qualifier();
+};
+
 /// C++11 'nullptr' expression.
 class CxxNullPtrExpression final : public Expression {
 public:
   CxxNullPtrExpression() : Expression(NodeKind::CxxNullPtrExpression) {}
   static bool classof(const Node *N) {
     return N->kind() == NodeKind::CxxNullPtrExpression;
   }
   syntax::Leaf *nullPtrKeyword();

clang/lib/Tooling/Syntax/BuildTree.cpp

public:
   // Some expressions are not yet handled by syntax trees.
   bool WalkUpFromExpr(Expr *E) {
     assert(!isImplicitExpr(E) && "should be handled by TraverseStmt");
     Builder.foldNode(Builder.getExprRange(E),
                      new (allocator()) syntax::UnknownExpression, E);
     return true;
   }
 
+  syntax::NestedNameSpecifier *
+  BuildNestedNameSpecifier(NestedNameSpecifierLoc NNS) {
+    if (!NNS)
+      return nullptr;
+    NestedNameSpecifierLoc it = NNS;
+    while (it) {
+      auto *NS = new (allocator()) syntax::NameQualifier;
+      Builder.foldNode(Builder.getRange(it.getLocalSourceRange()), NS, nullptr);
+      Builder.markChild(NS, syntax::NodeRole::Unknown);
+      it = it.getPrefix();
+    }
+    syntax::NestedNameSpecifier *sNNS =
+        new (allocator()) syntax::NestedNameSpecifier;
+    Builder.foldNode(Builder.getRange(NNS.getSourceRange()), sNNS, nullptr);
+    return sNNS;
+  }
+
+  bool WalkUpFromDeclRefExpr(DeclRefExpr *S) {
+    if (S->getNameInfo().getName().getNameKind() ==
+        clang::DeclarationName::CXXOperatorName) {
+      return true;
+    } else {
+      auto *sNNS = BuildNestedNameSpecifier(S->getQualifierLoc());
+      if (sNNS)
+        Builder.markChild(sNNS, syntax::NodeRole::IdExpression_qualifier);
+      Builder.markChildToken(S->getLocation(),
+                             syntax::NodeRole::IdExpression_unqualifiedId);
+      Builder.foldNode(Builder.getExprRange(S),
+                       new (allocator()) syntax::IdExpression, S);
+    }
+    return true;
+  }
+
   bool WalkUpFromIntegerLiteral(IntegerLiteral *S) {
     Builder.markChildToken(S->getLocation(), syntax::NodeRole::LiteralToken);
     Builder.foldNode(Builder.getExprRange(S),
                      new (allocator()) syntax::IntegerLiteralExpression, S);
     return true;
   }
 
   bool WalkUpFromCXXNullPtrLiteralExpr(CXXNullPtrLiteralExpr *S) {

clang/lib/Tooling/Syntax/Nodes.cpp

llvm::raw_ostream &syntax::operator<<(llvm::raw_ostream &OS, NodeKind K) {
   case NodeKind::IntegerLiteralExpression:
     return OS << "IntegerLiteralExpression";
   case NodeKind::PrefixUnaryOperatorExpression:
     return OS << "PrefixUnaryOperatorExpression";
   case NodeKind::PostfixUnaryOperatorExpression:
     return OS << "PostfixUnaryOperatorExpression";
   case NodeKind::BinaryOperatorExpression:
     return OS << "BinaryOperatorExpression";
+  case NodeKind::IdExpression:
+    return OS << "IdExpression";
   case NodeKind::UnknownStatement:
     return OS << "UnknownStatement";
   case NodeKind::DeclarationStatement:
     return OS << "DeclarationStatement";
   case NodeKind::EmptyStatement:
     return OS << "EmptyStatement";
   case NodeKind::SwitchStatement:
     return OS << "SwitchStatement";
llvm::raw_ostream &syntax::operator<<(llvm::raw_ostream &OS, NodeKind K) {
   case NodeKind::ArraySubscript:
     return OS << "ArraySubscript";
   case NodeKind::TrailingReturnType:
     return OS << "TrailingReturnType";
   case NodeKind::ParametersAndQualifiers:
     return OS << "ParametersAndQualifiers";
   case NodeKind::MemberPointer:
     return OS << "MemberPointer";
+  case NodeKind::Operator:
+    return OS << "Operator";
+  case NodeKind::NameQualifier:
+    return OS << "NameQualifier";
+  case NodeKind::NestedNameSpecifier:
+    return OS << "NestedNameSpecifier";
   }
   llvm_unreachable("unknown node kind");
 }
 
