Some UTF-8 todos.
[p5sagit/p5-mst-13.2.git] / README.jp
CommitLineData
d8416318 1If you read this file _as_is_, just ignore the funny characters you
2see. It is written in the POD format (see perlpod manpage) which is
3specially designed to be readable as is.
4
5The following documentation is written in FOO encoding.
6
7=head1 NAME
8
9perljp - ÆüËܸì Perl ¥¬¥¤¥É
10
11=head1 ÀâÌÀ
12
13¤è¤¦¤³¤½ Perl ¤Ø!
14
15Perl 5.8.0 ¤è¤ê¡¢Unicode¥µ¥Ý¡¼¥È¤¬ÂçÉý¤Ë¶¯²½¤µ¤ì¡¢¤½¤Î·ë²Ì¥é¥Æ¥óʸ»ú°Ê³°¤Îʸ»ú¥³¡¼¥É¤Î¥µ¥Ý¡¼¥È¤¬ CJK (Ãæ¹ñ¸ì¡¢ÆüËܸ졢¥Ï¥ó¥°¥ë)¤ò´Þ¤á¤Æ²Ã¤ï¤ê¤Þ¤·¤¿¡£Unicode¤ÏÀ¤³¦Ãæ¤Îʸ»ú¤ò°ì¤Ä¤Îʸ»ú¥³¡¼¥É¤Ç°·¤¦¤³¤È¤òÌܻؤ·¤¿É¸½àµ¬³Ê¤Ç¤¢¤ê¡¢Å줫¤éÀ¾¡¢¤Ï¤¿¤Þ¤¿¤½¤Î´Ö¤Îʸ»ú¡Ê¥®¥ê¥·¥ãʸ»ú¡¢¥­¥ê¡¼¥ëʸ»ú¡¢¥¢¥é¥Ó¥¢Ê¸»ú¡¢¥Ø¥Ö¥é¥¤Ê¸»ú¡¢¥Ç¥£¡¼¥ô¥¡¥Ê¥¬¡¼¥êʸ»ú¡¢¤Ê¤É¤Ê¤É¡Ë¤ä¡¢¤³¤ì¤Þ¤Ç¤ÏOS¥Ù¥ó¥À¡¼¤¬Æȼ«¤ËÄê¤á¤Æ¤¤¤¿Ê¸»ú(PC¤ª¤è¤ÓMacintosh)¤¬¤¹¤Ç¤Ë´Þ¤Þ¤ì¤Æ¤¤¤Þ¤¹¡£
16
17Perl ¼«¿È¤Ï Unicode ¤ÇÆ°ºî¤·¤Þ¤¹¡£Perl ¥¹¥¯¥ê¥×¥ÈÆâ¤Îʸ»úÎó¥ê¥Æ¥é¥ë¤äÀµµ¬É½¸½¤Ï Unicode ¤òÁ°Äó¤È¤·¤Æ¤¤¤Þ¤¹¡£¤½¤·¤ÆÆþ½ÐÎϤΤ¿¤á¤Ë¤Ï¡¢¤³¤ì¤Þ¤Ç»È¤ï¤ì¤Æ¤­¤¿¤µ¤Þ¤¶¤Þ¤Êʸ»ú¥³¡¼¥É¤ËÂбþ¤¹¤ë¥â¥¸¥å¡¼¥ë¡¢¡Ö Encode ¡×¤¬É¸½àÁõÈ÷¤µ¤ì¤Æ¤ª¤ê¡¢Unicode ¤È¤³¤ì¤é¤Îʸ»ú¥³¡¼¥É¤ÎÁê¸ßÊÑ´¹¤â´Êñ¤Ë¹Ô¤¨¤ë¤è¤¦¤Ë¤Ê¤Ã¤Æ¤¤¤Þ¤¹¡£
18
19¸½»þÅÀ¤Ç Encode ¤¬¥µ¥Ý¡¼¥È¤¹¤ëʸ»ú¥³¡¼¥É¤Ï°Ê²¼¤Î¤È¤ª¤ê¤Ç¤¹¡£
20
21 7bit-jis AdobeStandardEncoding AdobeSymbol AdobeZdingbat
22 ascii big5 big5-hkscs cp1006
23 cp1026 cp1047 cp1250 cp1251
24 cp1252 cp1253 cp1254 cp1255
25 cp1256 cp1257 cp1258 cp37
26 cp424 cp437 cp500 cp737
27 cp775 cp850 cp852 cp855
28 cp856 cp857 cp860 cp861
29 cp862 cp863 cp864 cp865
30 cp866 cp869 cp874 cp875
31 cp932 cp936 cp949 cp950
32 dingbats euc-cn euc-jp euc-kr
33 gb12345-raw gb2312-raw gsm0338 hp-roman8
