process: allow StartExecution() to take a main script ID

The idea is to allow the C++ layer to run arbitrary scripts
as the main script. This paves the way for

- cctest of the execution of Node.js instances
- Earlier handling of per-process CLI options that affect
  execution modes (those usually do not make sense for the
  embedders).
- Targets like mkcodecache or mksnapshot.

Also moves the handling of `_third_party_main.js` into C++.

PR-URL: https://github.com/nodejs/node/pull/25474
Reviewed-By: Anna Henningsen <anna@addaleax.net>
Reviewed-By: Minwoo Jung <minwoo@nodesource.com>

5 files changed, 46 insertions, 6 deletions

diff --git a/src/node.cc b/src/node.cc
index 7a585646f6..0f66847244 100644
--- a/src/node.cc
+++ b/src/node.cc
@@ -647,7 +647,28 @@ static MaybeLocal<Value> ExecuteBootstrapper(
 
 void LoadEnvironment(Environment* env) {
   RunBootstrapping(env);
-  StartExecution(env);
+
+  // To allow people to extend Node in different ways, this hook allows
+  // one to drop a file lib/_third_party_main.js into the build
+  // directory which will be executed instead of Node's normal loading.
+  if (per_process::native_module_loader.Exists("_third_party_main")) {
+    StartExecution(env, "_third_party_main");
+  } else {
+    // TODO(joyeecheung): create different scripts for different
+    // execution modes:
+    // - `main_thread_main.js` when env->is_main_thread()
+    // - `worker_thread_main.js` when !env->is_main_thread()
+    // - `run_third_party_main.js` for `_third_party_main`
+    // - `inspect_main.js` for `node inspect`
+    // - `mkcodecache_main.js` for the code cache generator
+    // - `print_help_main.js` for --help
+    // - `bash_completion_main.js` for --completion-bash
+    // - `internal/v8_prof_processor` for --prof-process
+    // And leave bootstrap/node.js dedicated to the setup of the environment.
+    // We may want to move this switch out of LoadEnvironment, especially for
+    // the per-process options.
+    StartExecution(env, nullptr);
+  }
 }
 
 void RunBootstrapping(Environment* env) {
@@ -724,7 +745,7 @@ void RunBootstrapping(Environment* env) {
     env->set_start_execution_function(start_execution.As<Function>());
 }
 
-void StartExecution(Environment* env) {
+void StartExecution(Environment* env, const char* main_script_id) {
   HandleScope handle_scope(env->isolate());
   // We have to use Local<>::New because of the optimized way in which we access
   // the object in the env->...() getters, which does not play well with
@@ -734,8 +755,19 @@ void StartExecution(Environment* env) {
   env->set_start_execution_function(Local<Function>());
 
   if (start_execution.IsEmpty()) return;
+
+  Local<Value> main_script_v;
+  if (main_script_id == nullptr) {
+    // TODO(joyeecheung): make this mandatory - we may also create an overload
+    // for main_script that is a Local<Function>.
+    main_script_v = Undefined(env->isolate());
+  } else {
+    main_script_v = OneByteString(env->isolate(), main_script_id);
+  }
+
+  Local<Value> argv[] = {main_script_v};
   USE(start_execution->Call(
-      env->context(), Undefined(env->isolate()), 0, nullptr));
+      env->context(), Undefined(env->isolate()), arraysize(argv), argv));
 }
 
 static void StartInspector(Environment* env, const char* path) {
diff --git a/src/node_internals.h b/src/node_internals.h
index 5dd0593f41..70c82dd2fc 100644
--- a/src/node_internals.h
+++ b/src/node_internals.h
@@ -369,7 +369,7 @@ bool SafeGetenv(const char* key, std::string* text);
 void DefineZlibConstants(v8::Local<v8::Object> target);
 
 void RunBootstrapping(Environment* env);
-void StartExecution(Environment* env);
+void StartExecution(Environment* env, const char* main_script_id);
 
 }  // namespace node
 
diff --git a/src/node_native_module.cc b/src/node_native_module.cc
index 1b1a5e8ec1..00775885d6 100644
--- a/src/node_native_module.cc
+++ b/src/node_native_module.cc
@@ -61,6 +61,10 @@ Local<Set> ToJsSet(Local<Context> context,
   return out;
 }
 
+bool NativeModuleLoader::Exists(const char* id) {
+  return source_.find(id) != source_.end();
+}
+
 void NativeModuleLoader::GetCacheUsage(
     const FunctionCallbackInfo<Value>& args) {
   Environment* env = Environment::GetCurrent(args);
diff --git a/src/node_native_module.h b/src/node_native_module.h
index 9a0afcc0b9..62c417a0b6 100644
--- a/src/node_native_module.h
+++ b/src/node_native_module.h
@@ -54,6 +54,8 @@ class NativeModuleLoader {
       std::vector<v8::Local<v8::Value>>* arguments,
       Environment* optional_env);
 
+  bool Exists(const char* id);
+
  private:
   static void GetCacheUsage(const v8::FunctionCallbackInfo<v8::Value>& args);
   // Passing ids of builtin module source code into JS land as
diff --git a/src/node_worker.cc b/src/node_worker.cc
index 65d3b7297c..dab7945aae 100644
--- a/src/node_worker.cc
+++ b/src/node_worker.cc
@@ -185,8 +185,10 @@ void Worker::Run() {
         HandleScope handle_scope(isolate_);
         Environment::AsyncCallbackScope callback_scope(env_.get());
         env_->async_hooks()->push_async_ids(1, 0);
-        // This loads the Node bootstrapping code.
-        LoadEnvironment(env_.get());
+        RunBootstrapping(env_.get());
+        // TODO(joyeecheung): create a main script for worker threads
+        // that starts listening on the message port.
+        StartExecution(env_.get(), nullptr);
         env_->async_hooks()->pop_async_id(1);
 
         Debug(this, "Loaded environment for worker %llu", thread_id_);