| 1 | .\" Automatically generated by Pod::Man v1.37, Pod::Parser v1.32 |
| 2 | .\" |
| 3 | .\" Standard preamble: |
| 4 | .\" ======================================================================== |
| 5 | .de Sh \" Subsection heading |
| 6 | .br |
| 7 | .if t .Sp |
| 8 | .ne 5 |
| 9 | .PP |
| 10 | \fB\\$1\fR |
| 11 | .PP |
| 12 | .. |
| 13 | .de Sp \" Vertical space (when we can't use .PP) |
| 14 | .if t .sp .5v |
| 15 | .if n .sp |
| 16 | .. |
| 17 | .de Vb \" Begin verbatim text |
| 18 | .ft CW |
| 19 | .nf |
| 20 | .ne \\$1 |
| 21 | .. |
| 22 | .de Ve \" End verbatim text |
| 23 | .ft R |
| 24 | .fi |
| 25 | .. |
| 26 | .\" Set up some character translations and predefined strings. \*(-- will |
| 27 | .\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left |
| 28 | .\" double quote, and \*(R" will give a right double quote. | will give a |
| 29 | .\" real vertical bar. \*(C+ will give a nicer C++. Capital omega is used to |
| 30 | .\" do unbreakable dashes and therefore won't be available. \*(C` and \*(C' |
| 31 | .\" expand to `' in nroff, nothing in troff, for use with C<>. |
| 32 | .tr \(*W-|\(bv\*(Tr |
| 33 | .ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p' |
| 34 | .ie n \{\ |
| 35 | . ds -- \(*W- |
| 36 | . ds PI pi |
| 37 | . if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch |
| 38 | . if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\" diablo 12 pitch |
| 39 | . ds L" "" |
| 40 | . ds R" "" |
| 41 | . ds C` "" |
| 42 | . ds C' "" |
| 43 | 'br\} |
| 44 | .el\{\ |
| 45 | . ds -- \|\(em\| |
| 46 | . ds PI \(*p |
| 47 | . ds L" `` |
| 48 | . ds R" '' |
| 49 | 'br\} |
| 50 | .\" |
| 51 | .\" If the F register is turned on, we'll generate index entries on stderr for |
| 52 | .\" titles (.TH), headers (.SH), subsections (.Sh), items (.Ip), and index |
| 53 | .\" entries marked with X<> in POD. Of course, you'll have to process the |
| 54 | .\" output yourself in some meaningful fashion. |
| 55 | .if \nF \{\ |
| 56 | . de IX |
| 57 | . tm Index:\\$1\t\\n%\t"\\$2" |
| 58 | .. |
| 59 | . nr % 0 |
| 60 | . rr F |
| 61 | .\} |
| 62 | .\" |
| 63 | .\" For nroff, turn off justification. Always turn off hyphenation; it makes |
| 64 | .\" way too many mistakes in technical documents. |
| 65 | .hy 0 |
| 66 | .if n .na |
| 67 | .\" |
| 68 | .\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2). |
| 69 | .\" Fear. Run. Save yourself. No user-serviceable parts. |
| 70 | . \" fudge factors for nroff and troff |
| 71 | .if n \{\ |
| 72 | . ds #H 0 |
| 73 | . ds #V .8m |
| 74 | . ds #F .3m |
| 75 | . ds #[ \f1 |
| 76 | . ds #] \fP |
| 77 | .\} |
| 78 | .if t \{\ |
| 79 | . ds #H ((1u-(\\\\n(.fu%2u))*.13m) |
| 80 | . ds #V .6m |
| 81 | . ds #F 0 |
| 82 | . ds #[ \& |
| 83 | . ds #] \& |
| 84 | .\} |
| 85 | . \" simple accents for nroff and troff |
| 86 | .if n \{\ |
| 87 | . ds ' \& |
| 88 | . ds ` \& |
| 89 | . ds ^ \& |
| 90 | . ds , \& |
| 91 | . ds ~ ~ |
| 92 | . ds / |
| 93 | .\} |
| 94 | .if t \{\ |
| 95 | . ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u" |
| 96 | . ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u' |
| 97 | . ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u' |
| 98 | . ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u' |
| 99 | . ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u' |
| 100 | . ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u' |
| 101 | .\} |
| 102 | . \" troff and (daisy-wheel) nroff accents |
| 103 | .ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V' |
| 104 | .ds 8 \h'\*(#H'\(*b\h'-\*(#H' |
