[SyntaxTree] Implement the List construct.

We defined a List construct to help with the implementation of list-like
grammar rules. This is a first implementation of this API.

Differential Revision: https://reviews.llvm.org/D85295

4 files changed, 166 insertions, 0 deletions

diff --git a/clang/include/clang/Tooling/Syntax/Nodes.h b/clang/include/clang/Tooling/Syntax/Nodes.h
index 2273cb7..fc44076 100644
--- a/clang/include/clang/Tooling/Syntax/Nodes.h
+++ b/clang/include/clang/Tooling/Syntax/Nodes.h
@@ -147,6 +147,8 @@ enum class NodeRole : uint8_t {
   /// statement, e.g. loop body for while, for, etc; inner statement for case,
   /// default, etc.
   BodyStatement,
+  List_element,
+  List_delimiter,
 
   // Roles specific to particular node kinds.
   OperatorExpression_operatorToken,
diff --git a/clang/include/clang/Tooling/Syntax/Tree.h b/clang/include/clang/Tooling/Syntax/Tree.h
index d35bc64..fcd169c 100644
--- a/clang/include/clang/Tooling/Syntax/Tree.h
+++ b/clang/include/clang/Tooling/Syntax/Tree.h
@@ -191,6 +191,59 @@ private:
   Node *FirstChild = nullptr;
 };
 
+/// A list of Elements separated or terminated by a fixed token.
+///
+/// This type models the following grammar construct:
+/// delimited-list(element, delimiter, termination, canBeEmpty)
+class List : public Tree {
+public:
+  template <typename Element> struct ElementAndDelimiter {
+    Element *element;
+    Leaf *delimiter;
+  };
+
+  enum class TerminationKind {
+    Terminated,
+    MaybeTerminated,
+    Separated,
+  };
+
+  using Tree::Tree;
+  /// Returns the elements and corresponding delimiters. Missing elements
+  /// and delimiters are represented as null pointers.
+  ///
+  /// For example, in a separated list:
+  /// "a, b, c" <=> [("a", ","), ("b", ","), ("c", null)]
+  /// "a, , c" <=> [("a", ","), (null, ","), ("c", ",)]
+  /// "a, b," <=> [("a", ","), ("b", ","), (null, null)]
+  ///
+  /// In a terminated or maybe-terminated list:
+  /// "a, b," <=> [("a", ","), ("b", ",")]
+  std::vector<ElementAndDelimiter<Node>> getElementsAsNodesAndDelimiters();
+
+  /// Returns the elements of the list. Missing elements are represented
+  /// as null pointers in the same way as in the return value of
+  /// `getElementsAsNodesAndDelimiters()`.
+  std::vector<Node *> getElementsAsNodes();
+
+  // These can't be implemented with the information we have!
+
+  /// Returns the appropriate delimiter for this list.
+  ///
+  /// Useful for discovering the correct delimiter to use when adding
+  /// elements to empty or one-element lists.
+  clang::tok::TokenKind getDelimiterTokenKind();
+
+  TerminationKind getTerminationKind();
+
+  /// Whether this list can be empty in syntactically and semantically correct
+  /// code.
+  ///
+  /// This list may be empty when the source code has errors even if
+  /// canBeEmpty() returns false.
+  bool canBeEmpty();
+};
+
 } // namespace syntax
 } // namespace clang
 
