| 1 | .\" Automatically generated by Pod::Man v1.34, Pod::Parser v1.13 |
| 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 "ENC2XS 1" |
| 132 | .TH ENC2XS 1 "2002-08-28" "perl v5.8.0" "Perl Programmers Reference Guide" |
| 133 | .SH "NAME" |
| 134 | enc2xs \-\- Perl Encode Module Generator |
| 135 | .SH "SYNOPSIS" |
| 136 | .IX Header "SYNOPSIS" |
| 137 | .Vb 3 |
| 138 | \& enc2xs -[options] |
| 139 | \& enc2xs -M ModName mapfiles... |
| 140 | \& enc2xs -C |
| 141 | .Ve |
| 142 | .SH "DESCRIPTION" |
| 143 | .IX Header "DESCRIPTION" |
| 144 | \&\fIenc2xs\fR builds a Perl extension for use by Encode from either |
| 145 | Unicode Character Mapping files (.ucm) or Tcl Encoding Files (.enc). |
| 146 | Besides being used internally during the build process of the Encode |
| 147 | module, you can use \fIenc2xs\fR to add your own encoding to perl. |
| 148 | No knowledge of \s-1XS\s0 is necessary. |
| 149 | .SH "Quick Guide" |
| 150 | .IX Header "Quick Guide" |
| 151 | If you want to know as little about Perl as possible but need to |
| 152 | add a new encoding, just read this chapter and forget the rest. |
| 153 | .IP "0." 4 |
| 154 | Have a .ucm file ready. You can get it from somewhere or you can write |
| 155 | your own from scratch or you can grab one from the Encode distribution |
| 156 | and customize it. For the \s-1UCM\s0 format, see the next Chapter. In the |
| 157 | example below, I'll call my theoretical encoding myascii, defined |
| 158 | in \fImy.ucm\fR. \f(CW\*(C`$\*(C'\fR is a shell prompt. |
| 159 | .Sp |
| 160 | .Vb 2 |
| 161 | \& $ ls -F |
| 162 | \& my.ucm |
| 163 | .Ve |
| 164 | .IP "1." 4 |
| 165 | Issue a command as follows; |
| 166 | .Sp |
| 167 | .Vb 5 |
| 168 | \& $ enc2xs -M My my.ucm |
| 169 | \& generating Makefile.PL |
| 170 | \& generating My.pm |
| 171 | \& generating README |
| 172 | \& generating Changes |
| 173 | .Ve |
| 174 | .Sp |
| 175 | Now take a look at your current directory. It should look like this. |
| 176 | .Sp |
| 177 | .Vb 2 |
| 178 | \& $ ls -F |
| 179 | \& Makefile.PL My.pm my.ucm t/ |
| 180 | .Ve |
| 181 | .Sp |
| 182 | The following files were created. |
| 183 | .Sp |
| 184 | .Vb 3 |
| 185 | \& Makefile.PL - MakeMaker script |
| 186 | \& My.pm - Encode submodule |
| 187 | \& t/My.t - test file |
| 188 | .Ve |
| 189 | .RS 4 |
| 190 | .IP "1.1." 4 |
| 191 | .IX Item "1.1." |
| 192 | If you want *.ucm installed together with the modules, do as follows; |
| 193 | .Sp |
| 194 | .Vb 3 |
| 195 | \& $ mkdir Encode |
| 196 | \& $ mv *.ucm Encode |
| 197 | \& $ enc2xs -M My Encode/*ucm |
| 198 | .Ve |
| 199 | .RE |
| 200 | .RS 4 |
| 201 | .RE |
| 202 | .IP "2." 4 |
| 203 | Edit the files generated. You don't have to if you have no time \s-1AND\s0 no |
| 204 | intention to give it to someone else. But it is a good idea to edit |
| 205 | the pod and to add more tests. |
| 206 | .IP "3." 4 |
| 207 | Now issue a command all Perl Mongers love: |
| 208 | .Sp |
| 209 | .Vb 2 |
| 210 | \& $ perl Makefile.PL |
| 211 | \& Writing Makefile for Encode::My |
| 212 | .Ve |
| 213 | .IP "4." 4 |
| 214 | Now all you have to do is make. |
| 215 | .Sp |
| 216 | .Vb 12 |
| 217 | \& $ make |
| 218 | \& cp My.pm blib/lib/Encode/My.pm |
| 219 | \& /usr/local/bin/perl /usr/local/bin/enc2xs -Q -O \e |
| 220 | \& -o encode_t.c -f encode_t.fnm |
| 221 | \& Reading myascii (myascii) |
| 222 | \& Writing compiled form |
| 223 | \& 128 bytes in string tables |
| 224 | \& 384 bytes (25%) saved spotting duplicates |
| 225 | \& 1 bytes (99.2%) saved using substrings |
| 226 | \& .... |
| 227 | \& chmod 644 blib/arch/auto/Encode/My/My.bs |
| 228 | \& $ |
| 229 | .Ve |
| 230 | .Sp |
| 231 | The time it takes varies depending on how fast your machine is and |
| 232 | how large your encoding is. Unless you are working on something big |
