nixpkgs/pkgs/development/libraries/languagemachines/mbt.nix
Matthew Bauer 02297beade treewide: add version to packages
Lots of packages are missing versions in their name. This adds them
where appropriate. These were found with this command:

 $ nix-env -qa -f. | grep -v '\-[0-9A-Za-z.-_+]*$' | grep -v '^hook$'

See issue #41007.
2018-05-25 15:48:05 -05:00

41 lines
1.5 KiB
Nix

{ stdenv, fetchurl
, automake, autoconf, bzip2, libtar, libtool, pkgconfig, autoconf-archive
, libxml2
, languageMachines
}:
let
release = builtins.fromJSON (builtins.readFile ./release-info/LanguageMachines-mbt.json);
in
stdenv.mkDerivation {
name = "mbt-${release.version}";
version = release.version;
src = fetchurl { inherit (release) url sha256;
name = "mbt-${release.version}.tar.gz"; };
nativeBuildInputs = [ pkgconfig ];
buildInputs = [ automake autoconf bzip2 libtar libtool autoconf-archive
libxml2
languageMachines.ticcutils
languageMachines.timbl
];
patches = [ ./mbt-add-libxml2-dep.patch ];
preConfigure = ''
sh bootstrap.sh
'';
meta = with stdenv.lib; {
description = "Memory Based Tagger";
homepage = https://languagemachines.github.io/mbt/;
license = licenses.gpl3;
platforms = platforms.all;
maintainers = with maintainers; [ roberth ];
longDescription = ''
MBT is a memory-based tagger-generator and tagger in one. The tagger-generator part can generate a sequence tagger on the basis of a training set of tagged sequences; the tagger part can tag new sequences. MBT can, for instance, be used to generate part-of-speech taggers or chunkers for natural language processing. It has also been used for named-entity recognition, information extraction in domain-specific texts, and disfluency chunking in transcribed speech.
Mbt is used by Frog for Dutch tagging.
'';
};
}