module: resolve and instantiate loader pipeline hooks

This enables a --loader flag for Node, which can provide custom
"resolve" and "dynamicInstantiate" methods for custom ES module
loading.

In the process, module providers have been converted from classes
into functions and the module APIs have been made to pass URL strings
over objects.

PR-URL: #15445
Reviewed-By: Bradley Farias <bradley.meck@gmail.com>
Reviewed-By: James M Snell <jasnell@gmail.com>
Reviewed-By: Jeremiah Senkpiel <fishrock123@rocketmail.com>
Reviewed-By: Michaël Zasso <targos@protonmail.com>
Reviewed-By: Timothy Gu <timothygu99@gmail.com>

Author: guybedford

.eslintrc.yaml

@@ -11,7 +11,7 @@ parserOptions:
   ecmaVersion: 2017
 
 overrides:
-  - files: ["doc/api/esm.md", "*.mjs"]
+  - files: ["doc/api/esm.md", "*.mjs", "test/es-module/test-esm-example-loader.js"]
     parserOptions:
       sourceType: module
 
@@ -117,6 +117,7 @@ rules:
   keyword-spacing: error
   linebreak-style: [error, unix]
   max-len: [error, {code: 80,
+                ignorePattern: "^\/\/ Flags:",
                 ignoreRegExpLiterals: true,
                 ignoreUrls: true,
                 tabWidth: 2}]

