Support cargo-driven wasm-bindgen linking

.circleci/config.yml

@@ -68,12 +68,18 @@ commands:
   install-rust:
     steps:
       - run:
-          name: install rust
+          name: install rust and wasm-bindgen
+          # rust and wasm-bindgen are always installed together so there is no
+          # CI environment with one but not the other. The wasm-bindgen-cli
+          # version is pinned to match the library the test crate depends on;
+          # wasm-bindgen requires the CLI and the library to be the exact same
+          # version.
           command: |
             curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y
             export PATH=${HOME}/.cargo/bin:${PATH}
             rustup target add wasm32-unknown-emscripten
             echo "export PATH=\"\$HOME/.cargo/bin:\$PATH\"" >> $BASH_ENV
+            cargo install wasm-bindgen-cli --version 0.2.126 --locked
   install-node-version:
     description: "install a specific version of node"
     parameters:

src/jsifier.mjs

@@ -934,6 +934,10 @@ var proxiedFunctionTable = [
       '//FORWARDED_DATA:' +
         JSON.stringify({
           librarySymbols,
+          // The final EXPORTED_FUNCTIONS set, including additions made by JS
+          // libraries (e.g. wasm-bindgen self-registering its exports), so the
+          // caller can re-derive which library symbols were exported.
+          exportedFunctions: Array.from(EXPORTED_FUNCTIONS),
           nativeAliases,
           warnings: warningOccured(),
           asyncFuncs,

src/postamble.js

@@ -242,7 +242,14 @@ function checkUnflushedContent() {
 #endif // EXIT_RUNTIME
 #endif // ASSERTIONS
 
+#if WASM_ESM_INTEGRATION
+// Provide the aggregate exports object for code that reaches the wasm exports by
+// name (e.g. wasm-bindgen's glue) via a namespace import. Emscripten's own named
+// imports are unaffected and remain tree-shakable.
+import * as wasmExports from './{{{ WASM_BINARY_FILE }}}';
+#else
 var wasmExports;
+#endif
 #if SPLIT_MODULE
 var wasmRawExports;
 #endif

test/rust/bindgen_greeter/.cargo/config.toml

@@ -0,0 +1,7 @@
+[build]
+target = "wasm32-unknown-emscripten"
+rustflags = [
+    "-Cllvm-args=-enable-emscripten-cxx-exceptions=0",
+    "-Cpanic=abort",
+    "-Crelocation-model=static",
+]

test/rust/bindgen_greeter/Cargo.toml

@@ -0,0 +1,10 @@
+[package]
+name = "bindgen_greeter"
+edition = "2021"
+
+[[bin]]
+name = "bindgen_greeter"
+path = "src/main.rs"
+
+[dependencies]
+wasm-bindgen = "=0.2.126"

test/rust/bindgen_greeter/src/main.rs

@@ -0,0 +1,23 @@
+use wasm_bindgen::prelude::*;
+
+#[wasm_bindgen]
+pub struct Greeter {
+    greeting: String,
+}
+
+#[wasm_bindgen]
+impl Greeter {
+    #[wasm_bindgen(constructor)]
+    pub fn new(greeting: String) -> Greeter {
+        Greeter { greeting }
+    }
+
+    pub fn greet(&self, name: String) -> String {
+        format!("{}, {}!", self.greeting, name)
+    }
+}
+
+fn main() {
+    // Matches the emscripten idiom: main runs automatically on init.
+    println!("main ran");
+}

test/test_other.py

@@ -271,6 +271,11 @@ def requires_rust(func):
   return requires_tool('cargo', 'RUST')(func)
 
 
+def requires_wasm_bindgen(func):
+  assert callable(func)
+  return requires_tool('wasm-bindgen', 'WASM_BINDGEN')(func)
+
+
 def requires_pkg_config(func):
   assert callable(func)
 
@@ -15014,9 +15019,12 @@ def test_rust_integration_basics(self):
     self.do_runf('main.cpp', 'Hello from rust!', cflags=[lib])
 
