osamu2001/jman2tmx.pl

## jman2tmx.pl
#!/usr/bin/perl
use strict;
use warnings;
use utf8;
use Encode;
my $ens="";
my $jas="";
my $mode="en";

&print_tmx_header();

while(<STDIN>){
  my $line = decode("utf8", $_);
  chomp $line;
#  $line =~ s/&/&amp;/g;
#  $line =~ s/"/&quot;/g;
#  $line =~ s/</&lt;/g;
#  $line =~ s/>/&gt;/g;
  $line = &HTMLSanitize($line);

  if($line =~ /^\/\/[\s\t]+(.+)/){
    $jas = $jas . " " .$1;
    $mode = "ja";
  }else{
    if(0 == length($line)){
      if((0 != length($ens))&&(0 != length($jas))){
        $ens =~ s/\.\s+/\.\n/g;
        $ens =~ s/[ 	]+/ /g;
        $jas =~ s/。\s*/。\n/g;
        $jas =~ s/、\s*/、/g;
        $jas =~ s/。\n$/。/g;

        unless($ens =~ /\n/){
          #single sentence.
          &print_tuv($ens,$jas);
        }else{
          #multi sentences.
          my $ensn = scalar(() = $ens =~ /\n/g);
          my $jasn = scalar(() = $jas =~ /\n/g);
          if($ensn==$jasn){
            my @enss = split(/\n/,$ens);
            my @jass = split(/\n/,$jas);
            for(my $i=0;$i<$ensn;$i=$i+1){
              &print_tuv($enss[$i],$jass[$i]);
            }
          }else{
#            print "\$ensn=$ensn, \$jasn=$jasn\n";
            &print_tuv($ens,$jas);
          }
        }
      }
      $ens = "";
      $jas = "";
    }else{
      $ens = $ens . " " . $line;
      $mode = "en";
    }
  }
}

&print_tmx_footer();
sub print_tuv{
  my ($ens,$jas) = @_;
  &print_tuv_en_b();
  print encode("utf8",$ens);
  &print_tuv_en_e();
  &print_tuv_ja_b();
  print encode("utf8",$jas);
  &print_tuv_ja_e();
}
sub print_tuv_en_b(){
  print << "TUV_EN";
<tu>
<tuv lang="EN-US">
TUV_EN
  print "<seg>";
}
sub print_tuv_en_e(){
  print << "TUV_EN";
</seg>
</tuv>
TUV_EN
}

sub print_tuv_ja_b(){
  print << "TUV_JA";
<tuv lang="JA">
TUV_JA
  print "<seg>";
}
sub print_tuv_ja_e(){
  print << "TUV_JA";
</seg>
</tuv>
</tu>
TUV_JA
}

sub print_tmx_footer(){
  print << "TMX_FOOTER";
</body>
</tmx>
TMX_FOOTER
}

sub print_tmx_header(){
print << "TMX_HEADER";
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE tmx SYSTEM "tmx11.dtd">
<tmx version="1.1">
  <header
    creationtool="OmegaT"
    creationtoolversion="2.0.2_1"
    segtype="sentence"
    o-tmf="OmegaT TMX"
    adminlang="EN-US"
    srclang="EN-US"
    datatype="plaintext"
  >
  </header>
  <body>
TMX_HEADER
}

sub HTMLSanitize {
    my $str = shift;
    $str =~ s/&/&amp;/g;
    $str =~ s/</&lt;/g;
    $str =~ s/>/&gt;/g;
    $str =~ s/"/&quot;/g;
    return $str;
}
	#!/usr/bin/perl
	use strict;
	use warnings;
	use utf8;
	use Encode;
	my $ens="";
	my $jas="";
	my $mode="en";

	&print_tmx_header();

	while(<STDIN>){
	my $line = decode("utf8", $_);
	chomp $line;
	# $line =~ s/&/&/g;
	# $line =~ s/"/"/g;
	# $line =~ s/</</g;
	# $line =~ s/>/>/g;
	$line = &HTMLSanitize($line);

	if($line =~ /^\/\/[\s\t]+(.+)/){
	$jas = $jas . " " .$1;
	$mode = "ja";
	}else{
	if(0 == length($line)){
	if((0 != length($ens))&&(0 != length($jas))){
	$ens =~ s/\.\s+/\.\n/g;
	$ens =~ s/[ ]+/ /g;
	$jas =~ s/。\s*/。\n/g;
	$jas =~ s/、\s*/、/g;
	$jas =~ s/。\n$/。/g;

	unless($ens =~ /\n/){
	#single sentence.
	&print_tuv($ens,$jas);
	}else{
	#multi sentences.
	my $ensn = scalar(() = $ens =~ /\n/g);
	my $jasn = scalar(() = $jas =~ /\n/g);
	if($ensn==$jasn){
	my @enss = split(/\n/,$ens);
	my @jass = split(/\n/,$jas);
	for(my $i=0;$i<$ensn;$i=$i+1){
	&print_tuv($enss[$i],$jass[$i]);
	}
	}else{
	# print "\$ensn=$ensn, \$jasn=$jasn\n";
	&print_tuv($ens,$jas);
	}
	}
	}
	$ens = "";
	$jas = "";
	}else{
	$ens = $ens . " " . $line;
	$mode = "en";
	}
	}
	}

	&print_tmx_footer();
	sub print_tuv{
	my ($ens,$jas) = @_;
	&print_tuv_en_b();
	print encode("utf8",$ens);
	&print_tuv_en_e();
	&print_tuv_ja_b();
	print encode("utf8",$jas);
	&print_tuv_ja_e();
	}
	sub print_tuv_en_b(){
	print << "TUV_EN";
	<tu>
	<tuv lang="EN-US">
	TUV_EN
	print "<seg>";
	}
	sub print_tuv_en_e(){
	print << "TUV_EN";
	</seg>
	</tuv>
	TUV_EN
	}

	sub print_tuv_ja_b(){
	print << "TUV_JA";
	<tuv lang="JA">
	TUV_JA
	print "<seg>";
	}
	sub print_tuv_ja_e(){
	print << "TUV_JA";
	</seg>
	</tuv>
	</tu>
	TUV_JA
	}

	sub print_tmx_footer(){
	print << "TMX_FOOTER";
	</body>
	</tmx>
	TMX_FOOTER
	}

	sub print_tmx_header(){
	print << "TMX_HEADER";
	<?xml version="1.0" encoding="UTF-8"?>
	<!DOCTYPE tmx SYSTEM "tmx11.dtd">
	<tmx version="1.1">
	<header
	creationtool="OmegaT"
	creationtoolversion="2.0.2_1"
	segtype="sentence"
	o-tmf="OmegaT TMX"
	adminlang="EN-US"
	srclang="EN-US"
	datatype="plaintext"
	>
	</header>
	<body>
	TMX_HEADER
	}

	sub HTMLSanitize {
	my $str = shift;
	$str =~ s/&/&/g;
	$str =~ s/</</g;
	$str =~ s/>/>/g;
	$str =~ s/"/"/g;
	return $str;
	}