qurator-spk/dinglehopper
1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-06-08 11:20:26 +02:00
Code Issues Releases Wiki Activity

🚧 Add OCR-D parameter for plain text encoding

Browse source
This commit is contained in:
Gerber, Mike 2025-02-13 16:48:50 +01:00
parent eca76a7db2
commit 323b389ef9
2 changed files with 7 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

5
src/dinglehopper/ocrd-tool.json
View file

@ -29,6 +29,11 @@
"enum": ["region", "line"], "enum": ["region", "line"],
"default": "region", "default": "region",
"description": "PAGE XML hierarchy level to extract the text from" "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"
} }
} }
} }

2
src/dinglehopper/ocrd_cli.py
View file

@ -36,6 +36,7 @@ class OcrdDinglehopperEvaluate(Processor):
metrics = self.parameter["metrics"] metrics = self.parameter["metrics"]
textequiv_level = self.parameter["textequiv_level"] textequiv_level = self.parameter["textequiv_level"]
plain_encoding = self.parameter["plain_encoding"]
gt_grp, ocr_grp = self.input_file_grp.split(",") gt_grp, ocr_grp = self.input_file_grp.split(",")
input_file_tuples = self.zip_input_files(on_error="abort") input_file_tuples = self.zip_input_files(on_error="abort")
@ -63,6 +64,7 @@ class OcrdDinglehopperEvaluate(Processor):
report_prefix, report_prefix,
metrics=metrics, metrics=metrics,
textequiv_level=textequiv_level, textequiv_level=textequiv_level,
plain_encoding=plain_encoding,
) )
# Add reports to the workspace # Add reports to the workspace