| 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::Encoding 3perl" |
| 58 |
.TH Encode::Encoding 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::Encoding \- Encode Implementation Base Class |
| 65 |
.SH SYNOPSIS |
| 66 |
.IX Header "SYNOPSIS" |
| 67 |
.Vb 2 |
| 68 |
\& package Encode::MyEncoding; |
| 69 |
\& use parent qw(Encode::Encoding); |
| 70 |
\& |
| 71 |
\& _\|_PACKAGE_\|_\->Define(qw(myCanonical myAlias)); |
| 72 |
.Ve |
| 73 |
.SH DESCRIPTION |
| 74 |
.IX Header "DESCRIPTION" |
| 75 |
As mentioned in Encode, encodings are (in the current |
| 76 |
implementation at least) defined as objects. The mapping of encoding |
| 77 |
name to object is via the \f(CW%Encode::Encoding\fR hash. Though you can |
| 78 |
directly manipulate this hash, it is strongly encouraged to use this |
| 79 |
base class module and add \fBencode()\fR and \fBdecode()\fR methods. |
| 80 |
.SS "Methods you should implement" |
| 81 |
.IX Subsection "Methods you should implement" |
| 82 |
You are strongly encouraged to implement methods below, at least |
| 83 |
either \fBencode()\fR or \fBdecode()\fR. |
| 84 |
.IP "\->encode($string [,$check])" 4 |
| 85 |
.IX Item "->encode($string [,$check])" |
| 86 |
MUST return the octet sequence representing \fR\f(CI$string\fR\fI\fR. |
| 87 |
.RS 4 |
| 88 |
.IP \(bu 2 |
| 89 |
If \fR\f(CI$check\fR\fI\fR is true, it SHOULD modify \fI\fR\f(CI$string\fR\fI\fR in place to remove |
| 90 |
the converted part (i.e. the whole string unless there is an error). |
| 91 |
If \fBperlio_ok()\fR is true, SHOULD becomes MUST. |
| 92 |
.IP \(bu 2 |
| 93 |
If an error occurs, it SHOULD return the octet sequence for the |
| 94 |
fragment of string that has been converted and modify \f(CW$string\fR in-place |
| 95 |
to remove the converted part leaving it starting with the problem |
| 96 |
fragment. If \fBperlio_ok()\fR is true, SHOULD becomes MUST. |
| 97 |
.IP \(bu 2 |
| 98 |
If \fR\f(CI$check\fR\fI\fR is false then \f(CW\*(C`encode\*(C'\fR MUST make a "best effort" to |
| 99 |
convert the string \- for example, by using a replacement character. |
| 100 |
.RE |
| 101 |
.RS 4 |
| 102 |
.RE |
| 103 |
.IP "\->decode($octets [,$check])" 4 |
| 104 |
.IX Item "->decode($octets [,$check])" |
| 105 |
MUST return the string that \fR\f(CI$octets\fR\fI\fR represents. |
| 106 |
.RS 4 |
| 107 |
.IP \(bu 2 |
| 108 |
If \fR\f(CI$check\fR\fI\fR is true, it SHOULD modify \fI\fR\f(CI$octets\fR\fI\fR in place to remove |
| 109 |
the converted part (i.e. the whole sequence unless there is an |
| 110 |
error). If \fBperlio_ok()\fR is true, SHOULD becomes MUST. |
| 111 |
.IP \(bu 2 |
| 112 |
If an error occurs, it SHOULD return the fragment of string that has |
| 113 |
been converted and modify \f(CW$octets\fR in-place to remove the converted |
| 114 |
part leaving it starting with the problem fragment. If \fBperlio_ok()\fR is |
| 115 |
true, SHOULD becomes MUST. |
| 116 |
.IP \(bu 2 |
| 117 |
If \fR\f(CI$check\fR\fI\fR is false then \f(CW\*(C`decode\*(C'\fR should make a "best effort" to |
| 118 |
convert the string \- for example by using Unicode's "\ex{FFFD}" as a |
| 119 |
replacement character. |
| 120 |
.RE |
| 121 |
.RS 4 |
| 122 |
.RE |
| 123 |
.PP |
| 124 |
If you want your encoding to work with encoding pragma, you should |
