Gecko [ dataharbor.africa ]

Name	Size	Permission
CPAN::Meta.3pm	14.93 KB	-r--r--r--
CPAN::Meta::Converter.3pm	6.34 KB	-r--r--r--
CPAN::Meta::Feature.3pm	4.16 KB	-r--r--r--
CPAN::Meta::History.3pm	7.61 KB	-r--r--r--
CPAN::Meta::Merge.3pm	3.43 KB	-r--r--r--
CPAN::Meta::Prereqs.3pm	6.71 KB	-r--r--r--
CPAN::Meta::Requirements.3pm	13.78 KB	-r--r--r--
CPAN::Meta::Spec.3pm	44.35 KB	-r--r--r--
CPAN::Meta::Validator.3pm	4.06 KB	-r--r--r--
CPAN::Meta::YAML.3pm	5.89 KB	-r--r--r--
Canary::Stability.3pm	5.84 KB	-r--r--r--
Encode.3pm	34.63 KB	-r--r--r--
Encode::Alias.3pm	7.29 KB	-r--r--r--
Encode::CJKConstants.3pm	4.01 KB	-r--r--r--
Encode::CN::HZ.3pm	3.98 KB	-r--r--r--
Encode::Config.3pm	3.98 KB	-r--r--r--
Encode::Encoder.3pm	8.59 KB	-r--r--r--
Encode::Encoding.3pm	11.59 KB	-r--r--r--
Encode::GSM0338.3pm	6.56 KB	-r--r--r--
Encode::Guess.3pm	9.77 KB	-r--r--r--
Encode::JP::H2Z.3pm	3.99 KB	-r--r--r--
Encode::JP::JIS7.3pm	3.99 KB	-r--r--r--
Encode::KR::2022_KR.3pm	4 KB	-r--r--r--
Encode::MIME::Header.3pm	9.78 KB	-r--r--r--
Encode::MIME::Name.3pm	4.04 KB	-r--r--r--
Encode::PerlIO.3pm	10.6 KB	-r--r--r--
Encode::Supported.3pm	39.11 KB	-r--r--r--
Encode::Unicode::UTF7.3pm	5.33 KB	-r--r--r--
Expect.3pm	60.58 KB	-r--r--r--
ExtUtils::Command.3pm	5.8 KB	-r--r--r--
ExtUtils::Command::MM.3pm	5.59 KB	-r--r--r--
ExtUtils::Install.3pm	12.21 KB	-r--r--r--
ExtUtils::Installed.3pm	8.4 KB	-r--r--r--
ExtUtils::Liblist.3pm	12.38 KB	-r--r--r--
ExtUtils::MM.3pm	2.76 KB	-r--r--r--
ExtUtils::MM_AIX.3pm	2.97 KB	-r--r--r--
ExtUtils::MM_Any.3pm	30.64 KB	-r--r--r--
ExtUtils::MM_BeOS.3pm	2.71 KB	-r--r--r--
ExtUtils::MM_Cygwin.3pm	3.39 KB	-r--r--r--
ExtUtils::MM_DOS.3pm	3.01 KB	-r--r--r--
ExtUtils::MM_Darwin.3pm	2.72 KB	-r--r--r--
ExtUtils::MM_MacOS.3pm	2.92 KB	-r--r--r--
ExtUtils::MM_NW5.3pm	3.19 KB	-r--r--r--
ExtUtils::MM_OS2.3pm	2.88 KB	-r--r--r--
ExtUtils::MM_OS390.3pm	2.9 KB	-r--r--r--
ExtUtils::MM_QNX.3pm	2.87 KB	-r--r--r--
ExtUtils::MM_UWIN.3pm	2.98 KB	-r--r--r--
ExtUtils::MM_Unix.3pm	21.34 KB	-r--r--r--
ExtUtils::MM_VMS.3pm	14.75 KB	-r--r--r--
ExtUtils::MM_VOS.3pm	2.86 KB	-r--r--r--
ExtUtils::MM_Win32.3pm	5.94 KB	-r--r--r--
ExtUtils::MM_Win95.3pm	3.2 KB	-r--r--r--
ExtUtils::MY.3pm	2.7 KB	-r--r--r--
ExtUtils::MakeMaker.3pm	80 KB	-r--r--r--
ExtUtils::MakeMaker::Config.3p...	2.53 KB	-r--r--r--
ExtUtils::MakeMaker::FAQ.3pm	26.17 KB	-r--r--r--
ExtUtils::MakeMaker::Locale.3p...	10.91 KB	-r--r--r--
ExtUtils::MakeMaker::Tutorial....	8.25 KB	-r--r--r--
