qurator-spk/dinglehopper
1
0
Fork 0
mirror of https://github.com/qurator-spk/dinglehopper.git synced 2025-07-01 06:29:59 +02:00
Code Issues Releases Wiki Activity

🐛 Add --plain-encoding option to dinglehopper-extract

Browse source
This commit is contained in:
Mike Gerber 2025-04-22 18:24:35 +02:00
parent a70260c10e
commit 14a4bc56d8
1 changed files with 9 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

11
src/dinglehopper/cli_extract.py
View file

@ -12,7 +12,12 @@ from .ocr_files import extract
help="PAGE TextEquiv level to extract text from",
metavar="LEVEL",
)
def main(input_file, textequiv_level):
@click.option(
"--plain-encoding",
default="autodetect",
help='Encoding (e.g. "utf-8") of plain text files',
)
def main(input_file, textequiv_level, plain_encoding):
"""
Extract the text of the given INPUT_FILE.
@ -23,7 +28,9 @@ def main(input_file, textequiv_level):
use "--textequiv-level line" to extract from the level of TextLine tags.
"""
initLogging()
input_text = extract(input_file, textequiv_level=textequiv_level).text
input_text = extract(
input_file, textequiv_level=textequiv_level, plain_encoding=plain_encoding
).text
print(input_text)