| 233 | like euc\-tw, it won't take too long. |
| 234 | .IP "5." 4 |
| 235 | You can \*(L"make install\*(R" already but you should test first. |
| 236 | .Sp |
| 237 | .Vb 8 |
| 238 | \& $ make test |
| 239 | \& PERL_DL_NONLAZY=1 /usr/local/bin/perl -Iblib/arch -Iblib/lib \e |
| 240 | \& -e 'use Test::Harness qw(&runtests $verbose); \e |
| 241 | \& $verbose=0; runtests @ARGV;' t/*.t |
| 242 | \& t/My....ok |
| 243 | \& All tests successful. |
| 244 | \& Files=1, Tests=2, 0 wallclock secs |
| 245 | \& ( 0.09 cusr + 0.01 csys = 0.09 CPU) |
| 246 | .Ve |
| 247 | .IP "6." 4 |
| 248 | If you are content with the test result, just \*(L"make install\*(R" |
| 249 | .IP "7." 4 |
| 250 | If you want to add your encoding to Encode's demand-loading list |
| 251 | (so you don't have to \*(L"use Encode::YourEncoding\*(R"), run |
| 252 | .Sp |
| 253 | .Vb 1 |
| 254 | \& enc2xs -C |
| 255 | .Ve |
| 256 | .Sp |
| 257 | to update Encode::ConfigLocal, a module that controls local settings. |
| 258 | After that, \*(L"use Encode;\*(R" is enough to load your encodings on demand. |
| 259 | .SH "The Unicode Character Map" |
| 260 | .IX Header "The Unicode Character Map" |
| 261 | Encode uses the Unicode Character Map (\s-1UCM\s0) format for source character |
| 262 | mappings. This format is used by \s-1IBM\s0's \s-1ICU\s0 package and was adopted |
| 263 | by Nick Ing-Simmons for use with the Encode module. Since \s-1UCM\s0 is |
| 264 | more flexible than Tcl's Encoding Map and far more user\-friendly, |
| 265 | this is the recommended formet for Encode now. |
| 266 | .PP |
| 267 | A \s-1UCM\s0 file looks like this. |
| 268 | .PP |
| 269 | .Vb 19 |
| 270 | \& # |
| 271 | \& # Comments |
| 272 | \& # |
| 273 | \& <code_set_name> "US-ascii" # Required |
| 274 | \& <code_set_alias> "ascii" # Optional |
| 275 | \& <mb_cur_min> 1 # Required; usually 1 |
| 276 | \& <mb_cur_max> 1 # Max. # of bytes/char |
| 277 | \& <subchar> \ex3F # Substitution char |
| 278 | \& # |
| 279 | \& CHARMAP |
| 280 | \& <U0000> \ex00 |0 # <control> |
| 281 | \& <U0001> \ex01 |0 # <control> |
| 282 | \& <U0002> \ex02 |0 # <control> |
| 283 | \& .... |
| 284 | \& <U007C> \ex7C |0 # VERTICAL LINE |
| 285 | \& <U007D> \ex7D |0 # RIGHT CURLY BRACKET |
| 286 | \& <U007E> \ex7E |0 # TILDE |
| 287 | \& <U007F> \ex7F |0 # <control> |
| 288 | \& END CHARMAP |
| 289 | .Ve |
| 290 | .IP "\(bu" 4 |
| 291 | Anything that follows \f(CW\*(C`#\*(C'\fR is treated as a comment. |
| 292 | .IP "\(bu" 4 |
| 293 | The header section continues until a line containing the word |
| 294 | \&\s-1CHARMAP\s0. This section has a form of \fI<keyword> value\fR, one |
| 295 | pair per line. Strings used as values must be quoted. Barewords are |
| 296 | treated as numbers. \fI\exXX\fR represents a byte. |
| 297 | .Sp |
| 298 | Most of the keywords are self\-explanatory. \fIsubchar\fR means |
| 299 | substitution character, not subcharacter. When you decode a Unicode |
| 300 | sequence to this encoding but no matching character is found, the byte |
| 301 | sequence defined here will be used. For most cases, the value here is |
| 302 | \&\ex3F; in \s-1ASCII\s0, this is a question mark. |
| 303 | .IP "\(bu" 4 |
| 304 | \&\s-1CHARMAP\s0 starts the character map section. Each line has a form as |
| 305 | follows: |
| 306 | .Sp |
| 307 | .Vb 5 |
| 308 | \& <UXXXX> \exXX.. |0 # comment |
| 309 | \& ^ ^ ^ |
| 310 | \& | | +- Fallback flag |
| 311 | \& | +-------- Encoded byte sequence |
| 312 | \& +-------------- Unicode Character ID in hex |
| 313 | .Ve |
| 314 | .Sp |
| 315 | The format is roughly the same as a header section except for the |
| 316 | fallback flag: | followed by 0..3. The meaning of the possible |
| 317 | values is as follows: |
| 318 | .RS 4 |
