/usr/bin/piconv is in perl 5.20.2-3+deb8u11.
This file is owned by root:root, with mode 0o755.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 | #!/usr/bin/perl
eval 'exec /usr/bin/perl -S $0 ${1+"$@"}'
if $running_under_some_shell;
#!./perl
# $Id: piconv,v 2.6 2014/03/28 02:37:42 dankogai Exp $
#
BEGIN { pop @INC if $INC[-1] eq '.' }
use 5.8.0;
use strict;
use Encode ;
use Encode::Alias;
my %Scheme = map {$_ => 1} qw(from_to decode_encode perlio);
use File::Basename;
my $name = basename($0);
use Getopt::Long qw(:config no_ignore_case);
my %Opt;
help()
unless
GetOptions(\%Opt,
'from|f=s',
'to|t=s',
'list|l',
'string|s=s',
'check|C=i',
'c',
'perlqq|p',
'htmlcref',
'xmlcref',
'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 = do {
if (defined $Opt{scheme}) {
if (!exists $Scheme{$Opt{scheme}}) {
warn "Unknown scheme '$Opt{scheme}', fallback to 'from_to'.\n";
'from_to';
} else {
$Opt{scheme};
}
} else {
'from_to';
}
};
$Opt{check} ||= $Opt{c};
$Opt{perlqq} and $Opt{check} = Encode::PERLQQ;
$Opt{htmlcref} and $Opt{check} = Encode::HTMLCREF;
$Opt{xmlcref} and $Opt{check} = Encode::XMLCREF;
if ($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
}
my %use_bom =
map { $_ => 1 } qw/UTF-16 UTF-16BE UTF-16LE UTF-32 UTF-32BE UTF-32LE/;
# we do not use <> (or ARGV) for the sake of binmode()
@ARGV or push @ARGV, \*STDIN;
unless ( $scheme eq 'perlio' ) {
binmode STDOUT;
my $need2slurp = $use_bom{ find_encoding($to)->name }
|| $use_bom{ find_encoding($from)->name };
for my $argv (@ARGV) {
my $ifh = ref $argv ? $argv : undef;
$ifh or open $ifh, "<", $argv or warn "Can't open $argv: $!" and next;
$ifh or open $ifh, "<", $argv or next;
binmode $ifh;
if ( $scheme eq 'from_to' ) { # default
if ($need2slurp){
local $/;
$_ = <$ifh>;
Encode::from_to( $_, $from, $to, $Opt{check} );
print;
}else{
while (<$ifh>) {
Encode::from_to( $_, $from, $to, $Opt{check} );
print;
}
}
}
elsif ( $scheme eq 'decode_encode' ) { # step-by-step
if ($need2slurp){
local $/;
$_ = <$ifh>;
my $decoded = decode( $from, $_, $Opt{check} );
my $encoded = encode( $to, $decoded );
print $encoded;
}else{
while (<$ifh>) {
my $decoded = decode( $from, $_, $Opt{check} );
my $encoded = encode( $to, $decoded );
print $encoded;
}
}
}
else { # won't reach
die "$name: unknown scheme: $scheme";
}
}
}
else {
# NI-S favorite
binmode STDOUT => "raw:encoding($to)";
for my $argv (@ARGV) {
my $ifh = ref $argv ? $argv : undef;
$ifh or open $ifh, "<", $argv or warn "Can't open $argv: $!" and next;
$ifh or open $ifh, "<", $argv or next;
binmode $ifh => "raw:encoding($from)";
print while (<$ifh>);
}
}
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]
[-p|--perlqq|--htmlcref|--xmlcref] [-C N|-c] [-D] [-S scheme]
[-s string|file...]
$name -l
$name -r encoding_alias
$name -h
Common options:
-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:
-C N | -c check the validity of the input
-D,--debug show debug information
-S,--scheme scheme use the scheme for conversion
Those are handy when you can only see ASCII characters:
-p,--perlqq transliterate characters missing in encoding to \\x{HHHH}
where HHHH is the hexadecimal Unicode code point
--htmlcref transliterate characters missing in encoding to &#NNN;
where NNN is the decimal Unicode code point
--xmlcref transliterate characters missing in encoding to &#xHHHH;
where HHHH is the hexadecimal Unicode code point
EOT
exit;
}
__END__
=head1 NAME
piconv -- iconv(1), reinvented in perl
=head1 SYNOPSIS
piconv [-f from_encoding] [-t to_encoding]
[-p|--perlqq|--htmlcref|--xmlcref] [-C N|-c] [-D] [-S scheme]
[-s string|file...]
piconv -l
piconv -r encoding_alias
piconv -h
=head1 DESCRIPTION
B<piconv> is perl version of B<iconv>, 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. Some options can be in short format (-f)
or long (--from) one.
=over 4
=item -f,--from I<from_encoding>
Specifies the encoding you are converting from. Unlike B<iconv>,
this option can be omitted. In such cases, the current locale is used.
=item -t,--to I<to_encoding>
Specifies the encoding you are converting to. Unlike B<iconv>,
this option can be omitted. In such cases, the current locale is used.
Therefore, when both -f and -t are omitted, B<piconv> just acts
like B<cat>.
=item -s,--string I<string>
uses I<string> 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<Encode::Supported>
for a full discussion.
=item -r,--resolve I<encoding_alias>
Resolve I<encoding_alias> to Encode canonical encoding name.
=item -C,--check I<N>
Check the validity of the stream if I<N> = 1. When I<N> = -1, something
interesting happens when it encounters an invalid character.
=item -c
Same as C<-C 1>.
=item -p,--perlqq
Transliterate characters missing in encoding to \x{HHHH} where HHHH is the
hexadecimal Unicode code point.
=item --htmlcref
Transliterate characters missing in encoding to &#NNN; where NNN is the
decimal Unicode code point.
=item --xmlcref
Transliterate characters missing in encoding to &#xHHHH; where HHHH is the
hexadecimal Unicode code point.
=item -h,--help
Show usage.
=item -D,--debug
Invokes debugging mode. Primarily for Encode hackers.
=item -S,--scheme I<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.
You should use this option if you are using UTF-16 and others which
linefeed is not $/.
=back
Like the I<-D> option, this is also for Encode hackers.
=back
=head1 SEE ALSO
L<iconv(1)>
L<locale(3)>
L<Encode>
L<Encode::Supported>
L<Encode::Alias>
L<PerlIO>
=cut
|