3 files changed, 39 insertions, 8 deletions
diff --git a/src/wasm/literal.cpp b/src/wasm/literal.cpp
index 7c674ffc5..afdc14c72 100644
--- a/src/wasm/literal.cpp
+++ b/src/wasm/literal.cpp
@@ -23,6 +23,7 @@
 #include "ir/bits.h"
 #include "pretty_printing.h"
 #include "support/bits.h"
+#include "support/string.h"
 #include "support/utilities.h"
 
 namespace wasm {
@@ -77,12 +78,15 @@ Literal::Literal(std::shared_ptr<GCData> gcData, HeapType type)
          (type.isBottom() && !gcData));
 }
 
-Literal::Literal(std::string string)
+Literal::Literal(std::string_view string)
   : gcData(nullptr), type(Type(HeapType::string, NonNullable)) {
   // TODO: we could in theory internalize strings
+  // Extract individual WTF-16LE code units.
   Literals contents;
-  for (auto c : string) {
-    contents.push_back(Literal(int32_t(c)));
+  assert(string.size() % 2 == 0);
+  for (size_t i = 0; i < string.size(); i += 2) {
+    int32_t u = uint8_t(string[i]) | (uint8_t(string[i + 1]) << 8);
+    contents.push_back(Literal(u));
   }
   gcData = std::make_shared<GCData>(HeapType::string, contents);
 }
@@ -636,10 +640,19 @@ std::ostream& operator<<(std::ostream& o, Literal literal) {
             o << "nullstring";
           } else {
             o << "string(\"";
+            // Convert WTF-16 literals to WTF-16 string.
+            std::stringstream wtf16;
             for (auto c : data->values) {
-              // TODO: more than ascii
-              o << char(c.getInteger());
+              auto u = c.getInteger();
+              assert(u < 0x10000);
+              wtf16 << uint8_t(u & 0xFF);
+              wtf16 << uint8_t(u >> 8);
             }
+            // Convert to WTF-8 for printing.
+            // TODO: Use wtf16.view() once we have C++20.
+            [[maybe_unused]] bool valid =
+              String::convertWTF16ToWTF8(o, wtf16.str());
+            assert(valid);
             o << "\")";
           }
           break;
diff --git a/src/wasm/wasm-binary.cpp b/src/wasm/wasm-binary.cpp
index 55cdd726c..f9a643d66 100644
--- a/src/wasm/wasm-binary.cpp
+++ b/src/wasm/wasm-binary.cpp
@@ -23,6 +23,7 @@
 #include "ir/type-updating.h"
 #include "support/bits.h"
 #include "support/debug.h"
+#include "support/string.h"
 #include "wasm-binary.h"
 #include "wasm-debug.h"
 #include "wasm-stack.h"
@@ -527,7 +528,12 @@ void WasmBinaryWriter::writeStrings() {
   // The number of strings and then their contents.
   o << U32LEB(num);
   for (auto& string : sorted) {
-    writeInlineString(string.str);
+    // Re-encode from WTF-16 to WTF-8.
+    std::stringstream wtf8;
+    [[maybe_unused]] bool valid = String::convertWTF16ToWTF8(wtf8, string.str);
+    assert(valid);
+    // TODO: Use wtf8.view() once we have C++20.
+    writeInlineString(wtf8.str());
   }
 
   finishSection(start);
@@ -2960,7 +2966,13 @@ void WasmBinaryReader::readStrings() {
   size_t num = getU32LEB();
   for (size_t i = 0; i < num; i++) {
     auto string = getInlineString();
-    strings.push_back(string);
+    // Re-encode from WTF-8 to WTF-16.
+    std::stringstream wtf16;
+    if (!String::convertWTF8ToWTF16(wtf16, string.str)) {
+      throwError("invalid string constant");
+    }
+    // TODO: Use wtf16.view() once we have C++20.
+    strings.push_back(wtf16.str());
   }
 }
 
diff --git a/src/wasm/wasm-s-parser.cpp b/src/wasm/wasm-s-parser.cpp
index 2d4f3fffe..d6df7ab0f 100644
--- a/src/wasm/wasm-s-parser.cpp
+++ b/src/wasm/wasm-s-parser.cpp
@@ -3335,7 +3335,13 @@ Expression* SExpressionWasmBuilder::makeStringConst(Element& s) {
   std::vector<char> data;
   stringToBinary(*s[1], s[1]->str().str, data);
   Name str = std::string_view(data.data(), data.size());
-  return Builder(wasm).makeStringConst(str);
+  // Re-encode from WTF-8 to WTF-16.
+  std::stringstream wtf16;
+  if (!String::convertWTF8ToWTF16(wtf16, str.str)) {
+    throw SParseException("invalid string constant", s);
+  }
+  // TODO: Use wtf16.view() once we have C++20.
+  return Builder(wasm).makeStringConst(wtf16.str());
 }
 
 Expression* SExpressionWasmBuilder::makeStringMeasure(Element& s,