 llvm::raw_ostream &syntax::operator<<(llvm::raw_ostream &OS, NodeRole R) {
   switch (R) {
   case syntax::NodeRole::Detached:
     return OS << "Detached";
llvm::raw_ostream &syntax::operator<<(llvm::raw_ostream &OS, NodeRole R) {
   case syntax::NodeRole::ArraySubscript_sizeExpression:
     return OS << "ArraySubscript_sizeExpression";
   case syntax::NodeRole::TrailingReturnType_declarator:
     return OS << "TrailingReturnType_declarator";
   case syntax::NodeRole::ParametersAndQualifiers_parameter:
     return OS << "ParametersAndQualifiers_parameter";
   case syntax::NodeRole::ParametersAndQualifiers_trailingReturn:
     return OS << "ParametersAndQualifiers_trailingReturn";
+  case syntax::NodeRole::IdExpression_unqualifiedId:
+    return OS << "IdExpression_unqualifiedId";
+  case syntax::NodeRole::IdExpression_qualifier:
+    return OS << "IdExpression_qualifier";
   }
   llvm_unreachable("invalid role");
 }
 
+std::vector<syntax::NameQualifier *> syntax::NestedNameSpecifier::specifiers() {
+  std::vector<syntax::NameQualifier *> Children;
+  for (auto *C = firstChild(); C; C = C->nextSibling()) {
+    Children.push_back(llvm::cast<syntax::NameQualifier>(C));
+  }
+  return Children;
+}
+syntax::Leaf *syntax::IdExpression::qualifier() {
+  return llvm::cast_or_null<syntax::Leaf>(
+      findChild(syntax::NodeRole::IdExpression_qualifier));
+}
+
+syntax::Leaf *syntax::IdExpression::unqualifiedId() {
+  return llvm::cast_or_null<syntax::Leaf>(
+      findChild(syntax::NodeRole::IdExpression_unqualifiedId));
+}
+
 syntax::Leaf *syntax::IntegerLiteralExpression::literalToken() {
   return llvm::cast_or_null<syntax::Leaf>(
       findChild(syntax::NodeRole::LiteralToken));
 }
 
 syntax::Leaf *syntax::CxxNullPtrExpression::nullPtrKeyword() {
   return llvm::cast_or_null<syntax::Leaf>(
       findChild(syntax::NodeRole::LiteralToken));

clang/unittests/Tooling/Syntax/TreeTest.cpp

`-CompoundStatement
     |-RangeBasedForStatement
     | |-for
     | |-(
     | |-SimpleDeclaration
     | | |-int
     | | |-SimpleDeclarator
     | | | `-x
     | | `-:
-    | |-UnknownExpression
+    | |-IdExpression
     | | `-a
     | |-)
     | `-EmptyStatement
     |   `-;
     `-}
 )txt"));
 }
 
`-SimpleDeclaration
   | |-test
   | `-ParametersAndQualifiers
   |   |-(
   |   `-)
   `-CompoundStatement
     |-{
     |-ExpressionStatement
     | |-UnknownExpression
-    | | |-UnknownExpression
+    | | |-IdExpression
     | | | `-test
     | | |-(
     | | `-)
     | `-;
     |-IfStatement
     | |-if
     | |-(
     | |-IntegerLiteralExpression
     | | `-1
     | |-)
     | |-ExpressionStatement
     | | |-UnknownExpression
-    | | | |-UnknownExpression
+    | | | |-IdExpression
     | | | | `-test
     | | | |-(
     | | | `-)
     | | `-;
     | |-else
     | `-ExpressionStatement
     |   |-UnknownExpression
-    |   | |-UnknownExpression
+    |   | |-IdExpression
     |   | | `-test
     |   | |-(
     |   | `-)
     |   `-;
     `-}
 )txt"));
 }
 
