Encode/SJIS/Pictogram.esr

#?PESRC/1.0
Name:
        SJIS::Pictogram
ShortDescription:
        The Encode module for shift JIS coding systems
Description:
        This module defines convertion between perl internal
        representation and shift JIS coding systems defined
        in standards of JIS (Japan Industrial Standards).

{
Name:
        sjis-imode
Alias:
        x-sjis-imode
Cversion:
        use:charset:Pictogram
        C:bit=8
        C:G0=G94:J      ## JIS X 0201:1997 Graphic character set for Latin letters
        C:G1=G94n:B@    ## JIS X 0208:1997
        C:G2=G94:I      ## JIS X 0201:1997 Graphic character set for Katakana
        C:G3=G256n:CSimode_g3   ## i-mode pictograph set
        C:option:{undef_char}=["\x22\x2E", {type => 'G94n', charset => 'B', revision => '@'}]
Encode:
        =>ucs_to_jisx0201_latin ucs_to_jisx0208_1997_latin ucs_to_jisx0201_katakana_hw ucs_to_imode
        ->sjis:C
Decode:
        <-sjis:C
        <=jisx0201_latin_to_ucs jisx0208_1997_latin_to_ucs jisx0201_katakana_hw_to_ucs imode_to_ucs
Description:
        Shift JIS with i-mode extended pictographs
}

{
Name:
        sjis-lmode
Alias:
        x-sjis-lmode
Cversion:
        use:charset:Pictogram
        C:bit=8
        C:G0=G94:J      ## JIS X 0201:1997 Graphic character set for Latin letters
        C:G1=G94n:B@    ## JIS X 0208:1997
        C:G2=G94:I      ## JIS X 0201:1997 Graphic character set for Katakana
        C:G3=G256n:CSlmode_g3   ## L-mode pictograph set
        C:option:{undef_char}=["\x22\x2E", {type => 'G94n', charset => 'B', revision => '@'}]
Encode:
        =>ucs_to_jisx0201_latin ucs_to_jisx0208_1997_latin ucs_to_jisx0201_katakana_hw ucs_to_lmode
        ->sjis:C
Decode:
        <-sjis:C
        <=jisx0201_latin_to_ucs jisx0208_1997_latin_to_ucs jisx0201_katakana_hw_to_ucs lmode_to_ucs
Description:
        Shift JIS with L-mode extended pictographs
}

{
Name:
        sjis-doti
Alias:
        x-sjis-doti
Cversion:
        use:charset:Pictogram
        C:bit=8
        C:G0=G94:J      ## JIS X 0201:1997 Graphic character set for Latin letters
        C:G1=G94n:B@    ## JIS X 0208:1997
        C:G2=G94:I      ## JIS X 0201:1997 Graphic character set for Katakana
        C:G3=G256n:CSdoti_g3    ## dot-i pictograph set
        C:option:{undef_char}=["\x22\x2E", {type => 'G94n', charset => 'B', revision => '@'}]
Encode:
        =>ucs_to_jisx0201_latin ucs_to_jisx0208_1997_latin ucs_to_jisx0201_katakana_hw ucs_to_doti
        ->sjis:C
Decode:
        <-sjis:C
        <=jisx0201_latin_to_ucs jisx0208_1997_latin_to_ucs jisx0201_katakana_hw_to_ucs doti_to_ucs
Description:
        Shift JIS with dot-i extended pictographs
}

{
Name:
        sjis-jphone
Alias:
        x-sjis-jphone sjis-jsky x-sjis-jsky
Cversion:
        use:charset:Pictogram
        C:bit=8
        C:G0=G94:B      ## ASCII + YEN SIGN
        C:G1=G94n:B@    ## JIS X 0208:1997
        C:G2=G94:I      ## JIS X 0201:1997 Graphic character set for Katakana
        C:G3=G94n:~     ## undef
        C:option:{undef_char}=["\x22\x2E", {type => 'G94n', charset => 'B', revision => '@'}]
Encode:Prepare:
        C:option:{fallback_from_ucs}=\&Encode::SJIS::_internal_to_page
Encode:
        =>ucs_to_ascii_yen ucs_to_jisx0208_1997_yen ucs_to_jisx0201_katakana_hw ucs_to_jphone
        ->sjis:C
Decode:
        !& Encode::SJIS::page_to_internal
        <-sjis:C
        <=ascii_yen_to_ucs jisx0208_1997_yen_to_ucs jisx0201_katakana_hw_to_ucs jphone_to_ucs
Description:
        Shift JIS with JPHONE extended pictographs
        
        RESTRICTION: In current implemention, pictograms can't be outputed in
        shortest form.  For example, C<0x1B 0x24 0x45 0x41 0x0F 0x1B 0x24 0x45 0x42 0x0F>
        can be represented as C<0x1B 0x24 0x45 0x41 0x42 0x0F> but this encoder
        always output former style.  (Although it is lengthy, it does not mean
        invalid and decoder supprots both form.)
}

POD:ENCODING:POSTAMBLE:
        

POD:SEE ALSO:
        [ASTEL] "Astel Pictograms",
        <http://www.yozan.co.jp/asteltokyo/doti/siyou/emoji.htm>.
        