   @requires_rust
+  @requires_wasm_bindgen
   def test_wasm_bindgen_integration(self):
     copytree(test_file('rust/bindgen_integration'), '.')
-    self.run_process(['cargo', 'add', 'wasm-bindgen'])
+    # Pin the library to the (managed) wasm-bindgen-cli version on PATH;
+    # wasm-bindgen requires the CLI and the library to match exactly.
+    self.run_process(['cargo', 'add', 'wasm-bindgen@=0.2.126'])
     self.run_process(['cargo', 'build'])
     lib = 'target/wasm32-unknown-emscripten/debug/libbindgen_integration.a'
     self.assertExists(lib)
@@ -15026,9 +15034,53 @@ def test_wasm_bindgen_integration(self):
       Module.onRuntimeInitialized = () => out(Module.rs_add(17, 25));
     ''')
 
-    self.run_process(['cargo', 'install', 'wasm-bindgen-cli'])
     self.do_runf('empty.c', '42', cflags=[lib, '-sWASM_BINDGEN', '--post-js=post.js', '-lexports.js'])
 
+  # ESM-integration and factory (MODULARIZE) surface the clean wasm-bindgen API
+  # differently (named ESM exports vs `Module.<name>`). Both must expose exactly
+  # the `Greeter` class and none of the raw wasm exports rustc lists.
+  @requires_rust
+  @requires_wasm_bindgen
+  @parameterized({
+    'esm': (['-sWASM_ESM_INTEGRATION'], '''
+      import init, * as mod from './bindgen_greeter.js';
+      await init();
+    '''),
+    'factory': (['-sMODULARIZE', '-sEXPORT_ES6'], '''
+      import Module from './bindgen_greeter.js';
+      const mod = await Module();
+    '''),
+  })
+  def test_wasm_bindgen_rustc_driven(self, cflags, prelude):
+    # cargo/rustc links via emcc; the wasm carries wasm-bindgen's marker section,
+    # which emcc detects and runs wasm-bindgen against (no -sWASM_BINDGEN needed).
+    copytree(test_file('rust/bindgen_greeter'), '.')
+    # rustc invokes emcc as the linker; ensure it uses *this* emcc and pass the
+    # output-mode settings through.
+    with env_modify({'CARGO_TARGET_WASM32_UNKNOWN_EMSCRIPTEN_LINKER': EMCC,
+                     'EMCC_CFLAGS': ' '.join(cflags)}):
+      self.run_process(['cargo', 'build'])
+
+    # cargo copies only the .js and .wasm; the ESM support module and snippets
+    # stay in deps/, so run from there.
+    out_dir = 'target/wasm32-unknown-emscripten/debug/deps'
+    create_file(os.path.join(out_dir, 'run.mjs'), prelude + '''
+      const greeting = new mod.Greeter('Hello').greet('world');
+      if (greeting !== 'Hello, world!') throw new Error('unexpected greeting: ' + greeting);
+      // None of the raw wasm exports leak into the user-facing API.
+      for (const name of ['_main', 'greeter_greet', '_greeter_greet',
+                          '__wbindgen_malloc', '___wbindgen_malloc']) {
+        if (mod[name] !== undefined) throw new Error('leaked export: ' + name);
+      }
+      console.log(greeting);
+    ''')
+    self.node_args += ['--experimental-wasm-modules', '--no-warnings']
+    output = self.run_js(os.path.join(out_dir, 'run.mjs'))
+    self.assertContained('Hello, world!', output)
+    # `main` runs automatically on init (matching the emscripten C++ idiom),
+    # even though `_main` is not surfaced as a user-facing export.
+    self.assertContained('main ran', output)
+
   def test_relative_em_cache(self):
     with env_modify({'EM_CACHE': 'foo'}):
       self.assert_fail([EMCC, '-c', test_file('hello_world.c')], 'emcc: error: environment variable EM_CACHE must be an absolute path: foo')

tools/building.py

@@ -57,6 +57,10 @@
 _is_ar_cache: dict[str, bool] = {}
 # the exports the user requested
 user_requested_exports: set[str] = set()
+# JS library symbols that were exported (MODULARIZE=instance), derived from the
+# JS compiler's librarySymbols and EXPORTED_FUNCTIONS; the WASM_ESM_INTEGRATION
+# wrapper re-exports them.
+exported_js_library_symbols: set[str] = set()
 # A list of feature flags to pass to each binaryen invocation (like `wasm-opt`,
 # etc.). This is received by the first call to binaryen (e.g. `wasm-emscripten-finalize`)
 # which reads it using `--detect-features`.
@@ -1285,6 +1289,14 @@ def run_wasm_opt(infile, outfile=None, args=[], **kwargs):  # noqa
   return run_binaryen_command('wasm-opt', infile, outfile, args=args, **kwargs)
 
