d8a7d04a29
Changelog: - Add heuristics for ambiguous quotation marks (issue #11). - Avoid false positives for emoticons that contain a space (issue #12). - Correctly tokenize obfuscated email addresses that contain spaces. - Do not split tl;dr and its German variant zl;ng. https://github.com/tsproisl/SoMaJo/releases/tag/v2.0.5
24 lines
619 B
Nix
24 lines
619 B
Nix
{ pkgs, stdenv, fetchFromGitHub, buildPythonPackage, isPy3k, regex }:
|
|
|
|
buildPythonPackage rec {
|
|
pname = "SoMaJo";
|
|
version = "2.0.5";
|
|
disabled = !isPy3k;
|
|
|
|
src = fetchFromGitHub {
|
|
owner = "tsproisl";
|
|
repo = pname;
|
|
rev = "v${version}";
|
|
sha256 = "01zvmqilnndh2b257z7bhcc7av5vhjm1g8gmdiiw15gcd2xfmqjs";
|
|
};
|
|
|
|
propagatedBuildInputs = [ regex ];
|
|
|
|
meta = with stdenv.lib; {
|
|
description = "Tokenizer and sentence splitter for German and English web texts";
|
|
homepage = "https://github.com/tsproisl/SoMaJo";
|
|
license = licenses.gpl3;
|
|
maintainers = with maintainers; [ danieldk ];
|
|
};
|
|
}
|