refactor: centralize sourceUrl and id-dedup checks across case-studies/radar-reports validators

scripts/lib/validate-utils.mjs

@@ -12,6 +12,8 @@
 
 import fs from 'node:fs';
 
+import { publishableCncfUrl, CNCF_HOST_SUFFIXES } from './url-safety.mjs';
+
 export {
   checkUrl,
   isSafeUrl,
@@ -239,6 +241,59 @@ export function checkNonEmptyString(errors, path, field, value) {
   return ok;
 }
 
+/**
+ * Push a "sourceUrl must be an https URL..." error when `value` is not a
+ * CNCF-hosted, userinfo-free https URL.
+ *
+ * validate-case-studies.mjs and validate-radar-reports.mjs each carried an
+ * independent copy of this top-of-file `sourceUrl` gate with an identically
+ * worded message — the same centralize-after-drift precedent already
+ * applied here to checkNonEmptyArray() and checkParseableDate().
+ *
+ * @param {Array<Object>} errors - Array to accumulate errors.
+ * @param {string} path - File path or identifier used as the error's path.
+ * @param {unknown} value - Candidate sourceUrl.
+ * @returns {boolean} Whether `value` passed the check.
+ */
+export function checkPublishableSourceUrl(errors, path, value) {
+  const ok = Boolean(value) && Boolean(publishableCncfUrl(value));
+  if (!ok) {
+    errors.push({
+      path,
+      severity: 'error',
+      message: `sourceUrl must be an https URL, with no userinfo, on ${CNCF_HOST_SUFFIXES.join(' or ')}`,
+    });
+  }
+  return ok;
+}
+
+/**
+ * Push a "duplicate or missing id" error when `id` is falsy or already in
+ * `seen`, then record `id` in `seen` regardless.
+ *
+ * validate-case-studies.mjs and validate-radar-reports.mjs each carried an
+ * independent copy of this per-entry id-dedup check, byte-identical apart
+ * from the `errors`/`ids` variable names.
+ *
+ * @param {Array<Object>} errors - Array to accumulate errors.
+ * @param {string} path - File path or identifier used as the error's path.
+ * @param {unknown} id - Candidate entry id (entry.id, not a display fallback).
+ * @param {Set<unknown>} seen - Set of ids already encountered; mutated.
+ * @returns {boolean} Whether `id` passed the check.
+ */
+export function checkDuplicateOrMissingId(errors, path, id, seen) {
+  const ok = Boolean(id) && !seen.has(id);
+  if (!ok) {
+    errors.push({
+      path,
+      severity: 'error',
+      message: 'duplicate or missing id',
+    });
+  }
+  seen.add(id);
+  return ok;
+}
+
 /**
  * Report collected errors and exit if any errors exist.
  * @param {Array<Object>} errors - Array of error objects with { path, severity, message }

scripts/validate-case-studies.mjs

@@ -1,8 +1,10 @@
 #!/usr/bin/env node
 import { readFileSync } from 'node:fs';
 import {
+  checkDuplicateOrMissingId,
   checkNonEmptyArray,
   checkParseableDate,
+  checkPublishableSourceUrl,
   publishableCncfUrl,
   reportAndExit,
   CNCF_HOST_SUFFIXES,
@@ -30,12 +32,7 @@ checkParseableDate(
   'generatedAt',
   data.generatedAt,
 );
-if (!data.sourceUrl || !publishableCncfUrl(data.sourceUrl))
-  errors.push({
-    path: 'case-studies.json',
-    severity: 'error',
-    message: `sourceUrl must be an https URL, with no userinfo, on ${CNCF_HOST_SUFFIXES.join(' or ')}`,
-  });
+checkPublishableSourceUrl(errors, 'case-studies.json', data.sourceUrl);
 checkNonEmptyArray(
   errors,
   'case-studies.json',
@@ -47,13 +44,7 @@ const ids = new Set();
 const urls = new Set();
 for (const entry of Array.isArray(data.caseStudies) ? data.caseStudies : []) {
   const id = entry.id ?? entry.slug ?? 'unknown';
-  if (!entry.id || ids.has(entry.id))
-    errors.push({
-      path: String(id),
-      severity: 'error',
-      message: 'duplicate or missing id',
-    });
-  ids.add(entry.id);
+  checkDuplicateOrMissingId(errors, String(id), entry.id, ids);
   if (!entry.organization)
     errors.push({
       path: String(id),

