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

#This program will extract the header information in 10K and 10Q filings
#as well as file sizes.

#Specify the directory containing the files that you want to read;
my $files_dir = 'C:\Test';
#Specify the directory containing the results/output;
my $write_dir = 'C:\Test Output';

#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 $cik=-99;
my $form_type="";
my $report_date=-99;
my $file_date=-99;
my $name="";
my $sic=-99;
my $sic1=-99;
my $HTML=0;

#Open the input file;
open my $FH_IN, '<',$files_dir.'/'.$filename or die "Can't open $filename";
#Within the file loop, read each line of the current file;
while (my $line = <$FH_IN>)  {     
next unless -f $files_dir.'/'.$filename;

#Open the ouput file;
open my $FH_OUT, '>',$write_dir.'/'.$filename or die "Can't open file $filename"; 
  
#The following steps obtain basic data from various lines in the file;
  if($line=~m/^\s*CENTRAL\s*INDEX\s*KEY:\s*(\d*)/m){$cik=$1;}
  if($line=~m/^\s*FORM\s*TYPE:\s*(.*$)/m){$form_type=$1;}
  if($line=~m/^\s*CONFORMED\s*PERIOD\s*OF\s*REPORT:\s*(\d*)/m){$report_date=$1;}
  if($line=~m/^\s*FILED\s*AS\s*OF\s*DATE:\s*(\d*)/m){$file_date=$1;}
  if($line=~m/^\s*COMPANY\s*CONFORMED\s*NAME:\s*(.*$)/m){$name=$1;}
  if($line=~m/^\s*STANDARD\s*INDUSTRIAL\s*CLASSIFICATION:\s*(\d*)/m){$sic=$1;}
  if($line=~m/^\s*STANDARD\s*INDUSTRIAL\s*CLASSIFICATION:.*?\[(\d{4})/m){$sic1=$1;}
  
#Update line counter;
++$line_count;

 }
 
#Now that we have reached EOF< grab file size, and save the results;

my $filesize = -s $files_dir . '/' . $filename;
my $sb = stat($files_dir . '/' . $filename)->size;

print $FH_OUT "$cik,$form_type,$report_date,$file_date,$name,$sic,$sic1,$filesize,$sb\n";

#close $FH_IN or die "unable to close $filename";

#Update file_counter;

#Update file counter;
  ++$file_count;
  
#Save/write results/output; 
print "$count lines read from $filename\n";
  
closedir($dir_handle);
close($FH_OUT);

}