DGNum/Stirling-PDF
14
0
Fork 0
Code Issues 4 Pull requests 1 Projects Releases Packages Wiki Activity

Refine Tesseract-OCR file backup process in DockerfileBase

Browse source
This commit is contained in:
Peter Dave Hello 2024-01-04 20:30:55 +08:00
parent 56afd35c82
commit 846ebe6dda
1 changed files with 1 additions and 10 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
DockerfileBase
View file

@ -33,6 +33,7 @@ apt-get update && \
ocrmypdf \ ocrmypdf \
unpaper && \ unpaper && \
rm -rf /var/lib/apt/lists/* && \ rm -rf /var/lib/apt/lists/* && \
mv /usr/share/tesseract-ocr /usr/share/tesseract-ocr-original && \
pip install --upgrade pip && \ pip install --upgrade pip && \
pip install --no-cache-dir --upgrade ocrmypdf && \ pip install --no-cache-dir --upgrade ocrmypdf && \
pip install --no-cache-dir --upgrade pillow==10.0.1 reportlab==3.6.13 wheel==0.38.1 setuptools==65.5.1 pyjwt==2.4.0 cryptography==39.0.1 pip install --no-cache-dir --upgrade pillow==10.0.1 reportlab==3.6.13 wheel==0.38.1 setuptools==65.5.1 pyjwt==2.4.0 cryptography==39.0.1
@ -40,13 +41,3 @@ apt-get update && \
#CV and HTML #CV and HTML
RUN pip install --no-cache-dir opencv-python-headless WeasyPrint RUN pip install --no-cache-dir opencv-python-headless WeasyPrint
# cleanup and etc
RUN mkdir /usr/share/tesseract-ocr-original && \
cp -r /usr/share/tesseract-ocr/* /usr/share/tesseract-ocr-original && \
rm -rf /usr/share/tesseract-ocr