Filter entities by name when extracting data from Arkindex

Closes #134 (closed)

dan/datasets/extract/__init__.py

@@ -87,16 +87,18 @@ def add_extract_parser(subcommands) -> None:
         action="store_true",
         help="Extract text with their entities.",
     )
-    parser.add_argument(
-        "--only-entities",
-        action="store_true",
-        help="Remove all text that does not belong to the tokens.",
-    )
     parser.add_argument(
         "--allow-unknown-entities",
         action="store_true",
         help="Ignore entities that do not appear in the list of tokens.",
     )
+    parser.add_argument(
+        "--entity-separators",
+        type=str,
+        nargs="+",
+        help="Removes all text that does not appear in an entity or in the list of given characters. Do not give any arguments for keeping the whole text.",
+        required=False,
+    )
     parser.add_argument(
         "--tokens",
         type=pathlib.Path,