ExtUtils::Manifest.3pm	11.68 KB	-r--r--r--
ExtUtils::Mkbootstrap.3pm	3.37 KB	-r--r--r--
ExtUtils::Mksymlists.3pm	6.54 KB	-r--r--r--
ExtUtils::Packlist.3pm	6.71 KB	-r--r--r--
ExtUtils::testlib.3pm	2.63 KB	-r--r--r--
HTTP::Config.3pm	13.14 KB	-r--r--r--
HTTP::Headers.3pm	22.04 KB	-r--r--r--
HTTP::Headers::Auth.3pm	4.32 KB	-r--r--r--
HTTP::Headers::ETag.3pm	4.32 KB	-r--r--r--
HTTP::Headers::Util.3pm	7.82 KB	-r--r--r--
HTTP::Message.3pm	19.31 KB	-r--r--r--
HTTP::Request.3pm	12.12 KB	-r--r--r--
HTTP::Request::Common.3pm	16.65 KB	-r--r--r--
HTTP::Response.3pm	17.19 KB	-r--r--r--
HTTP::Status.3pm	11.33 KB	-r--r--r--
HTTP::Tiny.3pm	29.44 KB	-r--r--r--
IO::Pty.3pm	10.14 KB	-r--r--r--
IO::Tty.3pm	9.91 KB	-r--r--r--
IO::Tty::Constant.3pm	11.25 KB	-r--r--r--
JSON::PP.3pm	48.9 KB	-r--r--r--
JSON::PP::Boolean.3pm	2.61 KB	-r--r--r--
JSON::Syck.3pm	7.9 KB	-r--r--r--
JSON::XS.3pm	88.67 KB	-r--r--r--
JSON::XS::Boolean.3pm	4.55 KB	-r--r--r--
LWP.3pm	27.74 KB	-r--r--r--
LWP::Authen::Ntlm.3pm	7.28 KB	-r--r--r--
LWP::ConnCache.3pm	10.25 KB	-r--r--r--
LWP::Debug.3pm	5.62 KB	-r--r--r--
LWP::MemberMixin.3pm	4.69 KB	-r--r--r--
LWP::Protocol.3pm	7.87 KB	-r--r--r--
LWP::Protocol::https.3pm	4 KB	-r--r--r--
LWP::RobotUA.3pm	8.14 KB	-r--r--r--
LWP::Simple.3pm	9.17 KB	-r--r--r--
LWP::UserAgent.3pm	47.79 KB	-r--r--r--
Mozilla::CA.3pm	5.25 KB	-r--r--r--
Net::HTTP.3pm	16.18 KB	-r--r--r--
Net::HTTP::Methods.3pm	4.37 KB	-r--r--r--
Net::HTTP::NB.3pm	5.46 KB	-r--r--r--
Net::HTTPS.3pm	5.68 KB	-r--r--r--
POD2::DE::local::lib.3pm	24.23 KB	-r--r--r--
POD2::PT_BR::local::lib.3pm	24.62 KB	-r--r--r--
Parse::CPAN::Meta.3pm	8.75 KB	-r--r--r--
Switch.3pm	20.33 KB	-r--r--r--
Try::Tiny.3pm	20.32 KB	-r--r--r--
Types::Serialiser.3pm	12.97 KB	-r--r--r--
Types::Serialiser::Error.3pm	4.4 KB	-r--r--r--
YAML::Syck.3pm	10.58 KB	-r--r--r--
common::sense.3pm	22.27 KB	-r--r--r--
encoding.3pm	23.24 KB	-r--r--r--
lib::core::only.3pm	7.28 KB	-r--r--r--
libwww::lwpcook.3pm	14.46 KB	-r--r--r--
libwww::lwptut.3pm	31.12 KB	-r--r--r--
local::lib.3pm	32.78 KB	-r--r--r--
version.3pm	13.61 KB	-r--r--r--
version::Internals.3pm	29.58 KB	-r--r--r--

Code Editor : Encode::Guess.3pm

.\" Automatically generated by Pod::Man 2.27 (Pod::Simple 3.28)
.\"
.\" Standard preamble:
.\" ========================================================================
.de Sp \" Vertical space (when we can't use .PP)
.if t .sp .5v
.if n .sp
..
.de Vb \" Begin verbatim text
.ft CW
.nf
.ne \\$1
..
.de Ve \" End verbatim text
.ft R
.fi
..
