Merge branch 'dev' into feature-use-celery

src/documents/consumer.py

@@ -111,14 +111,16 @@ class Consumer(LoggingMixin):
     def pre_check_duplicate(self):
         with open(self.path, "rb") as f:
             checksum = hashlib.md5(f.read()).hexdigest()
-        if Document.objects.filter(
+        existing_doc = Document.objects.filter(
             Q(checksum=checksum) | Q(archive_checksum=checksum),
-        ).exists():
+        )
+        if existing_doc.exists():
             if settings.CONSUMER_DELETE_DUPLICATES:
                 os.unlink(self.path)
             self._fail(
                 MESSAGE_DOCUMENT_ALREADY_EXISTS,
-                f"Not consuming {self.filename}: It is a duplicate.",
+                f"Not consuming {self.filename}: It is a duplicate of"
+                f" {existing_doc.get().title} (#{existing_doc.get().pk})",
             )
 
     def pre_check_directories(self):

src/paperless/checks.py

@@ -127,10 +127,10 @@ def settings_values_check(app_configs, **kwargs):
                 Error(f'OCR output type "{settings.OCR_OUTPUT_TYPE}" is not valid'),
             )
 
-        if settings.OCR_MODE not in {"force", "skip", "redo_ocr"}:
+        if settings.OCR_MODE not in {"force", "skip", "redo", "skip_noarchive"}:
             msgs.append(Error(f'OCR output mode "{settings.OCR_MODE}" is not valid'))
 
-        if settings.OCR_CLEAN not in {"clean", "clean_final"}:
+        if settings.OCR_CLEAN not in {"clean", "clean-final", "none"}:
             msgs.append(Error(f'OCR clean mode "{settings.OCR_CLEAN}" is not valid'))
         return msgs
 

src/paperless/settings.py

@@ -322,6 +322,7 @@ DATABASES = {
     "default": {
         "ENGINE": "django.db.backends.sqlite3",
         "NAME": os.path.join(DATA_DIR, "db.sqlite3"),
+        "OPTIONS": {},
     },
 }
 
@@ -343,21 +344,18 @@ if os.getenv("PAPERLESS_DBHOST"):
     # Leave room for future extensibility
     if os.getenv("PAPERLESS_DBENGINE") == "mariadb":
         engine = "django.db.backends.mysql"
-        options = {"read_default_file": "/etc/mysql/my.cnf"}
+        options = {"read_default_file": "/etc/mysql/my.cnf", "charset": "utf8mb4"}
     else:  # Default to PostgresDB
         engine = "django.db.backends.postgresql_psycopg2"
         options = {"sslmode": os.getenv("PAPERLESS_DBSSLMODE", "prefer")}
 
     DATABASES["default"]["ENGINE"] = engine
-    for key, value in options.items():
-        DATABASES["default"]["OPTIONS"][key] = value
+    DATABASES["default"]["OPTIONS"].update(options)
 
 if os.getenv("PAPERLESS_DB_TIMEOUT") is not None:
-    _new_opts = {"timeout": float(os.getenv("PAPERLESS_DB_TIMEOUT"))}
-    if "OPTIONS" in DATABASES["default"]:
-        DATABASES["default"]["OPTIONS"].update(_new_opts)
-    else:
-        DATABASES["default"]["OPTIONS"] = _new_opts
+    DATABASES["default"]["OPTIONS"].update(
+        {"timeout": float(os.getenv("PAPERLESS_DB_TIMEOUT"))},
+    )
 
 DEFAULT_AUTO_FIELD = "django.db.models.AutoField"
 

src/paperless/version.py

@@ -1,7 +1,7 @@
 from typing import Final
 from typing import Tuple
 
-__version__: Final[Tuple[int, int, int]] = (1, 9, 0)
+__version__: Final[Tuple[int, int, int]] = (1, 9, 2)
 # Version string like X.Y.Z
 __full_version_str__: Final[str] = ".".join(map(str, __version__))
 # Version string like X.Y

src/paperless_text/signals.py

@@ -11,5 +11,6 @@ def text_consumer_declaration(sender, **kwargs):
         "mime_types": {
             "text/plain": ".txt",
             "text/csv": ".csv",
+            "application/csv": ".csv",
         },
     }