Add StringLiteral to SyntaxTree

[gribozavr2]

LGTM with improved testing.

clang/unittests/Tooling/Syntax/TreeTest.cpp

1245

Could you add some non-ASCII characters to tests?

[eduucaldas]

Add unicode tests

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

enum class NodeKind : uint16_t {
   UnknownExpression,
   PrefixUnaryOperatorExpression,
   PostfixUnaryOperatorExpression,
   BinaryOperatorExpression,
   CxxNullPtrExpression,
   IntegerLiteralExpression,
   BoolLiteralExpression,
   CharacterLiteralExpression,
+  StringLiteralExpression,
   IdExpression,
 
   // Statements.
   UnknownStatement,
   DeclarationStatement,
   EmptyStatement,
   SwitchStatement,
   CaseStatement,

 public:
   BoolLiteralExpression() : Expression(NodeKind::BoolLiteralExpression) {}
   static bool classof(const Node *N) {
     return N->kind() == NodeKind::BoolLiteralExpression;
   }
   syntax::Leaf *literalToken();
 };
 
+/// Expression for string-literals. C++ [lex.string]
+class StringLiteralExpression final : public Expression {
+public:
+  StringLiteralExpression() : Expression(NodeKind::StringLiteralExpression) {}
+  static bool classof(const Node *N) {
+    return N->kind() == NodeKind::StringLiteralExpression;
+  }
+  syntax::Leaf *literalToken();
+};
+
 /// An abstract class for prefix and postfix unary operators.
 class UnaryOperatorExpression : public Expression {
 public:
   UnaryOperatorExpression(NodeKind K) : Expression(K) {}
   static bool classof(const Node *N) {
     return N->kind() == NodeKind::PrefixUnaryOperatorExpression ||
            N->kind() == NodeKind::PostfixUnaryOperatorExpression;
   }

clang/lib/Tooling/Syntax/BuildTree.cpp

public:
   }
 
   bool WalkUpFromCharacterLiteral(CharacterLiteral *S) {
     Builder.markChildToken(S->getLocation(), syntax::NodeRole::LiteralToken);
     Builder.foldNode(Builder.getExprRange(S),
                      new (allocator()) syntax::CharacterLiteralExpression, S);
     return true;
   }
+  bool WalkUpFromStringLiteral(StringLiteral *S) {
+    Builder.markChildToken(S->getBeginLoc(), syntax::NodeRole::LiteralToken);
+    Builder.foldNode(Builder.getExprRange(S),
+                     new (allocator()) syntax::StringLiteralExpression, S);
+    return true;
+  }
 
   bool WalkUpFromCXXNullPtrLiteralExpr(CXXNullPtrLiteralExpr *S) {
     Builder.markChildToken(S->getLocation(), syntax::NodeRole::LiteralToken);
     Builder.foldNode(Builder.getExprRange(S),
                      new (allocator()) syntax::CxxNullPtrExpression, S);
     return true;
   }
 

clang/lib/Tooling/Syntax/Nodes.cpp

llvm::raw_ostream &syntax::operator<<(llvm::raw_ostream &OS, NodeKind K) {
   case NodeKind::CxxNullPtrExpression:
     return OS << "CxxNullPtrExpression";
   case NodeKind::IntegerLiteralExpression:
     return OS << "IntegerLiteralExpression";
   case NodeKind::BoolLiteralExpression:
     return OS << "BoolLiteralExpression";
   case NodeKind::CharacterLiteralExpression:
     return OS << "CharacterLiteralExpression";
+  case NodeKind::StringLiteralExpression:
+    return OS << "StringLiteralExpression";
   case NodeKind::PrefixUnaryOperatorExpression:
     return OS << "PrefixUnaryOperatorExpression";
   case NodeKind::PostfixUnaryOperatorExpression:
     return OS << "PostfixUnaryOperatorExpression";
   case NodeKind::BinaryOperatorExpression:
     return OS << "BinaryOperatorExpression";
   case NodeKind::UnqualifiedId:
     return OS << "UnqualifiedId";
return llvm::cast_or_null<syntax::Leaf>(
       findChild(syntax::NodeRole::LiteralToken));
 }
 
 syntax::Leaf *syntax::CharacterLiteralExpression::literalToken() {
   return llvm::cast_or_null<syntax::Leaf>(
       findChild(syntax::NodeRole::LiteralToken));
 }
 
