Created
June 11, 2009 01:59
-
-
Save lopnor/127653 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!perl | |
use strict; | |
use warnings; | |
use utf8; | |
use Text::MeCab::Dict; | |
use File::Basename; | |
use Path::Class; | |
use Carp qw(confess); | |
{ | |
no warnings qw(redefine once); | |
my $orig = *Text::MeCab::Dict::new{CODE}; | |
Text::MeCab::Dict->mk_accessors('system_dict'); | |
*Text::MeCab::Dict::new = sub { | |
my ($class, %args) = @_; | |
my $self = $orig->($class, %args); | |
$self->system_dict($args{system_dict}); | |
return $self; | |
}; | |
*Text::MeCab::Dict::build = sub { | |
my ($self, $file, $target_dict) = @_; | |
$file or confess "source file required"; | |
$target_dict ||= [ fileparse($file,qr{\.[^.]*}) ]->[0] . '.dict'; | |
my $dict_source = $self->dict_source; | |
my $dict_index = $self->libexecdir->file('mecab-dict-index'); | |
my $curdir = Path::Class::Dir->new->absolute; | |
eval { | |
chdir $dict_source; | |
system($dict_index, | |
'-f' => $self->input_encoding, | |
'-t' => $self->output_encoding, | |
'-d' => $self->system_dict, | |
'-u' => $target_dict, | |
$file, | |
); | |
}; | |
if (my $e = $@) { | |
chdir $curdir; | |
die $e; | |
} | |
}; | |
} | |
my $dict = Text::MeCab::Dict->new( | |
system_dict => '/usr/local/lib/mecab/dic/naist-jdic', | |
dict_source => '.', | |
ie => 'utf-8', | |
oe => 'utf-8', | |
); | |
$dict->add( | |
surface => 'hごえhげお', | |
pos => '名詞', | |
category1 => '一般', | |
); | |
my $csv = 'mydict.csv'; | |
$dict->write($csv); | |
$dict->build($csv); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment