mirror of
https://github.com/TheAnachronism/docspell.git
synced 2025-11-03 18:00:11 +00:00
3d49ceaab5
- Use another external tool to convert pdf to pdf which also adds the extracted text as another layer into the pdf - Although not used, the external conversion routine will now check for an existing text file that is named as the pdf file with extension `.txt`. If present it is included in the conversion result and will be used as the extracted text. - text extraction for pdf files happens now on the converted file, because it may already contain the text from the conversion step and thus avoids running OCR twice. - All errors during conversion are not fatal; processing continues without a converted file.
48 lines
1.1 KiB
Docker
48 lines
1.1 KiB
Docker
FROM alpine:latest
|
|
|
|
ENV UNO_URL https://raw.githubusercontent.com/unoconv/unoconv/0.9.0/unoconv
|
|
|
|
LABEL maintainer="eikek0 <eike@docspell.org>"
|
|
|
|
RUN apk add --no-cache openjdk11-jre \
|
|
unzip \
|
|
bash \
|
|
curl \
|
|
ghostscript \
|
|
tesseract-ocr \
|
|
tesseract-ocr-data-deu \
|
|
unpaper \
|
|
wkhtmltopdf \
|
|
libreoffice \
|
|
ttf-droid-nonlatin \
|
|
ttf-droid \
|
|
ttf-dejavu \
|
|
ttf-freefont \
|
|
ttf-liberation \
|
|
libxml2-dev \
|
|
libxslt-dev \
|
|
pngquant \
|
|
zlib-dev \
|
|
g++ \
|
|
qpdf \
|
|
python3-dev \
|
|
libffi-dev\
|
|
qpdf-dev \
|
|
&& pip3 install --upgrade pip \
|
|
&& pip3 install ocrmypdf \
|
|
&& curl -Ls $UNO_URL -o /usr/local/bin/unoconv \
|
|
&& chmod +x /usr/local/bin/unoconv \
|
|
&& ln -s /usr/bin/python3 /usr/bin/python \
|
|
&& mkdir -p /opt \
|
|
&& cd /opt \
|
|
&& curl -L -o docspell.zip https://github.com/eikek/docspell/releases/download/v0.8.0/docspell-joex-0.8.0.zip \
|
|
&& unzip docspell.zip \
|
|
&& rm docspell.zip \
|
|
&& apk del curl unzip libxml2-dev libxslt-dev zlib-dev g++ python3-dev libffi-dev qpdf-dev
|
|
|
|
COPY entrypoint-joex.sh /opt/entrypoint.sh
|
|
|
|
EXPOSE 7878
|
|
|
|
ENTRYPOINT ["/opt/entrypoint.sh"]
|