#!/usr/bin/perl

#    CSV2srt.pl
#          
#    Copyright(C) Since 2009 Akira KAKINOHANA All Rights Reserved
#    Author :  Akira KAKINOHANA <kira@kirameister.net> 
#    Distributed at : http://softwares.kirameister.net/
#    
#    This program is free software: you can redistribute it and/or modify
#    it under the terms of the GNU General Public License as published by
#    the Free Software Foundation version 3.
#
#    This program is distributed in the hope that it will be useful,
#    but WITHOUT ANY WARRANTY; without even the implied warranty of
#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#    GNU General Public License for more details.
#
#    For GNU General Public License, see <http://www.gnu.org/licenses/>.

my $version = "0.05 - Sep  12 2009";

use strict;
use warnings;
use Text::CSV_XS;
use utf8;
binmode(STDOUT, ":utf8");

my $rfh;
my $tc = Text::CSV_XS->new({binary=>1, allow_loose_quotes=>1}); # to handle non_ascii characters;

my $csv_file = shift or help();
my $out_file  = shift;

open ($rfh, "<:utf8", $csv_file) or die "Cannot open the file $csv_file : $!\n";

chomp($out_file) if (defined($out_file));
if (defined($out_file)){
  open (OUT, ">:utf8", $out_file) or die "Cannot open the file $out_file : $!\n";
}
my $count = 0;
while(<$rfh>){
  ## this is for availding an unnecessary error on a line with double-quote and new line (which leaves only one double-quote..)
  $_ =~ s/^(.*)\".*?$/$1/ if (!($tc->parse($_)));
  next unless $tc->parse($_);
  my ($no, $s_time, $e_time, $en, $ja, $temp) = $tc->fields;
  chomp($no) if (defined($no) );
  chomp($s_time) if (defined($s_time) );
  chomp($e_time) if (defined($e_time) );
  chomp($ja) if (defined($ja) );
  next if ($no !~ m/\d+/);
  next if (!(defined($s_time)));

  next if ($s_time !~ m/^\d:\d\d:\d\d$/ &&
	   $s_time !~ m/^\d\d\:\d\d\:\d\d\.\d\d\d$/ &&
	   $s_time !~ m/^\d:\d\d:\d\d\.\d\d\d$/ );
  $s_time = "0" . $s_time . ",000" if ($s_time =~ m/^\d\:\d\d\:\d\d$/);
  if ($s_time =~ m/^\d:\d\d:\d\d.\d\d\d$/ ){
    $s_time =~ m/^(\d:\d\d:\d\d).(\d\d\d)$/;
    $s_time = "0" . $1 . "," . $2;
  }

  next if (!(defined($e_time)));
  next if ($e_time !~ m/^\d:\d\d:\d\d$/ &&
	   $e_time !~ m/^\d\d\:\d\d\:\d\d\.\d\d\d$/ &&
	   $e_time !~ m/^\d:\d\d:\d\d\.\d\d\d$/ );
  $e_time = "0" . $e_time . ",000" if ($e_time =~ m/^\d\:\d\d\:\d\d$/);
  if ($e_time =~ m/^\d:\d\d:\d\d.\d\d\d$/ ){
    $e_time =~ m/^(\d:\d\d:\d\d).(\d\d\d)$/;
    $e_time = "0" . $1 . "," . $2;
  }

#1,0:00:00.000,0:00:
  $ja = "" if (!(defined($ja)));
  $ja =~ s/''/\"/g if (defined($ja));

  $count++;
  if ($count != $no){
    print STDERR "Segment No. " . $count . " is missing..\n";
    $count = $no;
  }

  if ($ja eq ""){
    print STDERR "Segment No. " . $count . " has a technical problem. Skipping..\n";
    next;
  }

  if ($out_file){
    print OUT "$no\n";
    print OUT "$s_time --> $e_time\n";
    print OUT "$ja\n";
    print OUT "\n";
  }else{
    print "$no\n";
    print "$s_time --> $e_time\n";
    print "$ja\n";
    print "\n";
  }
}
close $rfh;
close (OUT);
sub help {
  die "Usage : perl $0 csv_file [out_file]\n";
}

__END__