#!/usr/bin/perl

#######################################
## final_v02_TEST.pl
## test.pl (for short)
## Program to parse a txt file given in
## tab-delimited format of physio data
## Parses all files in a directory and
## compiles the results into one file
## Looks through desired folders in dir
##
## Possible Additions:
## ADDITIONS MADE
##
## final_v02_TEST.pl Version .02 (6/20)
## - ADDED 'close IN;' statement (6/21)
## - Code altered to only work on given
##   text file                   (6/24)
## - NOTE USAGE:
##   perl test.pl FILE_NAME DIR_PATH
#######################################

$i_file;  ## Name of input file
$dir_path;  ## Directory path for $i_file
$full_name;  ## '$dir_path\$i_file'
$avg_file = ">>averages.txt";  ## Name of file where file averages are written to (append mode)
$ln_num = 0;  ## Line number in current file, used in @zeroat array to mark zeros
$i = 0;  ## Reference counter
$j = 0;  ## Reference counter (specifically for @avg_frmt array; counts through file loop)
@sums[3];  ## Holds HRT, SKT, and EMG sums, respectively
@avg->[3][2];  ## Holds 1st HRT, 2nd HRT, 1st SKT, 2nd SKT, 1st EMG, and 2nd EMG, averages, respectively
@files;  ## Array to hold desired filenames for current folder
@avg_frmt;  ## Array to hold formatting for $avg_file document (i.e., the formatted output)
@lines;  ## Array to hold lines of current file
@lines1;  ## Holds first part to be averaged
@lines2;  ## Holds second part to be averaged
@zeroat;  ## Tells where zeros are at in array @lines (holds the line number of the zeros; an index to @lines)

$i_file = $ARGV[0];  ## Get file name from command line (first argument)
$dir_path = $ARGV[1];  ## Get directory path from command line (second argument)
$full_name = "$dir_path\\$i_file";

open(IN,$full_name) or die "$i_file failed to open: $!";
@lines = <IN>;  ## Give file input to @lines
close IN;

## Retrieve desired rows
for $curline(@lines) {  ## $curline contains the current line being worked on
  (reverse $line) =~ /^\s*([05])/;  ## Get 0 or 5 from end
  $zeros[$ln_num] = $curline;
  $zeroat[$i] = $ln_num if $1 == 0;
  $ln_num++; $i++;
}

## Take Average
## Get all points between the starting and ending points, and separate into different arrays
for $i(@zeroat) {  ## $i is an index in @lines to where a zero is at
  $lines[$i] =~ /^([0-9]+.?[0-9]*)\t.*([05])\s*$/;  ## Get time (first column) and 0 or 5 (last column)
  if ($1 > .5 && $2 == 0) {  ## {If} time ($1) is more than .5 {AND} end column ($2) is 0 ...
    splice @lines,$i,1;  ## Remove $lines[$i] from @lines
    @lines1 = @lines;  ## Copy neccessary for next statement
    @lines2 = splice @lines1,$i,$#lines1-$i+1;  ## Splice removes desired elements from @lines1,
                                                ## which are given to @lines2 (splice's return value)
  } ## the zero is in the middle: split for averaging
}

## Reset sums
@sums = map { $sums[$_] = 0 } (0..2);

for $i(@lines1) {  ## go through first part and average
  @vals = split /\t/, $lines[$i];  ## Each column in the line has its own place in @vals
  map { $sums[$_] += $vals[$_] } (0..2);
}

## Get first average
map { $avg->[$_][1] = $sums[$_]/$#lines1 } (0..2);

## Reset sums
@sums = map { $sums[$_] = 0 } (0..2);

for $i(@lines2) {  ## go through second part and average
  @vals = split /\t/, $lines[$i];  ## Each column in the line has its own place in @vals
  map { $sums[$_] += $vals[$_] } (0..2);
}

## Get second average
map { $avg->[$_][2] = $sums[$_]/$#lines1 } (0..2);

## Put averages into tab delimited columns with desired format: File name followed by tab followed
## by averages; first line is resting condition; second line is cloud condition.
$avg_frmt[$j] = "$i_file\t$avg->[1][1]\t$avg->[2][1]\t$avg->[3][1]\n";  ## HRT, SKT, EMG is the
$avg_frmt[$j+1] = "$i_file\t$avg->[1][2]\t$avg->[2][2]\t$avg->[3][2]\n";  ## order for the averages
$j += 2;

## Open and print averages to $avg_file
open(OUT,$avg_file) or die "$avg_file failed to be created: $!";
print OUT @avg_frmt;