| 105 | .ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#] |
| 106 | .ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H' |
| 107 | .ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u' |
| 108 | .ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#] |
| 109 | .ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#] |
| 110 | .ds ae a\h'-(\w'a'u*4/10)'e |
| 111 | .ds Ae A\h'-(\w'A'u*4/10)'E |
| 112 | . \" corrections for vroff |
| 113 | .if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u' |
| 114 | .if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u' |
| 115 | . \" for low resolution devices (crt and lpr) |
| 116 | .if \n(.H>23 .if \n(.V>19 \ |
| 117 | \{\ |
| 118 | . ds : e |
| 119 | . ds 8 ss |
| 120 | . ds o a |
| 121 | . ds d- d\h'-1'\(ga |
| 122 | . ds D- D\h'-1'\(hy |
| 123 | . ds th \o'bp' |
| 124 | . ds Th \o'LP' |
| 125 | . ds ae ae |
| 126 | . ds Ae AE |
| 127 | .\} |
| 128 | .rm #[ #] #H #V #F C |
| 129 | .\" ======================================================================== |
| 130 | .\" |
| 131 | .IX Title "Encode::Encoding 3" |
| 132 | .TH Encode::Encoding 3 "2001-09-21" "perl v5.8.8" "Perl Programmers Reference Guide" |
| 133 | .SH "NAME" |
| 134 | Encode::Encoding \- Encode Implementation Base Class |
| 135 | .SH "SYNOPSIS" |
| 136 | .IX Header "SYNOPSIS" |
| 137 | .Vb 2 |
| 138 | \& package Encode::MyEncoding; |
| 139 | \& use base qw(Encode::Encoding); |
| 140 | .Ve |
| 141 | .PP |
| 142 | .Vb 1 |
| 143 | \& __PACKAGE__->Define(qw(myCanonical myAlias)); |
| 144 | .Ve |
| 145 | .SH "DESCRIPTION" |
| 146 | .IX Header "DESCRIPTION" |
| 147 | As mentioned in Encode, encodings are (in the current |
| 148 | implementation at least) defined as objects. The mapping of encoding |
| 149 | name to object is via the \f(CW%Encode::Encoding\fR hash. Though you can |
| 150 | directly manipulate this hash, it is strongly encouraged to use this |
| 151 | base class module and add \fIencode()\fR and \fIdecode()\fR methods. |
| 152 | .Sh "Methods you should implement" |
| 153 | .IX Subsection "Methods you should implement" |
| 154 | You are strongly encouraged to implement methods below, at least |
| 155 | either \fIencode()\fR or \fIdecode()\fR. |
| 156 | .IP "\->encode($string [,$check])" 4 |
| 157 | .IX Item "->encode($string [,$check])" |
| 158 | \&\s-1MUST\s0 return the octet sequence representing \fI$string\fR. |
| 159 | .RS 4 |
| 160 | .IP "*" 2 |
| 161 | If \fI$check\fR is true, it \s-1SHOULD\s0 modify \fI$string\fR in place to remove |
| 162 | the converted part (i.e. the whole string unless there is an error). |
| 163 | If \fIperlio_ok()\fR is true, \s-1SHOULD\s0 becomes \s-1MUST\s0. |
| 164 | .IP "*" 2 |
| 165 | If an error occurs, it \s-1SHOULD\s0 return the octet sequence for the |
| 166 | fragment of string that has been converted and modify \f(CW$string\fR in-place |
| 167 | to remove the converted part leaving it starting with the problem |
| 168 | fragment. If \fIperlio_ok()\fR is true, \s-1SHOULD\s0 becomes \s-1MUST\s0. |
| 169 | .IP "*" 2 |
| 170 | If \fI$check\fR is is false then \f(CW\*(C`encode\*(C'\fR \s-1MUST\s0 make a \*(L"best effort\*(R" to |
| 171 | convert the string \- for example, by using a replacement character. |
| 172 | .RE |
| 173 | .RS 4 |
| 174 | .RE |
| 175 | .IP "\->decode($octets [,$check])" 4 |
| 176 | .IX Item "->decode($octets [,$check])" |
| 177 | \&\s-1MUST\s0 return the string that \fI$octets\fR represents. |
| 178 | .RS 4 |
| 179 | .IP "*" 2 |
| 180 | If \fI$check\fR is true, it \s-1SHOULD\s0 modify \fI$octets\fR in place to remove |
