Add the new paperless_tika parser

This parser will use an external Tika and Gotenberg server to parse
"Office" documents (.doc, .xls, .odt, etc.)

Signed-off-by: Jo Vandeginste <Jo.Vandeginste@kuleuven.be>

src/paperless_tika/signals.py

@@ -0,0 +1,20 @@
+from .parsers import TikaDocumentParser
+
+
+def tika_consumer_declaration(sender, **kwargs):
+    return {
+        "parser": TikaDocumentParser,
+        "weight": 10,
+        "mime_types": {
+            "application/msword": ".doc",
+            "application/vnd.openxmlformats-officedocument.wordprocessingml.document": ".docx",
+            "application/vnd.ms-excel": ".xls",
+            "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet": ".xlsx",
+            "application/vnd.ms-powerpoint": ".ppt",
+            "application/vnd.openxmlformats-officedocument.presentationml.presentation": ".pptx",
+            "application/vnd.openxmlformats-officedocument.presentationml.slideshow": ".ppsx",
+            "application/vnd.oasis.opendocument.presentation": ".odp",
+            "application/vnd.oasis.opendocument.spreadsheet": ".ods",
+            "application/vnd.oasis.opendocument.text": ".odt",
+        },
+    }