1 |
wakaba |
1.1 |
#?PESRC/1.0 |
2 |
|
|
Name: |
3 |
|
|
ISO2022::EUCJACompatible |
4 |
|
|
ShortDescription: |
5 |
|
|
An Encode module of EUC (8-bit ISO/IEC 2022 |
6 |
|
|
based compatible coding system) for Japanese |
7 |
|
|
POD:DESCRIPTION: |
8 |
|
|
Due to the historical reason, some of current |
9 |
|
|
implementions of JIS coded character sets support |
10 |
|
|
pairs of same characters dupplicately, with |
11 |
|
|
halfwidth/fullwidth property. |
12 |
|
|
|
13 |
|
|
Although this situation is undesirable, we can't ignore |
14 |
|
|
such historical implementions and latest JIS coded |
15 |
|
|
character set standards admire such dupulicate |
16 |
|
|
encoding to and only to "keep compatibility with |
17 |
|
|
current practice." |
18 |
|
|
|
19 |
|
|
This module provides encoder and decoder for such |
20 |
|
|
coding systems that comform to JIS and that based |
21 |
|
|
on EUC (an 8-bit ISO/IEC 2022) structure. |
22 |
|
|
|
23 |
|
|
Those coding systems SHOULD not be used for new |
24 |
|
|
implemention or new data. They may not comform |
25 |
|
|
to future version of JIS or other standards. |
26 |
|
|
|
27 |
|
|
{ |
28 |
|
|
Name: |
29 |
|
|
euc-japan-1990-fullwidth |
30 |
|
|
Alias: |
31 |
|
|
euc-jp-1990-fullwidth ajec |
32 |
|
|
Cversion: |
33 |
|
|
C:bit=8 |
34 |
|
|
C:G0=G94:B ## ASCII |
35 |
|
|
C:G1=G94n:B@ ## JIS X 0208-1990 |
36 |
|
|
C:G2=G94:I ## JIS X 0201 Katakana |
37 |
|
|
C:G3=G94n:D ## JIS X 0212-1990 |
38 |
|
|
C:designate:*:default=-1 |
39 |
|
|
C:option:{Ginvoke_to_left}=[1,0,0,0] |
40 |
|
|
C:option:{Ginvoke_by_single_shift}=[0,0,1,1] |
41 |
|
|
C:option:{C1invoke_to_right}=1 |
42 |
|
|
C:option:{reset}->{Gdesignation}=0 |
43 |
|
|
C:option:{reset}->{Ginvoke}=0 |
44 |
|
|
C:option:{undef_char}=["\x22\x2E", {type => 'G94n', charset => 'B@'}] |
45 |
|
|
Encode: |
46 |
|
|
=>ucs_to_ascii ucs_to_jisx0208_1990_open_ascii ucs_to_jisx0212_1990_irv ucs_to_jisx0201_katakana_hw |
47 |
|
|
->iso2022:C |
48 |
|
|
Decode: |
49 |
|
|
<-iso2022:C |
50 |
|
|
<=jisx0208_1990_open_ascii_to_ucs jisx0212_1990_irv_to_ucs jisx0201_katakana_hw_to_ucs |
51 |
|
|
Description: |
52 |
|
|
EUC (ISO/IEC 2022 based 8-bit encoding) for Japanese, |
53 |
|
|
ISO/IEC 646 IRV + JIS X 0208-1990 + JIS X 0212-1990 |
54 |
|
|
+ JIS X 0201-1990 Katakana. Some characters defined |
55 |
|
|
in JIS X 0208 and all characters defined in JIS X 0201 |
56 |
|
|
are mapped to FULLWIDTH or HALFWIDTH characters of UCS |
57 |
|
|
as specified by JIS X 0221-1995 and JIS X 0208:1997. |
58 |
|
|
|
59 |
|
|
This encoding is same as C<euc-japan-1997-fullwidth> |
60 |
|
|
except that this encoding has private use areas as |
61 |
|
|
described in JIS X 0208-1990 and JIS X 0212-1990 |
62 |
|
|
(as the "free area") and defined in AJEC. (See "UI-OSF |
63 |
|
|
