blob: c9d9793d998f80cda18ff17e21e47cf7367460e1 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
|
pkgbase = uctodata
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.
pkgver = 0.11
pkgrel = 1
url = https://languagemachines.github.io/ucto
arch = any
license = GPL3
makedepends = libtool
makedepends = autoconf
makedepends = autoconf-archive
options = !libtool
source = https://github.com/LanguageMachines/uctodata/archive/v0.11.tar.gz
md5sums = 4539b58f799d75cc1067296c5087f19c
pkgname = uctodata
|