`-CompoundStatement
     | |-SimpleDeclaration
     | | |-int
     | | `-SimpleDeclarator
     | |   `-a
     | `-;
     |-ExpressionStatement
     | |-BinaryOperatorExpression
     | | |-IdExpression
-    | | | `-UnqualifiedId
-    | | |   `-a
+    | | | `-a
     | | |-=
     | | `-IdExpression
-    | |   `-UnqualifiedId
-    | |     `-b
+    | |   `-b
     | `-;
     `-}
 )txt"));
 }
 
 TEST_P(SyntaxTreeTest, QualifiedId) {
   if (!GetParam().isCXX()) {
     return;
`-SimpleDeclaration
   |   |-(
   |   |-SimpleDeclaration
   |   | |-int
   |   | `-SimpleDeclarator
   |   |   `-b
   |   `-)
   `-CompoundStatement
     |-{
-    |-DeclarationStatement
-    | |-SimpleDeclaration
-    | | |-a
-    | | |-::
-    | | |-b
-    | | |-::
-    | | |-S
-    | | `-SimpleDeclarator
-    | |   `-UnknownExpression
-    | |     `-s
-    | `-;
     |-ExpressionStatement
     | |-UnknownExpression
     | | |-IdExpression
     | | | |-NestedNameSpecifier
     | | | | |-NameQualifier
-    | | | | | |-GlobalNamespace
-    | | | | | `::
+    | | | | | `-::
     | | | | |-NameQualifier
-    | | | | | |-NamespaceName
-    | | | | | | `-a
+    | | | | | |-a
     | | | | | `-::
     | | | | |-NameQualifier
-    | | | | | |-NamespaceName
-    | | | | | | `-b
+    | | | | | |-b
     | | | | | `-::
     | | | | `-NameQualifier
-    | | | |   |-TypeName
-    | | | |   | `-S
+    | | | |   |-S
     | | | |   `-::
-    | | | `-UnqualifiedId
-    | | |   `-f
+    | | | `-f
     | | |-(
     | | `-)
     | `-;
     `-}
 )txt"));
 }
 
 TEST_P(SyntaxTreeTest, CxxNullPtrLiteral) {
`-SimpleDeclaration
   |   | |-int
   |   | `-SimpleDeclarator
   |   |   `-a
   |   `-)
   `-CompoundStatement
     |-{
     |-ExpressionStatement
     | |-PostfixUnaryOperatorExpression
-    | | |-UnknownExpression
+    | | |-IdExpression
     | | | `-a
     | | `-++
     | `-;
     |-ExpressionStatement
     | |-PostfixUnaryOperatorExpression
-    | | |-UnknownExpression
+    | | |-IdExpression
     | | | `-a
     | | `---
     | `-;
     `-}
 )txt"));
 }
 