diff --git a/clang/lib/Tooling/Syntax/Nodes.cpp b/clang/lib/Tooling/Syntax/Nodes.cpp
index b5a4c50b..5e8deb6 100644
--- a/clang/lib/Tooling/Syntax/Nodes.cpp
+++ b/clang/lib/Tooling/Syntax/Nodes.cpp
@@ -152,6 +152,10 @@ raw_ostream &syntax::operator<<(raw_ostream &OS, NodeRole R) {
     return OS << "TemplateKeyword";
   case syntax::NodeRole::BodyStatement:
     return OS << "BodyStatement";
+  case syntax::NodeRole::List_element:
+    return OS << "List_element";
+  case syntax::NodeRole::List_delimiter:
+    return OS << "List_delimiter";
   case syntax::NodeRole::CaseStatement_value:
     return OS << "CaseStatement_value";
   case syntax::NodeRole::IfStatement_thenStatement:
diff --git a/clang/lib/Tooling/Syntax/Tree.cpp b/clang/lib/Tooling/Syntax/Tree.cpp
index 6f9ee40..6070d16 100644
--- a/clang/lib/Tooling/Syntax/Tree.cpp
+++ b/clang/lib/Tooling/Syntax/Tree.cpp
@@ -268,3 +268,110 @@ syntax::Node *syntax::Tree::findChild(NodeRole R) {
   }
   return nullptr;
 }
+
+std::vector<syntax::List::ElementAndDelimiter<syntax::Node>>
+syntax::List::getElementsAsNodesAndDelimiters() {
+  if (!firstChild())
+    return {};
+
+  auto children = std::vector<syntax::List::ElementAndDelimiter<Node>>();
+  syntax::Node *elementWithoutDelimiter = nullptr;
+  for (auto *C = firstChild(); C; C = C->nextSibling()) {
+    switch (C->role()) {
+    case syntax::NodeRole::List_element: {
+      if (elementWithoutDelimiter) {
+        children.push_back({elementWithoutDelimiter, nullptr});
+      }
+      elementWithoutDelimiter = C;
+      break;
+    }
+    case syntax::NodeRole::List_delimiter: {
+      children.push_back({elementWithoutDelimiter, cast<syntax::Leaf>(C)});
+      elementWithoutDelimiter = nullptr;
+      break;
+    }
+    default:
+      llvm_unreachable(
+          "A list can have only elements and delimiters as children.");
+    }
+  }
+
+  switch (getTerminationKind()) {
+  case syntax::List::TerminationKind::Separated: {
+    children.push_back({elementWithoutDelimiter, nullptr});
+    break;
+  }
+  case syntax::List::TerminationKind::Terminated:
+  case syntax::List::TerminationKind::MaybeTerminated: {
+    if (elementWithoutDelimiter) {
+      children.push_back({elementWithoutDelimiter, nullptr});
+    }
+    break;
+  }
+  }
+
+  return children;
+}
+
+// Almost the same implementation of `getElementsAsNodesAndDelimiters` but
+// ignoring delimiters
+std::vector<syntax::Node *> syntax::List::getElementsAsNodes() {
+  if (!firstChild())
+    return {};
+
+  auto children = std::vector<syntax::Node *>();
+  syntax::Node *elementWithoutDelimiter = nullptr;
+  for (auto *C = firstChild(); C; C = C->nextSibling()) {
+    switch (C->role()) {
+    case syntax::NodeRole::List_element: {
+      if (elementWithoutDelimiter) {
+        children.push_back(elementWithoutDelimiter);
+      }
+      elementWithoutDelimiter = C;
+      break;
+    }
+    case syntax::NodeRole::List_delimiter: {
+      children.push_back(elementWithoutDelimiter);
+      elementWithoutDelimiter = nullptr;
+      break;
+    }
+    default:
+      llvm_unreachable("A list has only elements or delimiters.");
+    }
+  }
+
+  switch (getTerminationKind()) {
+  case syntax::List::TerminationKind::Separated: {
+    children.push_back(elementWithoutDelimiter);
+    break;
+  }
+  case syntax::List::TerminationKind::Terminated:
+  case syntax::List::TerminationKind::MaybeTerminated: {
+    if (elementWithoutDelimiter) {
+      children.push_back(elementWithoutDelimiter);
+    }
+    break;
+  }
+  }
+
+  return children;
+}
+
+// The methods below can't be implemented without information about the derived
+// list. These methods will be implemented by switching on the derived list's
+// `NodeKind`
+
+clang::tok::TokenKind syntax::List::getDelimiterTokenKind() {
+  llvm_unreachable("There are no subclasses of List, thus "
+                   "getDelimiterTokenKind() cannot be called");
+}
+
+syntax::List::TerminationKind syntax::List::getTerminationKind() {
+  llvm_unreachable("There are no subclasses of List, thus getTerminationKind() "
+                   "cannot be called");
+}
+
+bool syntax::List::canBeEmpty() {
+  llvm_unreachable(
+      "There are no subclasses of List, thus canBeEmpty() cannot be called");
+}