diff options
author | Julien Malka <julien@malka.sh> | 2024-02-27 13:42:58 +0100 |
---|---|---|
committer | GitHub <noreply@github.com> | 2024-02-27 13:42:58 +0100 |
commit | f52fdedfb0e03ab7308a5d23983670975ddcba0e (patch) | |
tree | 811332d342d5e234b39ff369eabd3508045e30bf /pkgs/by-name/cl | |
parent | 661d1becc7fdb64894cb4741528f574587537f2f (diff) | |
parent | 202dd43c67a840fcf460567fcd748341e7ba71bf (diff) |
Merge pull request #291173 from chvp/upd/mu
Diffstat (limited to 'pkgs/by-name/cl')
-rw-r--r-- | pkgs/by-name/cl/cld2/package.nix | 50 |
1 files changed, 50 insertions, 0 deletions
diff --git a/pkgs/by-name/cl/cld2/package.nix b/pkgs/by-name/cl/cld2/package.nix new file mode 100644 index 0000000000000..bf28b160f2bab --- /dev/null +++ b/pkgs/by-name/cl/cld2/package.nix @@ -0,0 +1,50 @@ +{ lib +, stdenv +, fetchFromGitHub +, cmake +, fetchpatch +}: + +stdenv.mkDerivation { + pname = "cld2"; + version = "unstable-2015-08-21"; + + src = fetchFromGitHub { + owner = "CLD2Owners"; + repo = "cld2"; + rev = "b56fa78a2fe44ac2851bae5bf4f4693a0644da7b"; + hash = "sha256-YhXs45IbriKWKULguZM4DgfV/Fzr73VHxA1pFTXCyv8="; + }; + + patches = [ + (fetchpatch { + name = "add-cmakelists.txt"; + url = "https://github.com/CLD2Owners/cld2/pull/65/commits/9cfac02c2ac7802ab7079560b38a474473c45f51.patch"; + hash = "sha256-uOjmUk8kMFl+wED44ErXoLRyblhgDwFx9K1Wj65Omh8="; + }) + ]; + + nativeBuildInputs = [ cmake ]; + + meta = with lib; { + homepage = "https://github.com/CLD2Owners/cld2"; + description = "Compact Language Detector 2"; + longDescription = '' + CLD2 probabilistically detects over 80 languages in Unicode UTF-8 text, + either plain text or HTML/XML. Legacy encodings must be converted to valid + UTF-8 by the caller. For mixed-language input, CLD2 returns the top three + languages found and their approximate percentages of the total text bytes + (e.g. 80% English and 20% French out of 1000 bytes of text means about 800 + bytes of English and 200 bytes of French). Optionally, it also returns a + vector of text spans with the language of each identified. This may be + useful for applying different spelling-correction dictionaries or + different machine translation requests to each span. The design target is + web pages of at least 200 characters (about two sentences); CLD2 is not + designed to do well on very short text, lists of proper names, part + numbers, etc. + ''; + license = licenses.asl20; + maintainers = with maintainers; [ chvp ]; + platforms = platforms.all; + }; +} |