added a setting: delete duplicate documents

paperless.conf.example

@@ -143,6 +143,10 @@ PAPERLESS_EMAIL_SECRET=""
 ####                          Software Tweaks                              ####
 ###############################################################################
 
+# When the consumer detects a duplicate document, it will not touch the
+# original document. This default behavior can be changed here.
+#PAPERLESS_CONSUMER_DELETE_DUPLICATES="false"
+
 # After a document is consumed, Paperless can trigger an arbitrary script if
 # you like.  This script will be passed a number of arguments for you to work
 # with.  The default is blank, which means nothing will be executed.  For more

src/documents/consumer.py

@@ -84,6 +84,8 @@ class Consumer:
                 "warning",
                 "Skipping {} as it appears to be a duplicate".format(doc)
             )
+            if settings.CONSUMER_DELETE_DUPLICATES:
+                self._cleanup_doc(doc)
             return False
 
         self.log("info", "Consuming {}".format(doc))

src/paperless/settings.py

@@ -258,6 +258,8 @@ Q_CLUSTER = {
 # Paperless Specific Settings                                                 #
 ###############################################################################
 
+CONSUMER_DELETE_DUPLICATES = __get_boolean("PAPERLESS_CONSUMER_DELETE_DUPLICATES")
+
 # The default language that tesseract will attempt to use when parsing
 # documents.  It should be a 3-letter language code consistent with ISO 639.
 OCR_LANGUAGE = os.getenv("PAPERLESS_OCR_LANGUAGE", "eng")