nixpkgs/pkgs/applications/graphics/tesseract/fetch-language-hashes
Erik Arvstedt b818997807
tesseract: add separate language derivations
This frees users from downloading all languages when building
Tesseract with a custom set of languages.

`enableLanguagesHash` is now obsolete.
2018-12-19 18:08:21 +01:00

36 lines
856 B
Bash
Executable File

#!/usr/bin/env bash
# Usage:
# ./fetch-language-hashes <tessdataRev> [<language code>…]
#
# Fetches all languages if no language codes are given.
#
# Example:
# ./fetch-language-hashes 4.0.0 eng spa
#
# Output:
# eng = "0iy0...";
# spa = "15kw...";
set -e
(( $# >= 1 )) || exit 1
tessdataRev=$1
shift
if (( $# > 0 )); then
langCodes="$@"
else
repoPage=$(curl -fs https://github.com/tesseract-ocr/tessdata/tree/$tessdataRev || {
>&2 echo "Invalid tessdataRev: $tessdataRev"
exit 1
})
langCodes=$(echo $(echo "$repoPage" | grep -ohP "(?<=/)[^/]+?(?=\.traineddata)" | sort))
fi
for lang in $langCodes; do
url=https://github.com/tesseract-ocr/tessdata/raw/$tessdataRev/$lang.traineddata
hash=$(nix-prefetch-url $url 2>/dev/null)
echo "$lang = \"$hash\";"
done