Luke Granger-Brown
57725ef3ec
git-subtree-dir: third_party/nixpkgs git-subtree-split: 76612b17c0ce71689921ca12d9ffdc9c23ce40b2
32 lines
1.3 KiB
Nix
32 lines
1.3 KiB
Nix
{ lib, stdenv, fetchurl
|
|
, automake, autoconf, libtool, pkg-config, autoconf-archive
|
|
}:
|
|
|
|
let
|
|
release = lib.importJSON ./release-info/LanguageMachines-uctodata.json;
|
|
in
|
|
|
|
stdenv.mkDerivation {
|
|
pname = "uctodata";
|
|
version = release.version;
|
|
src = fetchurl { inherit (release) url sha256;
|
|
name = "uctodata-${release.version}.tar.gz"; };
|
|
nativeBuildInputs = [ pkg-config automake autoconf ];
|
|
buildInputs = [ libtool autoconf-archive ];
|
|
preConfigure = "sh bootstrap.sh";
|
|
|
|
meta = with lib; {
|
|
description = "Rule-based tokenizer for natural language";
|
|
homepage = "https://languagemachines.github.io/ucto/";
|
|
license = licenses.gpl3;
|
|
platforms = platforms.all;
|
|
maintainers = with maintainers; [ roberth ];
|
|
|
|
longDescription = ''
|
|
Ucto tokenizes text files: it separates words from punctuation, and splits sentences. It offers several other basic preprocessing steps such as changing case that you can all use to make your text suited for further processing such as indexing, part-of-speech tagging, or machine translation.
|
|
|
|
Ucto comes with tokenisation rules for several languages and can be easily extended to suit other languages. It has been incorporated for tokenizing Dutch text in Frog, a Dutch morpho-syntactic processor.
|
|
'';
|
|
};
|
|
|
|
}
|