doc/api/esm.md

@@ -98,4 +98,111 @@ fs.readFile('./foo.txt', (err, body) => {
 });
 ```
 
+## Loader hooks
+
+<!-- type=misc -->
+
+To customize the default module resolution, loader hooks can optionally be
+provided via a `--loader ./loader-name.mjs` argument to Node.
+
+When hooks are used they only apply to ES module loading and not to any
+CommonJS modules loaded.
+
+### Resolve hook
+
+The resolve hook returns the resolved file URL and module format for a
+given module specifier and parent file URL:
+
+```js
+import url from 'url';
+
+export async function resolve(specifier, parentModuleURL, defaultResolver) {
+  return {
+    url: new URL(specifier, parentModuleURL).href,
+    format: 'esm'
+  };
+}
+```
+
+The default NodeJS ES module resolution function is provided as a third
+argument to the resolver for easy compatibility workflows.
+
+In addition to returning the resolved file URL value, the resolve hook also
+returns a `format` property specifying the module format of the resolved
+module. This can be one of `"esm"`, `"cjs"`, `"json"`, `"builtin"` or
+`"addon"`.
+
+For example a dummy loader to load JavaScript restricted to browser resolution
+rules with only JS file extension and Node builtin modules support could
+be written:
+
+```js
+import url from 'url';
+import path from 'path';
+import process from 'process';
+
+const builtins = new Set(
+  Object.keys(process.binding('natives')).filter((str) =>
+    /^(?!(?:internal|node|v8)\/)/.test(str))
+);
+const JS_EXTENSIONS = new Set(['.js', '.mjs']);
+
+export function resolve(specifier, parentModuleURL/*, defaultResolve */) {
+  if (builtins.has(specifier)) {
+    return {
+      url: specifier,
+      format: 'builtin'
+    };
+  }
+  if (/^\.{0,2}[/]/.test(specifier) !== true && !specifier.startsWith('file:')) {
+    // For node_modules support:
+    // return defaultResolve(specifier, parentModuleURL);
+    throw new Error(
+      `imports must begin with '/', './', or '../'; '${specifier}' does not`);
+  }
+  const resolved = new url.URL(specifier, parentModuleURL);
+  const ext = path.extname(resolved.pathname);
+  if (!JS_EXTENSIONS.has(ext)) {
+    throw new Error(
+      `Cannot load file with non-JavaScript file extension ${ext}.`);
+  }
+  return {
+    url: resolved.href,
+    format: 'esm'
+  };
+}
+```
+
+With this loader, running:
+
+```
+NODE_OPTIONS='--experimental-modules --loader ./custom-loader.mjs' node x.js
+```
+
+would load the module `x.js` as an ES module with relative resolution support
+(with `node_modules` loading skipped in this example).
+
+### Dynamic instantiate hook
+
+To create a custom dynamic module that doesn't correspond to one of the
+existing `format` interpretations, the `dynamicInstantiate` hook can be used.
+This hook is called only for modules that return `format: "dynamic"` from
+the `resolve` hook.
+
+```js
+export async function dynamicInstantiate(url) {
+  return {
+    exports: ['customExportName'],
+    execute: (exports) => {
+      // get and set functions provided for pre-allocated export names
+      exports.customExportName.set('value');
+    }
+  };
+}
+```
+
+With the list of module exports provided upfront, the `execute` function will
+then be called at the exact point of module evalutation order for that module
+in the import tree.
+
 [Node.js EP for ES Modules]: https://github.com/nodejs/node-eps/blob/master/002-es-modules.md

lib/internal/errors.js

@@ -253,6 +253,8 @@ E('ERR_SOCKET_DGRAM_NOT_RUNNING', 'Not running');
 E('ERR_STDERR_CLOSE', 'process.stderr cannot be closed');
 E('ERR_STDOUT_CLOSE', 'process.stdout cannot be closed');
 E('ERR_UNKNOWN_BUILTIN_MODULE', (id) => `No such built-in module: ${id}`);
+E('ERR_UNKNOWN_FILE_EXTENSION', 'Unknown file extension: %s');
+E('ERR_UNKNOWN_MODULE_FORMAT', 'Unknown module format: %s');
 E('ERR_UNKNOWN_SIGNAL', (signal) => `Unknown signal: ${signal}`);
 E('ERR_UNKNOWN_STDIN_TYPE', 'Unknown stdin file type');
 E('ERR_UNKNOWN_STREAM_TYPE', 'Unknown stream file type');

lib/internal/loader/Loader.js

@@ -1,20 +1,21 @@
 'use strict';
 
-const { URL } = require('url');
 const { getURLFromFilePath } = require('internal/url');
 
 const {
-  getNamespaceOfModuleWrap
+  getNamespaceOfModuleWrap,
+  createDynamicModule
 } = require('internal/loader/ModuleWrap');
 
 const ModuleMap = require('internal/loader/ModuleMap');
 const ModuleJob = require('internal/loader/ModuleJob');
-const resolveRequestUrl = require('internal/loader/resolveRequestUrl');
+const ModuleRequest = require('internal/loader/ModuleRequest');
 const errors = require('internal/errors');
+const debug = require('util').debuglog('esm');
 
 function getBase() {
   try {
-    return getURLFromFilePath(`${process.cwd()}/`);
+    return getURLFromFilePath(`${process.cwd()}/`).href;
   } catch (e) {
     e.stack;
     // If the current working directory no longer exists.
@@ -28,45 +29,75 @@ function getBase() {
 class Loader {
   constructor(base = getBase()) {
     this.moduleMap = new ModuleMap();
-    if (typeof base !== 'undefined' && base instanceof URL !== true) {
-      throw new errors.TypeError('ERR_INVALID_ARG_TYPE', 'base', 'URL');
+    if (typeof base !== 'string') {
+      throw new errors.TypeError('ERR_INVALID_ARG_TYPE', 'base', 'string');
     }
     this.base = base;
+    this.resolver = ModuleRequest.resolve.bind(null);
+    this.dynamicInstantiate = undefined;
   }
 
-  async resolve(specifier) {
-    const request = resolveRequestUrl(this.base, specifier);
-    if (request.url.protocol !== 'file:') {
-      throw new errors.Error('ERR_INVALID_PROTOCOL',
-                             request.url.protocol, 'file:');
-    }
-    return request.url;
+  hook({ resolve = ModuleRequest.resolve, dynamicInstantiate }) {
+    this.resolver = resolve.bind(null);