 TEST_P(SyntaxTreeTest, PrefixUnaryOperator) {
`-SimpleDeclaration
   |   |   |-*
   |   |   `-ap
   |   `-)
   `-CompoundStatement
     |-{
     |-ExpressionStatement
     | |-PrefixUnaryOperatorExpression
     | | |---
-    | | `-UnknownExpression
+    | | `-IdExpression
     | |   `-a
     | `-;
     |-ExpressionStatement
     | |-PrefixUnaryOperatorExpression
     | | |-++
-    | | `-UnknownExpression
+    | | `-IdExpression
     | |   `-a
     | `-;
     |-ExpressionStatement
     | |-PrefixUnaryOperatorExpression
     | | |-~
-    | | `-UnknownExpression
+    | | `-IdExpression
     | |   `-a
     | `-;
     |-ExpressionStatement
     | |-PrefixUnaryOperatorExpression
     | | |--
-    | | `-UnknownExpression
+    | | `-IdExpression
     | |   `-a
     | `-;
     |-ExpressionStatement
     | |-PrefixUnaryOperatorExpression
     | | |-+
-    | | `-UnknownExpression
+    | | `-IdExpression
     | |   `-a
     | `-;
     |-ExpressionStatement
     | |-PrefixUnaryOperatorExpression
     | | |-&
-    | | `-UnknownExpression
+    | | `-IdExpression
     | |   `-a
     | `-;
     |-ExpressionStatement
     | |-PrefixUnaryOperatorExpression
     | | |-*
-    | | `-UnknownExpression
+    | | `-IdExpression
     | |   `-ap
     | `-;
     |-ExpressionStatement
     | |-PrefixUnaryOperatorExpression
     | | |-!
-    | | `-UnknownExpression
+    | | `-IdExpression
     | |   `-a
     | `-;
     |-ExpressionStatement
     | |-PrefixUnaryOperatorExpression
     | | |-__real
-    | | `-UnknownExpression
+    | | `-IdExpression
     | |   `-a
     | `-;
     |-ExpressionStatement
     | |-PrefixUnaryOperatorExpression
     | | |-__imag
-    | | `-UnknownExpression
+    | | `-IdExpression
     | |   `-a
     | `-;
     `-}
 )txt"));
 }
 
 TEST_P(SyntaxTreeTest, PrefixUnaryOperatorCxx) {
   if (!GetParam().isCXX()) {
`-SimpleDeclaration
   |   | `-SimpleDeclarator
   |   |   `-b
   |   `-)
   `-CompoundStatement
     |-{
     |-ExpressionStatement
     | |-PrefixUnaryOperatorExpression
     | | |-compl
-    | | `-UnknownExpression
+    | | `-IdExpression
     | |   `-a
     | `-;
     |-ExpressionStatement
     | |-PrefixUnaryOperatorExpression
     | | |-not
-    | | `-UnknownExpression
+    | | `-IdExpression
     | |   `-b
     | `-;
     `-}
 )txt"));
 }
 
