#!/usr/bin/perl
use strict;
use warnings;

use File::Spec;

# IDENTIFY OS
my $OS;
if ($^O =~ /mswin/i) {$OS = "Windows";print "OS detected: Windows\n"}
elsif ($^O =~ /linux/i) {$OS = "Linux";print "OS detected: Linux\n"}
elsif ($^O =~ /darwin/i) {$OS = "Mac";print "OS detected: Mac OS X\n"} 
else {print "\nUnable to detect OS type, choose your OS:\n\nWindows	Any version of Microsoft Windows\nMac	Any flavour of Mac OS X\nLinux	Linux of some sort\n\n";
do {
	chomp ($OS = <STDIN>);
	print "\nIncorrect OS type. Try again.\n\n" unless $OS eq "Windows" or $OS eq "Mac" or $OS eq "Linux";} until ($OS eq "Windows" or $OS eq "Mac" or $OS eq "Linux");
}

# IDENTIFY SCRIPT PATH
my $script = File::Spec->rel2abs( __FILE__ );

$script =~ /(.*)[\/|\\](.*)/;
my $scriptpath = $1;

if (-d "$scriptpath/scripts/docx2txt") {
	# print "\nScript folder found.\n";# comment out

} else {

	do {
		print "\nThe script path found automatically (${scriptpath}) is not correct.\nPlease drag and drop the aligner script here and press enter. (If your OS doesn't support drag & drop, copy-paste the path here. You can paste by right clicking in the window or right clicking the icon in the top left corner of this window.)\n";
		chomp ($script = <STDIN>);
		$script =~ / *[\"\'](.*)[\/\\](.*)[\"\'] */;
		$scriptpath = $1;
		$scriptpath =~ s/^\s+//;					# strip leading whitespace
		$scriptpath =~ s/\s+$//;					# strip trailing whitespace

		if (-e "$scriptpath/scripts/docx2txt") {print "\nScript folder identified correctly.\n"}
	} until (-e "$scriptpath/scripts/docx2txt");
}


# DRAG AND DROP INPUT FILE
my $file1_full;
print "\n\nDrag and drop your input file here and press enter.\n";
chomp ($file1_full = <STDIN>);
$file1_full =~ s/^\s+//;					# strip leading whitespace
$file1_full =~ s/\s+$//;					# strip trailing whitespace

$file1_full =~ /^[\"\']?(.*)[\/\\]([^\"\']*)[\"\']?$/;
my $folder = $1;
my $file1 = $2;
$file1 =~ /(.*)\.(.*)/;
my $f1 = $1;
my $ext = lc($2);


# CONVERT DOCX TO UTF-8 TXT
if ($OS eq "Windows") {
	# create config file, run docx2txt.exe modded to use win config file
	open (DOCX2TXTCONFIG, "<", "$scriptpath/scripts/docx2txt/docx2txt.config") or die "Can't open file: $!";
	unlink "$scriptpath/scripts/docx2txt/docx2txt_win.config";
	open (DOCX2TXTCONFIG_WIN, ">>", "$scriptpath/scripts/docx2txt/docx2txt_win.config") or die "Can't open file: $!";
	while (<DOCX2TXTCONFIG>) {
		s/^unzip *=>.*$/unzip         => \'$scriptpath\\scripts\\docx2txt\\unzip\\unzip\.exe\',/;
		print DOCX2TXTCONFIG_WIN $_;
	}
	close DOCX2TXTCONFIG;
	close DOCX2TXTCONFIG_WIN;
	system ("\"$scriptpath\\scripts\\docx2txt\\docx2txt_win.exe\" \"$folder/$file1\" \"$folder/${f1}.txt\"");
} else { # linux and mac both use the original docx2txt.pl and both have unzip at usr/bun/unzip

	system ("perl \"$scriptpath/scripts/docx2txt/docx2txt.pl\" \"$folder/$file1\" \"$folder/${f1}.txt\"");
}

#work with the txt file from now on
$file1 = "${f1}.txt";

# CHECK FILE SIZE, ABORT IF 0
my $file_1_size = -s "$folder/$file1";

if ($file_1_size == 0) {
	print "\n\nThe file conversion seems to have failed: the generated file is empty. ABORTING.\n\n";
	sleep 3;
	die;
}

# DONE
print "\n$file1 created ($file_1_size bytes).\nPress enter to quit.\n";
<STDIN>;