[clang][Expr] Teach IgnoreUnlessSpelledInSource about implicit calls to std::get free function

clang/lib/AST/Expr.cpp

@@ -2544,6 +2544,19 @@ Stmt *BlockExpr::getBody() {
 //===----------------------------------------------------------------------===//
 // Generic Expression Routines
 //===----------------------------------------------------------------------===//
+namespace {
+/// Helper to determine wether \c E is a CXXConstructExpr constructing
+/// a DecompositionDecl. Used to skip Clang-generated calls to std::get
+/// for structured bindings.
+bool IsDecompositionDeclRefExpr(const Expr *E) {
+  const Expr *Unrwapped = E->IgnoreUnlessSpelledInSource();
+  const DeclRefExpr *Ref = llvm::dyn_cast_or_null<DeclRefExpr>(Unrwapped);
+  if (!Ref)
+    return false;
+
+  return llvm::isa_and_nonnull<DecompositionDecl>(Ref->getDecl());
+}
+} // namespace
 
 bool Expr::isReadIfDiscardedInCPlusPlus11() const {
   // In C++11, discarded-value expressions of a certain form are special,
@@ -3159,10 +3172,39 @@ Expr *Expr::IgnoreUnlessSpelledInSource() {
     }
     return E;
   };
+
+  // Used when Clang generates calls to std::get for decomposing
+  // structured bindings.
+  auto IgnoreImplicitCallSingleStep = [](Expr *E) {
+    auto *C = dyn_cast<CallExpr>(E);
+    if (!C)
+      return E;
+
+    // Looking for calls to a std::get, which usually just takes
+    // 1 argument (i.e., the structure being decomposed). If it has
+    // more than 1 argument, the others need to be defaulted.
+    unsigned NumArgs = C->getNumArgs();
+    if (NumArgs == 0 || (NumArgs > 1 && !isa<CXXDefaultArgExpr>(C->getArg(1))))
+      return E;
+
+    Expr *A = C->getArg(0);
+
+    // This was spelled out in source. Don't ignore.
+    if (A->getSourceRange() != E->getSourceRange())
+      return E;
+
+    // If the argument refers to a DecompositionDecl construction,
+    // ignore it.
+    if (IsDecompositionDeclRefExpr(A))
+      return A;
+
+    return E;
+  };
+
   return IgnoreExprNodes(
       this, IgnoreImplicitSingleStep, IgnoreImplicitCastsExtraSingleStep,
       IgnoreParensOnlySingleStep, IgnoreImplicitConstructorSingleStep,
-      IgnoreImplicitMemberCallSingleStep);
+      IgnoreImplicitMemberCallSingleStep, IgnoreImplicitCallSingleStep);
 }
 
 bool Expr::isDefaultArgument() const {

clang/test/DebugInfo/CXX/structured-binding.cpp

@@ -1,12 +1,20 @@
-// RUN: %clang_cc1 -emit-llvm -debug-info-kind=standalone -triple %itanium_abi_triple %s -o - | FileCheck %s --implicit-check-not="call void @llvm.dbg.declare"
+// RUN: %clang_cc1 -std=c++23 -emit-llvm -debug-info-kind=standalone -triple %itanium_abi_triple %s -o - | FileCheck %s --implicit-check-not="call void @llvm.dbg.declare"
 
