sporada/ocr
1
0
Fork 0
mirror of https://gitlab.ub.uni-bielefeld.de/sfb1288inf/ocr.git synced 2025-01-14 17:20:34 +00:00
Code Issues Projects Releases Wiki Activity

Compare commits

base: sporada:104598039ec15398165c06505671f4cdbe1aa82d
Branches Tags
sporada:master
sporada:v0.1.0
sporada:1.0.0b
sporada:1.0
..
compare: sporada:613bceb4ff32040be7829e6601ccbd4dd340f26c
Branches Tags
sporada:master
sporada:v0.1.0
sporada:1.0.0b
sporada:1.0

No commits in common. "104598039ec15398165c06505671f4cdbe1aa82d" and "613bceb4ff32040be7829e6601ccbd4dd340f26c" have entirely different histories.
104598039e ... 613bceb4ff

2 changed files with 5 additions and 6 deletions
Show Stats Expand all files Collapse all files

8
Dockerfile
View File

@ -1,7 +1,7 @@
FROM debian:buster-slim
LABEL authors="Patrick Jentsch <p.jentsch@uni-bielefeld.de>, Stephan Porada <porada@posteo.de>"
LABEL authors="Patrick Jentsch <p.jentsch@uni-bielefeld.de>"
ENV LANG=C.UTF-8
@ -91,12 +91,12 @@ RUN apt-get install --no-install-recommends --yes \
&& pip install natsort
RUN rm -r /var/lib/apt/lists/*
## Install Pipeline ##
COPY hocrtotei ocr /usr/local/bin/
RUN rm -r /var/lib/apt/lists/*
ENTRYPOINT ["ocr"]
CMD ["--help"]

3
ocr
View File

@ -3,8 +3,7 @@
"""An OCR pipeline for PDF file processing."""
__author__ = 'Patrick Jentsch <p.jentsch@uni-bielefeld.de>,' \
'Stephan Porada <porada@posteo.de>'
__author__ = 'Patrick Jentsch <p.jentsch@uni-bielefeld.de>'
__version__ = '1.0.0'
from argparse import ArgumentParser