require 'fileutils'

class DataPipeline
  # another run holds the lock
  class LockError < StandardError; end

  #
  # exclusive lock on a file, against overlapping runs (cron)
  #
  #   lock 'data/.cudo.lock'            -> in a pipeline: held from the start to the end of run
  #   etl run cudo.rb --lock=data/.lock -> for the whole script
  #
  # the lock is an flock on the file, released by the operating system when the process ends,
  # also after a crash; the file stays and holds the pid of the last holder
  #
  class Lock
    attr_reader :file

    def initialize file
      @file = file.to_s
    end

    def acquire
      return self if @io

      FileUtils.mkdir_p(File.dirname(@file))
      io = File.open(@file, File::RDWR | File::CREAT, 0o644)
      unless io.flock(File::LOCK_EX | File::LOCK_NB)
        holder = io.read.strip
        io.close
        raise LockError, "#{@file} is locked#{" by pid #{holder}" unless holder.empty?}: another run is still active"
      end
      io.truncate(0)
      io.write(Process.pid.to_s)
      io.flush
      @io = io
      self
    end

    def release
      return unless @io

      @io.flock(File::LOCK_UN)
      @io.close
      @io = nil
    end

    def locked? = !@io.nil?

    def synchronize
      acquire
      yield
    ensure
      release
    end
  end
end