| 125 |
also implement the method below. |
| 126 |
.ie n .IP "\->cat_decode($destination, $octets, $offset, $terminator [,$check])" 4 |
| 127 |
.el .IP "\->cat_decode($destination, \f(CW$octets\fR, \f(CW$offset\fR, \f(CW$terminator\fR [,$check])" 4 |
| 128 |
.IX Item "->cat_decode($destination, $octets, $offset, $terminator [,$check])" |
| 129 |
MUST decode \fR\f(CI$octets\fR\fI\fR with \fI\fR\f(CI$offset\fR\fI\fR and concatenate it to \fI\fR\f(CI$destination\fR\fI\fR. |
| 130 |
Decoding will terminate when \f(CW$terminator\fR (a string) appears in output. |
| 131 |
\&\fI\fR\f(CI$offset\fR\fI\fR will be modified to the last \f(CW$octets\fR position at end of decode. |
| 132 |
Returns true if \f(CW$terminator\fR appears output, else returns false. |
| 133 |
.SS "Other methods defined in Encode::Encodings" |
| 134 |
.IX Subsection "Other methods defined in Encode::Encodings" |
| 135 |
You do not have to override methods shown below unless you have to. |
| 136 |
.IP \->name 4 |
| 137 |
.IX Item "->name" |
| 138 |
Predefined As: |
| 139 |
.Sp |
| 140 |
.Vb 1 |
| 141 |
\& sub name { return shift\->{\*(AqName\*(Aq} } |
| 142 |
.Ve |
| 143 |
.Sp |
| 144 |
MUST return the string representing the canonical name of the encoding. |
| 145 |
.IP \->mime_name 4 |
| 146 |
.IX Item "->mime_name" |
| 147 |
Predefined As: |
| 148 |
.Sp |
| 149 |
.Vb 3 |
| 150 |
\& sub mime_name{ |
| 151 |
\& return Encode::MIME::Name::get_mime_name(shift\->name); |
| 152 |
\& } |
| 153 |
.Ve |
| 154 |
.Sp |
| 155 |
MUST return the string representing the IANA charset name of the encoding. |
| 156 |
.IP \->renew 4 |
| 157 |
.IX Item "->renew" |
| 158 |
Predefined As: |
| 159 |
.Sp |
| 160 |
.Vb 6 |
| 161 |
\& sub renew { |
| 162 |
\& my $self = shift; |
| 163 |
\& my $clone = bless { %$self } => ref($self); |
| 164 |
\& $clone\->{renewed}++; |
| 165 |
\& return $clone; |
| 166 |
\& } |
| 167 |
.Ve |
| 168 |
.Sp |
| 169 |
This method reconstructs the encoding object if necessary. If you need |
| 170 |
to store the state during encoding, this is where you clone your object. |
| 171 |
.Sp |
| 172 |
PerlIO ALWAYS calls this method to make sure it has its own private |
| 173 |
encoding object. |
| 174 |
.IP \->renewed 4 |
| 175 |
.IX Item "->renewed" |
| 176 |
Predefined As: |
| 177 |
.Sp |
| 178 |
.Vb 1 |
| 179 |
\& sub renewed { $_[0]\->{renewed} || 0 } |
| 180 |
.Ve |
| 181 |
.Sp |
| 182 |
Tells whether the object is renewed (and how many times). Some |
| 183 |
modules emit \f(CW\*(C`Use of uninitialized value in null operation\*(C'\fR warning |
| 184 |
unless the value is numeric so return 0 for false. |
| 185 |
.IP \->\fBperlio_ok()\fR 4 |
| 186 |
.IX Item "->perlio_ok()" |
| 187 |
Predefined As: |
| 188 |
.Sp |
| 189 |
.Vb 3 |
| 190 |
\& sub perlio_ok { |
| 191 |
\& return eval { require PerlIO::encoding } ? 1 : 0; |
| 192 |
\& } |
| 193 |
.Ve |
| 194 |
.Sp |
| 195 |
If your encoding does not support PerlIO for some reasons, just; |
| 196 |
.Sp |
| 197 |
.Vb 1 |
| 198 |
\& sub perlio_ok { 0 } |
| 199 |
.Ve |
| 200 |
.IP \->\fBneeds_lines()\fR 4 |
| 201 |
.IX Item "->needs_lines()" |
| 202 |
Predefined As: |
| 203 |
.Sp |
| 204 |
.Vb 1 |
| 205 |
\& sub needs_lines { 0 }; |
| 206 |
.Ve |
| 207 |
.Sp |