 
+def is_wasm_bindgen_module(wasm_file):
+  # wasm-bindgen marks modules built for the emscripten target with this custom
+  # section so emcc, when used as the linker (e.g. by cargo/rustc), knows to run
+  # wasm-bindgen as a post-link step.
+  with webassembly.Module(wasm_file) as module:
+    return module.get_custom_section('__wasm_bindgen_emscripten_marker') is not None
+
+
 def run_wasm_bindgen(infile):
   bindgen_out_dir = os.path.join(get_emscripten_temp_dir(), 'bindgen_out')
 
@@ -1299,16 +1311,33 @@ def run_wasm_bindgen(infile):
       '--out-dir',
       bindgen_out_dir,
   ]
+  exports_before = {e.name for e in webassembly.get_exports(infile)}
+
   check_call(cmd)
 
   # Don't try to predict the .wasm filename that wasm-bindgen outputs. Instead
   # just grab the .wasm file itself.
   all_output_files = os.listdir(bindgen_out_dir)
   new_wasm_file = [x for x in all_output_files if x.endswith('.wasm')][0]
+  new_wasm_path = os.path.join(bindgen_out_dir, new_wasm_file)
+
+  # Report which placeholder exports wasm-bindgen consumed so the caller can
+  # drop them from EXPORTED_FUNCTIONS.
+  removed_exports = exports_before - {e.name for e in webassembly.get_exports(new_wasm_path)}
+
+  shutil.copyfile(new_wasm_path, infile)
 
-  shutil.copyfile(os.path.join(bindgen_out_dir, new_wasm_file), infile)
+  # wasm-bindgen emits imported JS snippets into `snippets/` and the `import`
+  # statements referencing them into `library_bindgen.extern-pre.js`, only when
+  # the crate actually imports JS.
+  extern_pre_js = os.path.join(bindgen_out_dir, 'library_bindgen.extern-pre.js')
+  if not os.path.exists(extern_pre_js):
+    extern_pre_js = None
+  snippets_dir = os.path.join(bindgen_out_dir, 'snippets')
+  if not os.path.isdir(snippets_dir):
+    snippets_dir = None
 
-  return os.path.join(bindgen_out_dir, 'library_bindgen.js')
+  return os.path.join(bindgen_out_dir, 'library_bindgen.js'), removed_exports, extern_pre_js, snippets_dir
 
 
 intermediate_counter = 0

tools/emscripten.py

@@ -440,6 +440,13 @@ def emscript(in_wasm, out_wasm, outfile_js, js_syms, finalize=True, base_metadat
     pre += "}\n"
 
   report_missing_exports(forwarded_json['librarySymbols'])
+  # A JS library symbol is exported (MODULARIZE=instance) when it is in
+  # EXPORTED_FUNCTIONS; derive that set rather than tracking it separately. The
+  # forwarded EXPORTED_FUNCTIONS includes additions made by JS libraries (e.g.
+  # wasm-bindgen self-registering its exports).
+  exported_functions = set(forwarded_json['exportedFunctions'])
+  building.exported_js_library_symbols.update(
+    s for s in forwarded_json['librarySymbols'] if s in exported_functions)
 
   asm_const_pairs = ['%s: %s' % (key, value) for key, value in asm_consts]
   if asm_const_pairs or settings.MAIN_MODULE:
@@ -610,8 +617,14 @@ def finalize_wasm(infile, outfile, js_syms):
   unexpected_exports = [asmjs_mangle(e) for e in unexpected_exports]
   unexpected_exports = [e for e in unexpected_exports if e not in expected_exports]
 
