group_by_stemming.rb

require "rubygems"
require "lingua/stemmer"

stemmer = Lingua::Stemmer.new

tag_counts = {}
STDIN.lines.each{|l| c, t = l.split; tag_counts[t.strip] = c.to_i }

duplicates = Hash.new{|h, k| h[k] = []}
tag_counts.keys.each{|k| duplicates[k.split("_").map{|x| stemmer.stem(x)}] << k }
duplicates.values.each{|vs| vs.sort!{|x, y| tag_counts[y] <=> tag_counts[x]} }

new_tag_counts = {}
duplicates.values.each{|vs| new_tag_counts[vs[0]] = vs.map{|v| tag_counts[v]}.inject(0, &:+)}
puts new_tag_counts.to_a.sort{|x, y| y[1] <=> x[1]}.map{|t, c| "    #{c}  #{t}" }