| 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::Guess 3perl" |
| 58 |
.TH Encode::Guess 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::Guess \-\- Guesses encoding from data |
| 65 |
.SH SYNOPSIS |
| 66 |
.IX Header "SYNOPSIS" |
| 67 |
.Vb 1 |
| 68 |
\& # if you are sure $data won\*(Aqt contain anything bogus |
| 69 |
\& |
| 70 |
\& use Encode; |
| 71 |
\& use Encode::Guess qw/euc\-jp shiftjis 7bit\-jis/; |
| 72 |
\& my $utf8 = decode("Guess", $data); |
| 73 |
\& my $data = encode("Guess", $utf8); # this doesn\*(Aqt work! |
| 74 |
\& |
| 75 |
\& # more elaborate way |
| 76 |
\& use Encode::Guess; |
| 77 |
\& my $enc = guess_encoding($data, qw/euc\-jp shiftjis 7bit\-jis/); |
| 78 |
\& ref($enc) or die "Can\*(Aqt guess: $enc"; # trap error this way |
| 79 |
\& $utf8 = $enc\->decode($data); |
| 80 |
\& # or |
| 81 |
\& $utf8 = decode($enc\->name, $data) |
| 82 |
.Ve |
| 83 |
.SH ABSTRACT |
| 84 |
.IX Header "ABSTRACT" |
| 85 |
Encode::Guess enables you to guess in what encoding a given data is |
| 86 |
encoded, or at least tries to. |
| 87 |
.SH DESCRIPTION |
| 88 |
.IX Header "DESCRIPTION" |
| 89 |
By default, it checks only ascii, utf8 and UTF\-16/32 with BOM. |
| 90 |
.PP |
| 91 |
.Vb 1 |
| 92 |
\& use Encode::Guess; # ascii/utf8/BOMed UTF |
| 93 |
.Ve |
| 94 |
.PP |
| 95 |
To use it more practically, you have to give the names of encodings to |
| 96 |
check (\fIsuspects\fR as follows). The name of suspects can either be |
| 97 |
canonical names or aliases. |
| 98 |
.PP |
| 99 |
CAVEAT: Unlike UTF\-(16|32), BOM in utf8 is NOT AUTOMATICALLY STRIPPED. |
| 100 |
.PP |
| 101 |
.Vb 2 |
| 102 |
\& # tries all major Japanese Encodings as well |
| 103 |
\& use Encode::Guess qw/euc\-jp shiftjis 7bit\-jis/; |
| 104 |
.Ve |
| 105 |
.PP |
| 106 |
If the \f(CW$Encode::Guess::NoUTFAutoGuess\fR variable is set to a true |
| 107 |
value, no heuristics will be applied to UTF8/16/32, and the result |
| 108 |
will be limited to the suspects and \f(CW\*(C`ascii\*(C'\fR. |
| 109 |
.IP Encode::Guess\->set_suspects 4 |
| 110 |
.IX Item "Encode::Guess->set_suspects" |
| 111 |
You can also change the internal suspects list via \f(CW\*(C`set_suspects\*(C'\fR |
| 112 |
method. |
| 113 |
.Sp |
| 114 |
.Vb 2 |
| 115 |
\& use Encode::Guess; |
| 116 |
\& Encode::Guess\->set_suspects(qw/euc\-jp shiftjis 7bit\-jis/); |
| 117 |
.Ve |
| 118 |
.IP Encode::Guess\->add_suspects 4 |
| 119 |
.IX Item "Encode::Guess->add_suspects" |
| 120 |
Or you can use \f(CW\*(C`add_suspects\*(C'\fR method. The difference is that |
| 121 |
\&\f(CW\*(C`set_suspects\*(C'\fR flushes the current suspects list while |
| 122 |
\&\f(CW\*(C`add_suspects\*(C'\fR adds. |
| 123 |
.Sp |
| 124 |
.Vb 5 |
| 125 |
\& use Encode::Guess; |
| 126 |
\& Encode::Guess\->add_suspects(qw/euc\-jp shiftjis 7bit\-jis/); |
| 127 |
\& # now the suspects are euc\-jp,shiftjis,7bit\-jis, AND |
| 128 |
\& # euc\-kr,euc\-cn, and big5\-eten |
| 129 |
\& Encode::Guess\->add_suspects(qw/euc\-kr euc\-cn big5\-eten/); |
| 130 |
.Ve |
| 131 |
.IP "Encode::decode(""Guess"" ...)" 4 |
| 132 |
.IX Item "Encode::decode(""Guess"" ...)" |
| 133 |
When you are content with suspects list, you can now |
| 134 |
.Sp |
| 135 |
.Vb 1 |
| 136 |
\& my $utf8 = Encode::decode("Guess", $data); |
| 137 |
.Ve |
| 138 |
.IP Encode::Guess\->guess($data) 4 |
| 139 |
.IX Item "Encode::Guess->guess($data)" |
| 140 |
But it will croak if: |
| 141 |
.RS 4 |
| 142 |
.IP \(bu 4 |
| 143 |
Two or more suspects remain |
| 144 |
.IP \(bu 4 |
| 145 |
No suspects left |
| 146 |
.RE |
| 147 |
.RS 4 |
| 148 |
.Sp |
| 149 |
So you should instead try this; |
| 150 |
.Sp |
| 151 |
.Vb 1 |
| 152 |
\& my $decoder = Encode::Guess\->guess($data); |
| 153 |
.Ve |
| 154 |
.Sp |
| 155 |
On success, \f(CW$decoder\fR is an object that is documented in |
