#!/usr/bin/perl

use strict;

my $directory = "D:/Nagaraj/oup/OUP-Brenkert/Preprocessed";

use File::Find;
use strict;
        
my $count;
my $s;
my $nb;
my $cou;
my $i;
my $ss;
my $tag;

#my $directory = "";

find (\&process, $directory);

sub process
{
    my @outLines;  #Data we are going to output
    my $Replace;      #Data we are reading line by line

        #print "processing $_ / $File::Find::name\n";

    # Only parse files that end in .xml
    if ( ($File::Find::name =~ /\.XML$/) || ($File::Find::name =~ /\.xml$/)) {

        open (FILE, $File::Find::name ) or die "Cannot open file: $!";

        while ( $Replace = <FILE> ) {

                $cou =~ s/<tableGroup([^>]+)<\/tableGroup>/<tableGroup$1<\/tableGroup>/gi;
                        for($i=0;$i<=$cou;$i++)
                                {
                                    if(/(<tableGroup([^>]+)<\/tableGroup>)/)
                                    {
                                            $ss=$1;
                                            $count = ($ss =~ s/<row/<row/g);
                                            $Replace =~ s/<tgroup cols\="(.*?)">/<tgroup cols\="$1"><SPiTable><SPiTable-body xmlns\:aid\="http:\/\/ns.adobe.com\/AdobeInDesign\/4.0\/" aid\:table\="table" aid\:trows\="$count" aid:tcols="$1">/g;
                                            print $count;
                                   }

                                }
              #$Replace =~ s/&ndash;/&#x2013;/g;
              push(@outLines, $Replace);
              }

        close FILE;
        open ( OUTFILE, ">$File::Find::name" ) or
        die "Cannot open file: $!";

        print ( OUTFILE @outLines );
        close ( OUTFILE );

        undef( @outLines );
           }
        }

use strict;
use warnings;
# Define some file names.
my $infile="input.html";
my $outfile="output.html";

# Open the input file.
open (FILE, "<$infile") or die "$!\n";
my @input=<FILE>;		# This can be memory hungry if you have a large file, but it's quick-n-dirty enough for the sake of a demo.
close FILE;

# Now parse it.
my %row_counts;			# This is where we will keep the count. Keyed on the row where we found the table start.
my $current_id;			# We keep track of the row we fond the current table on.
# A C-style loop over the input.
for (my $i=0; $i<scalar(@input); $i++) {
	if ($input[$i]=~m/$\<table id=\"(.*?)\"/) {
		# We have a match, and $1 should contain the ID.
		$current_id=$i;
	}
	# Is this a "<row>" line?
	if ($input[$i]=~m/\<row\>/) {
		# Yes. Do we already have a count for this table?
		if ($row_counts{$current_id}) {
			# Yes, increment it.
			$row_counts{$current_id}++;
		} else {
			# No. This is the first row for this table, set the count to 1.
			$row_counts{$current_id}=1;
		}
	}
}
# We now have a has which holds all our row counts. The key of the hash is the row where the table started.
# Now print the entire array, but whenever we have a row where a table starts, insert the count.
for (my $i=0; $i<scalar(@input); $i++) {
	if ($row_counts{$i}) {
		# We are looking at a row where a table starts. We need to insert the row count.
		# split the line at whitespace.
		my @temp_array=split(/\s/, $input[$i]);
		# We should now have 3 elements:
		# ('<table', 'id="something"' and 'frame="none">'
		print "$temp_array[0] $temp_array[1] totalrow=\"$row_counts{$i}\" $temp_array[2]\n";
	} else {
		print "$input[$i]\n";
	}
	
	
}


print "Result:\n";
foreach(keys(%row_counts)) {
	print "$_=>$row_counts{$_}\n";
}