.\" Set up some character translations and predefined strings.  \*(-- will
.\" give an unbreakable dash, \*(PI will give pi, \*(L" will give a left
.\" double quote, and \*(R" will give a right double quote.  \*(C+ will
.\" give a nicer C++.  Capital omega is used to do unbreakable dashes and
.\" therefore won't be available.  \*(C` and \*(C' expand to `' in nroff,
.\" nothing in troff, for use with C<>.
.tr \(*W-
.ds C+ C\v'-.1v'\h'-1p'\s-2+\h'-1p'+\s0\v'.1v'\h'-1p'
.ie n \{\
.    ds -- \(*W-
.    ds PI pi
.    if (\n(.H=4u)&(1m=24u) .ds -- \(*W\h'-12u'\(*W\h'-12u'-\" diablo 10 pitch
.    if (\n(.H=4u)&(1m=20u) .ds -- \(*W\h'-12u'\(*W\h'-8u'-\"  diablo 12 pitch
.    ds L" ""
.    ds R" ""
.    ds C` ""
.    ds C' ""
'br\}
.el\{\
.    ds -- \|\(em\|
.    ds PI \(*p
.    ds L" ``
.    ds R" ''
.    ds C`
.    ds C'
'br\}
.\"
.\" Escape single quotes in literal strings from groff's Unicode transform.
.ie \n(.g .ds Aq \(aq
.el       .ds Aq '
.\"
.\" If the F register is turned on, we'll generate index entries on stderr for
.\" titles (.TH), headers (.SH), subsections (.SS), items (.Ip), and index
.\" entries marked with X<> in POD.  Of course, you'll have to process the
.\" output yourself in some meaningful fashion.
.\"
.\" Avoid warning from groff about undefined register 'F'.
.de IX
..
.nr rF 0
.if \n(.g .if rF .nr rF 1
.if (\n(rF:(\n(.g==0)) \{
.    if \nF \{
.        de IX
.        tm Index:\\$1\t\\n%\t"\\$2"
..
.        if !\nF==2 \{
.            nr % 0
.            nr F 2
.        \}
.    \}
.\}
.rr rF
.\"
.\" Accent mark definitions (@(#)ms.acc 1.5 88/02/08 SMI; from UCB 4.2).
.\" Fear.  Run.  Save yourself.  No user-serviceable parts.
.    \" fudge factors for nroff and troff
.if n \{\
.    ds #H 0
.    ds #V .8m
.    ds #F .3m
.    ds #[ \f1
.    ds #] \fP
.\}
.if t \{\
.    ds #H ((1u-(\\\\n(.fu%2u))*.13m)
.    ds #V .6m
.    ds #F 0
.    ds #[ \&
.    ds #] \&
.\}
.    \" simple accents for nroff and troff
.if n \{\
.    ds ' \&
.    ds ` \&
.    ds ^ \&
.    ds , \&
.    ds ~ ~
.    ds /
.\}
.if t \{\
.    ds ' \\k:\h'-(\\n(.wu*8/10-\*(#H)'\'\h"|\\n:u"
.    ds ` \\k:\h'-(\\n(.wu*8/10-\*(#H)'\`\h'|\\n:u'
.    ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'^\h'|\\n:u'
.    ds , \\k:\h'-(\\n(.wu*8/10)',\h'|\\n:u'
.    ds ~ \\k:\h'-(\\n(.wu-\*(#H-.1m)'~\h'|\\n:u'
.    ds / \\k:\h'-(\\n(.wu*8/10-\*(#H)'\z\(sl\h'|\\n:u'
.\}
.    \" troff and (daisy-wheel) nroff accents
.ds : \\k:\h'-(\\n(.wu*8/10-\*(#H+.1m+\*(#F)'\v'-\*(#V'\z.\h'.2m+\*(#F'.\h'|\\n:u'\v'\*(#V'
.ds 8 \h'\*(#H'\(*b\h'-\*(#H'
.ds o \\k:\h'-(\\n(.wu+\w'\(de'u-\*(#H)/2u'\v'-.3n'\*(#[\z\(de\v'.3n'\h'|\\n:u'\*(#]
.ds d- \h'\*(#H'\(pd\h'-\w'~'u'\v'-.25m'\f2\(hy\fP\v'.25m'\h'-\*(#H'
.ds D- D\\k:\h'-\w'D'u'\v'-.11m'\z\(hy\v'.11m'\h'|\\n:u'
.ds th \*(#[\v'.3m'\s+1I\s-1\v'-.3m'\h'-(\w'I'u*2/3)'\s-1o\s+1\*(#]
.ds Th \*(#[\s+2I\s-2\h'-\w'I'u*3/5'\v'-.3m'o\v'.3m'\*(#]
.ds ae a\h'-(\w'a'u*4/10)'e
.ds Ae A\h'-(\w'A'u*4/10)'E
.    \" corrections for vroff
.if v .ds ~ \\k:\h'-(\\n(.wu*9/10-\*(#H)'\s-2\u~\d\s+2\h'|\\n:u'
.if v .ds ^ \\k:\h'-(\\n(.wu*10/11-\*(#H)'\v'-.4m'^\v'.4m'\h'|\\n:u'
.    \" for low resolution devices (crt and lpr)
.if \n(.H>23 .if \n(.V>19 \
\{\
.    ds : e
.    ds 8 ss
.    ds o a
.    ds d- d\h'-1'\(ga
.    ds D- D\h'-1'\(hy
.    ds th \o'bp'
.    ds Th \o'LP'
.    ds ae ae
.    ds Ae AE
.\}
.rm #[ #] #H #V #F C
.\" ========================================================================
.\"
.IX Title "Encode::Guess 3"
.TH Encode::Guess 3 "2020-07-25" "perl v5.16.3" "User Contributed Perl Documentation"
.\" For nroff, turn off justification.  Always turn off hyphenation; it makes
.\" way too many mistakes in technical documents.