Application Platform Profile for Japanese Environment".) |
64 |
|
|
Its mapping to UCS private use area is defined by |
65 |
|
|
CDE/Motif WG. |
66 |
|
|
|
67 |
|
|
Even 1990 version of JIS coded character set standards |
68 |
|
|
allows "free area", current version of JIS does not. |
69 |
|
|
It should not be used without compatibility purpose. |
70 |
|
|
|
71 |
|
|
This encoding is a "compatible" version of |
72 |
|
|
C<euc-japan-1990> defined in Encode::ISO2022::EUCJA. |
73 |
|
|
} |
74 |
|
|
|
75 |
|
|
{ |
76 |
|
|
Name: |
77 |
|
|
eucJP-open |
78 |
|
|
Alias: |
79 |
|
|
eucJP-ascii |
80 |
|
|
Cversion: |
81 |
|
|
C:bit=8 |
82 |
|
|
C:G0=G94:B ## ASCII |
83 |
|
|
C:G1=G94n:B@ ## JIS X 0208-1990 |
84 |
|
|
C:G2=G94:I ## JIS X 0201 Katakana |
85 |
|
|
C:G3=G94n:D ## JIS X 0212-1990 |
86 |
|
|
C:designate:*:default=-1 |
87 |
|
|
C:option:{Ginvoke_to_left}=[1,0,0,0] |
88 |
|
|
C:option:{Ginvoke_by_single_shift}=[0,0,1,1] |
89 |
|
|
C:option:{C1invoke_to_right}=1 |
90 |
|
|
C:option:{reset}->{Gdesignation}=0 |
91 |
|
|
C:option:{reset}->{Ginvoke}=0 |
92 |
|
|
C:option:{undef_char}=["\x22\x2E", {type => 'G94n', charset => 'B@'}] |
93 |
|
|
Encode: |
94 |
|
|
=>ucs_to_ascii ucs_to_jisx0208_1990_open_ascii ucs_to_jisx0212_1990_open_ascii ucs_to_jisx0201_katakana_hw |
95 |
|
|
->iso2022:C |
96 |
|
|
Decode: |
97 |
|
|
<-iso2022:C |
98 |
|
|
<=jisx0208_1990_open_ascii_to_ucs jisx0212_1990_open_ascii_to_ucs jisx0201_katakana_hw_to_ucs |
99 |
|
|
Description: |
100 |
|
|
EUC (ISO/IEC 2022 based 8-bit encoding) for Japanese. |
101 |
|
|
|
102 |
|
|
This encoding is same as C<euc-japan-1990-fullwidth> |
103 |
|
|
except that this encoding has IBM extended characters |
104 |
|
|
as defined by CDE/Motif WG. |
105 |
|
|
|
106 |
|
|
Even 1990 version of JIS coded character set standards |
107 |
|
|
allows "free area", current version of JIS does not. |
108 |
|
|
It should not be used without compatibility purpose. |
109 |
|
|
} |
110 |
|
|
|
111 |
|
|
{ |
112 |
|
|
Name: |
113 |
|
|
eucJP-0201 |
114 |
|
|
Cversion: |
115 |
|
|
C:bit=8 |
116 |
|
|
C:G0=G94:J ## JIS X 0201 Roman |
117 |
|
|
C:G1=G94n:B@ ## JIS X 0208-1990 |
118 |
|
|
C:G2=G94:I ## JIS X 0201 Katakana |
119 |
|
|
C:G3=G94n:D ## JIS X 0212-1990 |
120 |
|
|
C:designate:*:default=-1 |
121 |
|
|
C:option:{Ginvoke_to_left}=[1,0,0,0] |
122 |
|
|
C:option:{Ginvoke_by_single_shift}=[0,0,1,1] |
123 |
|
|
C:option:{C1invoke_to_right}=1 |
124 |
|
|
C:option:{reset}->{Gdesignation}=0 |
125 |
|
|
C:option:{reset}->{Ginvoke}=0 |
126 |
|
|
C:option:{undef_char}=["\x22\x2E", {type => 'G94n', charset => 'B@'}] |
127 |
|
|
Encode: |
128 |
|
|
=>ucs_to_jisx0201_latin ucs_to_jisx0208_1990_open_0201 ucs_to_jisx0212_1990_open_0201 ucs_to_jisx0201_katakana_hw |
129 |
|
|
->iso2022:C |
130 |
|
|
Decode: |
131 |
|
|
<-iso2022:C |
