[clangd] Treat UserDefinedLiteral as a leaf in SelectionTree, sidestepping tokenization issues

Summary: Fixes https://github.com/clangd/clangd/issues/203

Reviewers: kadircet

Subscribers: ilya-biryukov, MaskRay, jkorous, arphaman, usaxena95, cfe-commits

Tags: #clang

Differential Revision: https://reviews.llvm.org/D70446

2 files changed, 24 insertions, 0 deletions

diff --git a/clang-tools-extra/clangd/Selection.cpp b/clang-tools-extra/clangd/Selection.cpp
index 04076df0c39..c91cd24e2f2 100644
--- a/clang-tools-extra/clangd/Selection.cpp
+++ b/clang-tools-extra/clangd/Selection.cpp
@@ -12,6 +12,7 @@
 #include "clang/AST/ASTTypeTraits.h"
 #include "clang/AST/DeclCXX.h"
 #include "clang/AST/Expr.h"
+#include "clang/AST/ExprCXX.h"
 #include "clang/AST/PrettyPrinter.h"
 #include "clang/AST/RecursiveASTVisitor.h"
 #include "clang/AST/TypeLoc.h"
@@ -245,6 +246,10 @@ public:
     if (canSafelySkipNode(N))
       return false;
     push(std::move(N));
+    if (shouldSkipChildren(X)) {
+      pop();
+      return false;
+    }
     return true;
   }
   bool dataTraverseStmtPost(Stmt *X) {
@@ -355,6 +360,15 @@ private:
     return true;
   }
 
+  // There are certain nodes we want to treat as leaves in the SelectionTree,
+  // although they do have children.
+  bool shouldSkipChildren(const Stmt *X) const {
+    // UserDefinedLiteral (e.g. 12_i) has two children (12 and _i).
+    // Unfortunately TokenBuffer sees 12_i as one token and can't split it.
+    // So we treat UserDefinedLiteral as a leaf node, owning the token.
+    return llvm::isa<UserDefinedLiteral>(X);
+  }
+
   // Pushes a node onto the ancestor stack. Pairs with pop().
   // Performs early hit detection for some nodes (on the earlySourceRange).
   void push(DynTypedNode Node) {
diff --git a/clang-tools-extra/clangd/unittests/SelectionTests.cpp b/clang-tools-extra/clangd/unittests/SelectionTests.cpp
index 7b8b33d8a25..2803aaaca1c 100644
--- a/clang-tools-extra/clangd/unittests/SelectionTests.cpp
+++ b/clang-tools-extra/clangd/unittests/SelectionTests.cpp
@@ -304,6 +304,16 @@ TEST(SelectionTest, CommonAncestor) {
             }
           )cpp",
           "CallExpr"},
+
+      // User-defined literals are tricky: is 12_i one token or two?
+      // For now we treat it as one, and the UserDefinedLiteral as a leaf.
+      {
+          R"cpp(
+            struct Foo{};
+            Foo operator""_ud(unsigned long long);
+            Foo x = [[^12_ud]];
+          )cpp",
+          "UserDefinedLiteral"},
   };
   for (const Case &C : Cases) {
     Annotations Test(C.Code);