.if n .ad l
.nh
.SH "NAME"
Encode::Guess \-\- Guesses encoding from data
.SH "SYNOPSIS"
.IX Header "SYNOPSIS"
.Vb 1
\&  # if you are sure $data won\*(Aqt contain anything bogus
\&
\&  use Encode;
\&  use Encode::Guess qw/euc\-jp shiftjis 7bit\-jis/;
\&  my $utf8 = decode("Guess", $data);
\&  my $data = encode("Guess", $utf8);   # this doesn\*(Aqt work!
\&
\&  # more elaborate way
\&  use Encode::Guess;
\&  my $enc = guess_encoding($data, qw/euc\-jp shiftjis 7bit\-jis/);
\&  ref($enc) or die "Can\*(Aqt guess: $enc"; # trap error this way
\&  $utf8 = $enc\->decode($data);
\&  # or
\&  $utf8 = decode($enc\->name, $data)
.Ve
.SH "ABSTRACT"
.IX Header "ABSTRACT"
Encode::Guess enables you to guess in what encoding a given data is
encoded, or at least tries to.
.SH "DESCRIPTION"
.IX Header "DESCRIPTION"
By default, it checks only ascii, utf8 and \s-1UTF\-16/32\s0 with \s-1BOM.\s0
.PP
.Vb 1
\&  use Encode::Guess; # ascii/utf8/BOMed UTF
.Ve
.PP
To use it more practically, you have to give the names of encodings to
check (\fIsuspects\fR as follows).  The name of suspects can either be
canonical names or aliases.
.PP
\&\s-1CAVEAT:\s0 Unlike \s-1UTF\-\s0(16|32), \s-1BOM\s0 in utf8 is \s-1NOT AUTOMATICALLY STRIPPED.\s0
.PP
.Vb 2
\& # tries all major Japanese Encodings as well
\&  use Encode::Guess qw/euc\-jp shiftjis 7bit\-jis/;
.Ve
.PP
If the \f(CW$Encode::Guess::NoUTFAutoGuess\fR variable is set to a true
value, no heuristics will be applied to \s-1UTF8/16/32,\s0 and the result
will be limited to the suspects and \f(CW\*(C`ascii\*(C'\fR.
.IP "Encode::Guess\->set_suspects" 4
.IX Item "Encode::Guess->set_suspects"
You can also change the internal suspects list via \f(CW\*(C`set_suspects\*(C'\fR
method.
.Sp
.Vb 2
\&  use Encode::Guess;
\&  Encode::Guess\->set_suspects(qw/euc\-jp shiftjis 7bit\-jis/);
.Ve
.IP "Encode::Guess\->add_suspects" 4
.IX Item "Encode::Guess->add_suspects"
Or you can use \f(CW\*(C`add_suspects\*(C'\fR method.  The difference is that
\&\f(CW\*(C`set_suspects\*(C'\fR flushes the current suspects list while
\&\f(CW\*(C`add_suspects\*(C'\fR adds.
.Sp
.Vb 5
\&  use Encode::Guess;
\&  Encode::Guess\->add_suspects(qw/euc\-jp shiftjis 7bit\-jis/);
\&  # now the suspects are euc\-jp,shiftjis,7bit\-jis, AND
\&  # euc\-kr,euc\-cn, and big5\-eten
\&  Encode::Guess\->add_suspects(qw/euc\-kr euc\-cn big5\-eten/);
.Ve
.ie n .IP "Encode::decode(""Guess"" ...)" 4
.el .IP "Encode::decode(``Guess'' ...)" 4
.IX Item "Encode::decode(Guess ...)"