+syntax::Leaf *syntax::StringLiteralExpression::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));
 }
 
 syntax::Expression *syntax::BinaryOperatorExpression::lhs() {
   return llvm::cast_or_null<syntax::Expression>(
       findChild(syntax::NodeRole::BinaryOperatorExpression_leftHandSide));

clang/unittests/Tooling/Syntax/TreeTest.cpp

 }
 
 TEST_P(SyntaxTreeTest, CharacterLiteral) {
   EXPECT_TRUE(treeDumpEqual(
       R"cpp(
 void test() {
   'a';
   '\n';
   '\x20';
   '\0';
   L'a';
   L'α';
 }
 )cpp",
       R"txt(
 *: TranslationUnit
 `-SimpleDeclaration
`-CompoundStatement
     |-ExpressionStatement
     | |-BoolLiteralExpression
     | | `-false
     | `-;
     `-}
 )txt"));
 }
 
+TEST_P(SyntaxTreeTest, StringLiteral) {
+  EXPECT_TRUE(treeDumpEqual(
+      R"cpp(
+void test() {
+  "a\n\0\x20";
+  L"αβ";
+}
+)cpp",
+      R"txt(
+*: TranslationUnit
+`-SimpleDeclaration
+  |-void
+  |-SimpleDeclarator
+  | |-test
+  | `-ParametersAndQualifiers
+  |   |-(
+  |   `-)
+  `-CompoundStatement
+    |-{
+    |-ExpressionStatement
+    | |-StringLiteralExpression
+    | | `-"a\n\0\x20"
+    | `-;
+    |-ExpressionStatement
+    | |-StringLiteralExpression
+    | | `-L"αβ"
+    | `-;
+    `-}
+)txt"));
+}
+
+TEST_P(SyntaxTreeTest, StringLiteralUtf) {
+  if (!GetParam().isCXX11OrLater()) {
+    return;
+  }
+  EXPECT_TRUE(treeDumpEqual(
+      R"cpp(
+void test() {
+  u8"a\x1f\x05";
+  u"C++抽象構文木";
+  U"📖🌲\n";
+}
+)cpp",
+      R"txt(
+*: TranslationUnit
+`-SimpleDeclaration
+  |-void
+  |-SimpleDeclarator
+  | |-test
+  | `-ParametersAndQualifiers
+  |   |-(
+  |   `-)
+  `-CompoundStatement
+    |-{
+    |-ExpressionStatement
+    | |-StringLiteralExpression
+    | | `-u8"a\x1f\x05"
+    | `-;
+    |-ExpressionStatement
+    | |-StringLiteralExpression
+    | | `-u"C++抽象構文木"
+    | `-;
+    |-ExpressionStatement
+    | |-StringLiteralExpression
+    | | `-U"📖🌲\n"
+    | `-;
+    `-}
+)txt"));
+}
+
+TEST_P(SyntaxTreeTest, StringLiteralRaw) {
+  if (!GetParam().isCXX11OrLater()) {
+    return;
+  }
+  EXPECT_TRUE(treeDumpEqual(
+      R"cpp(
+void test() {
+  R"SyntaxTree(
+  Hello "Syntax" \"
+  )SyntaxTree";
+}
+)cpp",
+      R"txt(
+*: TranslationUnit
+`-SimpleDeclaration
+  |-void
+  |-SimpleDeclarator
+  | |-test
+  | `-ParametersAndQualifiers
+  |   |-(
+  |   `-)
+  `-CompoundStatement
+    |-{
+    |-ExpressionStatement
+    | |-StringLiteralExpression
+    | | `-R"SyntaxTree(
+  Hello "Syntax" \"
+  )SyntaxTree"
+    | `-;
+    `-}
+)txt"));
+}
+
 TEST_P(SyntaxTreeTest, IntegerLiteral) {
   EXPECT_TRUE(treeDumpEqual(
       R"cpp(
 void test() {
   12;
   12u;
   12l;
   12ul;
)cpp",
       R"txt(
 *: TranslationUnit
 |-StaticAssertDeclaration
 | |-static_assert
 | |-(
 | |-BoolLiteralExpression
 | | `-true
 | |-,
-| |-UnknownExpression
+| |-StringLiteralExpression
 | | `-"message"
 | |-)
 | `-;
 `-StaticAssertDeclaration
   |-static_assert
   |-(
   |-BoolLiteralExpression
   | `-true