trivial_cache.rb

# This is a method I use when working with slow ruby scripts that
# operate on huge datasets.
#
# It caches the return value of a block of extremely slow code
# in a file so that subsequent runs are fast.
#
# It's indispensable to me when doing edit-debug-edit-debug-edit
# cycles on giant datasets.

# loads ruby object from a cache file or (if cache file doesn't exist) runs
# provided block and writes result to cache file
def cache(file)
  if File.exists?(file)
    STDERR.puts "(used cache)"
    Marshal.load(File.read(file))
  else
    object = yield
    File.open(file, 'w') { |f| f.print Marshal.dump(object) }
    object
  end
end

# usage example (loading 8,000 marc-xml files)

STDERR.puts "loading marc files"
marc_records = cache('marc_records.cache') do
  marc_records = {}
  marc_files.each do |f|
    doc = Document.new(File.read(f))
    title = doc.elements['//datafield[@tag="245"]/subfield[@code="a"]']
    marc_records[f] = title.text
  end
  marc_records
end