Add command to the CLI to validate the collection metadata file (#1134)

Author: Ndpnt

CHANGELOG.md

@@ -2,6 +2,14 @@
 
 All changes that impact users of this module are documented in this file, in the [Common Changelog](https://common-changelog.org) format with some additional specifications defined in the CONTRIBUTING file. This codebase adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## Unreleased [minor]
+
+> Development of this release was supported by the [French Ministry for Foreign Affairs](https://www.diplomatie.gouv.fr/fr/politique-etrangere-de-la-france/diplomatie-numerique/) through its ministerial [State Startups incubator](https://beta.gouv.fr/startups/open-terms-archive.html) under the aegis of the Ambassador for Digital Affairs.
+
+### Added
+
+- Add `ota validate metadata` command to the CLI to validate the collection metadata file
+
 ## 4.0.2 - 2025-02-04
 
 _Full changeset and discussions: [#1133](https://github.com/OpenTermsArchive/engine/pull/1133)._

bin/ota-lint.js

@@ -12,7 +12,7 @@ const __dirname = path.dirname(fileURLToPath(import.meta.url));
 const LINT_TEST_FILEPATH = '../scripts/declarations/lint/index.mocha.js';
 const LINT_PATH = path.resolve(__dirname, LINT_TEST_FILEPATH);
 
-// Mocha catches unhandled rejection from the user code and re-emits them to the process (see https://github.com/mochajs/mocha/blob/master/lib/runner.js#L198)
+// Mocha catches unhandled rejection from the user code and re-emits them to the process
 process.on('unhandledRejection', reason => {
   // Re-throw them so that the validation command fails in these cases (for example, if there is a syntax error when parsing JSON declaration files)
   throw reason;

bin/ota-validate.js

@@ -1,6 +1,5 @@
 #! /usr/bin/env node
 import './env.js';
-
 import path from 'path';
 import { fileURLToPath } from 'url';
 
@@ -9,49 +8,71 @@ import Mocha from 'mocha';
 
 const __dirname = path.dirname(fileURLToPath(import.meta.url));
 
-const VALIDATE_TEST_FILEPATH = '../scripts/declarations/validate/index.mocha.js';
-const VALIDATE_PATH = path.resolve(__dirname, VALIDATE_TEST_FILEPATH);
+export function createMocha({ delay = false, reporter = 'spec' } = {}) {
+  return new Mocha({
+    delay,
+    failZero: true,
+    reporter,
+  });
+}
+
+export async function runMochaTests(mocha, testPath) {
+  try {
+    mocha.addFile(testPath); // With `delay` option, this statement will not load the file directly, `loadFilesAsync` is required.
+    await mocha.loadFilesAsync(); // Load files previously added to the Mocha cache with `addFile`.
+
+    return new Promise(resolve => {
+      let hasFailedTests = false;
+
+      mocha.run()
+        .on('fail', () => { hasFailedTests = true; })
+        .on('end', () => { resolve(hasFailedTests ? 1 : 0); });
+    });
+  } catch (error) {
+    console.error('Error running tests:', error);
+
+    return 2;
+  }
+}
 
-// Mocha catches unhandled rejection from the user code and re-emits them to the process (see https://github.com/mochajs/mocha/blob/master/lib/runner.js#L198)
-process.on('unhandledRejection', reason => {
-  // Re-throw them so that the validation command fails in these cases (for example, if there is a syntax error when parsing JSON declaration files)
-  throw reason;
+process.on('unhandledRejection', reason => { // Mocha catches unhandled rejection from the user code and re-emits them to the process
+  throw reason; // Re-throw them so that the validation command fails in these cases (for example, if there is a syntax error when parsing JSON declaration files)
 });
 
 program
   .name('ota validate')
+  .description('Validate terms declarations and metadata files');
+
+program.command('declarations')
   .description('Run a series of tests to check the validity of terms declarations')
   .option('-s, --services [serviceId...]', 'service IDs of services to validate')
   .option('-t, --types [termsType...]', 'terms types to validate')
   .option('-m, --modified', 'target only services modified in the current git branch')
-  .option('-o, --schema-only', 'much faster check of declarations, but does not check that the documents are actually accessible');
+  .option('-o, --schema-only', 'much faster check of declarations, but does not check that the documents are actually accessible')
+  .action(async options => {
+    const VALIDATE_TEST_FILEPATH = '../scripts/declarations/validate/index.mocha.js';
+    const VALIDATE_PATH = path.resolve(__dirname, VALIDATE_TEST_FILEPATH);
 