| 208 |
If your encoding can work with PerlIO but needs line buffering, you |
| 209 |
MUST define this method so it returns true. 7bit ISO\-2022 encodings |
| 210 |
are one example that needs this. When this method is missing, false |
| 211 |
is assumed. |
| 212 |
.SS "Example: Encode::ROT13" |
| 213 |
.IX Subsection "Example: Encode::ROT13" |
| 214 |
.Vb 3 |
| 215 |
\& package Encode::ROT13; |
| 216 |
\& use strict; |
| 217 |
\& use parent qw(Encode::Encoding); |
| 218 |
\& |
| 219 |
\& _\|_PACKAGE_\|_\->Define(\*(Aqrot13\*(Aq); |
| 220 |
\& |
| 221 |
\& sub encode($$;$){ |
| 222 |
\& my ($obj, $str, $chk) = @_; |
| 223 |
\& $str =~ tr/A\-Za\-z/N\-ZA\-Mn\-za\-m/; |
| 224 |
\& $_[1] = \*(Aq\*(Aq if $chk; # this is what in\-place edit means |
| 225 |
\& return $str; |
| 226 |
\& } |
| 227 |
\& |
| 228 |
\& # Jr pna or ynml yvxr guvf; |
| 229 |
\& *decode = \e&encode; |
| 230 |
\& |
| 231 |
\& 1; |
| 232 |
.Ve |
| 233 |
.SH "Why the heck Encode API is different?" |
| 234 |
.IX Header "Why the heck Encode API is different?" |
| 235 |
It should be noted that the \fR\f(CI$check\fR\fI\fR behaviour is different from the |
| 236 |
outer public API. The logic is that the "unchecked" case is useful |
| 237 |
when the encoding is part of a stream which may be reporting errors |
| 238 |
(e.g. STDERR). In such cases, it is desirable to get everything |
| 239 |
through somehow without causing additional errors which obscure the |
| 240 |
original one. Also, the encoding is best placed to know what the |
| 241 |
correct replacement character is, so if that is the desired behaviour |
| 242 |
then letting low level code do it is the most efficient. |
| 243 |
.PP |
| 244 |
By contrast, if \fR\f(CI$check\fR\fI\fR is true, the scheme above allows the |
| 245 |
encoding to do as much as it can and tell the layer above how much |
| 246 |
that was. What is lacking at present is a mechanism to report what |
| 247 |
went wrong. The most likely interface will be an additional method |
| 248 |
call to the object, or perhaps (to avoid forcing per-stream objects |
| 249 |
on otherwise stateless encodings) an additional parameter. |
| 250 |
.PP |
| 251 |
It is also highly desirable that encoding classes inherit from |
| 252 |
\&\f(CW\*(C`Encode::Encoding\*(C'\fR as a base class. This allows that class to define |
| 253 |
additional behaviour for all encoding objects. |
| 254 |
.PP |
| 255 |
.Vb 2 |
| 256 |
\& package Encode::MyEncoding; |
| 257 |
\& use parent qw(Encode::Encoding); |
| 258 |
\& |
| 259 |
\& _\|_PACKAGE_\|_\->Define(qw(myCanonical myAlias)); |
| 260 |
.Ve |
| 261 |
.PP |
| 262 |
to create an object with \f(CW\*(C`bless {Name => ...}, $class\*(C'\fR, and call |
| 263 |
define_encoding. They inherit their \f(CW\*(C`name\*(C'\fR method from |
| 264 |
\&\f(CW\*(C`Encode::Encoding\*(C'\fR. |
| 265 |
.SS "Compiled Encodings" |
| 266 |
.IX Subsection "Compiled Encodings" |
| 267 |
For the sake of speed and efficiency, most of the encodings are now |
| 268 |
supported via a \fIcompiled form\fR: XS modules generated from UCM |
| 269 |
files. Encode provides the enc2xs tool to achieve that. Please see |
| 270 |
enc2xs for more details. |
| 271 |
.SH "SEE ALSO" |
| 272 |
.IX Header "SEE ALSO" |
| 273 |
perlmod, enc2xs |