Merge branch 'main' into fulldom-env

* main:
  Release v9.1.1
  Improve changelog
  Add test when mime type contains charset
  Fix PDF extraction when MIME type contains charset

Author: Ndpnt

CHANGELOG.md

@@ -12,6 +12,16 @@ All changes that impact users of this module are documented in this file, in the
 - Add debugging options to disable headless mode for visual troubleshooting during development; set `FETCHER_NO_HEADLESS=1` to show browser window
 - Add sandbox control for improved compatibility with Docker and containerized environments; set `FETCHER_NO_SANDBOX=1` when running in containers
 
+## 9.1.1 - 2025-10-07
+
+_Full changeset and discussions: [#1198](https://github.com/OpenTermsArchive/engine/pull/1198)._
+
+> 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.
+
+### Fixed
+
+- Increase robustness of PDF content type detection
+
 ## 9.1.0 - 2025-10-01
 
 _Full changeset and discussions: [#1197](https://github.com/OpenTermsArchive/engine/pull/1197)._

package-lock.json

@@ -1,6 +1,6 @@
 {
   "name": "@opentermsarchive/engine",
-  "version": "9.1.0",
+  "version": "9.1.1",
   "description": "Tracks and makes visible changes to the terms of online services",
   "homepage": "https://opentermsarchive.org",
   "bugs": {

package.json

@@ -18,7 +18,7 @@ export { ExtractDocumentError } from './errors.js';
  */
 export default async function extract(sourceDocument) {
   try {
-    if (sourceDocument.mimeType == mime.getType('pdf')) {
+    if (mime.getExtension(sourceDocument.mimeType) == 'pdf') {
       return await extractFromPDF(sourceDocument);
     }
 

src/archivist/extract/index.js

@@ -534,6 +534,10 @@ describe('Extract', () => {
         expect(await extract({ content: pdfContent, mimeType: mime.getType('pdf') })).to.equal(expectedExtractedContent);
       });
 
+      it('extracts content from PDF when MIME type includes charset parameter', async () => {
+        expect(await extract({ content: pdfContent, mimeType: 'application/pdf; charset=utf-8' })).to.equal(expectedExtractedContent);
+      });
+
       context('when PDF contains no text', () => {
         it('throws an ExtractDocumentError error', async () => {
           await expect(extract({ content: await fs.readFile(path.resolve(__dirname, '../../../test/fixtures/termsWithoutText.pdf')), mimeType: mime.getType('pdf') })).to.be.rejectedWith(ExtractDocumentError, /contains no text/);