qtl-xtrain

#!/usr/bin/env ruby

require 'set'

unless ARGV.length == 2
  puts """
  Verify that a directory of a train's skim files has the same list of
  run numbers as a directory of DST-file run directories.

  USAGE: qtl xtrain [TRAIN_DIR(S)] [DST_DIR]

  Both directories must be on /mss or /cache; the /mss dir is checked
  (even if the argument is /cache)

  Use globs to specify multiple TRAIN_DIRS (surround in quotes)
  """
  exit 2
end

train_dirs, dst_dir = ARGV
num_failures = 0

# loop over train directories glob
Dir.glob(train_dirs).select{|d|File.directory? d}.each do |train_dir|

  # function to get a set of run numbers from one of the argument dirs
  def get_runnums(path, type)
    runnums = Set.new
    path = path.sub /^\/cache\//, '/mss/' if path.match? /^\/cache\//
    raise "#{type} dir `#{path}` does not exist" unless Dir.exist? path

    # get list of files/directories within
    files = []
    case type
    when :train
      files = Dir.glob File.join(path, '*.hipo')
    when :DST
      files = Dir.glob File.join(path, '*/')
    else
      raise 'bad type'
    end
    raise "no #{type} files found in #{type} dir `#{path}`" if files.empty?

    # extract their run numbers
    files.each do |file|
      nums = File.basename(file).scan(/\d+/).map &:to_i
      raise "failed to get run number from #{type} object `#{file}`" if nums.empty?
      runnums << nums[-1]
    end
    raise "failed to get run numbers from #{type} dir `#{path}`" if runnums.empty?
    runnums
  end

  # get runnum lists
  train_runs = get_runnums train_dir, :train
  dst_runs   = get_runnums dst_dir,   :DST
  puts """
  ==================================================================================
  train dir: #{train_dir}
  run list: #{train_runs}
  -----
  DST dir: #{dst_dir}
  run list: #{dst_runs}
  =================================================================================="""

  # compare runnum sets
  only_in_trains = train_runs - dst_runs
  only_in_dsts   = dst_runs   - train_runs

  # print results
  $stdout.flush
  $stderr.flush
  code = 0
  unless only_in_trains.empty?
    $stderr.puts "ERROR: there are runs with skim files, but no corresponding DST-file directories:"
    $stderr.puts only_in_trains
    code = 1
  end
  unless only_in_dsts.empty?
    $stderr.puts "ERROR: there are runs with DST-file directories, but no corresponding skim files:"
    $stderr.puts only_in_dsts
    code = 1
  end

  # handle exit code
  if code == 0
    puts "All good"
  else
    num_failures += 1
  end
end
exit num_failures > 0 ? 1 : 0