| 1 |
.\" -*- mode: troff; coding: utf-8 -*- |
| 2 |
.\" Automatically generated by Pod::Man 5.0102 (Pod::Simple 3.45) |
| 3 |
.\" |
| 4 |
.\" Standard preamble: |
| 5 |
.\" ======================================================================== |
| 6 |
.de Sp \" Vertical space (when we can't use .PP) |
| 7 |
.if t .sp .5v |
| 8 |
.if n .sp |
| 9 |
.. |
| 10 |
.de Vb \" Begin verbatim text |
| 11 |
.ft CW |
| 12 |
.nf |
| 13 |
.ne \\$1 |
| 14 |
.. |
| 15 |
.de Ve \" End verbatim text |
| 16 |
.ft R |
| 17 |
.fi |
| 18 |
.. |
| 19 |
.\" \*(C` and \*(C' are quotes in nroff, nothing in troff, for use with C<>. |
| 20 |
.ie n \{\ |
| 21 |
. ds C` "" |
| 22 |
. ds C' "" |
| 23 |
'br\} |
| 24 |
.el\{\ |
| 25 |
. ds C` |
| 26 |
. ds C' |
| 27 |
'br\} |
| 28 |
.\" |
| 29 |
.\" Escape single quotes in literal strings from groff's Unicode transform. |
| 30 |
.ie \n(.g .ds Aq \(aq |
| 31 |
.el .ds Aq ' |
| 32 |
.\" |
| 33 |
.\" If the F register is >0, we'll generate index entries on stderr for |
| 34 |
.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index |
| 35 |
.\" entries marked with X<> in POD. Of course, you'll have to process the |
| 36 |
.\" output yourself in some meaningful fashion. |
| 37 |
.\" |
| 38 |
.\" Avoid warning from groff about undefined register 'F'. |
| 39 |
.de IX |
| 40 |
.. |
| 41 |
.nr rF 0 |
| 42 |
.if \n(.g .if rF .nr rF 1 |
| 43 |
.if (\n(rF:(\n(.g==0)) \{\ |
| 44 |
. if \nF \{\ |
| 45 |
. de IX |
| 46 |
. tm Index:\\$1\t\\n%\t"\\$2" |
| 47 |
.. |
| 48 |
. if !\nF==2 \{\ |
| 49 |
. nr % 0 |
| 50 |
. nr F 2 |
| 51 |
. \} |
| 52 |
. \} |
| 53 |
.\} |
| 54 |
.rr rF |
| 55 |
.\" ======================================================================== |
| 56 |
.\" |
| 57 |
.IX Title "Encode::JP 3perl" |
| 58 |
.TH Encode::JP 3perl 2025-11-16 "perl v5.40.1" "Perl Programmers Reference Guide" |
| 59 |
.\" For nroff, turn off justification. Always turn off hyphenation; it makes |
| 60 |
.\" way too many mistakes in technical documents. |
| 61 |
.if n .ad l |
| 62 |
.nh |
| 63 |
.SH NAME |
| 64 |
Encode::JP \- Japanese Encodings |
| 65 |
.SH SYNOPSIS |
| 66 |
.IX Header "SYNOPSIS" |
| 67 |
.Vb 3 |
| 68 |
\& use Encode qw/encode decode/; |
| 69 |
\& $euc_jp = encode("euc\-jp", $utf8); # loads Encode::JP implicitly |
| 70 |
\& $utf8 = decode("euc\-jp", $euc_jp); # ditto |
| 71 |
.Ve |
| 72 |
.SH ABSTRACT |
| 73 |
.IX Header "ABSTRACT" |
| 74 |
This module implements Japanese charset encodings. Encodings |
| 75 |
supported are as follows. |
| 76 |
.PP |
| 77 |
.Vb 10 |
| 78 |
\& Canonical Alias Description |
| 79 |
\& \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\- |
| 80 |
\& euc\-jp /\ebeuc.*jp$/i EUC (Extended Unix Character) |
| 81 |
\& /\ebjp.*euc/i |
| 82 |
\& /\ebujis$/i |
| 83 |
\& shiftjis /\ebshift.*jis$/i Shift JIS (aka MS Kanji) |
| 84 |
\& /\ebsjis$/i |
| 85 |
\& 7bit\-jis /\ebjis$/i 7bit JIS |
| 86 |
\& iso\-2022\-jp ISO\-2022\-JP [RFC1468] |
| 87 |
\& = 7bit JIS with all Halfwidth Kana |
| 88 |
\& converted to Fullwidth |
| 89 |
\& iso\-2022\-jp\-1 ISO\-2022\-JP\-1 [RFC2237] |
| 90 |
\& = ISO\-2022\-JP with JIS X 0212\-1990 |
| 91 |
\& support. See below |
| 92 |
\& MacJapanese Shift JIS + Apple vendor mappings |
| 93 |
\& cp932 /\ebwindows\-31j$/i Code Page 932 |
| 94 |
\& = Shift JIS + MS/IBM vendor mappings |
| 95 |
\& jis0201\-raw JIS0201, raw format |
| 96 |
\& jis0208\-raw JIS0208, raw format |
| 97 |
\& jis0212\-raw JIS0212, raw format |
| 98 |
\& \-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\-\- |
| 99 |
.Ve |
| 100 |
.SH DESCRIPTION |
| 101 |
.IX Header "DESCRIPTION" |
| 102 |
To find out how to use this module in detail, see Encode. |
| 103 |
.SH "Note on ISO\-2022\-JP(\-1)?" |
| 104 |
.IX Header "Note on ISO-2022-JP(-1)?" |
| 105 |
ISO\-2022\-JP\-1 (RFC2237) is a superset of ISO\-2022\-JP (RFC1468) which |
| 106 |
adds support for JIS X 0212\-1990. That means you can use the same |
| 107 |
code to decode to utf8 but not vice versa. |
| 108 |
.PP |
| 109 |
.Vb 1 |
| 110 |
\& $utf8 = decode(\*(Aqiso\-2022\-jp\-1\*(Aq, $stream); |
| 111 |
.Ve |
| 112 |
.PP |
| 113 |
and |
| 114 |
.PP |
| 115 |
.Vb 1 |
| 116 |
\& $utf8 = decode(\*(Aqiso\-2022\-jp\*(Aq, $stream); |
| 117 |
.Ve |
| 118 |
.PP |
| 119 |
yield the same result but |
| 120 |
.PP |
| 121 |
.Vb 1 |
| 122 |
\& $with_0212 = encode(\*(Aqiso\-2022\-jp\-1\*(Aq, $utf8); |
| 123 |
.Ve |
| 124 |
.PP |
| 125 |
is now different from |
| 126 |
.PP |
| 127 |
.Vb 1 |
| 128 |
\& $without_0212 = encode(\*(Aqiso\-2022\-jp\*(Aq, $utf8 ); |
| 129 |
.Ve |
| 130 |
.PP |
| 131 |
In the latter case, characters that map to 0212 are first converted |
| 132 |
to U+3013 (0xA2AE in EUC-JP; a white square also known as 'Tofu' or |
| 133 |
\&'geta mark') then fed to the decoding engine. U+FFFD is not used, |
| 134 |
in order to preserve text layout as much as possible. |
| 135 |
.SH BUGS |
| 136 |
.IX Header "BUGS" |
| 137 |
The ASCII region (0x00\-0x7f) is preserved for all encodings, even |
| 138 |
though this conflicts with mappings by the Unicode Consortium. |
| 139 |
.SH "SEE ALSO" |
| 140 |
.IX Header "SEE ALSO" |
| 141 |
Encode |