src: add support for externally shared js builtins

Refs: nodejs#44000

- add infra to support externally shared js builtins in
  support of distos that want to externalize deps that
  include JS/WASM instead of native code
- add support for externalizing
  - cjs_module_lexer/lexer
  - cjs_module_lexer/dist/lexer
  - undici/undici

Signed-off-by: Michael Dawson <[email protected]>

Author: mhdawson

configure.py

@@ -57,6 +57,11 @@
 with open ('tools/icu/icu_versions.json') as f:
   icu_versions = json.load(f)
 
+sharable_builtins = {'cjs_module_lexer/lexer': 'deps/cjs-module-lexer/lexer.js',
+                     'cjs_module_lexer/dist/lexer': 'deps/cjs-module-lexer/dist/lexer.js',
+                     'undici/undici': 'deps/undici/undici.js'
+}
+
 # create option groups
 shared_optgroup = parser.add_argument_group("Shared libraries",
     "Flags that allows you to control whether you want to build against "
@@ -70,6 +75,9 @@
     "library you want to build against.")
 http2_optgroup = parser.add_argument_group("HTTP2",
     "Flags that allows you to control HTTP2 features in Node.js")
+shared_builtin_optgroup = parser.add_argument_group("Shared builtins",
+    "Flags that allows you to control whether you want to build against "
+    "internal builtins or shared files.")
 
 # Options should be in alphabetical order but keep --prefix at the top,
 # that's arguably the one people will be looking for most.
@@ -422,6 +430,16 @@
 
 parser.add_argument_group(shared_optgroup)
 
+for builtin in sharable_builtins:
+  builtin_id = 'shared_builtin_' + builtin + '_path'
+  shared_builtin_optgroup.add_argument('--shared-builtin-' + builtin + '-path',
+    action='store',
+    dest='node_shared_builtin_' + builtin.replace('/', '_') + '_path',
+    help='Path to shared file for ' + builtin + ' builtin. '
+         'Will be used instead of bundled version at runtime')
+
+parser.add_argument_group(shared_builtin_optgroup)
+
 static_optgroup.add_argument('--static-zoslib-gyp',
     action='store',
     dest='static_zoslib_gyp',
@@ -1400,7 +1418,6 @@ def configure_library(lib, output, pkgname=None):
     elif pkg_libs:
       output['libraries'] += pkg_libs.split()
 
-
 def configure_v8(o):
   o['variables']['v8_enable_webassembly'] = 1
   o['variables']['v8_enable_javascript_promise_hooks'] = 1
@@ -1951,6 +1968,15 @@ def make_bin_override():
 configure_inspector(output)
 configure_section_file(output)
 
+# configure sharable builtins
+output['variables']['node_builtin_sharable_builtins'] = []
+for builtin in sharable_builtins:
+  builtin_id = 'node_shared_builtin_' + builtin.replace('/', '_') + '_path'
+  if getattr(options, builtin_id):
+    output['defines'] += [builtin_id.upper() + '=' + getattr(options, builtin_id)]
+  else:
+    output['variables']['node_builtin_sharable_builtins'] += [sharable_builtins[builtin]]
+
 # Forward OSS-Fuzz settings
 output['variables']['ossfuzz'] = b(options.ossfuzz)
 

node.gyp

@@ -48,9 +48,7 @@
       'deps/v8/tools/tickprocessor-driver.mjs',
       'deps/acorn/acorn/dist/acorn.js',
       'deps/acorn/acorn-walk/dist/walk.js',
-      'deps/cjs-module-lexer/lexer.js',
-      'deps/cjs-module-lexer/dist/lexer.js',
-      'deps/undici/undici.js',
+      '<@(node_builtin_sharable_builtins)',
     ],
     'node_mksnapshot_exec': '<(PRODUCT_DIR)/<(EXECUTABLE_PREFIX)node_mksnapshot<(EXECUTABLE_SUFFIX)',
     'conditions': [

src/node_builtins.cc

@@ -190,18 +190,47 @@ static std::string OnDiskFileName(const char* id) {
 
 MaybeLocal<String> BuiltinLoader::LoadBuiltinSource(Isolate* isolate,
                                                     const char* id) {
+  std::string filename;
+#ifdef NODE_SHARED_BUILTIN_CJS_MODULE_LEXER_LEXER_PATH
+  #define NODE_CHECK_FILE_NAME
+  if (strncmp(id, "cjs_module_lexer/lexer", strlen(id)) == 0 ) {
+    filename = STRINGIFY(NODE_SHARED_BUILTIN_CJS_MODULE_LEXER_LEXER_PATH);
+  }
+#endif  // NODE_SHARED_BUILTIN_CJS_MODULE_LEXER_LEXER_PATH
+
+#ifdef NODE_SHARED_BUILTIN_CJS_MODULE_LEXER_DIST_LEXER_PATH
+  #define NODE_CHECK_FILE_NAME
+  if (strncmp(id, "cjs_module_lexer/dist/lexer", strlen(id)) == 0 ) {
+    filename = STRINGIFY(NODE_SHARED_BUILTIN_CJS_MODULE_LEXER_DIST_LEXER_PATH);
+  }
+#endif  // NODE_SHARED_BUILTIN_CJS_MODULE_LEXER_DIST_LEXER_PATH
+
+#ifdef NODE_SHARED_BUILTIN_UNDICI_UNDICI_PATH
+  #define NODE_CHECK_FILE_NAME
+  if (strncmp(id, "undici/undici", strlen(id)) == 0 ) {
+    filename = STRINGIFY(NODE_SHARED_BUILTIN_CJS_MODULE_LEXER_DIST_LEXER_PATH);
+  }
+#endif  // NODE_SHARED_BUILTIN_UNDICI_UNDICI_PATH
+
+#ifdef NODE_CHECK_FILE_NAME
+  if (filename.empty()) {
+#endif  // NODE_CHECK_FILE_NAME
 #ifdef NODE_BUILTIN_MODULES_PATH
-  if (strncmp(id, "embedder_main_", strlen("embedder_main_")) == 0) {
+    if (strncmp(id, "embedder_main_", strlen("embedder_main_")) == 0) {
 #endif  // NODE_BUILTIN_MODULES_PATH
-    const auto source_it = source_.find(id);
-    if (UNLIKELY(source_it == source_.end())) {
-      fprintf(stderr, "Cannot find native builtin: \"%s\".\n", id);
-      ABORT();
-    }
-    return source_it->second.ToStringChecked(isolate);
+      const auto source_it = source_.find(id);
+      if (UNLIKELY(source_it == source_.end())) {
+        fprintf(stderr, "Cannot find native builtin: \"%s\".\n", id);
+        ABORT();
+      }
+      return source_it->second.ToStringChecked(isolate);
 #ifdef NODE_BUILTIN_MODULES_PATH
+    }
+    filename = OnDiskFileName(id);
+#endif  // NODE_BUILTIN_MODULES_PATH
+#ifdef NODE_CHECK_FILE_NAME
   }
-  std::string filename = OnDiskFileName(id);
+#endif  // NODE_CHECK_FILE_NAME
 
   std::string contents;
   int r = ReadFileSync(&contents, filename.c_str());
@@ -216,7 +245,6 @@ MaybeLocal<String> BuiltinLoader::LoadBuiltinSource(Isolate* isolate,
   }
   return String::NewFromUtf8(
       isolate, contents.c_str(), v8::NewStringType::kNormal, contents.length());
-#endif  // NODE_BUILTIN_MODULES_PATH
 }
 
 // Returns Local<Function> of the compiled module if return_code_cache