mingw/mingw-packages/mingw-w64-tesseract-data/PKGBUILD

# Maintainer: Alexey Pavlov <alexpux@gmail.com>
# Maintainer: Ray Donnelly <mingw.android@gmail.com>

# The traineddata and related files for all languages should be placed in tessdata directory
# Creates separate traineddata packages for each language
# osd.traineddata (Orientation and script detection) is included with tesseract-ocr

_langs=(afr amh ara asm aze aze_cyrl bel ben bod bos bul cat ceb ces
chi_sim chi_tra chr cym dan deu dzo ell eng enm epo
est eus fas fin fra frk frm gle glg grc guj hat heb hin hrv hun
iku ind isl ita ita_old jav jpn kan kat kat_old kaz khm kir kor
lao lat lav lit mal mar mkd mlt msa mya nep nld nor ori pan pol
por pus ron rus san sin slk slv spa spa_old sqi srp srp_latn
swa swe syr tam tel tgk tha tir tur uig ukr urd uzb uzb_cyrl vie yid)

_langs_deva=(hin mar nep san) 

_realname=tesseract-data
pkgbase=mingw-w64-${_realname}
pkgname=($(for l in ${_langs[@]}; do echo ${MINGW_PACKAGE_PREFIX}-${_realname}-${l}; done) )
tagver=4.0.0-beta.1
pkgver=4.0.0
pkgrel=1
pkgdesc="Language tessdata for Tesseract OCR engine (mingw-w64)"
arch=('any')
mingw_arch=('mingw32' 'mingw64' 'ucrt64' 'clang64' 'clang32')
url="https://github.com/tesseract-ocr/tessdata_fast"
license=("Apache License 2.0")

depends=()
source=(${_realname}-${pkgver}.tar.gz::https://github.com/tesseract-ocr/tessdata_fast/archive/${tagver}.tar.gz)
sha256sums=('cfae2d9e15887a719c995baad70c01ad8f68c0361f5f0a4f46e4aa9ed8a47120')

build() {
  true
}

# Declare the package functions for tessdata
for l in ${_langs[@]}; do
    eval "
package_${MINGW_PACKAGE_PREFIX}-${_realname}-${l}(){
    pkgdesc=\"($l) Language tessdata for Tesseract OCR engine (mingw-w64)\"
    groups=(${_realname})

    mkdir -p \${pkgdir}${MINGW_PREFIX}/share/tessdata
    cp \${srcdir}/tessdata_fast-${tagver}/${l}.* \${pkgdir}${MINGW_PREFIX}/share/tessdata/
    find \${pkgdir}${MINGW_PREFIX}/share/tessdata -type f -exec chmod 0644 {} \;
}
    "
done