aboutsummaryrefslogtreecommitdiff
path: root/gnu
diff options
context:
space:
mode:
authorJulien Lepiller <julien@lepiller.eu>2022-07-04 21:42:02 +0200
committerJulien Lepiller <julien@lepiller.eu>2023-04-01 16:38:16 +0200
commit4483296da3e2e1424d12d92d0f56fb428765ca43 (patch)
treee4e45e3af3173a59651935c4069100745a212705 /gnu
parent799abe85c53426b9ec4ae0244dc9e184e3bbc171 (diff)
downloadguix-4483296da3e2e1424d12d92d0f56fb428765ca43.tar.gz
guix-4483296da3e2e1424d12d92d0f56fb428765ca43.zip
gnu: Add mecab-unidic.
* gnu/packages/language.scm (mecab-unidic): New variable.
Diffstat (limited to 'gnu')
-rw-r--r--gnu/packages/language.scm27
1 files changed, 27 insertions, 0 deletions
diff --git a/gnu/packages/language.scm b/gnu/packages/language.scm
index 1f3d5a6cc8..208fab4f5b 100644
--- a/gnu/packages/language.scm
+++ b/gnu/packages/language.scm
@@ -28,6 +28,7 @@
#:use-module (gnu packages autotools)
#:use-module (gnu packages audio)
#:use-module (gnu packages base)
+ #:use-module (gnu packages compression)
#:use-module (gnu packages docbook)
#:use-module (gnu packages emacs)
#:use-module (gnu packages freedesktop)
@@ -58,6 +59,7 @@
#:use-module (gnu packages xorg)
#:use-module (guix packages)
#:use-module (guix build-system cmake)
+ #:use-module (guix build-system copy)
#:use-module (guix build-system glib-or-gtk)
#:use-module (guix build-system gnu)
#:use-module (guix build-system perl)
@@ -1004,3 +1006,28 @@ Corporation. The engine is independent of any language, dictionary or corpus.")
(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 user’s choice)
+ (license (list license:gpl2+ license:lgpl2.1 license:bsd-3))))