improve test coverage a little

scripts/start_services.sh

@@ -2,5 +2,5 @@
 
 docker run -p 5432:5432 -e POSTGRES_PASSWORD=password -v paperless_pgdata:/var/lib/postgresql/data -d postgres:13
 docker run -d -p 6379:6379 redis:latest
-docker run -p 3000:3000 -d gotenberg/gotenberg:7.6 gotenberg --chromium-disable-javascript=true --chromium-allow-list=file:///tmp/.*
+docker run -p 3000:3000 -d gotenberg/gotenberg:7.6 gotenberg --chromium-disable-javascript=true --chromium-allow-list="file:///tmp/.*"
 docker run -p 9998:9998 -d ghcr.io/paperless-ngx/tika:latest

src/paperless_mail/tests/samples/html.eml.html

@@ -30,7 +30,7 @@
       <div class="col-start-2 col-span-10 row-start-5" text-sm my-0.5></div>
 
 			<div class="col-start-1 row-start-6	 text-slate-400 text-right">Attachments</div>
-      <div class="col-start-2 col-span-10 row-start-6">IntM6gnXFm00FEV5.png (6.89 KiB)</div>
+      <div class="col-start-2 col-span-10 row-start-6">IntM6gnXFm00FEV5.png (6.89 KiB), 600+kbfile.txt (0.59 MiB)</div>
     </div>
 
     <!-- Separator-->

src/paperless_mail/tests/samples/simple_text.eml

@@ -14,6 +14,8 @@ User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:102.0) Gecko/20100101
  Thunderbird/102.3.1
 Content-Language: en-US
 To: some@one.de
+Cc: asdasd@æsdasd.de, asdadasdasdasda.asdasd@æsdasd.de
+Bcc: fdf@fvf.de
 From: Some One <mail@someserver.de>
 Content-Type: text/plain; charset=UTF-8; format=flowed
 Content-Transfer-Encoding: 7bit

src/paperless_mail/tests/test_parsers.py

@@ -69,7 +69,7 @@ class TestParser(TestCase):
 
         # The created intermediary pdf is not reproducible. But the thumbnail image should always look the same.
         expected_hash = (
-            "18a2513c80584e538c4a129e8a2b0ce19bf0276eab9c95b72fa93e941db38d12"
+            "eeb2cf861f4873d2e569d0dfbfd385c2ac11722accf0fd3a32a54e3b115317a9"
         )
         self.assertEqual(
             thumb_hash,
@@ -226,7 +226,7 @@ class TestParser(TestCase):
         # Validate parsing returns the expected results
         parser.parse(os.path.join(self.SAMPLE_FILES, "html.eml"), "message/rfc822")
 
-        text_expected = "Some Text\nand an embedded image.\n\nSubject: HTML Message\n\nFrom: Name <someone@example.de>\n\nTo: someone@example.de\n\nAttachments: IntM6gnXFm00FEV5.png (6.89 KiB)\n\nHTML content: Some Text\nand an embedded image.\nParagraph unchanged."
+        text_expected = "Some Text\r\n\r\nand an embedded image.\n\nSubject: HTML Message\n\nFrom: Name <someone@example.de>\n\nTo: someone@example.de\n\nAttachments: IntM6gnXFm00FEV5.png (6.89 KiB), 600+kbfile.txt (0.59 MiB)\n\nHTML content: Some Text\nand an embedded image.\nParagraph unchanged."
         self.assertEqual(text_expected, parser.text)
         self.assertEqual(
             datetime.datetime(
@@ -241,6 +241,27 @@ class TestParser(TestCase):
             parser.date,
         )
 
+        # Validate parsing returns the expected results
+        parser = MailDocumentParser(None)
+        parser.parse(
+            os.path.join(self.SAMPLE_FILES, "simple_text.eml"),
+            "message/rfc822",
+        )
+        text_expected = "This is just a simple Text Mail.\n\nSubject: Simple Text Mail\n\nFrom: Some One <mail@someserver.de>\n\nTo: some@one.de\n\nCC: asdasd@æsdasd.de, asdadasdasdasda.asdasd@æsdasd.de\n\nBCC: fdf@fvf.de\n\n"
+        self.assertEqual(text_expected, parser.text)
+        self.assertEqual(
+            datetime.datetime(
+                2022,
+                10,
+                12,
+                21,
+                40,
+                43,
+                tzinfo=datetime.timezone(datetime.timedelta(seconds=7200)),
+            ),
+            parser.date,
+        )
+
         # Just check if file exists, the unittest for generate_pdf() goes deeper.
         self.assertTrue(os.path.isfile(parser.archive_path))
 
@@ -267,6 +288,18 @@ class TestParser(TestCase):
         parsed = parser.tika_parse(html)
         self.assertEqual(expected_text, parsed)
 
+    @mock.patch("paperless_mail.parsers.MailDocumentParser.generate_pdf_from_mail")
+    @mock.patch("paperless_mail.parsers.MailDocumentParser.generate_pdf_from_html")
+    def test_generate_pdf_parse_error(self, m: mock.MagicMock, n: mock.MagicMock):
+        m.return_value = b""
+        n.return_value = b""
+        parser = MailDocumentParser(None)
+
+        # Check if exception is raised when the pdf can not be created.
+        parser.gotenberg_server = ""
+        with pytest.raises(ParseError):
+            parser.generate_pdf(os.path.join(self.SAMPLE_FILES, "html.eml"))
+
     @mock.patch("documents.loggers.LoggingMixin.log")  # Disable log output
     def test_generate_pdf(self, m):
         parser = MailDocumentParser(None)
@@ -295,7 +328,7 @@ class TestParser(TestCase):
 
         # The created pdf is not reproducible. But the converted image should always look the same.
         expected_hash = (
-            "23468c4597d63bbefd38825e27c7f05ac666573fc35447d9ddf1784c9c31c6ea"
+            "4f338619575a21c5227de003a14216b07ba00a372ca5f132745e974a1f990e09"
         )
         self.assertEqual(
             thumb_hash,
@@ -341,7 +374,7 @@ class TestParser(TestCase):
 
         # The created pdf is not reproducible. But the converted image should always look the same.
         expected_hash = (
-            "635bda532707faf69f06b040660445b656abcc7d622cc29c24a5c7fd2c713c5f"
+            "8734a3f0a567979343824e468cd737bf29c02086bbfd8773e94feb986968ad32"
         )
         self.assertEqual(
             thumb_hash,