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
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
|
#!/usr/bin/ruby
# Extracts multibyte characters from JIS0208.TXT.
# (ftp://ftp.unicode.org/Public/MAPPINGS/OBSOLETE/EASTASIA/JIS/JIS0208.TXT)
# 2003-03-03 .. 20xx-xx-xx, Hisashi MORITA. Use freely at your own risk.
# Usage: jis0208.rb <Ku> <Ten> <Codeset> #=> \xXX...
# Example: jis0208.rb 1 1 utf-8 #=> \xe3\x80\x80
class JIS0208
def utf16_to_utf8(utf16) # Convert UTF-16 to UTF-8N
utf16value = (utf16.unpack("C*")[0] * 256 + utf16.unpack("C*")[1])
if utf16value < 0x7f # 1-byte utf-8
utf8 = utf16value.to_a.pack("C*")
elsif utf16value < 0x800 # 2-byte utf-8
utf8 = [(0xC0 | (utf16value / 64)),
(0x80 | (utf16value % 64))].pack("C*")
else # 3-byte utf-8
utf8 = [(0xE0 | ((utf16value / 64) / 64)),
(0x80 | ((utf16value / 64) % 64)),
(0x80 | (utf16value % 64))].pack("C*")
end
end
def initialize()
@lines = File.readlines("JIS0208.TXT")
@lines = @lines.grep(/^[^\#]/) # remove comments
@lines = @lines.collect{|l| l.sub(/\s+\#[^\#]+$/,'')} # remove unicode names
@char_db = @lines.collect {|line|
sjis, jis, utf16 = line.split.collect{|string|
string.sub(/0x/, '').to_a.pack("H*") # "0xXXXX" to 8-bit byte string
}
jis_byte_pair = jis.unpack("C*")
# jis + 0x8080 => euc
euc = jis_byte_pair.collect {|byte| (byte + 0x80)}.pack("C*")
# jis - 0x2020 => ku, ten
ku, ten = jis_byte_pair.collect {|byte| (byte - 0x20)}
utf8 = utf16_to_utf8(utf16)
{:s=>sjis, :j=>jis, :u16=>utf16, :e=>euc, :u8=>utf8, :ku=>ku, :ten=>ten}
}
@characters = {}
@char_db.each{|char|
if @characters[char[:ku]].nil?
@characters[char[:ku]] = {}
end
if @characters[char[:ku]][char[:ten]].nil?
@characters[char[:ku]][char[:ten]] = {
:s=>char[:s],
:j=>char[:j],
:u16=>char[:u16],
:e=>char[:e],
:u8=>char[:u8]
}
end
}
end
attr_reader :char_db
attr_reader :characters
def char(ku, ten, codeset)
case
when /^[Ee]/ =~ codeset then codeset = :e
when /^[Ss]/ =~ codeset then codeset = :s
when /^[Jj]/ =~ codeset then codeset = :j
when /^[Uu].*16$/ =~ codeset then codeset = :u16
when /^[Uu].*8$/ =~ codeset then codeset = :u8
else
raise "invalid codeset name (#{codeset})\n"
end
characters[ku][ten][codeset].unpack('C*').collect{|byte|
sprintf("\\x%x",byte)
}.join
end
end
if __FILE__ == $0
# euc-jp
def euc_ja_alnum()
j = JIS0208.new
r = []
(3).to_a.each{|ku|(16..25).to_a.each{|ten|r << j.char(ku,ten,"e")}}
(3).to_a.each{|ku|(33..58).to_a.each{|ten|r << j.char(ku,ten,"e")}}
(3).to_a.each{|ku|(65..90).to_a.each{|ten|r << j.char(ku,ten,"e")}}
r
end
def euc_ja_blank()
j = JIS0208.new
r = []
(1).to_a.each{|ku|(1).to_a.each{|ten|r << j.char(ku,ten,"e")}}
r
end
def euc_ja_print()
euc_ja_graph() + euc_ja_blank()
end
def euc_ja_graph()
euc_ja_alnum() + euc_ja_punct()
end
def euc_ja_punct()
j = JIS0208.new
r = []
(1).to_a.each{|ku|( 2..94).to_a.each{|ten|r << j.char(ku,ten,"e")}}
