[FIX] core: add support for windows-874 encoding

Outlook and similar Windows based systems use windows-874 for encoding
Thai characters which is not natively known by Python.
Simply aliasing the Windows encoding as cp874 adds support for this
encoding.

opw-3684161

closes odoo/odoo#161117

X-original-commit: 65d4c2507e762dc273a02a2e2215c49a5976568d
Signed-off-by: Julien Castiaux (juc) <juc@odoo.com>
Co-authored-by: Julien Castiaux <juc@odoo.com>

addons/test_mail/data/test_mail_data.py

@@ -1312,3 +1312,24 @@ JVBERi0xLjEKJcKlwrHDqwoKMSAwIG9iagogIDw8IC9UeXBlIC9DYXRhbG9nCiAgICAgL1BhZ2VzIDIg
 """
 
 PDF_PARSED = b'''%PDF-1.1\n%\xc2\xa5\xc2\xb1\xc3\xab\n\n1 0 obj\n  << /Type /Catalog\n     /Pages 2 0 R\n  >>\nendobj\n\n2 0 obj\n  << /Type /Pages\n     /Kids [3 0 R]\n     /Count 1\n     /MediaBox [0 0 300 144]\n  >>\nendobj\n\n3 0 obj\n  <<  /Type /Page\n      /Parent 2 0 R\n      /Resources\n       << /Font\n           << /F1\n               << /Type /Font\n                  /Subtype /Type1\n                  /BaseFont /Times-Roman\n               >>\n           >>\n       >>\n      /Contents 4 0 R\n  >>\nendobj\n\n4 0 obj\n  << /Length 55 >>\nstream\n  BT\n    /F1 18 Tf\n    0 0 Td\n    (Hello World) Tj\n  ET\nendstream\nendobj\n\nxref\n0 5\n0000000000 65535 f \n0000000018 00000 n \n0000000077 00000 n \n0000000178 00000 n \n0000000457 00000 n \ntrailer\n  <<  /Root 1 0 R\n      /Size 5\n  >>\nstartxref\n565\n%%EOF\n'''
+
+THAI_EMAIL_WINDOWS_874 = '''\
+From: Thai Customer <outlook_windows@outlook.com>
+To: "Thai Odoo User" <thai-user@odoo.com>
+Subject: =?windows-874?B?4MPX6M2n?=
+Thread-Topic: =?windows-874?B?4MPX6M2n?=
+Thread-Index: AQHahRQ4qiMBoXtK0U2XwaGg8w9Y9g==
+X-MS-Exchange-MessageSentRepresentingType: 1
+Date: Tue, 2 Apr 2024 15:42:24 +0000
+Message-ID: <PH7P220MB158617DEAEC85ECA2A0D2CAFBC3E2@PH7P220MB1586.NAMP220.PROD.OUTLOOK.COM>
+Content-Language: en-US
+X-MS-Has-Attach:
+X-MS-Exchange-Organization-SCL: -1
+X-MS-TNEF-Correlator:
+X-MS-Exchange-Organization-RecordReviewCfmType: 0
+msip_labels:
+Content-Type: text/plain; charset="windows-874"
+Content-Transfer-Encoding: quoted-printable
+MIME-Version: 1.0
+
+=C3=E8=D2=A7=A1=D2=C2='''

addons/test_mail/tests/test_mail_gateway.py

@@ -14,7 +14,7 @@ from odoo import exceptions
 from odoo.addons.mail.models.mail_thread import MailThread
 from odoo.addons.mail.tests.common import mail_new_test_user, MailCommon
 from odoo.addons.test_mail.data import test_mail_data
-from odoo.addons.test_mail.data.test_mail_data import MAIL_TEMPLATE
+from odoo.addons.test_mail.data.test_mail_data import MAIL_TEMPLATE, THAI_EMAIL_WINDOWS_874
 from odoo.addons.test_mail.models.test_mail_models import MailTestGateway
 from odoo.sql_db import Cursor
 from odoo.tests import tagged, RecordCapturer
@@ -1772,6 +1772,18 @@ class TestMailgateway(MailCommon):
             content
         )
 
+    def test_message_windows_874(self):
+        # Email for Thai customers who use Microsoft email service.
+        # The charset is windows-874 which isn't natively supported by
+        # python, check that Odoo is still capable of decoding it.
+        # windows-874 is the Microsoft equivalent of cp874.
+        with self.mock_mail_gateway(), \
+             RecordCapturer(self.env['mail.test.gateway'], []) as capture:
+            self.env['mail.thread'].message_process('mail.test.gateway', THAI_EMAIL_WINDOWS_874)
+        capture.records.ensure_one()
+        self.assertEqual(capture.records.name, 'เรื่อง')
+        self.assertEqual(str(capture.records.message_ids.body), '<pre>ร่างกาย</pre>\n')
+
     # --------------------------------------------------
     # Emails loop detection
     # --------------------------------------------------

odoo/__init__.py

@@ -86,6 +86,13 @@ try:
 except ImportError:
     pass # no fix required
 
+# ---------------------------------------------------------
+# some charset are known by Python under a different name
+# ---------------------------------------------------------
+import encodings.aliases  # noqa: E402
+
+encodings.aliases.aliases['874'] = 'cp874'
+encodings.aliases.aliases['windows_874'] = 'cp874'
 
 #----------------------------------------------------------
 # alias hebrew iso-8859-8-i and iso-8859-8-e on iso-8859-8