+  # Marker-driven flow (rustc linked via emcc, no user -sWASM_BINDGEN): rustc's
+  # EXPORTED_FUNCTIONS is the raw wasm export set, not a user-chosen API. Treat
+  # it like a build with no exports specified - `main` still runs as the entry,
+  # but no raw wasm exports are surfaced.
+  marker_driven = settings.WASM_BINDGEN and 'WASM_BINDGEN' not in user_settings
+
   if (not settings.STANDALONE_WASM and 'main' in metadata.all_exports) or '__main_argc_argv' in metadata.all_exports:
-    if 'EXPORTED_FUNCTIONS' in user_settings and '_main' not in settings.USER_EXPORTS:
+    if not marker_driven and 'EXPORTED_FUNCTIONS' in user_settings and '_main' not in settings.USER_EXPORTS:
       # If `_main` was unexpectedly exported we assume it was added to
       # EXPORT_IF_DEFINED by `phase_linker_setup` in order that we can detect
       # it and report this warning.  After reporting the warning we explicitly
@@ -626,6 +639,11 @@ def finalize_wasm(infile, outfile, js_syms):
     else:
       unexpected_exports.append('_main')
 
+  # The user-facing API is exclusively wasm-bindgen's library symbols; the raw
+  # wasm exports are internal (including `_main`, which still runs via the entry).
+  if marker_driven:
+    unexpected_exports = []
+
   building.user_requested_exports.update(unexpected_exports)
   settings.EXPORTED_FUNCTIONS.extend(unexpected_exports)
 

tools/link.py

@@ -1903,9 +1903,39 @@ def phase_post_link(options, in_wasm, wasm_target, target, js_syms, base_metadat
 
   settings.TARGET_JS_NAME = os.path.basename(js_target)
 
+  # Two wasm-bindgen modes:
+  #  - C++-driven: user passes -sWASM_BINDGEN and owns EXPORTED_FUNCTIONS (the
+  #    staticlib flow); their exports are left untouched.
+  #  - marker-driven: user did *not* pass it, but cargo/rustc linked via emcc and
+  #    the wasm carries the marker section; rustc's EXPORTED_FUNCTIONS is the raw
+  #    wasm export set, not a user-facing API (see below).
+  marker_driven = 'WASM_BINDGEN' not in user_settings and building.is_wasm_bindgen_module(in_wasm)
+  if marker_driven:
+    settings.WASM_BINDGEN = 1
+
   if settings.WASM_BINDGEN:
-    bindgen_jslib = building.run_wasm_bindgen(in_wasm)
+    bindgen_jslib, removed_exports, extern_pre_js, snippets_dir = building.run_wasm_bindgen(in_wasm)
     settings.JS_LIBRARIES.append(bindgen_jslib)
+    # Drop the placeholder symbols wasm-bindgen consumed so they aren't reported
+    # as undefined exports.
+    removed = {shared.asmjs_mangle(e) for e in removed_exports}
+    settings.EXPORTED_FUNCTIONS = [e for e in settings.EXPORTED_FUNCTIONS if e not in removed]
+    settings.USER_EXPORTS = [e for e in settings.USER_EXPORTS if e not in removed]
+    building.user_requested_exports.difference_update(removed)
+    if marker_driven:
+      # rustc's exports are all wasm exports the glue reaches by name, not a
+      # user-facing API. Drop them from every user-export layer: the ESM wrapper
+      # (user_requested_exports) and the factory Module attachment
+      # (EXPORTED_FUNCTIONS, via should_export).
+      settings.EXPORTED_FUNCTIONS = [e for e in settings.EXPORTED_FUNCTIONS if e not in settings.USER_EXPORTS]
+      settings.USER_EXPORTS = []
+      building.user_requested_exports.clear()
+    # Imported JS: emit wasm-bindgen's `import` statements as extern-pre-js and
+    # place the snippet files alongside the output so relative imports resolve.
+    if extern_pre_js:
+      options.extern_pre_js.append(extern_pre_js)
+    if snippets_dir:
+      shutil.copytree(snippets_dir, os.path.join(os.path.dirname(js_target), 'snippets'), dirs_exist_ok=True)
 
   metadata = phase_emscript(in_wasm, wasm_target, js_syms, base_metadata)
 
@@ -2140,6 +2170,9 @@ def node_detection_code():
 
 def create_esm_wrapper(wrapper_file, support_target, wasm_target):
   js_exports = building.user_requested_exports.union(settings.EXPORTED_RUNTIME_METHODS)
+  # JS library symbols the support module exports at declaration (e.g.
+  # wasm-bindgen's); the wrapper must forward these too.
+  js_exports |= building.exported_js_library_symbols
   js_exports = ', '.join(sorted(js_exports))
 
   wrapper = []