sam-t2/devtools/v8plus/man/man3/Encode::JP.3

.\" Automatically generated by Pod::Man v1.37, Pod::Parser v1.32
.\"
.\" Standard preamble:
.\" ========================================================================
.de Sh \" Subsection heading
.br
.if t .Sp
.ne 5
.PP
\fB\\$1\fR
.PP
..
.de Sp \" Vertical space (when we can't use .PP)
.if t .sp .5v
.if n .sp
..
.de Vb \" Begin verbatim text
.ft CW
.nf
.ne \\$1
..
.de Ve \" End verbatim text
.ft R
.fi
..
.\" Set up some character translations and predefined strings.  \*(-- will
.\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
.\" double quote, and \*(R" will give a right double quote.  | will give a
.\" real vertical bar.  \*(C+ will give a nicer C++.  Capital omega is used to
.\" do unbreakable dashes and therefore won't be available.  \*(C` and \*(C'
.\" expand to `' in nroff, nothing in troff, for use with C<>.
.tr \(*W-|\(bv\*(Tr
.ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
.ie n \{\
.    ds -- \(*W-
.    ds PI pi
.    if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
.    if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\"  diablo 12 pitch
.    ds L" ""
.    ds R" ""
.    ds C` ""
.    ds C' ""
'br\}
.el\{\
.    ds -- \|\(em\|
.    ds PI \(*p
.    ds L" ``
.    ds R" ''
'br\}
.\"
.\" If the F register is turned on, we'll generate index entries on stderr for
.\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index
.\" entries marked with X<> in POD.  Of course, you'll have to process the
.\" output yourself in some meaningful fashion.
.if \nF \{\
.    de IX
.    tm Index:\\$1\t\\n%\t"\\$2"
..
.    nr % 0
.    rr F
.\}
.\"
.\" For nroff, turn off justification.  Always turn off hyphenation; it makes
.\" way too many mistakes in technical documents.
.hy 0
.if n .na
.\"
.\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
.\" Fear.  Run.  Save yourself.  No user-serviceable parts.
.    \" fudge factors for nroff and troff
.if n \{\
.    ds #H 0
.    ds #V .8m
.    ds #F .3m
.    ds #[ \f1
.    ds #] \fP
.\}
.if t \{\
.    ds #H ((1u-(\\\\n(.fu%2u))*.13m)
.    ds #V .6m
.    ds #F 0
.    ds #[ \&
.    ds #] \&
.\}
.    \" simple accents for nroff and troff
.if n \{\
.    ds ' \&
.    ds ` \&
.    ds ^ \&
.    ds , \&
.    ds ~ ~
.    ds /
.\}
.if t \{\
.    ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
.    ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
.    ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
.    ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
.    ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
.    ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
.\}
.    \" troff and (daisy-wheel) nroff accents
.ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
.ds 8 \h'\*(#H'\(*b\h'-\*(#H'
.ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
.ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
.ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
.ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
.ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
.ds ae a\h'-(\w'a'u*4/10)'e
.ds Ae A\h'-(\w'A'u*4/10)'E
.    \" corrections for vroff
.if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
.if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
.    \" for low resolution devices (crt and lpr)
.if \n(.H>23 .if \n(.V>19 \
\{\
.    ds : e
.    ds 8 ss
.    ds o a
.    ds d- d\h'-1'\(ga
.    ds D- D\h'-1'\(hy
.    ds th \o'bp'
.    ds Th \o'LP'
.    ds ae ae
.    ds Ae AE
.\}
.rm #[ #] #H #V #F C
.\" ========================================================================
.\"
.IX Title "Encode::JP 3"
.TH Encode::JP 3 "2001-09-21" "perl v5.8.8" "Perl Programmers Reference Guide"
.SH "NAME"
Encode::JP \- Japanese Encodings
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
.Vb 3
\&    use Encode qw/encode decode/;
\&    $euc_jp = encode("euc-jp", $utf8);   # loads Encode::JP implicitly
\&    $utf8   = decode("euc-jp", $euc_jp); # ditto
.Ve
.SH "ABSTRACT"
.IX Header "ABSTRACT"
This module implements Japanese charset encodings.  Encodings
supported are as follows.
.PP
.Vb 21
\&  Canonical   Alias             Description
\&  --------------------------------------------------------------------
\&  euc-jp      /\ebeuc.*jp$/i     EUC (Extended Unix Character)
\&              /\ebjp.*euc/i
\&              /\ebujis$/i
\&  shiftjis    /\ebshift.*jis$/i  Shift JIS (aka MS Kanji)
\&              /\ebsjis$/i
\&  7bit-jis    /\ebjis$/i         7bit JIS
\&  iso-2022-jp                   ISO-2022-JP                  [RFC1468]
\&                                = 7bit JIS with all Halfwidth Kana
\&                                  converted to Fullwidth
\&  iso-2022-jp-1                 ISO-2022-JP-1                [RFC2237]
\&                                = ISO-2022-JP with JIS X 0212-1990
\&                                  support.  See below
\&  MacJapanese                   Shift JIS + Apple vendor mappings
\&  cp932       /\ebwindows-31j$/i Code Page 932
\&                                = Shift JIS + MS/IBM vendor mappings
\&  jis0201-raw                   JIS0201, raw format
\&  jis0208-raw                   JIS0201, raw format
\&  jis0212-raw                   JIS0201, raw format
\&  --------------------------------------------------------------------
.Ve
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
To find out how to use this module in detail, see Encode.
.SH "Note on ISO\-2022\-JP(\-1)?"
.IX Header "Note on ISO-2022-JP(-1)?"
\&\s-1ISO\-2022\-JP\-1\s0 (\s-1RFC2237\s0) is a superset of \s-1ISO\-2022\-JP\s0 (\s-1RFC1468\s0) which
adds support for \s-1JIS\s0 X 0212\-1990.  That means you can use the same
code to decode to utf8 but not vice versa.
.PP
.Vb 1
\&  $utf8 = decode('iso-2022-jp-1', $stream);
.Ve
.PP
and
.PP
.Vb 1
\&  $utf8 = decode('iso-2022-jp',   $stream);
.Ve
.PP
yield the same result but
.PP
.Vb 1
\&  $with_0212 = encode('iso-2022-jp-1', $utf8);
.Ve
.PP
is now different from
.PP
.Vb 1
\&  $without_0212 = encode('iso-2022-jp', $utf8 );
.Ve
.PP
In the latter case, characters that map to 0212 are first converted
to U+3013 (0xA2AE in \s-1EUC\-JP\s0; a white square also known as 'Tofu' or
\&'geta mark') then fed to the decoding engine.  U+FFFD is not used,
in order to preserve text layout as much as possible.
.SH "BUGS"
.IX Header "BUGS"
The \s-1ASCII\s0 region (0x00\-0x7f) is preserved for all encodings, even
though this conflicts with mappings by the Unicode Consortium.  See
.PP
<http://www.debian.or.jp/~kubota/unicode\-symbols.html.en>
.PP
to find out why it is implemented that way.
.SH "SEE ALSO"
.IX Header "SEE ALSO"
Encode