| 181 | the converted part (i.e. the whole sequence unless there is an |
| 182 | error). If \fIperlio_ok()\fR is true, \s-1SHOULD\s0 becomes \s-1MUST\s0. |
| 183 | .IP "*" 2 |
| 184 | If an error occurs, it \s-1SHOULD\s0 return the fragment of string that has |
| 185 | been converted and modify \f(CW$octets\fR in-place to remove the converted |
| 186 | part leaving it starting with the problem fragment. If \fIperlio_ok()\fR is |
| 187 | true, \s-1SHOULD\s0 becomes \s-1MUST\s0. |
| 188 | .IP "*" 2 |
| 189 | If \fI$check\fR is false then \f(CW\*(C`decode\*(C'\fR should make a \*(L"best effort\*(R" to |
| 190 | convert the string \- for example by using Unicode's \*(L"\ex{\s-1FFFD\s0}\*(R" as a |
| 191 | replacement character. |
| 192 | .RE |
| 193 | .RS 4 |
| 194 | .RE |
| 195 | .PP |
| 196 | If you want your encoding to work with encoding pragma, you should |
| 197 | also implement the method below. |
| 198 | .ie n .IP "\->cat_decode($destination, $octets\fR, \f(CW$offset\fR, \f(CW$terminator [,$check])" 4 |
| 199 | .el .IP "\->cat_decode($destination, \f(CW$octets\fR, \f(CW$offset\fR, \f(CW$terminator\fR [,$check])" 4 |
| 200 | .IX Item "->cat_decode($destination, $octets, $offset, $terminator [,$check])" |
| 201 | \&\s-1MUST\s0 decode \fI$octets\fR with \fI$offset\fR and concatenate it to \fI$destination\fR. |
| 202 | Decoding will terminate when \f(CW$terminator\fR (a string) appears in output. |
| 203 | \&\fI$offset\fR will be modified to the last \f(CW$octets\fR position at end of decode. |
| 204 | Returns true if \f(CW$terminator\fR appears output, else returns false. |
| 205 | .Sh "Other methods defined in Encode::Encodings" |
| 206 | .IX Subsection "Other methods defined in Encode::Encodings" |
| 207 | You do not have to override methods shown below unless you have to. |
| 208 | .IP "\->name" 4 |
| 209 | .IX Item "->name" |
| 210 | Predefined As: |
| 211 | .Sp |
| 212 | .Vb 1 |
| 213 | \& sub name { return shift->{'Name'} } |
| 214 | .Ve |
| 215 | .Sp |
| 216 | \&\s-1MUST\s0 return the string representing the canonical name of the encoding. |
| 217 | .IP "\->renew" 4 |
| 218 | .IX Item "->renew" |
| 219 | Predefined As: |
| 220 | .Sp |
| 221 | .Vb 6 |
| 222 | \& sub renew { |
| 223 | \& my $self = shift; |
| 224 | \& my $clone = bless { %$self } => ref($self); |
| 225 | \& $clone->{renewed}++; |
| 226 | \& return $clone; |
| 227 | \& } |
| 228 | .Ve |
| 229 | .Sp |
| 230 | This method reconstructs the encoding object if necessary. If you need |
| 231 | to store the state during encoding, this is where you clone your object. |
| 232 | .Sp |
| 233 | PerlIO \s-1ALWAYS\s0 calls this method to make sure it has its own private |
| 234 | encoding object. |
| 235 | .IP "\->renewed" 4 |
| 236 | .IX Item "->renewed" |
| 237 | Predefined As: |
| 238 | .Sp |
| 239 | .Vb 1 |
| 240 | \& sub renewed { $_[0]->{renewed} || 0 } |
| 241 | .Ve |
| 242 | .Sp |
| 243 | Tells whether the object is renewed (and how many times). Some |
| 244 | modules emit \f(CW\*(C`Use of uninitialized value in null operation\*(C'\fR warning |
| 245 | unless the value is numeric so return 0 for false. |
| 246 | .IP "\->\fIperlio_ok()\fR" 4 |
| 247 | .IX Item "->perlio_ok()" |
| 248 | Predefined As: |
| 249 | .Sp |
| 250 | .Vb 4 |
| 251 | \& sub perlio_ok { |
| 252 | \& eval{ require PerlIO::encoding }; |
| 253 | \& return $@ ? 0 : 1; |
| 254 | \& } |
| 255 | .Ve |
| 256 | .Sp |
| 257 | If your encoding does not support PerlIO for some reasons, just; |
| 258 | .Sp |
| 259 | .Vb 1 |
| 260 | \& sub perlio_ok { 0 } |
| 261 | .Ve |
| 262 | .IP "\->\fIneeds_lines()\fR" 4 |