+    this.dynamicInstantiate = dynamicInstantiate;
   }
 
-  async getModuleJob(dependentJob, specifier) {
-    if (!this.moduleMap.has(dependentJob.url)) {
-      throw new errors.Error('ERR_MISSING_MODULE', dependentJob.url);
+  async resolve(specifier, parentURL = this.base) {
+    if (typeof parentURL !== 'string') {
+      throw new errors.TypeError('ERR_INVALID_ARG_TYPE',
+                                 'parentURL', 'string');
+    }
+    const { url, format } = await this.resolver(specifier, parentURL,
+                                                ModuleRequest.resolve);
+
+    if (typeof format !== 'string') {
+      throw new errors.TypeError('ERR_INVALID_ARG_TYPE', 'format',
+                                 ['esm', 'cjs', 'builtin', 'addon', 'json']);
+    }
+    if (typeof url !== 'string') {
+      throw new errors.TypeError('ERR_INVALID_ARG_TYPE', 'url', 'string');
+    }
+
+    if (format === 'builtin') {
+      return { url: `node:${url}`, format };
     }
-    const request = await resolveRequestUrl(dependentJob.url, specifier);
-    const url = `${request.url}`;
-    if (this.moduleMap.has(url)) {
-      return this.moduleMap.get(url);
+
+    if (format !== 'dynamic') {
+      if (!ModuleRequest.loaders.has(format)) {
+        throw new errors.Error('ERR_UNKNOWN_MODULE_FORMAT', format);
+      }
+      if (!url.startsWith('file:')) {
+        throw new errors.Error('ERR_INVALID_PROTOCOL', url, 'file:');
+      }
     }
-    const dependencyJob = new ModuleJob(this, request);
-    this.moduleMap.set(url, dependencyJob);
-    return dependencyJob;
+
+    return { url, format };
   }
 
-  async import(specifier) {
-    const request = await resolveRequestUrl(this.base, specifier);
-    const url = `${request.url}`;
-    let job;
-    if (this.moduleMap.has(url)) {
-      job = this.moduleMap.get(url);
-    } else {
-      job = new ModuleJob(this, request);
+  async getModuleJob(specifier, parentURL = this.base) {
+    const { url, format } = await this.resolve(specifier, parentURL);
+    let job = this.moduleMap.get(url);
+    if (job === undefined) {
+      let loaderInstance;
+      if (format === 'dynamic') {
+        loaderInstance = async (url) => {
+          const { exports, execute } = await this.dynamicInstantiate(url);
+          return createDynamicModule(exports, url, (reflect) => {
+            debug(`Loading custom loader ${url}`);
+            execute(reflect.exports);
+          });
+        };
+      } else {
+        loaderInstance = ModuleRequest.loaders.get(format);
+      }
+      job = new ModuleJob(this, url, loaderInstance);
       this.moduleMap.set(url, job);
     }
+    return job;
+  }
+
+  async import(specifier, parentURL = this.base) {
+    const job = await this.getModuleJob(specifier, parentURL);
     const module = await job.run();
     return getNamespaceOfModuleWrap(module);
   }

lib/internal/loader/ModuleJob.js

@@ -2,51 +2,40 @@
 
 const { SafeSet, SafePromise } = require('internal/safe_globals');
 const resolvedPromise = SafePromise.resolve();
-const resolvedArrayPromise = SafePromise.resolve([]);
-const { ModuleWrap } = require('internal/loader/ModuleWrap');
 
-const NOOP = () => { /* No-op */ };
 class ModuleJob {
   /**
    * @param {module: ModuleWrap?, compiled: Promise} moduleProvider
    */
-  constructor(loader, moduleProvider, url) {
-    this.url = `${moduleProvider.url}`;
-    this.moduleProvider = moduleProvider;
+  constructor(loader, url, moduleProvider) {
     this.loader = loader;
     this.error = null;
     this.hadError = false;
 
-    if (moduleProvider instanceof ModuleWrap !== true) {
-      // linked == promise for dependency jobs, with module populated,
-      // module wrapper linked
-      this.modulePromise = this.moduleProvider.createModule();
-      this.module = undefined;
-      const linked = async () => {
-        const dependencyJobs = [];
-        this.module = await this.modulePromise;
-        this.module.link(async (dependencySpecifier) => {
-          const dependencyJobPromise =
-            this.loader.getModuleJob(this, dependencySpecifier);
-          dependencyJobs.push(dependencyJobPromise);
-          const dependencyJob = await dependencyJobPromise;
-          return dependencyJob.modulePromise;
-        });
-        return SafePromise.all(dependencyJobs);
-      };
-      this.linked = linked();
+    // linked == promise for dependency jobs, with module populated,
+    // module wrapper linked
+    this.moduleProvider = moduleProvider;
+    this.modulePromise = this.moduleProvider(url);
+    this.module = undefined;
+    this.reflect = undefined;
+    const linked = async () => {
+      const dependencyJobs = [];
+      ({ module: this.module,
+         reflect: this.reflect } = await this.modulePromise);
+      this.module.link(async (dependencySpecifier) => {
+        const dependencyJobPromise =
+            this.loader.getModuleJob(dependencySpecifier, url);
+        dependencyJobs.push(dependencyJobPromise);
+        const dependencyJob = await dependencyJobPromise;
+        return (await dependencyJob.modulePromise).module;
+      });
+      return SafePromise.all(dependencyJobs);
+    };
+    this.linked = linked();
 
-      // instantiated == deep dependency jobs wrappers instantiated,
-      //module wrapper instantiated
-      this.instantiated = undefined;
-    } else {
-      const getModuleProvider = async () => moduleProvider;
-      this.modulePromise = getModuleProvider();
-      this.moduleProvider = { finish: NOOP };
-      this.module = moduleProvider;
-      this.linked = resolvedArrayPromise;
-      this.instantiated = this.modulePromise;
-    }
+    // instantiated == deep dependency jobs wrappers instantiated,
+    // module wrapper instantiated
+    this.instantiated = undefined;
   }
 
   instantiate() {