🚧 Add OCR-D parameter for plain text encoding

Author: mikegerber

src/dinglehopper/ocrd-tool.json

@@ -25,6 +25,11 @@
           "enum": ["region", "line"],
           "default": "region",
           "description": "PAGE XML hierarchy level to extract the text from"
+        },
+        "plain_encoding": {
+          "type": "string",
+          "default": "autodetect",
+          "description": "Encoding (e.g. \"utf-8\") of plain text files"
         }
       }
     }

src/dinglehopper/ocrd_cli.py

@@ -26,6 +26,7 @@ def process_page_file(self, *input_files: Optional[OcrdFileType]) -> None:
         assert self.parameter
         metrics = self.parameter["metrics"]
         textequiv_level = self.parameter["textequiv_level"]
+        plain_encoding = self.parameter["plain_encoding"]
 
         # wrong number of inputs: let fail
         gt_file, ocr_file = input_files
@@ -52,6 +53,7 @@ def process_page_file(self, *input_files: Optional[OcrdFileType]) -> None:
             self.output_file_grp,
             metrics=metrics,
             textequiv_level=textequiv_level,
+            plain_encoding=plain_encoding,
         )
 
         # Add reports to the workspace