+// CHECK: define {{.*}} i32 @_Z1fv
 // CHECK: #dbg_declare(ptr %{{[a-z]+}}, ![[VAR_0:[0-9]+]], !DIExpression(),
 // CHECK: #dbg_declare(ptr %{{[0-9]+}}, ![[VAR_1:[0-9]+]], !DIExpression(),
 // CHECK: #dbg_declare(ptr %{{[0-9]+}}, ![[VAR_2:[0-9]+]], !DIExpression(DW_OP_plus_uconst, 4),
 // CHECK: #dbg_declare(ptr %{{[0-9]+}}, ![[VAR_3:[0-9]+]], !DIExpression(DW_OP_deref),
 // CHECK: #dbg_declare(ptr %{{[0-9]+}}, ![[VAR_4:[0-9]+]], !DIExpression(DW_OP_deref, DW_OP_plus_uconst, 4),
 // CHECK: #dbg_declare(ptr %z1, ![[VAR_5:[0-9]+]], !DIExpression()
 // CHECK: #dbg_declare(ptr %z2, ![[VAR_6:[0-9]+]], !DIExpression()
+// CHECK: #dbg_declare(ptr %k, ![[VAR_7:[0-9]+]], !DIExpression()
+// CHECK: #dbg_declare(ptr %v, ![[VAR_8:[0-9]+]], !DIExpression()
+// CHECK: #dbg_declare(ptr %w, ![[VAR_9:[0-9]+]], !DIExpression()
+// CHECK: #dbg_declare(ptr %m, ![[VAR_10:[0-9]+]], !DIExpression()
+// CHECK: #dbg_declare(ptr %n, ![[VAR_11:[0-9]+]], !DIExpression()
+// CHECK: #dbg_declare(ptr %s, ![[VAR_12:[0-9]+]], !DIExpression()
+// CHECK: #dbg_declare(ptr %p, ![[VAR_13:[0-9]+]], !DIExpression()
 // CHECK: getelementptr inbounds nuw %struct.A, ptr {{.*}}, i32 0, i32 1, !dbg ![[Y1_DEBUG_LOC:[0-9]+]]
 // CHECK: getelementptr inbounds nuw %struct.A, ptr {{.*}}, i32 0, i32 1, !dbg ![[Y2_DEBUG_LOC:[0-9]+]]
 // CHECK: load ptr, ptr %z2, {{.*}}!dbg ![[Z2_DEBUG_LOC:[0-9]+]]
@@ -20,6 +28,13 @@
 // CHECK: ![[VAR_4]] = !DILocalVariable(name: "y2", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
 // CHECK: ![[VAR_5]] = !DILocalVariable(name: "z1", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
 // CHECK: ![[VAR_6]] = !DILocalVariable(name: "z2", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
+// CHECK: ![[VAR_7]] = !DILocalVariable(name: "k", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
+// CHECK: ![[VAR_8]] = !DILocalVariable(name: "v", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
+// CHECK: ![[VAR_9]] = !DILocalVariable(name: "w", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
+// CHECK: ![[VAR_10]] = !DILocalVariable(name: "m", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
+// CHECK: ![[VAR_11]] = !DILocalVariable(name: "n", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
+// CHECK: ![[VAR_12]] = !DILocalVariable(name: "s", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
+// CHECK: ![[VAR_13]] = !DILocalVariable(name: "p", scope: !{{[0-9]+}}, file: !{{[0-9]+}}, line: {{[0-9]+}}, type: !{{[0-9]+}})
 
 struct A {
   int x;
@@ -34,6 +49,22 @@ struct B {
   template<> int get<1>() { return z; }
 };
 
+struct C {
+  int w;
+  int z;
+  template<int> int get(this C&& self);
+  template<> int get<0>(this C&& self) { return self.w; }
+  template<> int get<1>(this C&& self) { return self.z; }
+};
+
+struct D {
+  int w;
+  int z;
+  template<int> int get(int unused = 0);
+  template<> int get<0>(int unused) { return w; }
+  template<> int get<1>(int unused) { return z; }
+};
+
 // Note: the following declarations are necessary for decomposition of tuple-like
 // structured bindings
 namespace std {
@@ -44,7 +75,35 @@ struct tuple_size<B> {
     static constexpr unsigned value = 2;
 };
 
+template<>
+struct tuple_size<C> {
+    static constexpr unsigned value = 2;
+};
+
+template<>
+struct tuple_size<D> {
+    static constexpr unsigned value = 2;
+};
+
 template<unsigned, typename T> struct tuple_element { using type = int; };
+
+// Decomposition of tuple-like bindings but where the `get` methods
+// are declared as free functions.
+struct triple {
+  int k;
+  int v;
+  int w;
+};
+
+template<>
+struct tuple_size<triple> {
+    static constexpr unsigned value = 3;
+};
+
+template <unsigned I> int get(triple);
+template <> int get<0>(triple p) { return p.k; }
+template <> int get<1>(triple p) { return p.v; }
+template <> int get<2>(triple p) { return p.w; }
 } // namespace std
 
 int f() {
@@ -58,6 +117,9 @@ int f() {
   auto &[c1, c2] = cmplx;
   int vctr __attribute__ ((vector_size (sizeof(int)*2)))= {1, 2};
   auto &[v1, v2] = vctr;
+  auto [k, v, w] = std::triple{3, 4, 5};
+  auto [m, n] = C{2, 3};
+  auto [s, p] = D{2, 3};
   return //
      x1 //
      +  //

clang/unittests/AST/ASTTraverserTest.cpp

@@ -1174,6 +1174,12 @@ struct Pair
     int x, y;
 };
 