34 hz iso-2022-jp iso-2022-jp-1 iso-8859-1
35 iso-8859-10 iso-8859-11 iso-8859-13 iso-8859-14
36 iso-8859-15 iso-8859-16 iso-8859-2 iso-8859-3
37 iso-8859-4 iso-8859-5 iso-8859-6 iso-8859-7
38 iso-8859-8 iso-8859-9 iso-ir-165 jis0201-raw
39 jis0208-raw jis0212-raw johab koi8-f
40 koi8-r koi8-u ksc5601-raw MacArabic
41 MacCentralEurRoman MacChineseSimp MacChineseTrad MacCroatian
42 MacCyrillic MacDingbats MacFarsi MacGreek
43 MacHebrew MacIcelandic MacJapanese MacKorean
44 MacRoman MacRomanian MacRumanian MacSami
45 MacSymbol MacThai MacTurkish MacUkrainian
46 nextstep posix-bc shiftjis symbol
47 UCS-2BE UCS-2LE UTF-16 UTF-16BE
48 UTF-16LE UTF-32 UTF-32BE UTF-32LE
49 utf8 viscii
50
51(Á´114¼ïÎà)
52
53Î㤨¤Ð¡¢Ê¸»ú¥³¡¼¥ÉFOO¤Î¥Õ¥¡¥¤¥ë¤òUTF-8¤ËÊÑ´¹¤¹¤ë¤Ë¤Ï¡¢°Ê²¼¤Î¤è¤¦¤Ë¤·¤Þ¤¹¡£
54
55 perl -Mencoding=FOO,STDOUT,utf8 -pe1 < file.FOO > file.utf8
56
57¤Þ¤¿¡¢Perl¤Ë¤Ï¡¢Á´Éô¤¬Perl¤Ç½ñ¤«¤ì¤¿Ê¸»ú¥³¡¼¥ÉÊÑ´¹¥æ¡¼¥Æ¥£¥ê¥Æ¥£¡¢piconv¤âÉÕ°¤·¤Æ¤¤¤ë¤Î¤Ç¡¢°Ê²¼¤Î¤è¤¦¤Ë¤¹¤ë¤³¤È¤â¤Ç¤­¤Þ¤¹¡£
58
59 piconv -f FOO -t utf8 < file.FOO > file.utf8
60 piconv -f utf8 -t FOO < file.utf8 > file.FOO
61
62=head2 About (jcode.pl|Jcode.pm|JPerl)
63
645.8°ÊÁ°¤Î¡¢¥¹¥¯¥ê¥×¥È¤¬EUC-JP¤Ç¤¢¤ì¤Ð¥ê¥Æ¥é¥ë¤À¤±¤Ï°·¤¦¤³¤È¤¬¤Ç¤­¤Þ¤·¤¿¡£¤Þ¤¿¡¢Æþ½ÐÎϤò°·¤¦¥â¥¸¥å¡¼¥ë¤È¤·¤Æ¤ÏJcode.pm¤¬( http://openlab.jp/Jcode/ )¡¢perl4ÍѤΥ桼¥Æ¥£¥ê¥Æ¥£¤È¤·¤Æ¤Ïjcode.pl( http://srekcah.org/jcode/ )¤¬¤½¤ì¤¾¤ì¸ºß¤·¡¢ÆüËܸì¤Î°·¤¨¤ëCGI¤Ç¤è¤¯ÍøÍѤµ¤ì¤Æ¤¤¤ë¤³¤È¤ò¸æ¸¤¸¤ÎÊý¤â¾¯¤Ê¤¯¤Ê¤¤¤«¤È»×¤ï¤ì¤Þ¤¹¡£¤¿¤À¤·¡¢ÆüËܸì¤Ë¤è¤ëÀµµ¬É½¸½¤ò¤¦¤Þ¤¯°·¤¦¤³¤È¤ÏÉÔ²Äǽ¤Ç¤·¤¿¡£
65
