#!/usr/bin/perl -w

use strict;
use warnings;

my @tick_data =
(
  # DATE & TIME          PRICE  VOL.
  "2025-01-12 09:30:00", 100.5,  200,
  "2025-01-12 09:30:30", 100.8,  100,
  "2025-01-12 09:31:00", 101.0,  150,
  "2025-01-12 09:31:00", 100.9,  250,
  "2025-01-12 09:31:01", 101.2,  300,
  "2025-01-12 09:31:05", 101.5,  100,
  "2025-01-12 09:31:13", 101.7,  85,
  "2025-01-12 09:31:14", 103.6,  3500,
  "2025-01-12 09:31:14", 103.5,  1500,
  "2025-01-12 09:31:15", 103.4,  800,
  "2025-01-12 09:31:17", 103.3,  50,
  "2025-01-12 09:31:29", 103.2,  100,
  "2025-01-12 09:31:31", 103.4,  450,
  "2025-01-12 09:31:45", 103.8,  930,
  "2025-01-12 09:32:00", 107.00, 40000,
  "2025-01-12 09:32:01", 105.85, 10550,
  "2025-01-12 09:32:02", 105.85, 500,
  "2025-01-12 09:32:03", 105.84, 7600,
  "2025-01-12 09:32:08", 105.8,  3600,
  "2025-01-12 09:32:11", 105.89, 100,
  "2025-01-12 09:32:18", 105.75, 200
);

# Display raw input data:
print "\n\tTIME STAMP\t\tPRICE\tVOLUME\n";
foreach (@tick_data) { print( (length($_) > 12) ? "\n" : '', "\t$_"); }

# Group data into OHLCV intervals (e.g., 1 minute)
my $interval_seconds = 30;   # Set interval in seconds
my $NOGAPS = 1;
# When NOGAPS=1, previous close will ALWAYS be equal next bar's open.
# When NOGAPS=0, there might be a gap between previous close and
# next bar's open.

# First, we convert time stamps to seconds
foreach (@tick_data)
{
  # Match time stamp format:
  $_ =~ m/\d{4}-\d{1,2}-\d{1,2}\s+\d{1,2}:\d{1,2}:\d{1,2}/
    and $_ = timestamp_to_epoch($_);
}
display_original_data(@tick_data);   # Show our work

# Next we convert the price data...
my @ohlcv_data = convert_tick_data($interval_seconds, @tick_data);

disply_ohlcv(@ohlcv_data);           # Show final result

exit;

####################################################################
sub convert_tick_data
{
  my $interval = shift;

  my @OUTPUT;

  my $O = 0;  # Open
  my $H = 0;  # High
  my $L = 0;  # Low
  my $C = 0;  # Close
  my $V = 0;  # Volume

  my $INIT_PRICE;
  my $i = 0;
  my $START = -1;
  my $DIFF;

  while ($i < @_)
  {
    my $TIME = $_[$i++];
    my $PRICE = $_[$i++];
    my $VOLUME = $_[$i++];

    if ($START >= 0)
    {
      $DIFF = $TIME - $START;
      if ($DIFF < $interval)    # Adjust O H L C V data as time goes
      {
        $PRICE > $H and $H = $PRICE;
        $PRICE < $L and $L = $PRICE;
        $V += $VOLUME;        
        $C = $PRICE;
        next;
      }
      if ($DIFF >= $interval)    # Take a snapshot here
      {
        $O and push(@OUTPUT, $O, $H, $L, $C, $V);

        # Reset values
        $START      = $TIME - ($DIFF % $interval);
        $V          = $VOLUME;
        $INIT_PRICE = $PRICE;

        if ($NOGAPS)
        {
          # Previous bar's close is the initial price:
          $O = $H = $L = $C;
          if ($INIT_PRICE)
          {   # If there's new data, then we process it here:
            $PRICE > $H and $H = $PRICE;
            $PRICE < $L and $L = $PRICE;
            $C = $PRICE;
          }
        }
        else
        {
          $O = $H = $L = $C = $INIT_PRICE;
        }
      }
    }
    else
    {
      $START = $TIME;
      $O = $H = $L = $C = $PRICE;
      $V = $VOLUME;
    }
  }
  $O and push(@OUTPUT, $O, $H, $L, $C, $V);

  return @OUTPUT;
}
####################################################################
sub disply_ohlcv
{
  print "\n\n\n\tOPEN\tHIGH\tLOW\tCLOSE\tVOLUME\n";
  while (@_ >= 5)
  {
    my $O = shift;
    my $H = shift;
    my $L = shift;
    my $C = shift;
    my $V = shift;
    print "\n\t$O\t$H\t$L\t$C\t$V";
  }
  print "\n";
}
####################################################################
#
# This function loosely converts a YYYY-MM-DD HH:MM:SS formatted
# time stamp to seconds.
#
# Usage: INTEGER = timestamp_to_epoch(STRING)
#
sub timestamp_to_epoch
{
  defined $_[0] or return 0;
  my @T = split(/\D+/, $_[0]);
  return $T[5] + $T[4] * 60
    + $T[3] * 3600 + $T[2] * 86400
    + $T[1] * 2678400 + $T[0] * 32140800;
}
####################################################################
#
sub display_original_data
{
  print "\n\n\n\tSECONDS\t\tPRICE   \tVOLUME\n";
  my $i = 0;
  while ($i < @_)
  {
    my $TIME = $_[$i++];
    my $PRICE = $_[$i++];
    my $VOLUME = $_[$i++];
    printf("\n\t%.0f\t%.4f\t%.4f", $TIME, $PRICE, $VOLUME);
  }
  print "\n";
}