Parse and statistics Medline (PubMed) abstract files

parse_and_stats_medline.rb

require 'bio'
# Input is abstract file in Medline format.
year_count = Hash.new(0)
File.read(ARGV[0]).split("\n\n").each do |article_block|
  article = Bio::MEDLINE.new(article_block)
  year_count[article.year] += 1
end

year_count.each do |year, count|
  puts "#{year}, #{count}"
end

p year_count.values.inject{|sum, x| sum + x}