When you are content with suspects list, you can now
.Sp
.Vb 1
\&  my $utf8 = Encode::decode("Guess", $data);
.Ve
.IP "Encode::Guess\->guess($data)" 4
.IX Item "Encode::Guess->guess($data)"
But it will croak if:
.RS 4
.IP "\(bu" 4
Two or more suspects remain
.IP "\(bu" 4
No suspects left
.RE
.RS 4
.Sp
So you should instead try this;
.Sp
.Vb 1
\&  my $decoder = Encode::Guess\->guess($data);
.Ve
.Sp
On success, \f(CW$decoder\fR is an object that is documented in
Encode::Encoding.  So you can now do this;
.Sp
.Vb 1
\&  my $utf8 = $decoder\->decode($data);
.Ve
.Sp
On failure, \f(CW$decoder\fR now contains an error message so the whole thing
would be as follows;
.Sp
.Vb 3
\&  my $decoder = Encode::Guess\->guess($data);
\&  die $decoder unless ref($decoder);
\&  my $utf8 = $decoder\->decode($data);
.Ve
.RE
.IP "guess_encoding($data, [, \fIlist of suspects\fR])" 4
.IX Item "guess_encoding($data, [, list of suspects])"
You can also try \f(CW\*(C`guess_encoding\*(C'\fR function which is exported by
default.  It takes \f(CW$data\fR to check and it also takes the list of
suspects by option.  The optional suspect list is \fInot reflected\fR to
the internal suspects list.
.Sp
.Vb 5
\&  my $decoder = guess_encoding($data, qw/euc\-jp euc\-kr euc\-cn/);
\&  die $decoder unless ref($decoder);
\&  my $utf8 = $decoder\->decode($data);
\&  # check only ascii, utf8 and UTF\-(16|32) with BOM
\&  my $decoder = guess_encoding($data);
.Ve
.SH "CAVEATS"
.IX Header "CAVEATS"
.IP "\(bu" 4
Because of the algorithm used, \s-1ISO\-8859\s0 series and other single-byte
encodings do not work well unless either one of \s-1ISO\-8859\s0 is the only
one suspect (besides ascii and utf8).
.Sp
.Vb 5
\&  use Encode::Guess;
\&  # perhaps ok
\&  my $decoder = guess_encoding($data, \*(Aqlatin1\*(Aq);
\&  # definitely NOT ok
\&  my $decoder = guess_encoding($data, qw/latin1 greek/);
.Ve
.Sp
The reason is that Encode::Guess guesses encoding by trial and error.
It first splits \f(CW$data\fR into lines and tries to decode the line for each
suspect.  It keeps it going until all but one encoding is eliminated
out of suspects list.  \s-1ISO\-8859\s0 series is just too successful for most
cases (because it fills almost all code points in \ex00\-\exff).
.IP "\(bu" 4
Do not mix national standard encodings and the corresponding vendor
encodings.
.Sp
.Vb 3
\&  # a very bad idea
\&  my $decoder
\&     = guess_encoding($data, qw/shiftjis MacJapanese cp932/);
.Ve
.Sp
The reason is that vendor encoding is usually a superset of national
standard so it becomes too ambiguous for most cases.
.IP "\(bu" 4
On the other hand, mixing various national standard encodings
automagically works unless \f(CW$data\fR is too short to allow for guessing.
.Sp
.Vb 6
\& # This is ok if $data is long enough
\& my $decoder =  
\&  guess_encoding($data, qw/euc\-cn
\&                           euc\-jp shiftjis 7bit\-jis
\&                           euc\-kr
\&                           big5\-eten/);
.Ve
.IP "\(bu" 4
\&\s-1DO NOT PUT TOO MANY SUSPECTS\s0!  Don't you try something like this!
.Sp
.Vb 2
\&  my $decoder = guess_encoding($data, 
\&                               Encode\->encodings(":all"));
.Ve
.PP
It is, after all, just a guess.  You should alway be explicit when it
comes to encodings.  But there are some, especially Japanese,
environment that guess-coding is a must.  Use this module with care.
.SH "TO DO"
.IX Header "TO DO"
Encode::Guess does not work on \s-1EBCDIC\s0 platforms.
.SH "SEE ALSO"
.IX Header "SEE ALSO"
Encode, Encode::Encoding

${this.title}

Code Editor : Encode::Guess.3pm