TheAnachronism/docspell
1
0
Fork 0
mirror of https://github.com/TheAnachronism/docspell.git synced 2025-06-22 02:18:26 +00:00
Code Issues Packages Projects Releases Wiki Activity

temporary download khmer traineddata before the package being added to registry

Browse Source
This commit is contained in:
xshadowlegendx
2023-03-17 17:50:48 +07:00
parent 7202f9f117
commit 40642dea10
1 changed files with 6 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
docker/dockerfiles/joex.dockerfile
View File

@ -33,7 +33,6 @@ RUN apk update && \
tesseract-ocr-data-pol \ tesseract-ocr-data-pol \
tesseract-ocr-data-est \ tesseract-ocr-data-est \
tesseract-ocr-data-ukr \ tesseract-ocr-data-ukr \
tesseract-ocr-data-khm \
unpaper \ unpaper \
weasyprint \ weasyprint \
libreoffice \ libreoffice \
@ -70,6 +69,12 @@ RUN wget ${joex_url:-https://github.com/eikek/docspell/releases/download/v$versi
ln -snf docspell-joex-* docspell-joex && \ ln -snf docspell-joex-* docspell-joex && \
rm docspell-joex/conf/docspell-joex.conf rm docspell-joex/conf/docspell-joex.conf
# temporary download traineddata directly for khmer lang
# before tesseract-ocr-data-khm being added to the registry
RUN \
wget https://github.com/tesseract-ocr/tessdata/raw/main/khm.traineddata && \
mv khm.traineddata /usr/share/tessdata
# Using these data files for japanese, because they work better. See #973 # Using these data files for japanese, because they work better. See #973
RUN \ 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_vert.traineddata && \