+// Tuple-like structure with a `get` method that has a default argument.
+struct Pair2
+{
+    int x, y;
+};
+
 // Note: these utilities are required to force binding to tuple like structure
 namespace std
 {
@@ -1188,6 +1194,12 @@ namespace std
         static constexpr size_t value = 2;
     };
 
+    template <>
+    struct tuple_size<Pair2>
+    {
+        static constexpr size_t value = 2;
+    };
+
     template <size_t I, class T>
     struct tuple_element
     {
@@ -1199,12 +1211,17 @@ namespace std
 template <size_t I>
 int &&get(Pair &&p);
 
+template <size_t I>
+int &&get(Pair2 &&p, int unused = 0);
+
 void decompTuple()
 {
     Pair p{1, 2};
     auto [a, b] = p;
 
     a = 3;
+
+    auto [c, d] = Pair2{3, 4};
 }
 
 )cpp",
@@ -1586,6 +1603,62 @@ DecompositionDecl ''
 |-DeclRefExpr 'p'
 |-BindingDecl 'a'
 `-BindingDecl 'b'
+)cpp");
+  }
+
+  {
+    auto FN = ast_matchers::match(
+        functionDecl(hasName("decompTuple"),
+                     hasDescendant(callExpr(hasAncestor(varDecl(
+                                                hasName("a"),
+                                                hasAncestor(bindingDecl()))))
+                                       .bind("decomp_call"))),
+        AST2->getASTContext());
+    EXPECT_EQ(FN.size(), 1u);
+
+    EXPECT_EQ(dumpASTString(TK_AsIs, FN[0].getNodeAs<CallExpr>("decomp_call")),
+              R"cpp(
+CallExpr
+|-ImplicitCastExpr
+| `-DeclRefExpr 'get'
+`-ImplicitCastExpr
+  `-DeclRefExpr ''
+)cpp");
+
+    EXPECT_EQ(dumpASTString(TK_IgnoreUnlessSpelledInSource,
+                            FN[0].getNodeAs<CallExpr>("decomp_call")),
+              R"cpp(
+DeclRefExpr ''
+)cpp");
+  }
+
+  {
+    auto FN = ast_matchers::match(
+        functionDecl(hasName("decompTuple"),
+                     hasDescendant(callExpr(hasAncestor(varDecl(
+                                                hasName("c"),
+                                                hasAncestor(bindingDecl()))))
+                                       .bind("decomp_call_with_default"))),
+        AST2->getASTContext());
+    EXPECT_EQ(FN.size(), 1u);
+
+    EXPECT_EQ(dumpASTString(TK_AsIs, FN[0].getNodeAs<CallExpr>(
+                                         "decomp_call_with_default")),
+              R"cpp(
+CallExpr
+|-ImplicitCastExpr
+| `-DeclRefExpr 'get'
+|-ImplicitCastExpr
+| `-DeclRefExpr ''
+`-CXXDefaultArgExpr
+  `-IntegerLiteral
+)cpp");
+
+    EXPECT_EQ(
+        dumpASTString(TK_IgnoreUnlessSpelledInSource,
+                      FN[0].getNodeAs<CallExpr>("decomp_call_with_default")),
+        R"cpp(
+DeclRefExpr ''
 )cpp");
   }
 }

lldb/test/API/lang/cpp/structured-binding/TestStructuredBinding.py

@@ -98,3 +98,17 @@ def test(self):
         self.expect_expr("tx2", result_value="4")
         self.expect_expr("ty2", result_value="'z'")
         self.expect_expr("tz2", result_value="10")
+
+        self.expect(
+            "frame variable",
+            substrs=[
+                "tx1 =",
+                "ty1 =",
+                "tz1 =",
+                "tx2 =",
+                "ty2 =",
+                "tz2 =",
+                "mp1 =",
+                "mp2 =",
+            ],
+        )