-const mocha = new Mocha({
-  delay: true, // as the validation script performs an asynchronous load before running the tests, the execution of the tests are delayed until run() is called
-  failZero: true, // consider that being called with no service to validate is a failure
-});
+    const mocha = createMocha({ delay: true }); // as the validation script performs an asynchronous load before running the tests, the execution of the tests are delayed until run() is called
+    const generateValidationTestSuite = (await import(VALIDATE_TEST_FILEPATH)).default;
 
-(async () => {
-  mocha.addFile(VALIDATE_PATH); // As `delay` has been called, this statement will not load the file directly, `loadFilesAsync` is required.
-  await mocha.loadFilesAsync() // Load files previously added to the Mocha cache with `addFile`.
-    .catch(error => {
-      console.error(error);
-      process.exit(2);
-    });
+    generateValidationTestSuite(options);
 
-  let hasFailedTests = false;
+    const exitCode = await runMochaTests(mocha, VALIDATE_PATH);
 
-  const generateValidationTestSuite = (await import(VALIDATE_TEST_FILEPATH)).default;
+    process.exit(exitCode);
+  });
 
-  generateValidationTestSuite(program.parse().opts());
+program.command('metadata')
+  .description('Validate the metadata file structure')
+  .action(async () => {
+    const VALIDATE_TEST_FILEPATH = '../scripts/metadata/index.mocha.js';
+    const VALIDATE_PATH = path.resolve(__dirname, VALIDATE_TEST_FILEPATH);
 
-  mocha.run()
-    .on('fail', () => { hasFailedTests = true; })
-    .on('end', () => {
-      if (hasFailedTests) {
-        process.exit(1);
-      }
+    const mocha = createMocha();
+    const exitCode = await runMochaTests(mocha, VALIDATE_PATH);
 
-      process.exit(0);
-    });
-})();
+    process.exit(exitCode);
+  });
+
+program.parse();

package-lock.json

@@ -36,10 +36,11 @@
     "dataset:release": "node bin/ota.js dataset --publish --remove-local-copy",
     "dataset:scheduler": "npm run dataset:release -- --schedule",
     "declarations:lint": "node bin/ota.js lint",
-    "declarations:validate": "node bin/ota.js validate",
+    "declarations:validate": "node bin/ota.js validate declarations",
     "declarations:validate:schema": "npm run declarations:validate -- --schema-only",
     "lint": "eslint src test scripts bin",
     "lint:fix": "npm run lint -- --fix",
+    "metadata:validate": "node bin/ota.js validate metadata",
     "start": "node -r dotenv/config --max-http-header-size=32768 bin/ota.js track",
     "start:api": "node bin/ota.js serve",
     "start:scheduler": "npm start -- --schedule",
@@ -54,7 +55,8 @@
     "@opentermsarchive/turndown": "^7.1.3",
     "@stylistic/eslint-plugin-js": "^1.4.1",
     "abort-controller": "^3.0.0",
-    "ajv": "^6.12.6",
+    "ajv": "^8.17.1",
+    "ajv-formats": "^3.0.1",
     "archiver": "^5.3.0",
     "async": "^3.2.2",
     "chai": "^4.3.4",

package.json

@@ -2,6 +2,7 @@ import fsApi from 'fs';
 import path from 'path';
 
 import Ajv from 'ajv';
+import addFormats from 'ajv-formats';
 import { expect } from 'chai';
 import config from 'config';
 import jsonSourceMap from 'json-source-map';
@@ -178,10 +179,9 @@ export default async options => {
   run();
 };
 
-const validator = new Ajv({
-  allErrors: true,
-  jsonPointers: true,
-});
+const validator = new Ajv({ allErrors: true });
+
+addFormats(validator);
 
 function assertValid(schema, subject) {
   const valid = validator.validate(schema, subject);
@@ -193,7 +193,6 @@ function assertValid(schema, subject) {
     const jsonLines = sourceMap.json.split('\n');
 
     validator.errors.forEach(error => {
-      console.log('error', error);
       errorMessage += `\n\n${validator.errorsText([error])}`;
       const errorPointer = sourceMap.pointers[error.dataPath];
 

scripts/declarations/validate/index.mocha.js

@@ -67,7 +67,10 @@ const schema = {
     singleSourceDocumentTerms: {
       allOf: [
         { $ref: '#/definitions/sourceDocument' },
-        { required: [ 'fetch', 'select' ] },
+        {
+          type: 'object',
+          required: [ 'fetch', 'select' ],
+        },
       ],
     },
     multipleSourceDocumentsTerms: {