libunicode-japanese-perl 0.49-1build1 / usr / bin / ujconv

#!/usr/bin/perl -w
## ----------------------------------------------------------------------------
#  ujconv
# -----------------------------------------------------------------------------
# Mastering programmed by YAMASHINA Hio
#
# Copyright 2005 YAMASHINA Hio
# -----------------------------------------------------------------------------
# $Id: ujconv 4697 2007-09-14 06:17:00Z pho $
# -----------------------------------------------------------------------------
package Unicode::Japanese::UJConv;
use strict;
use Unicode::Japanese;
our $VERSION = '0.02';

if( !caller )
{
  __PACKAGE__->do_work(@ARGV);
}

# -----------------------------------------------------------------------------
# main.
#
sub do_work
{
  my $pkg = shift;
  
  my $from = 'auto';
  my $to = 'auto';
  my $string;
  my @files;
  
  while(@_)
  {
    my $key = shift;
    if( $key !~ /^-/ )
    {
      push(@files,$key);
      next;
    }elsif( $key eq '--' )
    {
      push(@files,@_);
      last;
    }
    if( $key eq '-f' )
    {
      $from = shift;
      next;
    }elsif( $key eq '-t' )
    {
      $to = shift;
      next;
    }elsif( $key eq '-s' )
    {
      my $value = shift;
      push(@files,[$key,$value]);
      next;
    }elsif( $key =~ /^(-h|--help)$/ )
    {
      print_usage();
      return 1;
    }elsif( $key =~ /^(-V|--version)$/ )
    {
      print_version();
      return 1;
    }elsif( $key =~ /^(-l|--list)$/ )
    {
      print_list();
      return 1;
    }else
    {
      die "unkown argument [$key]";
    }
  }
  
  if( $to eq 'auto' )
  {
    my $lang = $ENV{LANG};
    if( $lang && $lang=~/\.(.*)/ )
    {
      my $code = $1;
      if( $code=~/^(ujis|jis|iso-2022-jp)$/i )
      {
        $to = 'jis';
      }elsif( $code=~/^(ujis|eucJP)$/i )
      {
        $to = 'euc';
      }elsif( $code=~/^(sjis|shift_?jis)$/i )
      {
        $to = 'sjis';
      }elsif( $code=~/^(utf-?8)$/i )
      {
        $to = 'utf8';
      }
    }
    if( $to eq 'auto' )
    {
      $to = $^O eq 'MSWin32' ? 'sjis' : 'euc';
    }
  }
  
  local($/) = undef;
  if( !@files )
  {
    my $text = <STDIN>;
    print Unicode::Japanese->new($text,$from)->conv($to);
  }
  foreach my $file (@files)
  {
    my $text;
    if( ref($file) )
    {
      $text = $file->[1];
    }elsif( $file eq '-' )
    {
      $text = <STDIN>;
    }else
    {
      open(FILE,$file) or die "could not open file [$file] : $!";
      $text = <FILE>;
      close(FILE);
    }
    print Unicode::Japanese->new($text,$from)->conv($to);
  }
  1;
}

# -----------------------------------------------------------------------------
# print_usage();
#
sub print_usage
{
  print "usage: ujconv [-f from_encode] [-t to_encode] [-s string] [files...]\n";
  print "see \`perldoc ujconv' for details.\n";
}

# -----------------------------------------------------------------------------
# print_version();
#
sub print_version
{
  print "ujconv $VERSION\n";
  print "Unicode::Janaese $Unicode::Japanese::VERSION\n";
}

# -----------------------------------------------------------------------------
# print_list();
#
sub print_list
{
  foreach my $enc (qw(
      utf8
      ucs2
      ucs4
      utf16
      jis
      euc
      euc-jp
      sjis
      cp932
      sjis-imode
      sjis-doti
      sjis-jsky
      jis-jsky
      jis-au
      sjis-icon-au
      euc-icon-au
      jis-icon-au
      utf8-icon-au
  ))
  {
    print "$enc\n";
  }
}

__END__

=head1 NAME

ujconv -- reinvented iconv(1) using Unicode::Japanese

=head1 SYNOPSIS

  ujconv [-f from_encoding] [-t to_encoding] [-s string] [files...]
  ujconv -l
  ujconv -h
  ujconv -V

=head1 VERSION

ujconv 0.02

=head1 DESCRIPTION

B<ujconv> is an iconv-like tool which is written in perl using
Unicode::Japanese.

B<ujconv> reads text from STDIN or files, convert them, and print them to
STDOUT.

Available options are as follows. Each options can be in short form (-f) or long
form (--from):

=over 4

=item -f,--from I<from_encoding>

Convert characters from I<from_encoding>. Unlike B<iconv> this option can be
omitted. In that case, the encoding of the input is guessed by B<ujconv>.

=item -t,--to I<to_encoding>

Convert characters to I<to_encoding>.

=item -s,--string I<string>

Input from the argument string instead of file or STDIN.

=item -l,--list

List all available encodings, one name per each lines.

=item -h,--help

Print a short help message.

=item -V,--version

Print the version of B<ujconv>.

=back

=head1 SEE ALSO

L<Unicode::Japanese>,
L<piconv(1)>,
L<iconv(1)>,
L<ujguess>

=cut

# -----------------------------------------------------------------------------
# End of File.
# -----------------------------------------------------------------------------