nixpkgs/pkgs/development/libraries/languagemachines/ucto.nix
Jonathan Ringer 9bb3fccb5b treewide: pkgs.pkgconfig -> pkgs.pkg-config, move pkgconfig to alias.nix
continuation of #109595

pkgconfig was aliased in 2018, however, it remained in
all-packages.nix due to its wide usage. This cleans
up the remaining references to pkgs.pkgsconfig and
moves the entry to aliases.nix.

python3Packages.pkgconfig remained unchanged because
it's the canonical name of the upstream package
on pypi.
2021-01-19 01:16:25 -08:00

50 lines
1.9 KiB
Nix

{ stdenv, fetchurl
, automake, autoconf, libtool, pkg-config, autoconf-archive
, libxml2, icu, bzip2, libtar
, languageMachines
}:
let
release = builtins.fromJSON (builtins.readFile ./release-info/LanguageMachines-ucto.json);
in
stdenv.mkDerivation {
name = "ucto-${release.version}";
version = release.version;
src = fetchurl { inherit (release) url sha256;
name = "ucto-${release.version}.tar.gz"; };
nativeBuildInputs = [ pkg-config ];
buildInputs = [ automake autoconf bzip2 libtool autoconf-archive
icu libtar libxml2
languageMachines.ticcutils
languageMachines.libfolia
languageMachines.uctodata
# TODO textcat from libreoffice? Pulls in X11 dependencies?
];
preConfigure = "sh bootstrap.sh;";
postInstall = ''
# ucto expects the data files installed in the same prefix
mkdir -p $out/share/ucto/;
for f in ${languageMachines.uctodata}/share/ucto/*; do
echo "Linking $f"
ln -s $f $out/share/ucto/;
done;
'';
meta = with stdenv.lib; {
description = "A 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.
'';
};
}