132 |
|
|
<=jisx0201_latin_to_ucs jisx0208_1990_open_02101_to_ucs jisx0212_1990_open_0201_to_ucs jisx0201_katakana_hw_to_ucs |
133 |
|
|
Description: |
134 |
|
|
ISO/IEC 2022 based 8-bit encoding for Japanese. |
135 |
|
|
|
136 |
|
|
This encoding is same as C<eucJP-ascii> but use JIS X 0201 |
137 |
|
|
roman set instead of ASCII, as defined by CDE/Motif WG. |
138 |
|
|
|
139 |
|
|
EUC is defined to use ASCII but this coding system use |
140 |
|
|
JIS X 0201 roman, so this coding system SHOULD NOT be |
141 |
|
|
used without compatibility purpose. |
142 |
|
|
} |
143 |
|
|
|
144 |
|
|
{ |
145 |
|
|
Name: |
146 |
|
|
euc-japan-1997-fullwidth |
147 |
|
|
Alias: |
148 |
|
|
euc-jp-1997-fullwidth |
149 |
|
|
Cversion: |
150 |
|
|
C:bit=8 |
151 |
|
|
C:G0=G94:B ## ASCII |
152 |
|
|
C:G1=G94n:B@ ## JIS X 0208:1997 |
153 |
|
|
C:G2=G94:I ## JIS X 0201 Katakana |
154 |
|
|
C:G3=G94n:D ## JIS X 0212-1990 |
155 |
|
|
C:designate:*:default=-1 |
156 |
|
|
C:option:{Ginvoke_to_left}=[1,0,0,0] |
157 |
|
|
C:option:{Ginvoke_by_single_shift}=[0,0,1,1] |
158 |
|
|
C:option:{C1invoke_to_right}=1 |
159 |
|
|
C:option:{reset}->{Gdesignation}=0 |
160 |
|
|
C:option:{reset}->{Ginvoke}=0 |
161 |
|
|
C:option:{undef_char}=["\x22\x2E", {type => 'G94n', charset => 'B@'}] |
162 |
|
|
Encode: |
163 |
|
|
=>ucs_to_ascii ucs_to_jisx0208_1997_irv ucs_to_jisx0212_1990_irv ucs_to_jisx0201_katakana_hw |
164 |
|
|
->iso2022:C |
165 |
|
|
Decode: |
166 |
|
|
<-iso2022:C |
167 |
|
|
<=jisx0208_1997_irv_to_ucs jisx0212_1990_irv_to_ucs jisx0201_katakana_hw_to_ucs |
168 |
|
|
Description: |
169 |
|
|
EUC (ISO/IEC 2022 based 8-bit encoding) for Japanese, |
170 |
|
|
ISO/IEC 646 IRV + JIS X 0208:1997 + JIS X 0212-1990 |
171 |
|
|
+ JIS X 0201:1997 Katakana. Some characters defined |
172 |
|
|
in JIS X 0208 and all characters defined in JIS X 0201 |
173 |
|
|
are mapped to FULLWIDTH or HALFWIDTH characters of UCS |
174 |
|
|
as specified by JIS X 0221-1995 and JIS X 0208:1997. |
175 |
|
|
|
176 |
|
|
This encoding is a "compatible" version of |
177 |
|
|
C<euc-japan-1997> defined in Encode::ISO2022::EUCJA. |
178 |
|
|
} |
179 |
|
|
|
180 |
|
|
{ |
181 |
|
|
Name: |
182 |
|
|
euc-jisx0213-fullwidth |
183 |
|
|
Alias: |
184 |
|
|
euc-japan-2000-fullwidth euc-jp-2000-fullwidth |
185 |
|
|
Cversion: |
186 |
|
|
C:bit=8 |
187 |
|
|
C:G0=G94:B ## ASCII |
188 |
|
|
C:G1=G94n:O ## JIS X 0213:2000 plane 1 |
189 |
|
|
C:G2=G94:I ## JIS X 0201 Katakana |
190 |
|
|
C:G3=G94n:P ## JIS X 0213:2000 plane 2 |
191 |
|
|
C:designate:*:default=-1 |
192 |
|
|
C:option:{Ginvoke_to_left}=[1,0,0,0] |
193 |
|
|
C:option:{Ginvoke_by_single_shift}=[0,0,1,1] |
194 |
|
|
C:option:{C1invoke_to_right}=1 |
195 |
|
|
C:option:{reset}->{Gdesignation}=0 |
196 |
|
|
C:option:{reset}->{Ginvoke}=0 |
197 |
|
|
