Stirling-PDF/scripts/init.sh
Anthony Stirling 71e93e3cb5
print (WIP), fake scan (WIP) and text conversion for ultra-lite (#1098)
* Changes!

* lang

* fake scan init, print init and pdf to text for exe

* Hardening suggestions for Stirling-PDF / changes (#1099)

* Switch order of literals to prevent NullPointerException

* Introduced protections against predictable RNG abuse

---------

Co-authored-by: pixeebot[bot] <104101892+pixeebot[bot]@users.noreply.github.com>

* Update README.md

* install custom fonts

* Formats etc

* version bump

* disable WIP work

* remove chinese font

---------

Co-authored-by: pixeebot[bot] <104101892+pixeebot[bot]@users.noreply.github.com>
Co-authored-by: systo <systo@host.docker.internal>
2024-04-21 23:06:44 +01:00

31 lines
1.0 KiB
Bash

#!/bin/bash
# Copy the original tesseract-ocr files to the volume directory without overwriting existing files
echo "Copying original files without overwriting existing files"
mkdir -p /usr/share/tessdata
cp -rn /usr/share/tessdata-original/* /usr/share/tessdata
if [ -d /usr/share/tesseract-ocr/4.00/tessdata ]; then
cp -r /usr/share/tesseract-ocr/4.00/tessdata/* /usr/share/tessdata || true;
fi
if [ -d /usr/share/tesseract-ocr/5/tessdata ]; then
cp -r /usr/share/tesseract-ocr/5/tessdata/* /usr/share/tessdata || true;
fi
# Check if TESSERACT_LANGS environment variable is set and is not empty
if [[ -n "$TESSERACT_LANGS" ]]; then
# Convert comma-separated values to a space-separated list
LANGS=$(echo $TESSERACT_LANGS | tr ',' ' ')
pattern='^[a-zA-Z]{2,4}(_[a-zA-Z]{2,4})?$'
# Install each language pack
for LANG in $LANGS; do
if [[ $LANG =~ $pattern ]]; then
apk add --no-cache "tesseract-ocr-data-$LANG"
else
echo "Skipping invalid language code"
fi
done
fi
/scripts/init-without-ocr.sh "$@"