initial import

tesseract/PKGBUILD

@@ -0,0 +1,62 @@
+# Maintainer: Jesus E. <heckyel@riseup.net>
+
+_langs=(afr amh ara asm aze aze_cyrl bel ben bod bos bre bul cat ceb ces
+    chi_sim chi_tra chr cos cym dan dan_frak deu deu_frak div dzo ell eng enm epo
+    equ est eus fao fas fil fin fra frk frm fry gla gle glg grc guj hat heb
+    hin hrv hun hye iku ind isl ita ita_old jav jpn kan kat kat_old kaz khm
+    kir kmr kor kor_vert lao lat lav lit ltz mal mar mkd mlt mon mri msa
+    mya nep nld nor oci ori osd pan pol por pus que ron rus san sin slk
+    slk_frak slv snd spa spa_old sqi srp srp_latn sun swa swe syr tam tat
+    tel tgk tgl tha tir ton tur uig ukr urd uzb uzb_cyrl vie yid yor)
+
+pkgname=tesseract
+pkgver=4.1.1
+_debver=4.1.1
+_debrel=2.1
+pkgrel=1
+pkgdesc='An OCR program'
+arch=('i686' 'x86_64')
+url='https://github.com/tesseract-ocr/tesseract'
+license=('Apache-2.0')
+depends=('libpng' 'libtiff' 'libjpeg-turbo' 'zlib' 'giflib' 'gcc-libs' 'curl' 'libarchive' 'leptonica')
+makedepends=('icu' 'cairo' 'pango' 'asciidoc' 'quilt')
+install=tesseract.install
+optdepends=('icu' 'cairo' 'pango'
+	    $(for l in ${_langs[@]}; do echo tesseract-data-${l}; done))
+source=($pkgname-$pkgver.tar.gz::https://github.com/tesseract-ocr/tesseract/archive/$pkgver.tar.gz
+        https://deb.debian.org/debian/pool/main/t/tesseract/tesseract_$_debver-$_debrel.debian.tar.xz
+        https://github.com/tesseract-ocr/tessdata/raw/bf82613055ebc6e63d9e3b438a5c234bfd638c93/osd.traineddata)
+sha512sums=('017723a2268be789fe98978eed02fd294968cc8050dde376dee026f56f2b99df42db935049ae5e72c4519a920e263b40af1a6a40d9942e66608145b3131a71a2'
+            '458f805cb13dce5538e9811ea0e243275e82d7bcb7aef8f468c7ed20a0e278bcee1ff4cc874ba1952a8d9d27b2f5f1eabaa4cad659668a38474d579e4334082d'
+            'c54f481903187bed19cf14c69b24c44044b540f50814de66dff8d35e6987eea71ef4464492a8fae9242fcb22cccbe59e009f3a4dab6c36ad63f78c52ebe9628f')
+
+prepare() {
+  cd "$srcdir"/$pkgname-${pkgver}
+  if [[ ${pkgver%.*} = ${_debver%.*} ]]; then
+    # Debian patches
+    export QUILT_PATCHES=debian/patches
+    export QUILT_REFRESH_ARGS='-p ab --no-timestamps --no-index'
+    export QUILT_DIFF_ARGS='--no-timestamps'
+
+    mv "$srcdir"/debian .
+
+    quilt push -av
+  fi
+}
+
+build() {
+  cd "$srcdir"/$pkgname-${pkgver}
+  [ -x configure ] || ./autogen.sh
+  [ -f Makefile ] || ./configure --prefix=/usr
+  make
+  make training
+}
+
+package() {
+  cd "$srcdir"/$pkgname-${pkgver}
+  make DESTDIR="$pkgdir" install
+  make DESTDIR="$pkgdir" training-install
+  mkdir -p "$pkgdir"/usr/share/tessdata
+  install -Dm0644 "$srcdir"/osd.traineddata "$pkgdir"/usr/share/tessdata/osd.traineddata
+  install -Dm644 LICENSE -t "${pkgdir}/usr/share/licenses/$pkgname"
+}