scripts/validate-radar-reports.mjs

@@ -1,8 +1,10 @@
 #!/usr/bin/env node
 import { readFileSync } from 'node:fs';
 import {
+  checkDuplicateOrMissingId,
   checkNonEmptyArray,
   checkParseableDate,
+  checkPublishableSourceUrl,
   publishableCncfUrl,
   reportAndExit,
   CNCF_HOST_SUFFIXES,
@@ -31,12 +33,7 @@ checkParseableDate(
   'generatedAt',
   data.generatedAt,
 );
-if (!data.sourceUrl || !publishableCncfUrl(data.sourceUrl))
-  errors.push({
-    path: 'radar-reports.json',
-    severity: 'error',
-    message: `sourceUrl must be an https URL, with no userinfo, on ${CNCF_HOST_SUFFIXES.join(' or ')}`,
-  });
+checkPublishableSourceUrl(errors, 'radar-reports.json', data.sourceUrl);
 checkNonEmptyArray(
   errors,
   'radar-reports.json',
@@ -47,13 +44,7 @@ checkNonEmptyArray(
 const ids = new Set();
 for (const entry of Array.isArray(data.radarReports) ? data.radarReports : []) {
   const id = entry.id ?? entry.slug ?? 'unknown';
-  if (!entry.id || ids.has(entry.id))
-    errors.push({
-      path: String(id),
-      severity: 'error',
-      message: 'duplicate or missing id',
-    });
-  ids.add(entry.id);
+  checkDuplicateOrMissingId(errors, String(id), entry.id, ids);
   if (!entry.title)
     errors.push({
       path: String(id),

tests/validate-utils.test.mjs

@@ -4,10 +4,12 @@ import { spawnSync } from 'node:child_process';
 import fs from 'node:fs';
 import { fileURLToPath } from 'node:url';
 import {
+  checkDuplicateOrMissingId,
   checkIsoTimestamp,
   checkNonEmptyArray,
   checkNonEmptyString,
   checkParseableDate,
+  checkPublishableSourceUrl,
   checkUrl,
   collectError,
   isSafeUrl,
@@ -563,6 +565,57 @@ test('checkNonEmptyArray reports an empty array, a non-array and a missing value
   }
 });
 
+test('checkPublishableSourceUrl accepts a trimmed https URL on a CNCF host and pushes no error', () => {
+  const errors = [];
+  const ok = checkPublishableSourceUrl(
+    errors,
+    'case-studies.json',
+    'https://www.cncf.io/case-studies/',
+  );
+  assert.equal(ok, true);
+  assert.deepEqual(errors, []);
+});
+
+test('checkPublishableSourceUrl reports a missing or off-list sourceUrl', () => {
+  for (const value of [undefined, null, '', 'https://evil.example/']) {
+    const errors = [];
+    const ok = checkPublishableSourceUrl(errors, 'radar-reports.json', value);
+    assert.equal(ok, false, String(value));
+    assert.deepEqual(errors, [
+      {
+        path: 'radar-reports.json',
+        severity: 'error',
+        message: 'sourceUrl must be an https URL, with no userinfo, on cncf.io',
+      },
+    ]);
+  }
+});
+
+test('checkDuplicateOrMissingId accepts a new truthy id and records it as seen', () => {
+  const errors = [];
+  const seen = new Set();
+  const ok = checkDuplicateOrMissingId(errors, 'swisscom', 'swisscom', seen);
+  assert.equal(ok, true);
+  assert.deepEqual(errors, []);
+  assert.equal(seen.has('swisscom'), true);
+});
+
+test('checkDuplicateOrMissingId reports a missing id and a repeat of one already seen', () => {
+  const seen = new Set(['swisscom']);
+  for (const id of [undefined, null, '', 'swisscom']) {
+    const errors = [];
+    const ok = checkDuplicateOrMissingId(errors, 'display-path', id, seen);
+    assert.equal(ok, false, String(id));
+    assert.deepEqual(errors, [
+      {
+        path: 'display-path',
+        severity: 'error',
+        message: 'duplicate or missing id',
+      },
+    ]);
+  }
+});
+
 test('checkIsoTimestamp accepts a strict ISO 8601 UTC value and pushes no error', () => {
   const errors = [];
   const ok = checkIsoTimestamp(