blob: 83abf3790c7c8bdd8d192632a63250914f58ae74 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
|
# Maintainer: Maarten van Gompel <proycon at anaproy dot nl>
pkgname=uctodata
pkgver=0.4
pkgrel=1
pkgdesc="An advanced rule-based (regular-expression) and unicode-aware tokenizer for various languages. Tokenization is an essential first step in any NLP pipeline. This package contains the necessary data."
arch=('any')
license=('GPL3')
makedepends=('libtool' 'autoconf' 'autoconf-archive')
options=(!libtool)
_gituser="LanguageMachines"
_gitname="uctodata"
url="https://languagemachines.github.io/ucto"
source=(https://github.com/LanguageMachines/uctodata/archive/v0.4.tar.gz)
md5sums=(18375c2045aa853aed52bd564fae4d2a)
build() {
cd $srcdir/$pkgname-$pkgver
bash bootstrap.sh
./configure --prefix=/usr --sysconfdir=/etc --localstatedir=/var
make
}
package() {
cd $srcdir/$pkgname-$pkgver
make DESTDIR=$pkgdir install
}
|