diff mbox series

[bug#56386,3/3] gnu: Add mecab-unidic.

Message ID 20220704194202.30958-3-julien@lepiller.eu
State New
Headers
Series [bug#56386,1/3] gnu: Add mecab. |

Commit Message

Julien Lepiller July 4, 2022, 7:42 p.m. UTC 
  * gnu/packages/language.scm (mecab-unidic): New variable.
---
 gnu/packages/language.scm | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

Comments

Ludovic Courtès July 17, 2022, 7:33 p.m. UTC | #1 
Hi,

Julien Lepiller <julien@lepiller.eu> skribis:

> +    (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).")
> +    (license (list license:gpl2+ license:lgpl2.1 license:bsd-3))))

Maybe add a comment stating whether this is triple-licensed (at the
user’s choice) or if that means that there are files under each of
these.

Otherwise the whole series LGTM!

Ludo’.
diff mbox series

Patch

diff --git a/gnu/packages/language.scm b/gnu/packages/language.scm
index 63654c544b..f97b982cb9 100644
--- a/gnu/packages/language.scm
+++ b/gnu/packages/language.scm
@@ -27,6 +27,7 @@  (define-module (gnu packages language)
   #: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)
@@ -57,6 +58,7 @@  (define-module (gnu packages language)
   #: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)
@@ -997,3 +999,27 @@  (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).")
+    (license (list license:gpl2+ license:lgpl2.1 license:bsd-3))))