| 263 | .IX Item "->needs_lines()" |
| 264 | Predefined As: |
| 265 | .Sp |
| 266 | .Vb 1 |
| 267 | \& sub needs_lines { 0 }; |
| 268 | .Ve |
| 269 | .Sp |
| 270 | If your encoding can work with PerlIO but needs line buffering, you |
| 271 | \&\s-1MUST\s0 define this method so it returns true. 7bit \s-1ISO\-2022\s0 encodings |
| 272 | are one example that needs this. When this method is missing, false |
| 273 | is assumed. |
| 274 | .Sh "Example: Encode::ROT13" |
| 275 | .IX Subsection "Example: Encode::ROT13" |
| 276 | .Vb 3 |
| 277 | \& package Encode::ROT13; |
| 278 | \& use strict; |
| 279 | \& use base qw(Encode::Encoding); |
| 280 | .Ve |
| 281 | .PP |
| 282 | .Vb 1 |
| 283 | \& __PACKAGE__->Define('rot13'); |
| 284 | .Ve |
| 285 | .PP |
| 286 | .Vb 6 |
| 287 | \& sub encode($$;$){ |
| 288 | \& my ($obj, $str, $chk) = @_; |
| 289 | \& $str =~ tr/A-Za-z/N-ZA-Mn-za-m/; |
| 290 | \& $_[1] = '' if $chk; # this is what in-place edit means |
| 291 | \& return $str; |
| 292 | \& } |
| 293 | .Ve |
| 294 | .PP |
| 295 | .Vb 2 |
| 296 | \& # Jr pna or ynml yvxr guvf; |
| 297 | \& *decode = \e&encode; |
| 298 | .Ve |
| 299 | .PP |
| 300 | .Vb 1 |
| 301 | \& 1; |
| 302 | .Ve |
| 303 | .SH "Why the heck Encode API is different?" |
| 304 | .IX Header "Why the heck Encode API is different?" |
| 305 | It should be noted that the \fI$check\fR behaviour is different from the |
| 306 | outer public \s-1API\s0. The logic is that the \*(L"unchecked\*(R" case is useful |
| 307 | when the encoding is part of a stream which may be reporting errors |
| 308 | (e.g. \s-1STDERR\s0). In such cases, it is desirable to get everything |
| 309 | through somehow without causing additional errors which obscure the |
| 310 | original one. Also, the encoding is best placed to know what the |
| 311 | correct replacement character is, so if that is the desired behaviour |
| 312 | then letting low level code do it is the most efficient. |
| 313 | .PP |
| 314 | By contrast, if \fI$check\fR is true, the scheme above allows the |
| 315 | encoding to do as much as it can and tell the layer above how much |
| 316 | that was. What is lacking at present is a mechanism to report what |
| 317 | went wrong. The most likely interface will be an additional method |
| 318 | call to the object, or perhaps (to avoid forcing per-stream objects |
| 319 | on otherwise stateless encodings) an additional parameter. |
| 320 | .PP |
| 321 | It is also highly desirable that encoding classes inherit from |
| 322 | \&\f(CW\*(C`Encode::Encoding\*(C'\fR as a base class. This allows that class to define |
| 323 | additional behaviour for all encoding objects. |
| 324 | .PP |
| 325 | .Vb 2 |
| 326 | \& package Encode::MyEncoding; |
| 327 | \& use base qw(Encode::Encoding); |
| 328 | .Ve |
| 329 | .PP |
| 330 | .Vb 1 |
| 331 | \& __PACKAGE__->Define(qw(myCanonical myAlias)); |
| 332 | .Ve |
| 333 | .PP |
| 334 | to create an object with \f(CW\*(C`bless {Name => ...}, $class\*(C'\fR, and call |
| 335 | define_encoding. They inherit their \f(CW\*(C`name\*(C'\fR method from |
| 336 | \&\f(CW\*(C`Encode::Encoding\*(C'\fR. |
| 337 | .Sh "Compiled Encodings" |
| 338 | .IX Subsection "Compiled Encodings" |
| 339 | For the sake of speed and efficiency, most of the encodings are now |
| 340 | supported via a \fIcompiled form\fR: \s-1XS\s0 modules generated from \s-1UCM\s0 |
| 341 | files. Encode provides the enc2xs tool to achieve that. Please see |
| 342 | enc2xs for more details. |
| 343 | .SH "SEE ALSO" |
| 344 | .IX Header "SEE ALSO" |
| 345 | perlmod, enc2xs |