mirror of
https://github.com/NixOS/nixpkgs.git
synced 2024-12-28 00:24:18 +00:00
4f0dadbf38
After final improvements to the official formatter implementation, this commit now performs the first treewide reformat of Nix files using it. This is part of the implementation of RFC 166. Only "inactive" files are reformatted, meaning only files that aren't being touched by any PR with activity in the past 2 months. This is to avoid conflicts for PRs that might soon be merged. Later we can do a full treewide reformat to get the rest, which should not cause as many conflicts. A CI check has already been running for some time to ensure that new and already-formatted files are formatted, so the files being reformatted here should also stay formatted. This commit was automatically created and can be verified using nix-builda08b3a4d19
.tar.gz \ --argstr baseRevb32a094368
result/bin/apply-formatting $NIXPKGS_PATH
61 lines
1.5 KiB
Nix
61 lines
1.5 KiB
Nix
{
|
|
lib,
|
|
stdenv,
|
|
fetchurl,
|
|
automake,
|
|
autoconf,
|
|
bzip2,
|
|
libtar,
|
|
libtool,
|
|
pkg-config,
|
|
autoconf-archive,
|
|
libxml2,
|
|
languageMachines,
|
|
}:
|
|
|
|
let
|
|
release = lib.importJSON ./release-info/LanguageMachines-mbt.json;
|
|
in
|
|
|
|
stdenv.mkDerivation {
|
|
pname = "mbt";
|
|
version = release.version;
|
|
src = fetchurl {
|
|
inherit (release) url sha256;
|
|
name = "mbt-${release.version}.tar.gz";
|
|
};
|
|
nativeBuildInputs = [
|
|
pkg-config
|
|
automake
|
|
autoconf
|
|
];
|
|
buildInputs = [
|
|
bzip2
|
|
libtar
|
|
libtool
|
|
autoconf-archive
|
|
libxml2
|
|
languageMachines.ticcutils
|
|
languageMachines.timbl
|
|
];
|
|
patches = [ ./mbt-add-libxml2-dep.patch ];
|
|
preConfigure = ''
|
|
sh bootstrap.sh
|
|
'';
|
|
|
|
meta = with 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.
|
|
'';
|
|
};
|
|
|
|
}
|