C:option:{undef_char}=["\x22\x2E", {type => 'G94n', charset => 'O'}] |
198 |
|
|
Encode: |
199 |
|
|
=>ucs_to_ascii ucs_to_jisx0213_2000_1_irv ucs_to_jisx0213_2000_2 ucs_to_jisx0201_katakana_hw |
200 |
|
|
->iso2022:C |
201 |
|
|
Decode: |
202 |
|
|
<-iso2022:C |
203 |
|
|
<=jisx0213_2000_1_irv_to_ucs jisx0213_2000_2_to_ucs jisx0201_katakana_hw_to_ucs |
204 |
|
|
Description: |
205 |
|
|
EUC (ISO/IEC 2022 based 8-bit encoding) for Japanese, |
206 |
|
|
ISO/IEC 646 IRV + JIS X 0213:2000 + JIS X 0201:1997 |
207 |
|
|
Katakana. Some characters defined in JIS X 0213 and |
208 |
|
|
all characters defined in JIS X 0201 are mapped to |
209 |
|
|
FULLWIDTH or HALFWIDTH characters of UCS as specified |
210 |
|
|
by JIS X 0213:2000. |
211 |
|
|
|
212 |
|
|
This encoding is a "compatible" version of |
213 |
|
|
C<euc-jisx0213> defined in Encode::ISO2022::EUCJA. |
214 |
|
|
} |
215 |
|
|
|
216 |
|
|
POD:EXAMPLE: |
217 |
|
|
use %%MYSELF%%; |
218 |
|
|
while (<>) { |
219 |
|
|
print "FW-> : ". Encode::encode ('euc-jp-1997', Encode::decode ('euc-jp-1997-fullwidth', $_)); |
220 |
|
|
print "FW->FW: ". Encode::encode ('euc-jp-1997-fullwidth', Encode::decode ('euc-jp-1997-fullwidth', $_)); |
221 |
|
|
print " ->FW: ". Encode::encode ('euc-jp-1997-fullwidth', Encode::decode ('euc-jp-1997', $_)); |
222 |
|
|
print " -> : ". Encode::encode ('euc-jp-1997', Encode::decode ('euc-jp-1997', $_)); |
223 |
|
|
} |
224 |
|
|
|
225 |
|
|
POD:SEE ALSO: |
226 |
|
|
%%ReferenceJISX0212_1995%% |
227 |
|
|
|
228 |
|
|
%%ReferenceJISX0208_1997%% |
229 |
|
|
|
230 |
|
|
%%ReferenceJISX0213_2000%% |
231 |
|
|
|
232 |
|
|
L<Encode::ISO2022::EUCJA> |
233 |
|
|
|
234 |
|
|
"UI-OSF Application Platform Profile for Japanese Environment |
235 |
|
|
Version 1.1", UI-OSF Japanese Localization Group, 1993-05-21. |
236 |
|
|
<http://www.li18nux.org/~numa/uocjle-a4.pdf> (In Japanese) |
237 |
|
|
or <http://www.li18nux.org/~numa/uocjleE.pdf> (In English). |
238 |
|
|
|
239 |
|
|
"OSF/JVC Recommended Code Set Conversion Specification |
240 |
|
|
between Japanese EUC and Shift-JIS, and |
241 |
|
|
Survey on Actual Situation of Japanese Code Sets", |
242 |
|
|
OSF/JVC CDE/Motif Technical WG, 1996-01-19. |
243 |
|
|
<http://www.opengroup.or.jp/jvc/cde/sjis-euc.html> (In Japanese) |
244 |
|
|
or <http://www.opengroup.or.jp/jvc/cde/sjis-euc-e.html> (In English). |
245 |
|
|
|
246 |
|
|
"Problems and Solutions for Unicode and User/Vendor Defined Characters", |
247 |
|
|
TOG/JVC CDE/Motif Technical WG, 1996-10-25. |
248 |
|
|
<http://www.opengroup.or.jp/jvc/cde/ucs-conv.html> (In Japanese) |
249 |
|
|
or <http://www.opengroup.or.jp/jvc/cde/ucs-conv-e.html> (In English). |
250 |
|
|
|
251 |
|
|
POD:LICENSE: |
252 |
|
|
Copyright %%YEAR%% Wakaba <w@suika.fam.cx> |
253 |
|
|
|
254 |
|
|
%%PerlLicense%% |