From 6c07a328e5ce0e1ac187a55d07faf6be642774a5 Mon Sep 17 00:00:00 2001
From: Thomas Lively <tlively@google.com>
Date: Mon, 16 Sep 2024 15:42:28 -0700
Subject: Require string-style identifiers to be UTF-8 (#6941)

In the WebAssembly text format, strings can generally be arbitrary
bytes, but identifiers must be valid UTF-8. Check for UTF-8 validity
when parsing string-style identifiers in the lexer.

Update StringLowering to generate valid UTF-8 global names even for
strings that may not be valid UTF-8 and test that text round tripping
works correctly after StringLowering.

Fixes #6937.
---
 src/parser/lexer.cpp          | 10 ++++++++++
 src/passes/StringLowering.cpp |  7 +++++--
 2 files changed, 15 insertions(+), 2 deletions(-)

(limited to 'src')

diff --git a/src/parser/lexer.cpp b/src/parser/lexer.cpp
index bb6428e87..44aecdc2b 100644
--- a/src/parser/lexer.cpp
+++ b/src/parser/lexer.cpp
@@ -280,6 +280,13 @@ struct LexStrResult : LexResult {
   // Allocate a string only if there are escape sequences, otherwise just use
   // the original string_view.
   std::optional<std::string> str;
+
+  std::string_view getStr() {
+    if (str) {
+      return *str;
+    }
+    return span;
+  }
 };
 
 struct LexStrCtx : LexCtx {
@@ -860,6 +867,9 @@ std::optional<LexIdResult> ident(std::string_view in) {
     return {};
   }
   if (auto s = str(ctx.next())) {
+    if (!String::isUTF8(s->getStr())) {
+      return {};
+    }
     ctx.isStr = true;
     ctx.str = s->str;
     ctx.take(*s);
diff --git a/src/passes/StringLowering.cpp b/src/passes/StringLowering.cpp
index 349ba8cd0..081db6068 100644
--- a/src/passes/StringLowering.cpp
+++ b/src/passes/StringLowering.cpp
@@ -153,9 +153,12 @@ struct StringGathering : public Pass {
       [[maybe_unused]] bool valid =
         String::convertWTF16ToWTF8(wtf8, string.str);
       assert(valid);
-      // TODO: Use wtf8.view() once we have C++20.
+      // Then escape it because identifiers must be valid UTF-8.
+      // TODO: Use wtf8.view() and escaped.view() once we have C++20.
+      std::stringstream escaped;
+      String::printEscaped(escaped, wtf8.str());
       auto name = Names::getValidGlobalName(
-        *module, std::string("string.const_") + std::string(wtf8.str()));
+        *module, std::string("string.const_") + std::string(escaped.str()));
       globalName = name;
       newNames.insert(name);
       auto* stringConst = builder.makeStringConst(string);
-- 
cgit v1.2.3