| 319 | .IP "|0" 4 |
| 320 | .IX Item "|0" |
| 321 | Round trip safe. A character decoded to Unicode encodes back to the |
| 322 | same byte sequence. Most characters have this flag. |
| 323 | .IP "|1" 4 |
| 324 | .IX Item "|1" |
| 325 | Fallback for unicode \-> encoding. When seen, enc2xs adds this |
| 326 | character for the encode map only. |
| 327 | .IP "|2" 4 |
| 328 | .IX Item "|2" |
| 329 | Skip sub-char mapping should there be no code point. |
| 330 | .IP "|3" 4 |
| 331 | .IX Item "|3" |
| 332 | Fallback for encoding \-> unicode. When seen, enc2xs adds this |
| 333 | character for the decode map only. |
| 334 | .RE |
| 335 | .RS 4 |
| 336 | .RE |
| 337 | .IP "\(bu" 4 |
| 338 | And finally, \s-1END\s0 \s-1OF\s0 \s-1CHARMAP\s0 ends the section. |
| 339 | .PP |
| 340 | When you are manually creating a \s-1UCM\s0 file, you should copy ascii.ucm |
| 341 | or an existing encoding which is close to yours, rather than write |
| 342 | your own from scratch. |
| 343 | .PP |
| 344 | When you do so, make sure you leave at least \fBU0000\fR to \fBU0020\fR as |
| 345 | is, unless your environment is \s-1EBCDIC\s0. |
| 346 | .PP |
| 347 | \&\fB\s-1CAVEAT\s0\fR: not all features in \s-1UCM\s0 are implemented. For example, |
| 348 | icu:state is not used. Because of that, you need to write a perl |
| 349 | module if you want to support algorithmical encodings, notably |
| 350 | the \s-1ISO\-2022\s0 series. Such modules include Encode::JP::2022_JP, |
| 351 | Encode::KR::2022_KR, and Encode::TW::HZ. |
| 352 | .Sh "Coping with duplicate mappings" |
| 353 | .IX Subsection "Coping with duplicate mappings" |
| 354 | When you create a map, you \s-1SHOULD\s0 make your mappings round-trip safe. |
| 355 | That is, \f(CW\*(C`encode('your\-encoding', decode('your\-encoding', $data)) eq |
| 356 | $data\*(C'\fR stands for all characters that are marked as \f(CW\*(C`|0\*(C'\fR. Here is |
| 357 | how to make sure: |
| 358 | .IP "\(bu" 4 |
| 359 | Sort your map in Unicode order. |
| 360 | .IP "\(bu" 4 |
| 361 | When you have a duplicate entry, mark either one with '|1' or '|3'. |
| 362 | .IP "\(bu" 4 |
| 363 | And make sure the '|1' or '|3' entry \s-1FOLLOWS\s0 the '|0' entry. |
| 364 | .PP |
| 365 | Here is an example from big5\-eten. |
| 366 | .PP |
| 367 | .Vb 2 |
| 368 | \& <U2550> \exF9\exF9 |0 |
| 369 | \& <U2550> \exA2\exA4 |3 |
| 370 | .Ve |
| 371 | .PP |
| 372 | Internally Encoding \-> Unicode and Unicode \-> Encoding Map looks like |
| 373 | this; |
| 374 | .PP |
| 375 | .Vb 4 |
| 376 | \& E to U U to E |
| 377 | \& -------------------------------------- |
| 378 | \& \exF9\exF9 => U2550 U2550 => \exF9\exF9 |
| 379 | \& \exA2\exA4 => U2550 |
| 380 | .Ve |
| 381 | .PP |
| 382 | So it is round-trip safe for \exF9\exF9. But if the line above is upside |
| 383 | down, here is what happens. |
| 384 | .PP |
| 385 | .Vb 4 |
| 386 | \& E to U U to E |
| 387 | \& -------------------------------------- |
| 388 | \& \exA2\exA4 => U2550 U2550 => \exF9\exF9 |
| 389 | \& (\exF9\exF9 => U2550 is now overwritten!) |
| 390 | .Ve |
| 391 | .PP |
| 392 | The Encode package comes with \fIucmlint\fR, a crude but sufficient |
| 393 | utility to check the integrity of a \s-1UCM\s0 file. Check under the |
| 394 | Encode/bin directory for this. |
| 395 | .SH "Bookmarks" |
| 396 | .IX Header "Bookmarks" |
| 397 | .IP "\(bu" 4 |
| 398 | \&\s-1ICU\s0 Home Page |
| 399 | <http://oss.software.ibm.com/icu/> |
| 400 | .IP "\(bu" 4 |
| 401 | \&\s-1ICU\s0 Character Mapping Tables |
| 402 | <http://oss.software.ibm.com/icu/charset/> |
| 403 | .IP "\(bu" 4 |
| 404 | ICU:Conversion Data |
| 405 | <http://oss.software.ibm.com/icu/userguide/conversion\-data.html> |
| 406 | .SH "SEE ALSO" |
| 407 | .IX Header "SEE ALSO" |
| 408 | Encode, |
| 409 | perlmod, |
| 410 | perlpod |