(2).to_a.each{|ku|( 1..14).to_a.each{|ten|r << j.char(ku,ten,"e")}}
(2).to_a.each{|ku|(26..33).to_a.each{|ten|r << j.char(ku,ten,"e")}}
(2).to_a.each{|ku|(42..48).to_a.each{|ten|r << j.char(ku,ten,"e")}}
(2).to_a.each{|ku|(60..74).to_a.each{|ten|r << j.char(ku,ten,"e")}}
(2).to_a.each{|ku|(82..89).to_a.each{|ten|r << j.char(ku,ten,"e")}}
(2).to_a.each{|ku|(94 ).to_a.each{|ten|r << j.char(ku,ten,"e")}}
(6).to_a.each{|ku|( 1..24).to_a.each{|ten|r << j.char(ku,ten,"e")}}
(6).to_a.each{|ku|(33..56).to_a.each{|ten|r << j.char(ku,ten,"e")}}
(7).to_a.each{|ku|( 1..33).to_a.each{|ten|r << j.char(ku,ten,"e")}}
(7).to_a.each{|ku|(49..81).to_a.each{|ten|r << j.char(ku,ten,"e")}}
(8).to_a.each{|ku|( 1..32).to_a.each{|ten|r << j.char(ku,ten,"e")}}
r
end
def euc_ja_space()
j = JIS0208.new
r = []
(1).to_a.each{|ku|(1).to_a.each{|ten|r << j.char(ku,ten,"e")}}
r
end
def euc_hiragana()
j = JIS0208.new
r = []
(4).to_a.each{|ku|(1..83).to_a.each{|ten|r << j.char(ku,ten,"e")}}
r
end
def euc_katakana()
j = JIS0208.new
r = []
(5).to_a.each{|ku|(1..86).to_a.each{|ten|r << j.char(ku,ten,"e")}}
r
end
def euc_kanji()
j = JIS0208.new
r = []
(16..46).to_a.each{|ku| r << "#{j.char(ku,1,'e')}-#{j.char(ku,94,'e')}"}
(47).to_a.each{|ku|r << "#{j.char(ku,1,'e')}-#{j.char(ku,51,'e')}"}
(48..83).to_a.each{|ku|r << "#{j.char(ku,1,'e')}-#{j.char(ku,94,'e')}"}
(84).to_a.each{|ku|r << "#{j.char(ku,1,'e')}-#{j.char(ku,6,'e')}"}
r
end
# sjis (cp932)
def sjis_ja_alnum()
j = JIS0208.new
r = []
(3).to_a.each{|ku|(16..25).to_a.each{|ten|r << j.char(ku,ten,"s")}}
(3).to_a.each{|ku|(33..58).to_a.each{|ten|r << j.char(ku,ten,"s")}}
(3).to_a.each{|ku|(65..90).to_a.each{|ten|r << j.char(ku,ten,"s")}}
r
end
def sjis_ja_blank()
j = JIS0208.new
r = []
(1).to_a.each{|ku|(1).to_a.each{|ten|r << j.char(ku,ten,"s")}}
r
end
def sjis_ja_print()
sjis_ja_graph() + sjis_ja_blank()
end
def sjis_ja_graph()
sjis_ja_alnum() + sjis_ja_punct()
end
def sjis_ja_punct()
j = JIS0208.new
r = []
(1).to_a.each{|ku|(2..94).to_a.each{|ten|r << j.char(ku,ten,"s")}}
(2).to_a.each{|ku|(1..14).to_a.each{|ten|r << j.char(ku,ten,"s")}}
(2).to_a.each{|ku|(26..33).to_a.each{|ten|r << j.char(ku,ten,"s")}}
(2).to_a.each{|ku|(42..48).to_a.each{|ten|r << j.char(ku,ten,"s")}}
(2).to_a.each{|ku|(60..74).to_a.each{|ten|r << j.char(ku,ten,"s")}}
(2).to_a.each{|ku|(82..89).to_a.each{|ten|r << j.char(ku,ten,"s")}}
(2).to_a.each{|ku|(94).to_a.each{|ten|r << j.char(ku,ten,"s")}}
(6).to_a.each{|ku|(1..24).to_a.each{|ten|r << j.char(ku,ten,"s")}}
(6).to_a.each{|ku|(33..56).to_a.each{|ten|r << j.char(ku,ten,"s")}}
(7).to_a.each{|ku|(1..33).to_a.each{|ten|r << j.char(ku,ten,"s")}}
(7).to_a.each{|ku|(49..81).to_a.each{|ten|r << j.char(ku,ten,"s")}}
(8).to_a.each{|ku|(1..32).to_a.each{|ten|r << j.char(ku,ten,"s")}}