 TEST_P(SyntaxTreeTest, BinaryOperator) {
   EXPECT_TRUE(treeDumpEqual(
`-CompoundStatement
     | | |-IntegerLiteralExpression
     | | | `-1
     | | |-==
     | | `-IntegerLiteralExpression
     | |   `-2
     | `-;
     |-ExpressionStatement
     | |-BinaryOperatorExpression
-    | | |-UnknownExpression
+    | | |-IdExpression
     | | | `-a
     | | |-=
     | | `-IntegerLiteralExpression
     | |   `-1
     | `-;
     |-ExpressionStatement
     | |-BinaryOperatorExpression
-    | | |-UnknownExpression
+    | | |-IdExpression
     | | | `-a
     | | |-<<=
     | | `-IntegerLiteralExpression
     | |   `-1
     | `-;
     |-ExpressionStatement
     | |-BinaryOperatorExpression
     | | |-IntegerLiteralExpression
     | | | `-1
     | | |-||
     | | `-IntegerLiteralExpression
     | |   `-0
     | `-;
     |-ExpressionStatement
     | |-BinaryOperatorExpression
     | | |-IntegerLiteralExpression
     | | | `-1
     | | |-&
     | | `-IntegerLiteralExpression
     | |   `-2
     | `-;
     |-ExpressionStatement
     | |-BinaryOperatorExpression
-    | | |-UnknownExpression
+    | | |-IdExpression
     | | | `-a
     | | |-^=
     | | `-IntegerLiteralExpression
     | |   `-3
     | `-;
     `-}
 )txt"));
 }
`-CompoundStatement
     | | |-IntegerLiteralExpression
     | | | `-1
     | | |-bitand
     | | `-IntegerLiteralExpression
     | |   `-2
     | `-;
     |-ExpressionStatement
     | |-BinaryOperatorExpression
-    | | |-UnknownExpression
+    | | |-IdExpression
     | | | `-a
     | | |-xor_eq
     | | `-IntegerLiteralExpression
     | |   `-3
     | `-;
     `-}
 )txt"));
 }
`-CompoundStatement
     | |   | |-/
     | |   | `-IntegerLiteralExpression
     | |   |   `-2
     | |   `-)
     | `-;
     |-ExpressionStatement
     | |-BinaryOperatorExpression
     | | |-BinaryOperatorExpression
-    | | | |-UnknownExpression
+    | | | |-IdExpression
     | | | | `-a
     | | | |-+
-    | | | `-UnknownExpression
+    | | | `-IdExpression
     | | |   `-b
     | | |-+
     | | `-IntegerLiteralExpression
     | |   `-42
     | `-;
     |-ExpressionStatement
     | |-BinaryOperatorExpression
-    | | |-UnknownExpression
+    | | |-IdExpression
     | | | `-a
     | | |-=
     | | `-BinaryOperatorExpression
-    | |   |-UnknownExpression
+    | |   |-IdExpression
     | |   | `-b
     | |   |-=
     | |   `-IntegerLiteralExpression
     | |     `-42
     | `-;
     |-ExpressionStatement
     | |-BinaryOperatorExpression
     | | |-BinaryOperatorExpression
-    | | | |-UnknownExpression
+    | | | |-IdExpression
     | | | | `-a
     | | | |-+
     | | | `-BinaryOperatorExpression
-    | | |   |-UnknownExpression
+    | | |   |-IdExpression
     | | |   | `-b
     | | |   |-*
     | | |   `-IntegerLiteralExpression
     | | |     `-4
     | | |-+
     | | `-IntegerLiteralExpression
     | |   `-2
     | `-;
     |-ExpressionStatement
     | |-BinaryOperatorExpression
     | | |-BinaryOperatorExpression
-    | | | |-UnknownExpression
+    | | | |-IdExpression
     | | | | `-a
     | | | |-%
     | | | `-IntegerLiteralExpression
     | | |   `-2
     | | |-+
     | | `-BinaryOperatorExpression
-    | |   |-UnknownExpression
+    | |   |-IdExpression
     | |   | `-b
     | |   |-*
     | |   `-IntegerLiteralExpression
     | |     `-42
     | `-;
     `-}
 )txt"));
 }
`-SimpleDeclaration
   |   | |-X
   |   | `-SimpleDeclarator
   |   |   `-y
   |   `-)
   `-CompoundStatement
     |-{
     |-ExpressionStatement
     | |-BinaryOperatorExpression
-    | | |-UnknownExpression
+    | | |-IdExpression
     | | | `-x
-    | | |-UnknownExpression
-    | | | `-=
-    | | `-UnknownExpression
+    | | |-=
+    | | `-IdExpression
     | |   `-y
     | `-;
     |-ExpressionStatement
     | |-BinaryOperatorExpression
     | | |-UnknownExpression
-    | | | `-UnknownExpression
+    | | | `-IdExpression
     | | |   `-x
-    | | |-UnknownExpression
-    | | | `-+
-    | | `-UnknownExpression
+    | | |-+
+    | | `-IdExpression
     | |   `-y
     | `-;
     |-ExpressionStatement
     | |-BinaryOperatorExpression
-    | | |-UnknownExpression
+    | | |-IdExpression
     | | | `-x
-    | | |-UnknownExpression
-    | | | `-<
-    | | `-UnknownExpression
+    | | |-<
+    | | `-IdExpression
     | |   `-y
     | `-;
     `-}
 )txt"));
 }
 
 TEST_P(SyntaxTreeTest, MultipleDeclaratorsGrouping) {
   EXPECT_TRUE(treeDumpEqual(