gnu: Add mecab-unidic.

* gnu/packages/language.scm (mecab-unidic): New variable.
This commit is contained in:
Julien Lepiller 2022-07-04 21:42:02 +02:00 committed by Maxim Cournoyer
parent 04688c56e1
commit c16251be05
No known key found for this signature in database
GPG key ID: 1260E46482E63562

View file

@ -1006,3 +1006,28 @@ (define-public mecab-ipadic
(description "This package contains dictionnary data derived from
ipadic for use with MeCab.")
(license (license:non-copyleft "mecab-ipadic/COPYING"))))
(define-public mecab-unidic
(package
(name "mecab-unidic")
(version "3.1.0")
(source (origin
(method url-fetch)
(uri (string-append "https://clrd.ninjal.ac.jp/unidic_archive/cwj/"
version "/unidic-cwj-" version ".zip"))
(sha256
(base32
"1z132p2q3bgchiw529j2d7dari21kn0fhkgrj3vcl0ncg2m521il"))))
(build-system copy-build-system)
(arguments
`(#:install-plan
'(("." "lib/mecab/dic"
#:include-regexp ("\\.bin$" "\\.def$" "\\.dic$" "dicrc")))))
(native-inputs (list unzip))
(home-page "https://clrd.ninjal.ac.jp/unidic/en/")
(synopsis "Dictionary data for MeCab")
(description "UniDic for morphological analysis is a dictionary for
analysis with the morphological analyser MeCab, where the short units exported
from the database are used as entries (heading terms).")
;; triple-licensed (at the users choice)
(license (list license:gpl2+ license:lgpl2.1 license:bsd-3))))