Perform an operation on a set of models including ActiveRecord callbacks, without instantiating all models at once.

Step through and instantiate each member of the class and execute on it, but instantiate no more than per_page instances at any given time.
Safe for destructive actions or actions that modify the fields your :order or :conditions clauses operate on.

module ActiveRecord
  class Base
    def each_by_page per_page, options = {}, &block
      # By-id for model-modifying blocks
      # Build SQL to get ids of all matching records using the options provided by the user
      sql = construct_finder_sql(options.dup.merge({ :select => 'id' }))
      # Get the results as an array of tiny hashes { "id" => "1" } and flatten them out to just the ids
      all_ids = connection.select_all(sql).map { |h| h['id'] }
      at_a_time = 0..(per_page-1)
 
      # chop apart the all_ids array a segment at a time
      begin
        ids = all_ids.slice!(at_a_time)
        ids_cases = []
        ids.each_with_index { |id, i| ids_cases << "WHEN #{id} THEN #{i}" }
        ids_cases = ids_cases.join(' ')
 
        # Do the deed on this page of results
        find(:all, options.merge(
          :conditions => [ 'id IN (?)', ids ],
          :order => "CASE id #{ids_cases} END"
        )).each &block
 
      end until all_ids.empty?
    end
  end
end

link to blog entry

Split a string into an array of roughly equal sized chunks based on a string or regular expression delimiter.
Delimiter is preserved in output.

class String
  def chunk_string(average_segment_size = 40, sclice_on = /\s+/)
    out = []
    slices_estimate = self.size.divmod(average_segment_size)
    slice_count = (slices_estimate[1] > 0 ? slices_estimate[0] + 1 : slices_estimate[0])
    slice_guess = self.size / slice_count
    previous_slice_location = 0
    (1..slice_count - 1).each do
      |i|
      slice_location = self.nearest_split(slice_guess * i, sclice_on)
      out << self.slice(previous_slice_location..slice_location)
      previous_slice_location = slice_location + 1
    end
    out << self.slice(previous_slice_location..self.size)
    out
  end

  def nearest_split(slice_start, slice_on)
    left_scan_location  = (self.slice(0..slice_start).rindex(slice_on)).to_i
    right_scan_location = (self.slice((slice_start+1)..self.size).index(slice_on)).to_i + slice_start
    ((slice_start - left_scan_location) < (right_scan_location - slice_start) ? left_scan_location : right_scan_location)
  end
end

// Return the extension from a file name

/(.*\.)(.*$)/.match(File.basename(file_name))[2]