Documentation: Fix typos with automated tool (#5319)

---------

Co-authored-by: shamoon <4887959+shamoon@users.noreply.github.com>

src/documents/double_sided.py

@@ -35,7 +35,7 @@ def collate(input_doc: ConsumableDocument) -> str:
     in reverse order, since the ADF will have scanned the pages from bottom
     to top.
 
-    Returns a status message on succcess, or raises a ConsumerError
+    Returns a status message on success, or raises a ConsumerError
     in case of failure.
     """
 

src/documents/file_handling.py

@@ -224,7 +224,7 @@ def generate_filename(
             if settings.FILENAME_FORMAT_REMOVE_NONE:
                 path = path.replace("/-none-/", "/")  # remove empty directories
                 path = path.replace(" -none-", "")  # remove when spaced, with space
-                path = path.replace("-none-", "")  # remove rest of the occurences
+                path = path.replace("-none-", "")  # remove rest of the occurrences
 
             path = path.replace("-none-", "none")  # backward compatibility
             path = path.strip(os.sep)

src/documents/management/commands/document_consumer.py

@@ -264,7 +264,7 @@ class Command(BaseCommand):
         polling_interval = settings.CONSUMER_POLLING
         if polling_interval == 0:  # pragma: no cover
             # Only happens if INotify failed to import
-            logger.warn("Using polling of 10s, consider settng this")
+            logger.warn("Using polling of 10s, consider setting this")
             polling_interval = 10
 
         with ThreadPoolExecutor(max_workers=4) as pool:

src/documents/matching.py

@@ -345,7 +345,7 @@ def existing_document_matches_workflow(
         )
         trigger_matched = False
 
-    # Document correpondent vs trigger has_correspondent
+    # Document correspondent vs trigger has_correspondent
     if (
         trigger.filter_has_correspondent is not None
         and document.correspondent != trigger.filter_has_correspondent

src/documents/migrations/0017_auto_20170512_0507.py

@@ -22,7 +22,7 @@ class Migration(migrations.Migration):
                     (5, "Fuzzy Match"),
                 ],
                 default=1,
-                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containg imperfections that foil accurate OCR.',
+                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
             ),
         ),
         migrations.AlterField(
@@ -37,7 +37,7 @@ class Migration(migrations.Migration):
                     (5, "Fuzzy Match"),
                 ],
                 default=1,
-                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containg imperfections that foil accurate OCR.',
+                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
             ),
         ),
     ]

src/documents/migrations/1000_update_paperless_all.py

@@ -66,7 +66,7 @@ class Migration(migrations.Migration):
                             (6, "Automatic Classification"),
                         ],
                         default=1,
-                        help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containg imperfections that foil accurate OCR.',
+                        help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
                     ),
                 ),
                 ("is_insensitive", models.BooleanField(default=True)),
@@ -100,7 +100,7 @@ class Migration(migrations.Migration):
                     (6, "Automatic Classification"),
                 ],
                 default=1,
-                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containg imperfections that foil accurate OCR.',
+                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
             ),
         ),
         migrations.AlterField(
@@ -116,7 +116,7 @@ class Migration(migrations.Migration):
                     (6, "Automatic Classification"),
                 ],
                 default=1,
-                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containg imperfections that foil accurate OCR.',
+                help_text='Which algorithm you want to use when matching text to the OCR\'d PDF.  Here, "any" looks for any occurrence of any word provided in the PDF, while "all" requires that every word provided appear in the PDF, albeit not in the order provided.  A "literal" match means that the text you enter must appear in the PDF exactly as you\'ve entered it, and "regular expression" uses a regex to match the PDF.  (If you don\'t know what a regex is, you probably don\'t want this option.)  Finally, a "fuzzy match" looks for words or phrases that are mostly—but not exactly—the same, which can be useful for matching against documents containing imperfections that foil accurate OCR.',
             ),
         ),
         migrations.AlterField(

src/documents/migrations/1012_fix_archive_files.py

@@ -207,7 +207,7 @@ def create_archive_version(doc, retry_count=3):
                 return
             else:
                 # This is mostly here for the tika parser in docker
-                # environemnts. The servers for parsing need to come up first,
+                # environments. The servers for parsing need to come up first,
                 # and the docker setup doesn't ensure that tika is running
                 # before attempting migrations.
                 logger.error("Parse error, will try again in 5 seconds...")

src/documents/serialisers.py

@@ -546,7 +546,7 @@ class CustomFieldInstanceSerializer(serializers.ModelSerializer):
                 if doc_id not in target_doc_ids:
                     self.remove_doclink(document, field, doc_id)
 
