mirror of
https://github.com/TheAnachronism/docspell.git
synced 2024-11-13 02:31:10 +00:00
5cd5ba46af
zlib 1.2.12-r0 is not working with openjdk, it affects the checksum calculation of the db migrations. It must be at least 1.2.12-r1. For some reason joex has this newer version, but the restserver image not. They are installed explicitely now on both images. That's why the migration is now disabled on rest-server in the docker-compose file. It is ok if this is run on one server. It can now happen that on first start joex is migrating the db and the restserver tries to do things that don't work yet - it is a corner case. This is removed with the next version. Refs: #1517
84 lines
2.4 KiB
Docker
84 lines
2.4 KiB
Docker
FROM alpine:3.14
|
|
|
|
ARG version=
|
|
ARG joex_url=
|
|
ARG UNO_URL=https://raw.githubusercontent.com/unoconv/unoconv/0.9.0/unoconv
|
|
ARG TARGETPLATFORM
|
|
|
|
RUN JDKPKG="openjdk11-jre"; \
|
|
if [[ $TARGETPLATFORM = linux/arm* ]]; then JDKPKG="openjdk8-jre"; fi; \
|
|
apk update && \
|
|
apk add --no-cache $JDKPKG \
|
|
tzdata \
|
|
bash \
|
|
curl \
|
|
docker \
|
|
ghostscript \
|
|
tesseract-ocr \
|
|
tesseract-ocr-data-deu \
|
|
tesseract-ocr-data-fra \
|
|
tesseract-ocr-data-ita \
|
|
tesseract-ocr-data-spa \
|
|
tesseract-ocr-data-por \
|
|
tesseract-ocr-data-ces \
|
|
tesseract-ocr-data-nld \
|
|
tesseract-ocr-data-dan \
|
|
tesseract-ocr-data-fin \
|
|
tesseract-ocr-data-nor \
|
|
tesseract-ocr-data-swe \
|
|
tesseract-ocr-data-rus \
|
|
tesseract-ocr-data-ron \
|
|
tesseract-ocr-data-lav \
|
|
tesseract-ocr-data-jpn \
|
|
tesseract-ocr-data-heb \
|
|
tesseract-ocr-data-lit \
|
|
tesseract-ocr-data-pol \
|
|
unpaper \
|
|
wkhtmltopdf \
|
|
libreoffice \
|
|
ttf-droid-nonlatin \
|
|
ttf-droid \
|
|
ttf-dejavu \
|
|
ttf-freefont \
|
|
ttf-liberation \
|
|
libxml2-dev \
|
|
libxslt-dev \
|
|
pngquant \
|
|
zlib-dev \
|
|
g++ \
|
|
qpdf \
|
|
py3-pip \
|
|
python3-dev \
|
|
libffi-dev\
|
|
qpdf-dev \
|
|
openssl-dev \
|
|
ocrmypdf \
|
|
&& apk add 'zlib=1.2.12-r1' \
|
|
&& pip3 install --upgrade pip \
|
|
&& pip3 install ocrmypdf \
|
|
&& curl -Ls $UNO_URL -o /usr/local/bin/unoconv \
|
|
&& chmod +x /usr/local/bin/unoconv \
|
|
&& apk del libxml2-dev libxslt-dev zlib-dev g++ python3-dev py3-pip libffi-dev qpdf-dev openssl-dev \
|
|
&& ln -s /usr/bin/python3 /usr/bin/python
|
|
|
|
WORKDIR /opt
|
|
RUN wget ${joex_url:-https://github.com/eikek/docspell/releases/download/v$version/docspell-joex-$version.zip} && \
|
|
unzip docspell-joex-*.zip && \
|
|
rm docspell-joex-*.zip && \
|
|
ln -snf docspell-joex-* docspell-joex && \
|
|
rm docspell-joex/conf/docspell-joex.conf
|
|
|
|
# Using these data files for japanese, because they work better. See #973
|
|
RUN \
|
|
wget https://raw.githubusercontent.com/tesseract-ocr/tessdata_fast/master/jpn_vert.traineddata && \
|
|
wget https://raw.githubusercontent.com/tesseract-ocr/tessdata_fast/master/jpn.traineddata && \
|
|
mv jpn*.traineddata /usr/share/tessdata
|
|
|
|
COPY joex-entrypoint.sh /opt/joex-entrypoint.sh
|
|
|
|
ENTRYPOINT ["/opt/joex-entrypoint.sh", "-J-XX:+UseG1GC"]
|
|
EXPOSE 7878
|
|
|
|
HEALTHCHECK --interval=1m --timeout=10s --retries=2 --start-period=30s \
|
|
CMD wget --spider http://localhost:7878/api/info/version
|