1 |
wakaba |
1.1 |
#?PESRC/1.0 |
2 |
|
|
Name: |
3 |
|
|
ISO2022::JISCompatible |
4 |
|
|
ShortDescription: |
5 |
|
|
An Encode module of ISO/IEC 2022 |
6 |
|
|
based compatible coding systems 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 |
|
|
Even 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 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 |
|
|
iso-2022-jp-3-fullwidth |
30 |
|
|
Encode: |
31 |
|
|
use:Encode::ISO2022::SevenBit |
32 |
|
|
=>ucs_to_ascii ucs_to_jisx0213_2000_1_irv ucs_to_jisx0213_2000_2 |
33 |
|
|
->iso-2022-jp-3 |
34 |
|
|
Decode: |
35 |
|
|
use:Encode::ISO2022::SevenBit |
36 |
|
|
<-iso-2022-jp-3 |
37 |
|
|
<=jisx0213_2000_1_irv_to_ucs jisx0213_2000_2_to_ucs jisx0208_1997_irv_to_ucs |
38 |
|
|
Description: |
39 |
|
|
ISO/IEC 2022 based 7-bit encoding for Japanese, |
40 |
|
|
ISO/IEC 646 IRV + JIS X 0213:2000. Some characters |
41 |
|
|
defined in JIS X 0213 are mapped to FULLWIDTH or |
42 |
|
|
HALFWIDTH area of UCS as specified in JIS X 0213:2000. |
43 |
|
|
|
44 |
|
|
This encoding is a "compatible" version of |
45 |
|
|
C<iso-2022-jp-3> defined in Encode::ISO2022::SevenBit. |
46 |
|
|
} |
47 |
|
|
|
48 |
|
|
{ |
49 |
|
|
Name: |
50 |
|
|
euc-jp-1997-fullwidth |
51 |
|
|
Alias: |
52 |
|
|
euc-japan-1997-fullwidth euc-jp-1990-fullwidth euc-japan-1990-fullwidth |
53 |
|
|
Encode: |
54 |
|
|
=>ucs_to_ascii ucs_to_jisx0208_1997_irv ucs_to_jisx0212_1990_irv ucs_to_jisx0201_katakana_hw |
55 |
|
|
->euc-jp-1997 |
56 |
|
|
Decode: |
57 |
|
|
<-euc-jp-1997 |
58 |
|
|
<=jisx0208_1997_irv_to_ucs jisx0212_1990_irv_to_ucs jisx0201_katakana_hw_to_ucs |
59 |
|
|
Description: |
60 |
|
|
EUC (ISO/IEC 2022 based 8-bit encoding) for Japanese, |
61 |
|
|
ISO/IEC 646 IRV + JIS X 0208:1997 + JIS X 0212-1990 |
62 |
|
|
+ JIS X 0201:1997 Katakana. Some characters defined |
63 |
|
|
in JIS X 0208 and all characters defined in JIS X 0201 |
64 |
|
|
are mapped to FULLWIDTH or HALFWIDTH characters of UCS |
65 |
|
|
as specified by JIS X 0221-1995 and JIS X 0208:1997. |
66 |
|
|
|
67 |
|
|
This encoding is a "compatible" version of |
68 |
|
|
C<euc-jp-1997> defined in Encode::ISO2022::EightBit. |
69 |
|
|
} |
70 |
|
|
|
71 |
|
|
{ |
72 |
|
|
Name: |
73 |
|
|
euc-jisx0213-fullwidth |
74 |
|
|
Alias: |
75 |
|
|
euc-japan-2000-fullwidth euc-jp-2000-fullwidth |
76 |
|
|
Encode: |
77 |
|
|
use:Encode::ISO2022::EightBit |
78 |
|
|
=>ucs_to_ascii ucs_to_jisx0213_2000_1_irv ucs_to_jisx0213_2000_2 ucs_to_jisx0201_katakana_hw |
79 |
|
|
->euc-jisx0213 |
80 |
|
|
Decode: |
81 |
|
|
use:Encode::ISO2022::EightBit |
82 |
|
|
<-euc-jisx0213 |
83 |
|
|
<=jisx0213_2000_1_irv_to_ucs jisx0213_2000_2_to_ucs jisx0201_katakana_hw_to_ucs |
84 |
|
|
Description: |
85 |
|
|
EUC (ISO/IEC 2022 based 8-bit encoding) for Japanese, |
86 |
|
|
ISO/IEC 646 IRV + JIS X 0213:2000 + JIS X 0201:1997 |
87 |
|
|
Katakana. Some characters defined in JIS X 0213 and |
88 |
|
|
all characters defined in JIS X 0201 are mapped to |
89 |
|
|
FULLWIDTH or HALFWIDTH characters of UCS as specified |
90 |
|
|
by JIS X 0213:2000. |
91 |
|
|
|
92 |
|
|
This encoding is a "compatible" version of |
93 |
|
|
C<euc-jisx0213> defined in Encode::ISO2022::EightBit. |
94 |
|
|
} |
95 |
|
|
|
96 |
|
|
POD:EXAMPLE: |
97 |
|
|
use %%MYSELF%%; |
98 |
|
|
while (<>) { |
99 |
|
|
print "FW-> : ". Encode::encode ('euc-jp-1997', Encode::decode ('euc-jp-1997-fullwidth', $_)); |
100 |
|
|
print "FW->FW: ". Encode::encode ('euc-jp-1997-fullwidth', Encode::decode ('euc-jp-1997-fullwidth', $_)); |
101 |
|
|
print " ->FW: ". Encode::encode ('euc-jp-1997-fullwidth', Encode::decode ('euc-jp-1997', $_)); |
102 |
|
|
print " -> : ". Encode::encode ('euc-jp-1997', Encode::decode ('euc-jp-1997', $_)); |
103 |
|
|
} |
104 |
|
|
} |
105 |
|
|
|
106 |
|
|
POD:SEE ALSO: |
107 |
|
|
JIS X 0221-1995, "Universal multi-octet coded character |
108 |
|
|
set (UCS)", Japan Industrial Standards Committee |
109 |
|
|
<http://www.jisc.go.jp/>, 1995. IDT with ISO/IEC 10646-1:1993 |
110 |
|
|
but three additional appendixes. |
111 |
|
|
|
112 |
|
|
JIS X 0208:1997, "7-bit and 8-bit double byte coded |
113 |
|
|
Kanji set for information interchange", Japan |
114 |
|
|
Industrial Standards Committee <http://www.jisc.go.jp/>, |
115 |
|
|
1997. |
116 |
|
|
|
117 |
|
|
JIS X 0213:2000, "7-bit and 8-bit double byte extended |
118 |
|
|
coded Kanji set for information interchange", Japan |
119 |
|
|
Industrial Standards Committee <http://www.jisc.go.jp/>, |
120 |
|
|
2000. |
121 |
|
|
|
122 |
|
|
L<Encode::ISO2022::EightBit> |
123 |
|
|
|
124 |
|
|
POD:TO DO: |
125 |
|
|
Support of C<iso-2022-jp-fullwidth> |
126 |
|
|
|
127 |
|
|
POD:LICENSE: |
128 |
|
|
Copyright %%YEAR%% Wakaba <w@suika.fam.cx> |
129 |
|
|
|
130 |
|
|
%%PerlLicense%% |