| 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 "Encode::Guess 3" |
| 132 | .TH Encode::Guess 3 "2002-06-01" "perl v5.8.0" "Perl Programmers Reference Guide" |
| 133 | .SH "NAME" |
| 134 | Encode::Guess \-\- Guesses encoding from data |
| 135 | .SH "SYNOPSIS" |
| 136 | .IX Header "SYNOPSIS" |
| 137 | .Vb 1 |
| 138 | \& # if you are sure $data won't contain anything bogus |
| 139 | .Ve |
| 140 | .PP |
| 141 | .Vb 4 |
| 142 | \& use Encode; |
| 143 | \& use Encode::Guess qw/euc-jp shiftjis 7bit-jis/; |
| 144 | \& my $utf8 = decode("Guess", $data); |
| 145 | \& my $data = encode("Guess", $utf8); # this doesn't work! |
| 146 | .Ve |
| 147 | .PP |
| 148 | .Vb 7 |
| 149 | \& # more elaborate way |
| 150 | \& use Encode::Guess, |
| 151 | \& my $enc = guess_encoding($data, qw/euc-jp shiftjis 7bit-jis/); |
| 152 | \& ref($enc) or die "Can't guess: $enc"; # trap error this way |
| 153 | \& $utf8 = $enc->decode($data); |
| 154 | \& # or |
| 155 | \& $utf8 = decode($enc->name, $data) |
| 156 | .Ve |
| 157 | .SH "ABSTRACT" |
| 158 | .IX Header "ABSTRACT" |
| 159 | Encode::Guess enables you to guess in what encoding a given data is |
| 160 | encoded, or at least tries to. |
| 161 | .SH "DESCRIPTION" |
| 162 | .IX Header "DESCRIPTION" |
| 163 | By default, it checks only ascii, utf8 and \s-1UTF\-16/32\s0 with \s-1BOM\s0. |
| 164 | .PP |
| 165 | .Vb 1 |
| 166 | \& use Encode::Guess; # ascii/utf8/BOMed UTF |
| 167 | .Ve |
| 168 | .PP |
| 169 | To use it more practically, you have to give the names of encodings to |
| 170 | check (\fIsuspects\fR as follows). The name of suspects can either be |
| 171 | canonical names or aliases. |
| 172 | .PP |
| 173 | .Vb 2 |
| 174 | \& # tries all major Japanese Encodings as well |
| 175 | \& use Encode::Guess qw/euc-jp shiftjis 7bit-jis/; |
| 176 | .Ve |
| 177 | .IP "Encode::Guess\->set_suspects" 4 |
| 178 | .IX Item "Encode::Guess->set_suspects" |
| 179 | You can also change the internal suspects list via \f(CW\*(C`set_suspects\*(C'\fR |
| 180 | method. |
| 181 | .Sp |
| 182 | .Vb 2 |
| 183 | \& use Encode::Guess; |
| 184 | \& Encode::Guess->set_suspects(qw/euc-jp shiftjis 7bit-jis/); |
| 185 | .Ve |
| 186 | .IP "Encode::Guess\->add_suspects" 4 |
| 187 | .IX Item "Encode::Guess->add_suspects" |
| 188 | Or you can use \f(CW\*(C`add_suspects\*(C'\fR method. The difference is that |
| 189 | \&\f(CW\*(C`set_suspects\*(C'\fR flushes the current suspects list while |
| 190 | \&\f(CW\*(C`add_suspects\*(C'\fR adds. |
| 191 | .Sp |
| 192 | .Vb 5 |
| 193 | \& use Encode::Guess; |
| 194 | \& Encode::Guess->add_suspects(qw/euc-jp shiftjis 7bit-jis/); |
| 195 | \& # now the suspects are euc-jp,shiftjis,7bit-jis, AND |
| 196 | \& # euc-kr,euc-cn, and big5-eten |
| 197 | \& Encode::Guess->add_suspects(qw/euc-kr euc-cn big5-eten/); |
| 198 | .Ve |
| 199 | .ie n .IP "Encode::decode(""Guess"" ...)" 4 |
| 200 | .el .IP "Encode::decode(``Guess'' ...)" 4 |
| 201 | .IX Item "Encode::decode(Guess ...)" |
| 202 | When you are content with suspects list, you can now |
| 203 | .Sp |
| 204 | .Vb 1 |
| 205 | \& my $utf8 = Encode::decode("Guess", $data); |
| 206 | .Ve |
| 207 | .IP "Encode::Guess\->guess($data)" 4 |
| 208 | .IX Item "Encode::Guess->guess($data)" |
| 209 | But it will croak if Encode::Guess fails to eliminate all other |
| 210 | suspects but the right one or no suspect was good. So you should |
| 211 | instead try this; |
| 212 | .Sp |
| 213 | .Vb 1 |
| 214 | \& my $decoder = Encode::Guess->guess($data); |
| 215 | .Ve |
| 216 | .Sp |
| 217 | On success, \f(CW$decoder\fR is an object that is documented in |
| 218 | Encode::Encoding. So you can now do this; |
| 219 | .Sp |
| 220 | .Vb 1 |
