gnu: Add mecab.

* gnu/packages/language.scm (mecab): New variable.
* gnu/packages/patches/mecab-variable-param.patch: New file.
* gnu/local.mk (dist_patch_DATA): Add it.

2 files changed, 80 insertions, 1 deletions

diff --git a/gnu/packages/language.scm b/gnu/packages/language.scm
index f7e3ea6cd6..5dda0c1eeb 100644
--- a/gnu/packages/language.scm
+++ b/gnu/packages/language.scm
@@ -4,7 +4,7 @@
 ;;; Copyright © 2018 Nikita <nikita@n0.is>
 ;;; Copyright © 2019 Alex Vong <alexvong1995@gmail.com>
 ;;; Copyright © 2020 Ricardo Wurmus <rekado@elephly.net>
-;;; Copyright © 2020 Julien Lepiller <julien@lepiller.eu>
+;;; Copyright © 2020, 2022 Julien Lepiller <julien@lepiller.eu>
 ;;; Copyright © 2022 Milran <milranmike@protonmail.com>
 ;;;
 ;;; This file is part of GNU Guix.
@@ -928,3 +928,52 @@ and manipulation.")
     (description
      "libskk is a library to deal with Japanese kana-to-kanji conversion method.")
     (license license:gpl3+)))
+
+(define-public mecab
+  (package
+    (name "mecab")
+    (version "0.996")
+    (source (origin
+              (method git-fetch)
+              (uri (git-reference
+                     (url "https://github.com/taku910/mecab")
+                     ;; latest commit
+                     (commit "046fa78b2ed56fbd4fac312040f6d62fc1bc31e3")))
+              (file-name (git-file-name name version))
+              (sha256
+               (base32
+                "1hdv7rgn8j0ym9gsbigydwrbxa8cx2fb0qngg1ya15vvbw0lk4aa"))
+              (patches
+                (search-patches
+                  "mecab-variable-param.patch"))))
+    (build-system gnu-build-system)
+    (native-search-paths
+      (list (search-path-specification
+              (variable "MECAB_DICDIR")
+              (separator #f)
+              (files '("lib/mecab/dic")))))
+    (arguments
+     `(#:phases
+       (modify-phases %standard-phases
+         (add-after 'unpack 'chdir
+           (lambda _
+             (chdir "mecab")))
+         (add-before 'build 'add-mecab-dicdir-variable
+           (lambda _
+             (substitute* "mecabrc.in"
+               (("dicdir = .*")
+                "dicdir = $MECAB_DICDIR"))
+             (substitute* "mecab-config.in"
+               (("echo @libdir@/mecab/dic")
+                "if [ -z \"$MECAB_DICDIR\" ]; then
+  echo @libdir@/mecab/dic
+else
+  echo \"$MECAB_DICDIR\"
+fi")))))))
+    (inputs (list libiconv))
+    (home-page "https://taku910.github.io/mecab")
+    (synopsis "Morphological analysis engine for texts")
+    (description "Mecab is a morphological analysis engine developped as a
+collaboration between the Kyoto university and Nippon Telegraph and Telephone
+Corporation.  The engine is independent of any language, dictionary or corpus.")
+    (license (list license:gpl2+ license:lgpl2.1+ license:bsd-3))))
diff --git a/gnu/packages/patches/mecab-variable-param.patch b/gnu/packages/patches/mecab-variable-param.patch
new file mode 100644
index 0000000000..4457cf3f44
--- /dev/null
+++ b/gnu/packages/patches/mecab-variable-param.patch
@@ -0,0 +1,30 @@
+From 2396e90056706ef897acab3aaa081289c7336483 Mon Sep 17 00:00:00 2001
+From: LEPILLER Julien <julien.lepiller@irisa.fr>
+Date: Fri, 19 Apr 2019 11:48:39 +0200
+Subject: [PATCH] Allow variable parameters
+
+---
+ mecab/src/param.cpp | 6 +++++-
+ 1 file changed, 5 insertions(+), 1 deletion(-)
+
+diff --git a/mecab/src/param.cpp b/mecab/src/param.cpp
+index 65328a2..006b1b5 100644
+--- a/mecab/src/param.cpp
++++ b/mecab/src/param.cpp
+@@ -79,8 +79,12 @@ bool Param::load(const char *filename) {
+     size_t s1, s2;
+     for (s1 = pos+1; s1 < line.size() && isspace(line[s1]); s1++);
+     for (s2 = pos-1; static_cast<long>(s2) >= 0 && isspace(line[s2]); s2--);
+-    const std::string value = line.substr(s1, line.size() - s1);
++    std::string value = line.substr(s1, line.size() - s1);
+     const std::string key   = line.substr(0, s2 + 1);
++
++    if(value.find('$') == 0) {
++        value = std::getenv(value.substr(1).c_str());
++    }
+     set<std::string>(key.c_str(), value, false);
+   }
+ 
+-- 
+2.20.1
+