[clang] 6fa1795 - [clang][Interp] Implement String- and CharacterLiterals

[Timm Bäder via cfe-commits]

Author: Timm Bäder
Date: 2022-10-28T12:49:38+02:00
New Revision: 6fa1795d1fd4770f9f5c00f5a30937d68c3feb17

URL: https://github.com/llvm/llvm-project/commit/6fa1795d1fd4770f9f5c00f5a30937d68c3feb17
DIFF: https://github.com/llvm/llvm-project/commit/6fa1795d1fd4770f9f5c00f5a30937d68c3feb17.diff

LOG: [clang][Interp] Implement String- and CharacterLiterals

Differential Revision: https://reviews.llvm.org/D135366

Added: 
    

Modified: 
    clang/lib/AST/Interp/ByteCodeExprGen.cpp
    clang/lib/AST/Interp/ByteCodeExprGen.h
    clang/test/AST/Interp/literals.cpp
    clang/test/Lexer/char-escapes.c

Removed: 
    


################################################################################
diff  --git a/clang/lib/AST/Interp/ByteCodeExprGen.cpp b/clang/lib/AST/Interp/ByteCodeExprGen.cpp
index 9472f1aed9178..7e00fc4f707e9 100644
--- a/clang/lib/AST/Interp/ByteCodeExprGen.cpp
+++ b/clang/lib/AST/Interp/ByteCodeExprGen.cpp
@@ -397,6 +397,18 @@ bool ByteCodeExprGen<Emitter>::VisitAbstractConditionalOperator(
   return true;
 }
 
+template <class Emitter>
+bool ByteCodeExprGen<Emitter>::VisitStringLiteral(const StringLiteral *E) {
+  unsigned StringIndex = P.createGlobalString(E);
+  return this->emitGetPtrGlobal(StringIndex, E);
+}
+
+template <class Emitter>
+bool ByteCodeExprGen<Emitter>::VisitCharacterLiteral(
+    const CharacterLiteral *E) {
+  return this->emitConst(E, E->getValue());
+}
+
 template <class Emitter> bool ByteCodeExprGen<Emitter>::discard(const Expr *E) {
   OptionScope<Emitter> Scope(this, /*NewDiscardResult=*/true);
   return this->Visit(E);

diff  --git a/clang/lib/AST/Interp/ByteCodeExprGen.h b/clang/lib/AST/Interp/ByteCodeExprGen.h
index a254a1baee8f9..1759d17d3288f 100644
--- a/clang/lib/AST/Interp/ByteCodeExprGen.h
+++ b/clang/lib/AST/Interp/ByteCodeExprGen.h
@@ -83,6 +83,8 @@ class ByteCodeExprGen : public ConstStmtVisitor<ByteCodeExprGen<Emitter>, bool>,
   bool VisitArrayInitIndexExpr(const ArrayInitIndexExpr *E);
   bool VisitOpaqueValueExpr(const OpaqueValueExpr *E);
   bool VisitAbstractConditionalOperator(const AbstractConditionalOperator *E);
+  bool VisitStringLiteral(const StringLiteral *E);
+  bool VisitCharacterLiteral(const CharacterLiteral *E);
 
 protected:
   bool visitExpr(const Expr *E) override;

diff  --git a/clang/test/AST/Interp/literals.cpp b/clang/test/AST/Interp/literals.cpp
index f0083e63f35d9..ca76be9b0bf94 100644
--- a/clang/test/AST/Interp/literals.cpp
+++ b/clang/test/AST/Interp/literals.cpp
@@ -278,3 +278,46 @@ namespace bitOr {
   static_assert((0 | gimme(12)) == 12, "");
   static_assert((12 | true) == 13, "");
 };
+
+namespace strings {
+  constexpr const char *S = "abc";
+  static_assert(S[0] == 97, "");
+  static_assert(S[1] == 98, "");
+  static_assert(S[2] == 99, "");
+  static_assert(S[3] == 0, "");
+
+  static_assert("foobar"[2] == 'o', "");
+  static_assert(2["foobar"] == 'o', "");
+
+  constexpr const wchar_t *wide = L"bar";
+  static_assert(wide[0] == L'b', "");
+
+  constexpr const char32_t *u32 = U"abc";
+  static_assert(u32[1] == U'b', "");
+
+  constexpr char32_t c = U'\U0001F60E';
+  static_assert(c == 0x0001F60EL, "");
+
+  constexpr char k = -1;
+  static_assert(k == -1, "");
+
+  static_assert('\N{LATIN CAPITAL LETTER E}' == 'E', "");
+  static_assert('\t' == 9, "");
+
+#pragma clang diagnostic push
+#pragma clang diagnostic ignored "-Wmultichar"
+  constexpr int mc = 'abc';
+  static_assert(mc == 'abc', "");
+  __WCHAR_TYPE__ wm = L'abc'; // ref-error{{wide character literals may not contain multiple characters}} \
+                              // expected-error{{wide character literals may not contain multiple characters}}
+  __WCHAR_TYPE__ wu = u'abc'; // ref-error{{Unicode character literals may not contain multiple characters}} \
+                              // expected-error{{Unicode character literals may not contain multiple characters}}
+  __WCHAR_TYPE__ wU = U'abc'; // ref-error{{Unicode character literals may not contain multiple characters}} \
+                              // expected-error{{Unicode character literals may not contain multiple characters}}
+#if __cplusplus > 201103L
+  __WCHAR_TYPE__ wu8 = u8'abc'; // ref-error{{Unicode character literals may not contain multiple characters}} \
+                                // expected-error{{Unicode character literals may not contain multiple characters}}
+#endif
+
+#pragma clang diagnostic pop
+};

diff  --git a/clang/test/Lexer/char-escapes.c b/clang/test/Lexer/char-escapes.c
index 32a1c6140d53c..11e25a6d251fe 100644
--- a/clang/test/Lexer/char-escapes.c
+++ b/clang/test/Lexer/char-escapes.c
@@ -1,4 +1,5 @@
 // RUN: %clang_cc1 -fsyntax-only -pedantic -verify %s
+// RUN: %clang_cc1 -fsyntax-only -pedantic -fexperimental-new-constant-interpreter -verify %s
 
 int test['\\' == 92 ? 1 : -1];
 int test['\"' == 34 ? 1 : -1];