lldb/test/API/lang/cpp/structured-binding/main.cpp

@@ -1,13 +1,80 @@
 // Structured binding in C++ can bind identifiers to subobjects of an object.
 //
-// There are three cases we need to test:
+// There are four cases we need to test:
 // 1) arrays
-// 2) tuples like objects
-// 3) non-static data members
+// 2) tuple-like objects with `get` member functions
+// 3) tuple-like objects with `get` free functions
+// 4) non-static data members
 //
 // They can also bind by copy, reference or rvalue reference.
 
-#include <tuple>
+struct MyPair {
+  int m1;
+  int m2;
+
+  // Helpers to enable tuple-like decomposition.
+  template <unsigned> int get();
+  template <> int get<0>() { return m1; }
+  template <> int get<1>() { return m2; }
+};
+
+namespace std {
+template <typename T1, typename T2, typename T3> struct mock_tuple {
+  T1 m1;
+  T2 m2;
+  T3 m3;
+};
+
+template <typename T> struct tuple_size;
+
+template <unsigned, typename T> struct tuple_element;
+
+// Helpers to enable tuple-like decomposition for MyPair
+template <unsigned I> struct tuple_element<I, MyPair> {
+  using type = int;
+};
+
+template <> struct tuple_size<MyPair> {
+  static constexpr unsigned value = 2;
+};
+
+// Helpers to enable tuple-like decomposition for mock_tuple
+template <typename T1, typename T2, typename T3>
+struct tuple_element<0, mock_tuple<T1, T2, T3>> {
+  using type = T1;
+};
+
+template <typename T1, typename T2, typename T3>
+struct tuple_element<1, mock_tuple<T1, T2, T3>> {
+  using type = T2;
+};
+
+template <typename T1, typename T2, typename T3>
+struct tuple_element<2, mock_tuple<T1, T2, T3>> {
+  using type = T3;
+};
+
+template <typename T1, typename T2, typename T3>
+struct tuple_size<mock_tuple<T1, T2, T3>> {
+  static constexpr unsigned value = 3;
+};
+
+template <unsigned I, typename T1, typename T2, typename T3>
+typename tuple_element<I, mock_tuple<T1, T2, T3>>::type
+get(mock_tuple<T1, T2, T3> p) {
+  switch (I) {
+  case 0:
+    return p.m1;
+  case 1:
+    return p.m2;
+  case 2:
+    return p.m3;
+  default:
+    __builtin_trap();
+  }
+}
+
+} // namespace std
 
 struct A {
   int x;
@@ -54,16 +121,18 @@ int main() {
   char y{'z'};
   int z{10};
 
-  std::tuple<float, char, int> tpl(x, y, z);
+  std::mock_tuple<float, char, int> tpl{.m1 = x, .m2 = y, .m3 = z};
   auto [tx1, ty1, tz1] = tpl;
   auto &[tx2, ty2, tz2] = tpl;
 
+  auto [mp1, mp2] = MyPair{.m1 = 1, .m2 = 2};
+
   return a1.x + b1 + c1 + d1 + e1 + f1 + a2.y + b2 + c2 + d2 + e2 + f2 + a3.x +
          b3 + c3 + d3 + e3 + f3 + carr_copy1 + carr_copy2 + carr_copy3 +
          sarr_copy1 + sarr_copy2 + sarr_copy3 + iarr_copy1 + iarr_copy2 +
          iarr_copy3 + carr_ref1 + carr_ref2 + carr_ref3 + sarr_ref1 +
          sarr_ref2 + sarr_ref3 + iarr_ref1 + iarr_ref2 + iarr_ref3 +
          carr_rref1 + carr_rref2 + carr_rref3 + sarr_rref1 + sarr_rref2 +
          sarr_rref3 + iarr_rref1 + iarr_rref2 + iarr_rref3 + tx1 + ty1 + tz1 +
-         tx2 + ty2 + tz2; // break here
+         tx2 + ty2 + tz2 + mp1 + mp2; // break here
 }