#!/home/grinnz/projects/perldoc-browser/perls/5.8.2/bin/perl eval 'exec /home/grinnz/projects/perldoc-browser/perls/5.8.2/bin/perl -S $0 ${1+"$@"}' if $running_under_some_shell; #!./perl # $Id: piconv,v 1.27 2003/06/18 09:29:02 dankogai Exp $ # use 5.8.0; use strict; use Encode ; use Encode::Alias; my %Scheme = map {$_ => 1} qw(from_to decode_encode perlio); use File::Basename; my $name = basename($0); use Getopt::Long; my %Opt; help() unless GetOptions(\%Opt, 'from|f=s', 'to|t=s', 'list|l', 'string|s=s', 'check|C=i', 'c', 'perlqq|p', 'debug|D', 'scheme|S=s', 'resolve|r=s', 'help', ); $Opt{help} and help(); $Opt{list} and list_encodings(); my $locale = $ENV{LC_CTYPE} || $ENV{LC_ALL} || $ENV{LANG}; defined $Opt{resolve} and resolve_encoding($Opt{resolve}); $Opt{from} || $Opt{to} || help(); my $from = $Opt{from} || $locale or help("from_encoding unspecified"); my $to = $Opt{to} || $locale or help("to_encoding unspecified"); $Opt{string} and Encode::from_to($Opt{string}, $from, $to) and print $Opt{string} and exit; my $scheme = exists $Scheme{$Opt{Scheme}} ? $Opt{Scheme} : 'from_to'; $Opt{check} ||= $Opt{c}; $Opt{perlqq} and $Opt{check} = Encode::FB_PERLQQ; if ($Opt{debug}){ my $cfrom = Encode->getEncoding($from)->name; my $cto = Encode->getEncoding($to)->name; print <<"EOT"; Scheme: $scheme From: $from => $cfrom To: $to => $cto EOT } # default if ($scheme eq 'from_to'){ while(<>){ Encode::from_to($_, $from, $to, $Opt{check}); print; }; # step-by-step }elsif ($scheme eq 'decode_encode'){ while(<>){ my $decoded = decode($from, $_, $Opt{check}); my $encoded = encode($to, $decoded); print $encoded; }; # NI-S favorite }elsif ($scheme eq 'perlio'){ binmode(STDIN, ":encoding($from)"); binmode(STDOUT, ":encoding($to)"); while(<>){ print; } } else { # won't reach die "$name: unknown scheme: $scheme"; } sub list_encodings{ print join("\n", Encode->encodings(":all")), "\n"; exit 0; } sub resolve_encoding { if (my $alias = Encode::resolve_alias($_[0])) { print $alias, "\n"; exit 0; } else { warn "$name: $_[0] is not known to Encode\n"; exit 1; } } sub help{ my $message = shift; $message and print STDERR "$name error: $message\n"; print STDERR <<"EOT"; $name [-f from_encoding] [-t to_encoding] [-s string] [files...] $name -l $name -r encoding_alias -l,--list lists all available encodings -r,--resolve encoding_alias resolve encoding to its (Encode) canonical name -f,--from from_encoding when omitted, the current locale will be used -t,--to to_encoding when omitted, the current locale will be used -s,--string string "string" will be the input instead of STDIN or files The following are mainly of interest to Encode hackers: -D,--debug show debug information -C N | -c | -p check the validity of the input -S,--scheme scheme use the scheme for conversion EOT exit; } __END__ =head1 NAME piconv -- iconv(1), reinvented in perl =head1 SYNOPSIS piconv [-f from_encoding] [-t to_encoding] [-s string] [files...] piconv -l piconv [-C N|-c|-p] piconv -S scheme ... piconv -r encoding piconv -D ... piconv -h =head1 DESCRIPTION B is perl version of B, a character encoding converter widely available for various Unixen today. This script was primarily a technology demonstrator for Perl 5.8.0, but you can use piconv in the place of iconv for virtually any case. piconv converts the character encoding of either STDIN or files specified in the argument and prints out to STDOUT. Here is the list of options. Each option can be in short format (-f) or long (--from). =over 4 =item -f,--from from_encoding Specifies the encoding you are converting from. Unlike B, this option can be omitted. In such cases, the current locale is used. =item -t,--to to_encoding Specifies the encoding you are converting to. Unlike B, this option can be omitted. In such cases, the current locale is used. Therefore, when both -f and -t are omitted, B just acts like B. =item -s,--string I uses I instead of file for the source of text. =item -l,--list Lists all available encodings, one per line, in case-insensitive order. Note that only the canonical names are listed; many aliases exist. For example, the names are case-insensitive, and many standard and common aliases work, such as "latin1" for "ISO-8859-1", or "ibm850" instead of "cp850", or "winlatin1" for "cp1252". See L for a full discussion. =item -C,--check I Check the validity of the stream if I = 1. When I = -1, something interesting happens when it encounters an invalid character. =item -c Same as C<-C 1>. =item -p,--perlqq Same as C<-C -1>. =item -h,--help Show usage. =item -D,--debug Invokes debugging mode. Primarily for Encode hackers. =item -S,--scheme scheme Selects which scheme is to be used for conversion. Available schemes are as follows: =over 4 =item from_to Uses Encode::from_to for conversion. This is the default. =item decode_encode Input strings are decode()d then encode()d. A straight two-step implementation. =item perlio The new perlIO layer is used. NI-S' favorite. =back Like the I<-D> option, this is also for Encode hackers. =back =head1 SEE ALSO L L L L L L =cut