@@ -1,43 +1,24 @@
|
||||
# Main stage
|
||||
FROM ubuntu:latest AS base
|
||||
|
||||
|
||||
FROM alpine:3.19.0
|
||||
|
||||
# JDK for app
|
||||
RUN apt-get update && \
|
||||
apt-get install -y --no-install-recommends \
|
||||
openjdk-17-jre && \
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
|
||||
RUN apk add --no-cache \
|
||||
ca-certificates \
|
||||
tzdata \
|
||||
tini \
|
||||
bash \
|
||||
curl \
|
||||
openjdk17-jre \
|
||||
# Doc conversion
|
||||
RUN apt-get update && \
|
||||
apt-get install -y --no-install-recommends \
|
||||
libreoffice-core \
|
||||
libreoffice-common \
|
||||
libreoffice-writer \
|
||||
libreoffice-calc \
|
||||
libreoffice-impress \
|
||||
python3-uno \
|
||||
curl \
|
||||
unoconv && \
|
||||
rm -rf /var/lib/apt/lists/*
|
||||
|
||||
|
||||
libreoffice \
|
||||
# OCR MY PDF (unpaper for descew and other advanced featues)
|
||||
RUN apt-get update && apt-get install -y --no-install-recommends software-properties-common gnupg2 && \
|
||||
add-apt-repository ppa:alex-p/tesseract-ocr5 && apt install -y --no-install-recommends tesseract-ocr && \
|
||||
apt-get update && \
|
||||
apt-get install -y --no-install-recommends \
|
||||
ghostscript \
|
||||
python3-pip \
|
||||
ocrmypdf \
|
||||
unpaper && \
|
||||
rm -rf /var/lib/apt/lists/* && \
|
||||
mv /usr/share/tesseract-ocr /usr/share/tesseract-ocr-original && \
|
||||
pip install --no-cache-dir --upgrade pip && \
|
||||
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
|
||||
|
||||
|
||||
#CV and HTML
|
||||
RUN pip install --no-cache-dir opencv-python-headless WeasyPrint
|
||||
tesseract-ocr-data-eng \
|
||||
# CV
|
||||
py3-opencv \
|
||||
# python3/pip
|
||||
python3 && \
|
||||
wget https://bootstrap.pypa.io/get-pip.py -qO - | python3 - --break-system-packages --no-cache-dir --upgrade && \
|
||||
# uno unoconv and HTML
|
||||
pip install --break-system-packages --no-cache-dir --upgrade unoconv WeasyPrint && \
|
||||
mv /usr/share/tessdata /usr/share/tessdata-original
|
||||
|
||||
Reference in New Issue
Block a user