#(13).to_a.each{|ku|(1..30).to_a.each{|ten|r << j.char(ku,ten,"s")}}#cp932
#(13).to_a.each{|ku|(32..54).to_a.each{|ten|r << j.char(ku,ten,"s")}}#cp932
#(13).to_a.each{|ku|(63..92).to_a.each{|ten|r << j.char(ku,ten,"s")}}#cp932
#(92).to_a.each{|ku|(81..94).to_a.each{|ten|r << j.char(ku,ten,"s")}}#cp932
r
end
def sjis_ja_space()
j = JIS0208.new
r = []
(1).to_a.each{|ku|(1).to_a.each{|ten|r << j.char(ku,ten,"s")}}
r
end
def sjis_hiragana()
j = JIS0208.new
r = []
(4).to_a.each{|ku|(1..83).to_a.each{|ten|r << j.char(ku,ten,"s")}}
r
end
def sjis_katakana()
j = JIS0208.new
r = []
(5).to_a.each{|ku|(1..86).to_a.each{|ten|r << j.char(ku,ten,"s")}}
r
end
def sjis_kanji()
j = JIS0208.new
r = []
(16..46).to_a.each{|ku|r << "#{j.char(ku,1,'s')}-#{j.char(ku,94,'s')}"}
(47).to_a.each{|ku|r << "#{j.char(ku,1,'s')}-#{j.char(ku,51,'s')}"}
(48..83).to_a.each{|ku|r << "#{j.char(ku,1,'s')}-#{j.char(ku,94,'s')}"}
(84).to_a.each{|ku|r << "#{j.char(ku,1,'s')}-#{j.char(ku,6,'s')}"}
(89..91).to_a.each{|ku|r << "#{j.char(ku,1,'s')}-#{j.char(ku,94,'s')}"}#cp932
(92).to_a.each{|ku|r << "#{j.char(ku,1,'s')}-#{j.char(ku,78,'s')}"}#cp932
r
end
# utf8
def utf8_ja_alnum()
j = JIS0208.new
r = []
(3).to_a.each{|ku|(16..25).to_a.each{|ten|r << j.char(ku,ten,"u8")}}
(3).to_a.each{|ku|(33..58).to_a.each{|ten|r << j.char(ku,ten,"u8")}}
(3).to_a.each{|ku|(65..90).to_a.each{|ten|r << j.char(ku,ten,"u8")}}
r
end
def utf8_ja_blank()
j = JIS0208.new
r = []
(1).to_a.each{|ku|(1).to_a.each{|ten|r << j.char(ku,ten,"u8")}}
r
end
def utf8_ja_print()
utf8_ja_graph() + utf8_ja_blank()
end
def utf8_ja_graph()
utf8_ja_alnum() + utf8_ja_punct()
end
def utf8_ja_punct()
j = JIS0208.new
r = []
(1).to_a.each{|ku|( 2..94).to_a.each{|ten|r << j.char(ku,ten,"u8")}}
(2).to_a.each{|ku|( 1..14).to_a.each{|ten|r << j.char(ku,ten,"u8")}}
(2).to_a.each{|ku|(26..33).to_a.each{|ten|r << j.char(ku,ten,"u8")}}
(2).to_a.each{|ku|(42..48).to_a.each{|ten|r << j.char(ku,ten,"u8")}}
(2).to_a.each{|ku|(60..74).to_a.each{|ten|r << j.char(ku,ten,"u8")}}
(2).to_a.each{|ku|(82..89).to_a.each{|ten|r << j.char(ku,ten,"u8")}}
(2).to_a.each{|ku|(94 ).to_a.each{|ten|r << j.char(ku,ten,"u8")}}
(6).to_a.each{|ku|( 1..24).to_a.each{|ten|r << j.char(ku,ten,"u8")}}
(6).to_a.each{|ku|(33..56).to_a.each{|ten|r << j.char(ku,ten,"u8")}}
(7).to_a.each{|ku|( 1..33).to_a.each{|ten|r << j.char(ku,ten,"u8")}}
(7).to_a.each{|ku|(49..81).to_a.each{|ten|r << j.char(ku,ten,"u8")}}
(8).to_a.each{|ku|( 1..32).to_a.each{|ten|r << j.char(ku,ten,"u8")}}
r
end
def utf8_ja_space()
j = JIS0208.new
r = []
(1).to_a.each{|ku|(1).to_a.each{|ten|r << j.char(ku,ten,"u8")}}
r
end
def utf8_hiragana()
j = JIS0208.new
r = []
(4).to_a.each{|ku|(1..83).to_a.each{|ten|r << j.char(ku,ten,"utf-8")}}
r
end
def utf8_katakana()
j = JIS0208.new
r = []
(5).to_a.each{|ku|(1..86).to_a.each{|ten|r << j.char(ku,ten,"utf-8")}}
