| 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::TW 3" |
| 132 | .TH Encode::TW 3 "2001-09-21" "perl v5.8.8" "Perl Programmers Reference Guide" |
| 133 | .SH "NAME" |
| 134 | Encode::TW \- Taiwan\-based Chinese Encodings |
| 135 | .SH "SYNOPSIS" |
| 136 | .IX Header "SYNOPSIS" |
| 137 | .Vb 3 |
| 138 | \& use Encode qw/encode decode/; |
| 139 | \& $big5 = encode("big5", $utf8); # loads Encode::TW implicitly |
| 140 | \& $utf8 = decode("big5", $big5); # ditto |
| 141 | .Ve |
| 142 | .SH "DESCRIPTION" |
| 143 | .IX Header "DESCRIPTION" |
| 144 | This module implements tradition Chinese charset encodings as used |
| 145 | in Taiwan and Hong Kong. |
| 146 | Encodings supported are as follows. |
| 147 | .PP |
| 148 | .Vb 12 |
| 149 | \& Canonical Alias Description |
| 150 | \& -------------------------------------------------------------------- |
| 151 | \& big5-eten /\ebbig-?5$/i Big5 encoding (with ETen extensions) |
| 152 | \& /\ebbig5-?et(en)?$/i |
| 153 | \& /\ebtca-?big5$/i |
| 154 | \& big5-hkscs /\ebbig5-?hk(scs)?$/i |
| 155 | \& /\ebhk(scs)?-?big5$/i |
| 156 | \& Big5 + Cantonese characters in Hong Kong |
| 157 | \& MacChineseTrad Big5 + Apple Vendor Mappings |
| 158 | \& cp950 Code Page 950 |
| 159 | \& = Big5 + Microsoft vendor mappings |
| 160 | \& -------------------------------------------------------------------- |
| 161 | .Ve |
| 162 | .PP |
| 163 | To find out how to use this module in detail, see Encode. |
| 164 | .SH "NOTES" |
| 165 | .IX Header "NOTES" |
| 166 | Due to size concerns, \f(CW\*(C`EUC\-TW\*(C'\fR (Extended Unix Character), \f(CW\*(C`CCCII\*(C'\fR |
| 167 | (Chinese Character Code for Information Interchange), \f(CW\*(C`BIG5PLUS\*(C'\fR |
| 168 | (\s-1CMEX\s0's Big5+) and \f(CW\*(C`BIG5EXT\*(C'\fR (\s-1CMEX\s0's Big5e) are distributed separately |
| 169 | on \s-1CPAN\s0, under the name Encode::HanExtra. That module also contains |
| 170 | extra China-based encodings. |
| 171 | .SH "BUGS" |
| 172 | .IX Header "BUGS" |
| 173 | Since the original \f(CW\*(C`big5\*(C'\fR encoding (1984) is not supported anywhere |
| 174 | (glibc and DOS-based systems uses \f(CW\*(C`big5\*(C'\fR to mean \f(CW\*(C`big5\-eten\*(C'\fR; Microsoft |
| 175 | uses \f(CW\*(C`big5\*(C'\fR to mean \f(CW\*(C`cp950\*(C'\fR), a conscious decision was made to alias |
| 176 | \&\f(CW\*(C`big5\*(C'\fR to \f(CW\*(C`big5\-eten\*(C'\fR, which is the de facto superset of the original |
| 177 | big5. |
| 178 | .PP |
| 179 | The \f(CW\*(C`CNS11643\*(C'\fR encoding files are not complete. For common \f(CW\*(C`CNS11643\*(C'\fR |
| 180 | manipulation, please use \f(CW\*(C`EUC\-TW\*(C'\fR in Encode::HanExtra, which contains |
| 181 | planes 1\-7. |
| 182 | .PP |
| 183 | The \s-1ASCII\s0 region (0x00\-0x7f) is preserved for all encodings, even |
| 184 | though this conflicts with mappings by the Unicode Consortium. See |
| 185 | .PP |
| 186 | <http://www.debian.or.jp/~kubota/unicode\-symbols.html.en> |
| 187 | .PP |
| 188 | to find out why it is implemented that way. |
| 189 | .SH "SEE ALSO" |
| 190 | .IX Header "SEE ALSO" |
| 191 | Encode |