        [JGUIDE] "HTML Contents for J-Sky Service Development Guide", J-Phone Co., LTD,
        2002-01-15, <http://www.dp.j-phone.com/file/JSkyHTMLGuide_20020115.pdf>.
        See also <http://www.dp.j-phone.com/jsky/tech.html>.
        (Note that J-PHONE and J-SKY is the trademarks or registered trademarks
        of J-PHONE Corporation.)
        
        [LSPEC] "'L-mode' Technical Specification for Contents Providers, Version 2.2",
        Nippon Telegraph and Telephone East Corporation,
        Nippon Telegraph and Telephone West Corportation, 2002-11.
        Available from <http://www.ntt-east.co.jp/Lmode/06_contents/02_tsukuri.html>.
        (Note that L-mode is the trade mark of NTT EAST and WEST.)
        
        SuikaWiki:"Extention to Shift JIS on portable phones"
        <http://suika.fam.cx/~wakaba/-temp/wiki/wiki?%B7%C8%C2%D3%C5%C5%CF%C3%A4%CE%A5%B7%A5%D5%A5%C8JIS%B3%C8%C4%A5>
        
        L<Encode::SJIS>

POD:LICENSE:
        Copyright %%YEAR%% Nanashi-san <nanashi-san@nanashi.invalid>
        