r
end
def utf8_kanji()
j = JIS0208.new
r = []
(16..46).to_a.each{|ku|(1..94).to_a.each{|ten|r << j.char(ku,ten,"utf-8")}}
(47).to_a.each{|ku|(1..51).to_a.each{|ten|r << j.char(ku,ten,"utf-8")}}
(48..83).to_a.each{|ku|(1..94).to_a.each{|ten|r << j.char(ku,ten,"utf-8")}}
(84).to_a.each{|ku|(1..6).to_a.each{|ten|r << j.char(ku,ten,"utf-8")}}
r
end
jis0208 = JIS0208.new
if ARGV.size == 3
ku, ten, codeset = ARGV[0].to_i, ARGV[1].to_i, ARGV[2].to_s
puts jis0208.char(ku, ten, codeset)
exit(0)
elsif ARGV.size == 2
codeset, charclass = ARGV[0].to_s, ARGV[1].to_s
else
puts "Usage: jis0208.rb (<Ku> <Ten> <Codeset> | <Codeset> <CharClass>)"
puts "Supported codeset: EUC-JP, Shift_JIS, UTF-8"
puts "Supported charclass: blank, space, alnum, punct, print, graph, hiragana, katakana, kanji"
puts "Example 1: jis0208.rb 16 1 utf-8"
puts "Example 2: jis0208.rb euc-jp punct"
exit(0)
end
case
when (/^e/i.match codeset) # euc-jp
case
when (/^space/i.match charclass) then puts euc_ja_space()
when (/^blank/i.match charclass) then puts euc_ja_blank()
when (/^alnum/i.match charclass) then puts euc_ja_alnum()
when (/^punct/i.match charclass) then puts euc_ja_punct()
when (/^print/i.match charclass) then puts euc_ja_print()
when (/^graph/i.match charclass) then puts euc_ja_graph()
when (/^hira/i.match charclass) then puts euc_hiragana()
when (/^kata/i.match charclass) then puts euc_katakana()
when (/^kanji/i.match charclass) then puts euc_kanji()
else
raise "invalid charclass (#{charclass}).\n"
end
when (/^s/i.match codeset) # sjis
case
when (/^space/i.match charclass) then puts sjis_ja_space()
when (/^blank/i.match charclass) then puts sjis_ja_blank()
when (/^alnum/i.match charclass) then puts sjis_ja_alnum()
when (/^punct/i.match charclass) then puts sjis_ja_punct()
when (/^print/i.match charclass) then puts sjis_ja_print()
when (/^graph/i.match charclass) then puts sjis_ja_graph()
when (/^hira/i.match charclass) then puts sjis_hiragana()
when (/^kata/i.match charclass) then puts sjis_katakana()
when (/^kanji/i.match charclass) then puts sjis_kanji()
else
raise "invalid charclass (#{charclass}).\n"
end
when (/^u/i.match codeset) # utf-8
case
when (/^space/i.match charclass) then puts utf8_ja_space()
when (/^blank/i.match charclass) then puts utf8_ja_blank()
when (/^alnum/i.match charclass) then puts utf8_ja_alnum()
when (/^punct/i.match charclass) then puts utf8_ja_punct()
when (/^print/i.match charclass) then puts utf8_ja_print()
when (/^graph/i.match charclass) then puts utf8_ja_graph()
when (/^hira/i.match charclass) then puts utf8_hiragana()
when (/^kata/i.match charclass) then puts utf8_katakana()
when (/^kanji/i.match charclass) then puts utf8_kanji()
else
raise "invalid charclass (#{charclass}).\n"
end
else
raise "invalid codeset (#{codeset}) or charclass (#{charclass}).\n"
end
end
|