665.005°ÊÁ°¤ÎPerl¤Ë¤Ï¡¢ÆüËܸì¤ËÆò½¤·¤¿¥í¡¼¥«¥é¥¤¥ºÈÇ¡¢Jperl¤¬Â¸ºß¤·¤Þ¤·¤¿( http://homepage2.nifty.com/kipp/perl/jperl/index.html )¡£¤Þ¤¿¡¢MacOS 9.x/ClassicÍѤÎPerl¡¢MacPerl¤ÎÆüËܸìÈǤâMacJPerl¤È¤·¤Æ¸ºß¤·¤Æ¤Þ¤·¤¿¡£( http://world.std.com/~habilis/macjperl/ ).¤³¤ì¤é¤Ç¤Ïʸ»ú¥³¡¼¥É¤È¤·¤ÆEUC-JP¤Ë²Ã¤¨Shift_JIS¤â¤½¤Î¤Þ¤Þ°·¤¦¤³¤È¤¬¤Ç¤­¡¢¤Þ¤¿ÆüËܸì¤Ë¤è¤ëÀµµ¬É½¸½¤ò°·¤¦¤³¤È¤â²Äǽ¤Ç¤·¤¿¡£
67
68Perl5.8¤Ç¤Ï¡¢¤³¤ì¤é¤Îµ¡Ç½¤¬¤¹¤Ù¤ÆPerlËÜÂΤÀ¤±¤Ç¼Â¸½¤Ç¤­¤ë¾å¤Ë¡¢ÆüËܸì¤Î¤ß¤Ê¤é¤º¾åµ­114¤Îʸ»ú¥³¡¼¥É¤ò¤¹¤Ù¤Æ¡¢¤·¤«¤âƱ»þ¤Ë°·¤¦¤³¤È¤¬¤Ç¤­¤Þ¤¹¡£¤µ¤é¤Ë¡¢CPAN¤Ê¤É¤«¤é¿·¤·¤¤Ê¸»ú¥³¡¼¥ÉÍѤΥ⥸¥å¡¼¥ë¤òÆþ¼ê¤¹¤ë¤³¤È¤â´Êñ¤Ë¤Ç¤­¤ë¤è¤¦¤Ë¤Ê¤Ã¤Æ¤¤¤Þ¤¹¡£
69
70=over 4
71
72=item¡¡Æþ½ÐÎÏ
73
74°Ê²¼¤ÎÎã¤Ï¤¤¤Å¤ì¤âShift_JIS¤ÎÆþÎϤòEUC-JP¤ËÊÑ´¹¤·¤Æ½ÐÎϤ·¤Þ¤¹¡£
75
76 # jcode.pl
77 require "jcode.pl";
78 while(<>){
79 jcode::convert(*_, 'euc', 'sjis);
80 print;
81 }
82 # Jcode.pm
83 use Jcode;
84 while(<>){
85 print Jcode->new($_, 'sjis')->euc;
86 }
87 # Perl 5.8
88 use Encode;
89 while(<>){
90 from_to($_, 'shiftjis', 'euc-jp');
91 print;
92 }
93 # Perl 5.8 - encoding ¤òÍøÍѤ·¤Æ
94 use encoding 'euc-jp', STDIN=>'shiftjis'
95 while(<>){
96 print;
97 }
98
99=item Jperl ¸ß´¹¥¹¥¯¥ê¥×¥È
100
101 ¤¤¤ï¤æ¤ë"shebang"¤òÊѹ¹¤¹¤ë¤À¤±¤Ç¡¢JperlÍѤÎscript¤Î¤Û¤È¤ó¤É¤ÏÊѹ¹¤Ê¤·¤ËÍøÍѲÄǽ¤À¤È»×¤ï¤ì¤Þ¤¹¡£
102
103 #!/path/to/jperl
104 ¢­
105 #!/path/to/perl -Mencoding=euc-jp
106
107 ¾Ü¤·¤¯¤Ï perldoc encoding ¤ò»²¾È¤·¤Æ¤¯¤À¤µ¤¤¡£
108
109=back
110
111=head2 ¤µ¤é¤Ë¾Ü¤·¤¯
112
113Perl¤Ë¤ÏËÄÂç¤Ê»ñÎÁ¤¬ÉÕ°¤·¤Æ¤ª¤ê¡¢Perl¤Î¿·µ¡Ç½¤äUnicode¥µ¥Ý¡¼¥È¡¢¤½¤·¤ÆEncode¥â¥¸¥å¡¼¥ë¤Î»ÈÍÑË¡¤Ê¤É¤¬ºÙ¤«¤¯ÌÖÍ夵¤ì¤Æ¤¤¤Þ¤¹¡Ê»ÄÇ°¤Ê¤¬¤é¡¢¤Û¤È¤ó¤É±Ñ¸ì¤Ç¤Ï¤¢¤ê¤Þ¤¹¤¬¡Ë¡£°Ê²¼¤Î¥³¥Þ¥ó¥É¤Ç¤½¤ì¤é¤Î°ìÉô¤ò±ÜÍ÷¤¹¤ë¤³¤È¤¬²Äǽ¤Ç¤¹¡£
114
115 perldoc perlunicode # Perl¤ÎUnicode¥µ¥Ý¡¼¥ÈÁ´ÈÌ
116 perldoc Encode # Encode¥â¥¸¥å¡¼¥ë¤Ë´Ø¤·¤Æ
117 perldoc Encode::JP # ¤¦¤ÁÆüËܸìʸ»ú¥³¡¼¥É¤Ë´Ø¤·¤Æ