| 156 |
Encode::Encoding. So you can now do this; |
| 157 |
.Sp |
| 158 |
.Vb 1 |
| 159 |
\& my $utf8 = $decoder\->decode($data); |
| 160 |
.Ve |
| 161 |
.Sp |
| 162 |
On failure, \f(CW$decoder\fR now contains an error message so the whole thing |
| 163 |
would be as follows; |
| 164 |
.Sp |
| 165 |
.Vb 3 |
| 166 |
\& my $decoder = Encode::Guess\->guess($data); |
| 167 |
\& die $decoder unless ref($decoder); |
| 168 |
\& my $utf8 = $decoder\->decode($data); |
| 169 |
.Ve |
| 170 |
.RE |
| 171 |
.IP "guess_encoding($data, [, \fIlist of suspects\fR])" 4 |
| 172 |
.IX Item "guess_encoding($data, [, list of suspects])" |
| 173 |
You can also try \f(CW\*(C`guess_encoding\*(C'\fR function which is exported by |
| 174 |
default. It takes \f(CW$data\fR to check and it also takes the list of |
| 175 |
suspects by option. The optional suspect list is \fInot reflected\fR to |
| 176 |
the internal suspects list. |
| 177 |
.Sp |
| 178 |
.Vb 5 |
| 179 |
\& my $decoder = guess_encoding($data, qw/euc\-jp euc\-kr euc\-cn/); |
| 180 |
\& die $decoder unless ref($decoder); |
| 181 |
\& my $utf8 = $decoder\->decode($data); |
| 182 |
\& # check only ascii, utf8 and UTF\-(16|32) with BOM |
| 183 |
\& my $decoder = guess_encoding($data); |
| 184 |
.Ve |
| 185 |
.SH CAVEATS |
| 186 |
.IX Header "CAVEATS" |
| 187 |
.IP \(bu 4 |
| 188 |
Because of the algorithm used, ISO\-8859 series and other single-byte |
| 189 |
encodings do not work well unless either one of ISO\-8859 is the only |
| 190 |
one suspect (besides ascii and utf8). |
| 191 |
.Sp |
| 192 |
.Vb 5 |
| 193 |
\& use Encode::Guess; |
| 194 |
\& # perhaps ok |
| 195 |
\& my $decoder = guess_encoding($data, \*(Aqlatin1\*(Aq); |
| 196 |
\& # definitely NOT ok |
| 197 |
\& my $decoder = guess_encoding($data, qw/latin1 greek/); |
| 198 |
.Ve |
| 199 |
.Sp |
| 200 |
The reason is that Encode::Guess guesses encoding by trial and error. |
| 201 |
It first splits \f(CW$data\fR into lines and tries to decode the line for each |
| 202 |
suspect. It keeps it going until all but one encoding is eliminated |
| 203 |
out of suspects list. ISO\-8859 series is just too successful for most |
| 204 |
cases (because it fills almost all code points in \ex00\-\exff). |
| 205 |
.IP \(bu 4 |
| 206 |
Do not mix national standard encodings and the corresponding vendor |
| 207 |
encodings. |
| 208 |
.Sp |
| 209 |
.Vb 3 |
| 210 |
\& # a very bad idea |
| 211 |
\& my $decoder |
| 212 |
\& = guess_encoding($data, qw/shiftjis MacJapanese cp932/); |
| 213 |
.Ve |
| 214 |
.Sp |
| 215 |
The reason is that vendor encoding is usually a superset of national |
| 216 |
standard so it becomes too ambiguous for most cases. |
| 217 |
.IP \(bu 4 |
| 218 |
On the other hand, mixing various national standard encodings |
| 219 |
automagically works unless \f(CW$data\fR is too short to allow for guessing. |
| 220 |
.Sp |
| 221 |
.Vb 6 |
| 222 |
\& # This is ok if $data is long enough |
| 223 |
\& my $decoder = |
| 224 |
\& guess_encoding($data, qw/euc\-cn |
| 225 |
\& euc\-jp shiftjis 7bit\-jis |
| 226 |
\& euc\-kr |
| 227 |
\& big5\-eten/); |
| 228 |
.Ve |
| 229 |
.IP \(bu 4 |
| 230 |
DO NOT PUT TOO MANY SUSPECTS! Don't you try something like this! |
| 231 |
.Sp |
| 232 |
.Vb 2 |
| 233 |
\& my $decoder = guess_encoding($data, |
| 234 |
\& Encode\->encodings(":all")); |
| 235 |
.Ve |
| 236 |
.PP |
| 237 |
It is, after all, just a guess. You should alway be explicit when it |
| 238 |
comes to encodings. But there are some, especially Japanese, |
| 239 |
environment that guess-coding is a must. Use this module with care. |
| 240 |
.SH "TO DO" |
| 241 |
.IX Header "TO DO" |
| 242 |
Encode::Guess does not work on EBCDIC platforms. |
| 243 |
.SH "SEE ALSO" |
| 244 |
.IX Header "SEE ALSO" |
| 245 |
Encode, Encode::Encoding |