mirror of
https://github.com/NixOS/nixpkgs.git
synced 2025-01-14 17:04:42 +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-build a08b3a4d19.tar.gz \
--argstr baseRev b32a094368
result/bin/apply-formatting $NIXPKGS_PATH
72 lines
1.8 KiB
Nix
72 lines
1.8 KiB
Nix
{
|
|
lib,
|
|
stdenv,
|
|
fetchurl,
|
|
automake,
|
|
autoconf,
|
|
libtool,
|
|
pkg-config,
|
|
autoconf-archive,
|
|
libxml2,
|
|
icu,
|
|
bzip2,
|
|
libtar,
|
|
languageMachines,
|
|
}:
|
|
|
|
let
|
|
release = lib.importJSON ./release-info/LanguageMachines-ucto.json;
|
|
in
|
|
|
|
stdenv.mkDerivation {
|
|
pname = "ucto";
|
|
version = release.version;
|
|
src = fetchurl {
|
|
inherit (release) url sha256;
|
|
name = "ucto-${release.version}.tar.gz";
|
|
};
|
|
nativeBuildInputs = [
|
|
pkg-config
|
|
automake
|
|
autoconf
|
|
];
|
|
buildInputs = [
|
|
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 lib; {
|
|
description = "Rule-based tokenizer for natural language";
|
|
mainProgram = "ucto";
|
|
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.
|
|
'';
|
|
};
|
|
|
|
}
|