/usr/share/skktools/convert2skk/chasen2skk.rb is in skktools 1.3.3+0.20150901-1.
This file is owned by root:root, with mode 0o755.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 | #!/usr/bin/ruby -Ke
# -*- coding: euc-jp -*-
## Copyright (C) 2005 MITA Yuusuke <clefs@mail.goo.ne.jp>
##
## Author: MITA Yuusuke <clefs@mail.goo.ne.jp>
## Maintainer: SKK Development Team <skk@ring.gr.jp>
## Version: $Id: chasen2skk.rb,v 1.5 2013/05/26 09:47:48 skk-cvs Exp $
## Keywords: japanese, dictionary
## Last Modified: $Date: 2013/05/26 09:47:48 $
##
## This program is free software; you can redistribute it and/or modify
## it under the terms of the GNU General Public License as published by
## the Free Software Foundation; either version 2, or (at your option)
## any later version.
## This program is distributed in the hope that it will be useful,
## but WITHOUT ANY WARRANTY; without even the implied warranty of
## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
## General Public License for more details.
## You should have received a copy of the GNU General Public License
## along with this program, see the file COPYING. If not, write to the
## Free Software Foundation Inc., 51 Franklin St, Fifth Floor, Boston,
## MA 02110-1301, USA.
##
### Commentary:
##
### Instruction:
##
## This script tries to extract SKK pairs from the output of ChaSen.
##
## % chasen | chasen2skk.rb
## or
## % mecab -Ochasen | chasen2skk.rb
##
##
## skkdictools.rb required.
##
## TODO: pick up compound-verbs, eg. ¡ÖÉñ¤¤»¶¤ë¡×
## Éñ¤¤ ¥Þ¥¤ Éñ¤¦ Æ°»ì-¼«Î© ¸ÞÃÊ¡¦¥ï¹ÔÂ¥²»ÊØ Ï¢ÍÑ·Á
## »¶¤ë ¥Á¥ë »¶¤ë Æ°»ì-¼«Î© ¸ÞÃÊ¡¦¥é¹Ô ´ðËÜ·Á
##
require 'jcode' if RUBY_VERSION.to_f < 1.9
require 'kconv'
require 'skkdictools'
#require 'cgi'
#require 'socket'
#require 'timeout'
require 'optparse'
opt = OptionParser.new
katakana_words = false
#katakana_majiri = false
#append_goohits = false
keyword = ""
#fetch_from_goo = false
append_notes = false
allow_noun_chains = true
#allow_verb_chains = true
handle_prefix = true
min_length = 2 * 2
max_length = 100 * 2
# -g might be a bad idea; better eliminate pairs already in SKK-JISYO.L first
#opt.on('-g', 'append goo hit numbers') { append_goohits = true }
opt.on('-k', '--extract-katakana', 'extract katakana words (if WORD not given)') { katakana_words = true }
#opt.on('-K', 'extract words containing katakana') { katakana_majiri = true }
opt.on('-m VAL', '--min-length=VAL', 'ignore words less than VAL letters') { |v| min_length = v.to_i * 2 }
opt.on('-M VAL', '--max-length=VAL', 'ignore words more than VAL letters') { |v| max_length = v.to_i * 2 }
opt.on('-n', '--append-notes', 'append grammatical notes') { append_notes = true }
opt.on('-N', '--disallow-noun-chains', 'disallow noun chains containing hiragana') { allow_noun_chains = false }
opt.on('-P', '--ignore-prefixes', 'don\'t take prefixes into consideration') { handle_prefix = false }
opt.on('-w WORD', '--extract-word=WORD', 'extract pairs containing WORD') { |v| keyword = v }
#opt.on('-W WORD', 'query goo and extract pairs containing WORD') { |v| keyword = v; fetch_from_goo = true }
begin
opt.parse!(ARGV)
rescue OptionParser::InvalidOption => e
print "'#{$0} -h' for help.\n"
exit 1
end
#keyword_pat = Regexp.compile("[°¡-ô¦]*#{keyword}[°¡-ô¦]*")
count = 0
#key = word = last_key = last_word = last_part = ""
key = word = last_part = ""
poisoned = terminate = false
while gets
midasi, yomi, root, part, conj = $_.split(" ", 5)
#if midasi !~ /^[°¡-ô¦¥¡-¥ó¥ô¡¼]+$/ || terminate
if (midasi !~ /^[°¡-ô¦¥¡-¥ó¥ô¡¼¡¹]+$/ &&
(!allow_noun_chains || part !~ /̾»ì/ || part =~ /Èó¼«Î©/ ||
midasi !~ /^[°¡-ô¦¥¡-¥ó¥ô¡¼¡¹¤¡-¤ó]+$/ )) || terminate
#if (midasi !~ /^[°¡-ô¦¥¡-¥ó¥ô¡¼]+$/ && conj !~ /Ï¢ÍÑ·Á/) || terminate
#next if count < 1
if count < 1
next if !handle_prefix
if part =~ /ÀÜƬ»ì/
# kludge - keep prefix w/o increasing count (cf.¡Ö¤´Î©Çɡס֤ªÌ£Á¹¡×)
key = yomi.to_hiragana
word = midasi
last_part = part
#elsif part =~ /¼«Î©/ && conj =~ /Ï¢ÍÑ·Á/
# hogehoge
else
key = word = last_part = ""
end
next
end
if midasi =~ /^[^°¡-ô¦¥¡-¥ó¥ô¡¼¡¹]+$/ && !terminate
# nothing
else
if part =~ /Àܳ»ì|ÀÜƬ»ì|Éû»ì[^²Ä]/
# nothing - decline some parts
elsif midasi =~ /ʤÓ|µÚ¤Ó/
# nothing - (HACK) decline conjonctions that ChaSen overlooks
elsif midasi =~ /^[¤¡-¤ó]+[°¡-ô¦¥¡-¥ó¥ô¡¼¡¹]+/
# nothing - this applies to quasi-words such as:
# ¤Ë´Ø¤¹¤ë ¥Ë¥«¥ó¥¹¥ë ¤Ë´Ø¤¹¤ë ½õ»ì-³Ê½õ»ì-Ï¢¸ì
else
key += yomi.to_hiragana
word += midasi
last_part = part
# asayaKify here?
end
end
if word =~ /^[¤¡-¤ó¡¼]+$/
# nothing
elsif !katakana_words && word =~ /^[¥¡-¥ó¥ô¡¼]+$/
# nothing
elsif !keyword.empty? && !word.include?(keyword)
# nothing
elsif poisoned || word.size < min_length || word.size > max_length
# nothing
else
print_pair(key, word, nil, append_notes ? "<autogen>,#{last_part.chomp}" : nil)
end
key = word = last_part = ""
poisoned = terminate = false
count = 0
else
if count > 0 && part =~ /Àܳ»ì|ÀÜƬ»ì|Éû»ì[^²Ä]/
terminate = true
redo
elsif count == 0 && part =~ /ÀÜÈø/
# avoid generating ¡Ö²óÂç²ñ¡× from ¡ÖÂ裳²óÂç²ñ¡×
# ²ó ¥«¥¤ ²ó ̾»ì-ÀÜÈø-½õ¿ô»ì
key = word = last_part = ""
next
end
count += 1
key += yomi.to_hiragana
word += midasi
last_part = part
poisoned = true if part =~ /̤Ãθì/
end
end
|