| 221 | \& my $utf8 = $decoder->decode($data); |
| 222 | .Ve |
| 223 | .Sp |
| 224 | On failure, \f(CW$decoder\fR now contains an error message so the whole thing |
| 225 | would be as follows; |
| 226 | .Sp |
| 227 | .Vb 3 |
| 228 | \& my $decoder = Encode::Guess->guess($data); |
| 229 | \& die $decoder unless ref($decoder); |
| 230 | \& my $utf8 = $decoder->decode($data); |
| 231 | .Ve |
| 232 | .IP "guess_encoding($data, [, \fIlist of suspects\fR])" 4 |
| 233 | .IX Item "guess_encoding($data, [, list of suspects])" |
| 234 | You can also try \f(CW\*(C`guess_encoding\*(C'\fR function which is exported by |
| 235 | default. It takes \f(CW$data\fR to check and it also takes the list of |
| 236 | suspects by option. The optional suspect list is \fInot reflected\fR to |
| 237 | the internal suspects list. |
| 238 | .Sp |
| 239 | .Vb 5 |
| 240 | \& my $decoder = guess_encoding($data, qw/euc-jp euc-kr euc-cn/); |
| 241 | \& die $decoder unless ref($decoder); |
| 242 | \& my $utf8 = $decoder->decode($data); |
| 243 | \& # check only ascii and utf8 |
| 244 | \& my $decoder = guess_encoding($data); |
| 245 | .Ve |
| 246 | .SH "CAVEATS" |
| 247 | .IX Header "CAVEATS" |
| 248 | .IP "\(bu" 4 |
| 249 | Because of the algorithm used, \s-1ISO\-8859\s0 series and other single-byte |
| 250 | encodings do not work well unless either one of \s-1ISO\-8859\s0 is the only |
| 251 | one suspect (besides ascii and utf8). |
| 252 | .Sp |
| 253 | .Vb 5 |
| 254 | \& use Encode::Guess; |
| 255 | \& # perhaps ok |
| 256 | \& my $decoder = guess_encoding($data, 'latin1'); |
| 257 | \& # definitely NOT ok |
| 258 | \& my $decoder = guess_encoding($data, qw/latin1 greek/); |
| 259 | .Ve |
| 260 | .Sp |
| 261 | The reason is that Encode::Guess guesses encoding by trial and error. |
| 262 | It first splits \f(CW$data\fR into lines and tries to decode the line for each |
| 263 | suspect. It keeps it going until all but one encoding was eliminated |
| 264 | out of suspects list. \s-1ISO\-8859\s0 series is just too successful for most |
| 265 | cases (because it fills almost all code points in \ex00\-\exff). |
| 266 | .IP "\(bu" 4 |
| 267 | Do not mix national standard encodings and the corresponding vendor |
| 268 | encodings. |
| 269 | .Sp |
| 270 | .Vb 3 |
| 271 | \& # a very bad idea |
| 272 | \& my $decoder |
| 273 | \& = guess_encoding($data, qw/shiftjis MacJapanese cp932/); |
| 274 | .Ve |
| 275 | .Sp |
| 276 | The reason is that vendor encoding is usually a superset of national |
| 277 | standard so it becomes too ambiguous for most cases. |
| 278 | .IP "\(bu" 4 |
| 279 | On the other hand, mixing various national standard encodings |
| 280 | automagically works unless \f(CW$data\fR is too short to allow for guessing. |
| 281 | .Sp |
| 282 | .Vb 6 |
| 283 | \& # This is ok if $data is long enough |
| 284 | \& my $decoder = |
| 285 | \& guess_encoding($data, qw/euc-cn |
| 286 | \& euc-jp shiftjis 7bit-jis |
| 287 | \& euc-kr |
| 288 | \& big5-eten/); |
| 289 | .Ve |
| 290 | .IP "\(bu" 4 |
| 291 | \&\s-1DO\s0 \s-1NOT\s0 \s-1PUT\s0 \s-1TOO\s0 \s-1MANY\s0 \s-1SUSPECTS\s0! Don't you try something like this! |
| 292 | .Sp |
| 293 | .Vb 2 |
| 294 | \& my $decoder = guess_encoding($data, |
| 295 | \& Encode->encodings(":all")); |
| 296 | .Ve |
| 297 | .PP |
| 298 | It is, after all, just a guess. You should alway be explicit when it |
| 299 | comes to encodings. But there are some, especially Japanese, |
| 300 | environment that guess-coding is a must. Use this module with care. |
| 301 | .SH "TO DO" |
| 302 | .IX Header "TO DO" |
| 303 | Encode::Guess does not work on \s-1EBCDIC\s0 platforms. |
| 304 | .SH "SEE ALSO" |
| 305 | .IX Header "SEE ALSO" |
| 306 | Encode, Encode::Encoding |