#!/usr/bin/perl -w

# 
# Copyright Yves Dorfsman 2006.
#
# $Revision: 0.2 $
# $Date: 2006/04/20 04:44:46 $
#
# This is a very early very crude version. I will finish it, but I have a need
# to extract data very soon....
#
# -----------------------------------------------------------------------------
# extrallator is free software; you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by
# the Free Software Foundation; either version 2 of the License, or
# (at your option) any later version.
#
# extrallator is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
# or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public
# License for more details.
#
# You should have received a copy of the GNU General Public License
# along with Orca in the COPYING-GPL file; if not, write to the Free
# Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA
# 02111-1307 USA
# -----------------------------------------------------------------------------
#
# extrallator is a simple perl script used to extract one column from a list
# of files that were produced by an Orca (http://orcaware.com/orca) data
# gatherer such as orcallator, procallator or winallator.
#
# syntax for now is:
#     extrallator column_name list_of_files [file [directory]]
#
# eg: extrallator 'mem_used%' /var/orca/procallator/ginette
#
# Assumptions:
# -the columns name are on the first line
# -the file extensions are correct (gz = gziped etc...)
# -.gz ==> gzip'ed, .bz2 ==> bzip2'd
# -gzip and bzip2 are in the path
#

use strict;

sub usage
  {
  print "\nWrong syntax....\n";
  print "I'll update the usage section later\n\n";
  }


if  ($#ARGV < 1)
  {
  usage;
  exit 1;
  }

my $pattern = shift @ARGV;

# Build a list of files. If argument is a directory, open all the files in
# that directory, but do not recurse (well, at least for now).

#print "column: $column\n";
my @files;
foreach (@ARGV)
  {
  my $entry = $_;
  if (-d $entry)
    {
    opendir(DIR, $entry);
    while (defined(my $file = readdir(DIR)))
      {
      my $path_to_ent = $entry . "/" . $file;
      push @files, $path_to_ent if (-f $path_to_ent);
      }
    closedir DIR;
    }
  else
    {
    push @files, $entry;
    }
  }


# Now open each file and look for the pattern
foreach (@files)
  {
  my $file = $_;
  my $decomp;
  my $timestampIndex;
  my $patternIndex;

  $decomp = "gizp" if (/.*\.gz$/);
  $decomp = "bzip2" if (/.*\.bz2$/);
  
  if (defined $decomp)
    {
    open FILE, ("$decomp -cd $file |");
    }
  else
    {
    open FILE, $file;
    }

  # read first line which should be the titles
  my $line     = <FILE>;
  chomp $line;
  my @lineList = split / +/, $line;

  for (my $i = 0 ; $i < $#lineList ; $i++)
    {
    $timestampIndex = $i  if $lineList[$i] =~ /^timestamp$/;
    $patternIndex = $i    if $lineList[$i] =~ /^$pattern$/;
    }

  # the pattern won't necessarely be present in all the files
  # (timestamp should though, but just in case)
  next if (! defined $timestampIndex);
  next if (! defined $patternIndex);

  while ($line = <FILE>)
    {
    chomp $line;
    @lineList = split / +/, $line;

    # transform the timestamp into human time
  (my $lts, my $ltm, my $lth, my $ltd, my $ltM, my $lty, my $ltw, undef, undef)
                                       = localtime($lineList[$timestampIndex]);
    $lty += 1900;
    $ltM++;
    $ltM = sprintf "%02d", $ltM;
    $lth = sprintf "%02d", $lth;
    $ltm = sprintf "%02d", $ltm;
    $lts = sprintf "%02d", $lts;
    print "$lty-$ltM-$ltd $lth:$ltm:$lts $lineList[$patternIndex]\n";
    }
  
  close FILE;
  
  
  }