118
119=head2 PerlÁ´È̤˴ؤ¹¤ë URL
120
121=over 4
122
123=item L<http://www.perl.com/>
124
125Perl ¥Û¡¼¥à¥Ú¡¼¥¸ (O'Reilly and Associates)
126
127=item L<http://www.cpan.org/>
128
129CPAN (Comprehensive Perl Archive Network)
130
131=item L<http://lists.perl.org/>
132
133Perl ¥á¡¼¥ê¥ó¥°¥ê¥¹¥È½¸
134
135=back
136
137=head2 Perl¤Î½¤ÆÀ¤ËÌòΩ¤Ä URL
138
139=over 4
140
141=item L<http://www.oreilly.com.tw/chinese/>
142
143O'Reilly ¼Ò¤ÎPerl´ØÏ¢½ñÀÒ(ÈËÂλúÃæ¹ñ¸ì)
144
145=item L<http://www.oreilly.com.cn/chinese/>
146
147O'Reilly ¼Ò¤ÎPerl´ØÏ¢½ñÀÒ(´ÊÂλúÃæ¹ñ¸ì)
148
149=item L<http://www.oreilly.co.jp/catalog.htm>
150
151¥ª¥é¥¤¥ê¡¼¼Ò¤ÎPerl´ØÏ¢½ñÀÒ(ÆüËܸì)
152
153=back
154
155=head2 Perl ¥æ¡¼¥¶¡¼¥°¥ë¡¼¥×
156
157=over 4
158
159=item L<http://www.pm.org/groups/asia.shtml#China>
160
161Ãæ¹ñ¡ÊÃæ²Ú¿Í̱¶¦Ï¹ñ¡Ë
162
163=item L<http://www.pm.org/groups/asia.shtml#Japan>
164
165ÆüËÜ
166
167=item L<http://www.pm.org/groups/asia.shtml#Korea%20(Republic%20of)>
168
169´Ú¹ñ¡ÊÂç´Ú̱¹ñ¡Ë
170
171=item L<http://www.pm.org/groups/asia.shtml#Taiwan>
172
173ÂæÏÑ¡ÊÃæ²Ú̱¹ñ¡Ë
174
175=back
176
177=head2 Unicode´ØÏ¢¤ÎURL
178
179=over 4
180
181=item L<http://www.unicode.org/>
182
183Unicode ¥³¥ó¥½¡¼¥·¥¢¥à (Unicodeµ¬³Ê¤ÎÁªÄêÃÄÂÎ)
184
185=item L<http://www.cl.cam.ac.uk/%7Emgk25/unicode.html>
186
187UTF-8 and Unicode FAQ for Unix/Linux
188
189=item L<http://kldp.org/Translations/html/UTF8-Unicode-KLDP/UTF8-Unicode-KLDP.html>
190
191UTF-8 and Unicode FAQ for Unix/Linux (¥Ï¥ó¥°¥ëÌõ)
192
193=back
194
195=head1 AUTHORS
196
197Jarkko Hietaniemi E<lt>jhi@iki.fiE<gt>
198Dan Kogai (¾®»ô¡¡ÃÆ) E<lt>dankogai@dan.co.jpE<gt>
199
200=cut