#!/usr/bin/perl -w
use strict;
use warnings;
use File::stat;
use lib "c:/strawberry/perl/site/lib";

#This program will extract Exhibit 21 info from 10-K filings;

#Specify the directory containing the files that you want to read;
my $files_dir = 'E:\research\audit fee models\filings\test';
#Specify the directory containing the results/output;
my $write_dir =  'E:\research\audit fee models\filings\filenames\Exhibit21.txt';

#Open the directory containing the files you plan to read;
opendir(my $dir_handle, $files_dir) or die "Can't open directory $!";

#Initialize file counter variable;
my $file_count = 0;

#Loop for reading each file in the input directory;
while (my $filename = readdir($dir_handle))  {
    next unless -f $files_dir.'/'.$filename;
    print "Processing $filename\n";

   #Initialize the variable names.
   my $line_count=0;
   my $access_num="";
   my $cik=-99;
   my $name="";
   my $stuff="";
   my $line="";
   my $htm ="";

   #Open the input file;
   
   open my $FH_IN, '<',$files_dir.'/'.$filename or die "Can't open $filename <:$!>";
   use Cwd; print getcwd(), "\n";
   #Within the file loop, read each line of the current file;

   $/="</DOCUMENT>";

   while (my $doc = <$FH_IN>)  {     #Begin new document section;
       
       if ($doc =~ m/^\s*<FILENAME>(.*?)(ex21)/igm )   
    
       #if ($doc =~ m/^\s*<FILENAME>(.*?)(ex21)(.*?)(.htm$)/igm ||
        #   $doc =~ m/^\s*<FILENAME>(.*?)(EX-21)(.*?)(.htm$)/igm ||
         #  $doc =~ m/^\s*<FILENAME>(.*?)(ex21)(.*?)(.htm$)/igm  ||
          # $doc =~ m/^\s*<FILENAME>(.*?)(EX-21)(.*?)(.htm$)/igm)        
             { $htm=join('',$1,$2);  }     
     
     print $htm;
                      
    #close $FH_IN or die "Cannot close $filename: $!"; 
    close $FH_IN;                         

#Open the ouput file;
    open my $FH_OUT, '>>',$write_dir or die "Can't open file $write_dir >:$!>"; 
    #Save the output to disk;
    print $FH_OUT "$htm\n"; 
#closedir($dir_handle);
    close($FH_OUT);
    
                                }      #end of document section;
}  #end of current file;