-        # Create an instance if target doc doesnt have this field or append it to an existing one
+        # Create an instance if target doc doesn't have this field or append it to an existing one
         existing_custom_field_instances = {
             custom_field.document_id: custom_field
             for custom_field in CustomFieldInstance.objects.filter(

src/documents/signals/handlers.py

@@ -617,7 +617,7 @@ def run_workflow(
                             ).count()
                             == 0
                         ):
-                            # can be triggered on existing docs, so only add the field if it doesnt already exist
+                            # can be triggered on existing docs, so only add the field if it doesn't already exist
                             CustomFieldInstance.objects.create(
                                 field=field,
                                 document=document,

src/documents/tests/test_api_documents.py

@@ -1276,7 +1276,7 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
         GIVEN:
             - NUMBER_OF_SUGGESTED_DATES = 0 (disables feature)
         WHEN:
-            - API reuqest for document suggestions
+            - API request for document suggestions
         THEN:
             - Dont check for suggested dates at all
         """
@@ -1526,7 +1526,7 @@ class TestDocumentApi(DirectoriesMixin, DocumentConsumeDelayMixin, APITestCase):
         GIVEN:
             - A document with a single note
         WHEN:
-            - API reuqest for document notes is made
+            - API request for document notes is made
         THEN:
             - The associated note is returned
         """

src/documents/tests/test_api_search.py

@@ -55,7 +55,7 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         with AsyncWriter(index.open_index()) as writer:
             # Note to future self: there is a reason we dont use a model signal handler to update the index: some operations edit many documents at once
             # (retagger, renamer) and we don't want to open a writer for each of these, but rather perform the entire operation with one writer.
-            # That's why we cant open the writer in a model on_save handler or something.
+            # That's why we can't open the writer in a model on_save handler or something.
             index.update_document(writer, d1)
             index.update_document(writer, d2)
             index.update_document(writer, d3)
@@ -903,8 +903,8 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         GIVEN:
             - Documents with owners set & without
         WHEN:
-            - API reuqest for advanced query (search) is made by non-superuser
-            - API reuqest for advanced query (search) is made by superuser
+            - API request for advanced query (search) is made by non-superuser
+            - API request for advanced query (search) is made by superuser
         THEN:
             - Only owned docs are returned for regular users
             - All docs are returned for superuser
@@ -959,7 +959,7 @@ class TestDocumentSearchApi(DirectoriesMixin, APITestCase):
         GIVEN:
             - Documents with granted view permissions to others
         WHEN:
-            - API reuqest for advanced query (search) is made by user
+            - API request for advanced query (search) is made by user
         THEN:
             - Only docs with granted view permissions are returned
         """

src/documents/tests/test_date_parsing.py

@@ -212,8 +212,8 @@ class TestDate(TestCase):
 
     def test_multiple_dates(self):
         text = """This text has multiple dates.
-                  For example 02.02.2018, 22 July 2022 and Dezember 2021.
-                  But not 24-12-9999 because its in the future..."""
+                  For example 02.02.2018, 22 July 2022 and December 2021.
+                  But not 24-12-9999 because it's in the future..."""
         dates = list(parse_date_generator("", text))
         self.assertEqual(len(dates), 3)
         self.assertEqual(

src/documents/tests/test_delayedquery.py

@@ -43,7 +43,7 @@ class TestDelayedQuery(TestCase):
         )
 
     def test_get_permission_criteria(self):
-        # tests contains touples of user instances and the expected filter
+        # tests contains tuples of user instances and the expected filter
         tests = (
             (None, [query.Term("has_owner", False)]),
             (User(42, username="foo", is_superuser=True), []),
@@ -113,7 +113,7 @@ class TestDelayedQuery(TestCase):
             )
 
     def test_tags_query_filters(self):
-        # tests contains touples of query_parameter dics and the expected whoosh query
+        # tests contains tuples of query_parameter dics and the expected whoosh query
         param = "tags"
         field, _ = DelayedQuery.param_map[param]
         tests = (

src/documents/tests/test_migration_encrypted_webp_conversion.py

@@ -165,7 +165,7 @@ class TestMigrateToEncrytpedWebPThumbnails(TestMigrations):
     ):
         """
         GIVEN:
-            - Encrytped document exists with existing encrypted WebP thumbnail path
+            - Encrypted document exists with existing encrypted WebP thumbnail path
         WHEN:
             - Migration is attempted
         THEN:

src/paperless/checks.py

@@ -95,8 +95,8 @@ def debug_mode_check(app_configs, **kwargs):
         return [
             Warning(
                 "DEBUG mode is enabled. Disable Debug mode. This is a serious "
-                "security issue, since it puts security overides in place which "
-                "are meant to be only used during development. This "
+                "security issue, since it puts security overrides in place "
+                "which are meant to be only used during development. This "
                 "also means that paperless will tell anyone various "
                 "debugging information when something goes wrong.",
             ),

src/paperless/settings.py

@@ -499,8 +499,8 @@ AUTH_PASSWORD_VALIDATORS = [
 
 # Disable Django's artificial limit on the number of form fields to submit at
 # once. This is a protection against overloading the server, but since this is
-# a self-hosted sort of gig, the benefits of being able to mass-delete a tonne
-# of log entries outweight the benefits of such a safeguard.
+# a self-hosted sort of gig, the benefits of being able to mass-delete a ton
+# of log entries outweigh the benefits of such a safeguard.
 
 DATA_UPLOAD_MAX_NUMBER_FIELDS = None
 

src/paperless_mail/mail.py

@@ -767,7 +767,7 @@ class MailAccountHandler(LoggingMixin):
                 message=message,
             )
         else:
-            # No files to consume, just mark as processed if it wasnt by .eml processing
+            # No files to consume, just mark as processed if it wasn't by .eml processing
             if not ProcessedMail.objects.filter(
                 rule=rule,
                 uid=message.uid,