18.998403205 fluoride [F-] W00662 - - water_solubility 0.00169 mg/mL at 25 °C - - formal_charge -1 ChemAxon ##

##

sub load_files() {
  #get a list of all files in directory; ignore all files beginning with a . and other sub directories
  opendir(my $dh, $dirname) or die "can't opendir $dirname: $!";
  my @files = grep (/^[^\.]/ && -f "$dirname/$_", readdir($dh)); #only keep those not beginning with '.' and are files  
  @files = sort(@files); #sort lexically, 'B' comes before 'a', so that output list is always in same order
  closedir $dh;
  
  my $numfiles = 0;

  foreach my $file (@files) { #loop through the files
    $numfiles++;
    
    my $accefound = 0;
    my $namefound = 0;
    my $monofound = 0;
    my $chargefound =0;
        
    open(my $file_fh, "< $dirname/$file") or die("$$: Error: failed to open file $dirname/$file. $!\n");
    while(<$file_fh>) { #read each line of file
      if (/()(.+)(<\/weight>)/ && !$monofound) { #if first encounter with the tag
        $monofound = $2;
        $monofound =~ s/^\s+//; #trim leading whitespace of string
        $monofound =~ s/\s+$//; #trim trailing whitespace of string
      }
    elsif (/()(.+)(<\/name>)/ && !$namefound) { #if first encounter with the tag
        $namefound = $2;
        $namefound =~ s/^\s+//; #trim leading whitespace of string
        $namefound =~ s/\s+$//; #trim trailing whitespace of string
      }
    
      elsif (/()(.+)(<\/accession>)/ && !$accefound) { #if first encounter with the tag (the tag might not be unique)
        $accefound = $2;
        $accefound =~ s/^\s+//; #trim leading whitespace of string
        $accefound =~ s/\s+$//; #trim trailing whitespace of string
      }
      
         elsif (/()(.+)(<\/formal_charge>)/ && !$chargefound) { #if first encounter with the tag
        $chargefound = $2;
        $chargefound =~ s/^\s+//; #trim leading whitespace of string
        $chargefound =~ s/\s+$//; #trim trailing whitespace of string
      }

    }
    print "$monofound\t$namefound\t$accefound\t$chargefound\n";
 
    close($file_fh) or die("$$: Error: failed to close file $dirname/$file. $!\n");
  }
      
}



main();

##

##

_OUTPUT DATA_
18.998403205	fluoride	W00662	0


##

##

-
	formal_charge
	-1  
	ChemAxon