blob: 278723db2311e69e3035d88bab0c3c82b80972f7 (
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
27
28
29
30
31
32
33
34
35
36
|
# Maintainer: Maarten van Gompel <proycon at anaproy.nl>
_pkgname=uctodata
pkgname=uctodata-git
pkgver=8
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. These are the data files."
arch=('any')
url="http://languagemachines.github.io/ucto/"
license=('GPL')
provides=('uctodata')
conflicts=('uctodata')
makedepends=('libtool' 'autoconf')
options=(!libtool)
source=("git://github.com/LanguageMachines/uctodata.git")
_gitname=("uctodata")
noextract=()
md5sums=('SKIP')
pkgver() {
cd "$srcdir/$_gitname"
git rev-list --count HEAD
}
build() {
cd "$srcdir/$_gitname"
bash bootstrap.sh || return 1
./configure --prefix=/usr --sysconfdir=/etc --localstatedir=/var || return 1
make || return 1
}
package() {
cd "$srcdir/$_gitname"
make DESTDIR=$pkgdir install
}
|