SINGLE_FILE_BINARY_ENCODE: report a non-UTF-8 read clearly under ASSERTIONS

src/binaryDecode.js

@@ -2,7 +2,16 @@
 // Closure may analyze through the WASM_BINARY_DATA placeholder string into this
 // function, leading into incorrect results.
 /** @noinline */
+#if ASSERTIONS
+function binaryDecode(bin, expectedLength) {
+  // Each byte of the binary is one character of the string, so if the lengths
+  // differ, the file was not read as UTF-8 (for example a page without
+  // <meta charset="utf-8"> loading it from file://), and the bytes are wrong.
+  // Say so here, rather than let it fail as a confusing wasm CompileError.
+  assert(bin.length === expectedLength, `The embedded Wasm binary is ${bin.length} characters long, but should be ${expectedLength}: this file was not read as UTF-8 (SINGLE_FILE_BINARY_ENCODE). Serve it with charset=utf-8, add <meta charset="utf-8"> to the page, or build with -sSINGLE_FILE_BINARY_ENCODE=0`);
+#else
 function binaryDecode(bin) {
+#endif
   for (var i = 0, l = bin.length, o = new Uint8Array(l), c; i < l; ++i) {
     c = bin.charCodeAt(i);
     o[i] = ~c >> 8 & c; // Recover the null byte in a manner that is compatible with https://crbug.com/453961758

src/postamble_minimal.js

@@ -154,7 +154,11 @@ var instantiatePromise;
 #endif
 
 #if SINGLE_FILE && SINGLE_FILE_BINARY_ENCODE && !WASM2JS
+#if ASSERTIONS
+Module['wasm'] = binaryDecode("<<< WASM_BINARY_DATA >>>", "<<< WASM_BINARY_SIZE >>>");
+#else
 Module['wasm'] = binaryDecode("<<< WASM_BINARY_DATA >>>");
+#endif
 #elif SINGLE_FILE && WASM == 1 && !WASM2JS
 Module['wasm'] = base64Decode('<<< WASM_BINARY_DATA >>>');
 #endif

src/preamble.js

@@ -418,7 +418,11 @@ function getWasmBinary(file) {}
 
 function findWasmBinary() {
 #if SINGLE_FILE && SINGLE_FILE_BINARY_ENCODE && !WASM2JS
+#if ASSERTIONS
+  return binaryDecode("<<< WASM_BINARY_DATA >>>", "<<< WASM_BINARY_SIZE >>>");
+#else
   return binaryDecode("<<< WASM_BINARY_DATA >>>");
+#endif
 #elif SINGLE_FILE
   return base64Decode('<<< WASM_BINARY_DATA >>>');
 #elif AUDIO_WORKLET || !EXPORT_ES6 // For an Audio Worklet, we cannot use `new URL()`.

test/test_browser.py

@@ -4727,6 +4727,18 @@ def test_single_file_locate_file(self):
 
     self.run_browser('test.html', '/report_result?0')
 
+  # Tests that a SINGLE_FILE build loaded from a page whose charset is not UTF-8
+  # reports that, rather than failing to compile the mangled Wasm binary.
+  def test_single_file_not_utf8(self):
+    self.compile_btest('browser_test_hello_world.c', ['-o', 'test.js', '-sSINGLE_FILE', '-sASSERTIONS'])
+
+    create_file('test.html', '''
+      <meta charset="windows-1252">
+      <script src="test.js"></script>
+    ''')
+
+    self.run_browser('test.html', 'this file was not read as UTF-8')
+
   # Tests that SINGLE_FILE works as intended in a Worker in JS output
   def test_single_file_worker_js(self):
     self.btest_exit('browser_test_hello_world.c', cflags=['-sSINGLE_FILE'], run_in_worker=True)

test/test_other.py

@@ -9445,12 +9445,23 @@ def test_single_file_instantiate_failure(self):
     self.run_process([EMCC, test_file('hello_world.c'), '-sSINGLE_FILE', '-sASSERTIONS=1', '-o', 'out.js'])
     code = read_file('out.js')
     # Stub out binaryDecode so that it returns an invalid wasm binary.
-    code = code.replace('function binaryDecode(bin) {', 'function binaryDecode(bin) { return new Uint8Array([0]);')
+    code = code.replace('function binaryDecode(bin, expectedLength) {', 'function binaryDecode(bin, expectedLength) { return new Uint8Array([0]);')
     write_file('out_bad.js', code)
     out = self.run_js('out_bad.js', assert_returncode=1)
     self.assertContained('Aborted(CompileError', out)
     self.assertNotContained('startsWith is not a function', out)
 
+  def test_single_file_not_utf8(self):
+    # A SINGLE_FILE_BINARY_ENCODE build read in an encoding other than UTF-8
+    # (as a browser does from a page with no charset) gets a mangled Wasm
+    # binary. With ASSERTIONS it says so instead of failing to compile it.
+    self.run_process([EMCC, test_file('hello_world.c'), '-sSINGLE_FILE', '-sASSERTIONS', '-o', 'out.js'])
+    # Each byte read as one Latin-1 character, as a Windows-1252 read does.
+    write_file('out_latin1.js', read_binary('out.js').decode('latin-1'))
+    out = self.run_js('out_latin1.js', assert_returncode=1)
+    self.assertContained('this file was not read as UTF-8', out)
+    self.assertNotContained('CompileError', out)
+
   def test_single_file_disables_source_map(self):
     cmd = [EMCC, test_file('hello_world.c'), '-sSINGLE_FILE', '-gsource-map']
     stderr = self.run_process(cmd, stderr=PIPE).stderr

tools/link.py

@@ -2453,6 +2453,8 @@ def phase_binaryen(target, wasm_target):
 
     if settings.SINGLE_FILE_BINARY_ENCODE:
       js = do_replace(js, '"<<< WASM_BINARY_DATA >>>"', binary_encode(wasm_target))
+      if settings.ASSERTIONS:
+        js = do_replace(js, '"<<< WASM_BINARY_SIZE >>>"', str(os.path.getsize(wasm_target)))
     else:
       js = do_replace(js, '<<< WASM_BINARY_DATA >>>', base64_encode(wasm_target))
     delete_file(wasm_target)