        %%PerlLicense%%
1	wakaba	1.1	#?PESRC/1.0
2			Name:
3			SJIS::Pictogram
4			ShortDescription:
5			The Encode module for shift JIS coding systems
6			Description:
7			This module defines convertion between perl internal
8			representation and shift JIS coding systems defined
9			in standards of JIS (Japan Industrial Standards).
10
11			{
12			Name:
13			sjis-imode
14			Alias:
15			x-sjis-imode
16			Cversion:
17			use:charset:Pictogram
18			C:bit=8
19			C:G0=G94:J ## JIS X 0201:1997 Graphic character set for Latin letters
20			C:G1=G94n:B@ ## JIS X 0208:1997
21			C:G2=G94:I ## JIS X 0201:1997 Graphic character set for Katakana
22			C:G3=G256n:CSimode_g3 ## i-mode pictograph set
23			C:option:{undef_char}=["\x22\x2E", {type => 'G94n', charset => 'B', revision => '@'}]
24			Encode:
25			=>ucs_to_jisx0201_latin ucs_to_jisx0208_1997_latin ucs_to_jisx0201_katakana_hw ucs_to_imode
26			->sjis:C
27			Decode:
28			<-sjis:C
29			<=jisx0201_latin_to_ucs jisx0208_1997_latin_to_ucs jisx0201_katakana_hw_to_ucs imode_to_ucs
30			Description:
31			Shift JIS with i-mode extended pictographs
32			}
33
34			{
35			Name:
36			sjis-lmode
37			Alias:
38			x-sjis-lmode
39			Cversion:
40			use:charset:Pictogram
41			C:bit=8
42			C:G0=G94:J ## JIS X 0201:1997 Graphic character set for Latin letters
43			C:G1=G94n:B@ ## JIS X 0208:1997
44			C:G2=G94:I ## JIS X 0201:1997 Graphic character set for Katakana
45			C:G3=G256n:CSlmode_g3 ## L-mode pictograph set
46			C:option:{undef_char}=["\x22\x2E", {type => 'G94n', charset => 'B', revision => '@'}]
47			Encode:
48			=>ucs_to_jisx0201_latin ucs_to_jisx0208_1997_latin ucs_to_jisx0201_katakana_hw ucs_to_lmode
49			->sjis:C
50			Decode:
51			<-sjis:C
52			<=jisx0201_latin_to_ucs jisx0208_1997_latin_to_ucs jisx0201_katakana_hw_to_ucs lmode_to_ucs
53			Description:
54			Shift JIS with L-mode extended pictographs
55			}
56
57			{
58			Name:
59			sjis-doti
60			Alias:
61			x-sjis-doti
62			Cversion:
63			use:charset:Pictogram
64			C:bit=8
65			C:G0=G94:J ## JIS X 0201:1997 Graphic character set for Latin letters
66			C:G1=G94n:B@ ## JIS X 0208:1997
67			C:G2=G94:I ## JIS X 0201:1997 Graphic character set for Katakana
68			C:G3=G256n:CSdoti_g3 ## dot-i pictograph set
69			C:option:{undef_char}=["\x22\x2E", {type => 'G94n', charset => 'B', revision => '@'}]
70			Encode:
71			=>ucs_to_jisx0201_latin ucs_to_jisx0208_1997_latin ucs_to_jisx0201_katakana_hw ucs_to_doti
72			->sjis:C
73			Decode:
74			<-sjis:C
75			<=jisx0201_latin_to_ucs jisx0208_1997_latin_to_ucs jisx0201_katakana_hw_to_ucs doti_to_ucs
76			Description:
77			Shift JIS with dot-i extended pictographs
78			}
79
80			{
81			Name:
82			sjis-jphone
83			Alias:
84	wakaba	1.2	x-sjis-jphone sjis-jsky x-sjis-jsky
85	wakaba	1.1	Cversion:
86			use:charset:Pictogram
87			C:bit=8
88	wakaba	1.2	C:G0=G94:B ## ASCII + YEN SIGN
89	wakaba	1.1	C:G1=G94n:B@ ## JIS X 0208:1997
90			C:G2=G94:I ## JIS X 0201:1997 Graphic character set for Katakana
91			C:G3=G94n:~ ## undef
92			C:option:{undef_char}=["\x22\x2E", {type => 'G94n', charset => 'B', revision => '@'}]
93			Encode:Prepare:
94			C:option:{fallback_from_ucs}=\&Encode::SJIS::_internal_to_page
95			Encode:
96	wakaba	1.2	=>ucs_to_ascii_yen ucs_to_jisx0208_1997_yen ucs_to_jisx0201_katakana_hw ucs_to_jphone
97	wakaba	1.1	->sjis:C
98			Decode:
99			!& Encode::SJIS::page_to_internal
100			<-sjis:C
101	wakaba	1.2	<=ascii_yen_to_ucs jisx0208_1997_yen_to_ucs jisx0201_katakana_hw_to_ucs jphone_to_ucs
102	wakaba	1.1	Description:
103			Shift JIS with JPHONE extended pictographs
104
105			RESTRICTION: In current implemention, pictograms can't be outputed in
106			shortest form. For example, C<0x1B 0x24 0x45 0x41 0x0F 0x1B 0x24 0x45 0x42 0x0F>
107			can be represented as C<0x1B 0x24 0x45 0x41 0x42 0x0F> but this encoder
108			always output former style. (Although it is lengthy, it does not mean
109			invalid and decoder supprots both form.)
110			}
111
112			POD:ENCODING:POSTAMBLE:
113
114
115			POD:SEE ALSO:
116			[ASTEL] "Astel Pictograms",
117			<http://www.yozan.co.jp/asteltokyo/doti/siyou/emoji.htm>.
118
119			[JGUIDE] "HTML Contents for J-Sky Service Development Guide", J-Phone Co., LTD,
120			2002-01-15, <http://www.dp.j-phone.com/file/JSkyHTMLGuide_20020115.pdf>.
121			See also <http://www.dp.j-phone.com/jsky/tech.html>.
122			(Note that J-PHONE and J-SKY is the trademarks or registered trademarks
123			of J-PHONE Corporation.)
124
125			[LSPEC] "'L-mode' Technical Specification for Contents Providers, Version 2.2",
126			Nippon Telegraph and Telephone East Corporation,
127			Nippon Telegraph and Telephone West Corportation, 2002-11.
128			Available from <http://www.ntt-east.co.jp/Lmode/06_contents/02_tsukuri.html>.
129			(Note that L-mode is the trade mark of NTT EAST and WEST.)
130
131			SuikaWiki:"Extention to Shift JIS on portable phones"
132			<http://suika.fam.cx/~wakaba/-temp/wiki/wiki?%B7%C8%C2%D3%C5%C5%CF%C3%A4%CE%A5%B7%A5%D5%A5%C8JIS%B3%C8%C4%A5>
133
134			L<Encode::SJIS>
135
136			POD:LICENSE:
137			Copyright %%YEAR%% Nanashi-san <nanashi-san@nanashi.invalid>
138
139			%%PerlLicense%%