Complete index and query solution. Naively implemented with nested loops.

index-and-query.rb

#!/usr/bin/ruby

require 'rubygems'
require 'fast_stemmer'

def doc_prep(docs)
  prepped_docs = {}
	doc_id = 0
	stop_words = "a,able,about,across,after,all,almost,also,am,among,an,and,any,are,as,at,be,because,been,but,by,can,cannot,could,dear,did,do,does,either,else,ever,every,for,from,get,got,had,has,have,he,her,hers,him,his,how,however,i,if,in,into,is,it,its,just,least,let,like,likely,may,me,might,most,must,my,neither,no,nor,not,of,off,often,on,only,or,other,our,own,rather,said,say,says,she,should,since,so,some,than,that,the,their,them,then,there,these,they,this,tis,to,too,twas,us,wants,was,we,were,what,when,where,which,while,who,whom,why,will,with,would,yet,you,your,use,used".split(',')

	docs.each do |doc|
		doc_id += 1
		unstemmed_words =  doc.gsub(/[[:punct:]]/, '').downcase.split.select { |word| !stop_words.include?(word) }
		stemmed_words = []
		unstemmed_words.each { |word| stemmed_words << word.stem }
		prepped_docs[doc_id] = stemmed_words
	end

	return prepped_docs
end

def create_dictionary_and_postings(docs)
	dictionary = {}
	postings = 
	term_id = 0
	docs.each do |doc_id, doc|
		words_in_this_doc = []
		doc.each do |word|
			symbolized_word = word.to_sym
			if dictionary.has_key?(symbolized_word)
				dictionary[symbolized_word][:cf] += 1
				if !words_in_this_doc.include?(symbolized_word)
					words_in_this_doc << symbolized_word
					dictionary[symbolized_word][:df] += 1
					dictionary[symbolized_word][:postings] << {doc_id: doc_id, tf: 1}
				else
					dictionary[symbolized_word][:postings].each do |posting|
						posting[:tf] = posting[:tf] += 1 if posting[:doc_id] == doc_id
					end
				end	
			else
				dictionary[symbolized_word] = {term_id: term_id += 1, cf: 1, df: 1, postings: [{doc_id: doc_id, tf: 1}]}
				words_in_this_doc << symbolized_word
			end
		end
	end

	return dictionary
end


docs = []
ARGV.each do |doc|
	docs << doc
end
docs = doc_prep(docs)
index = create_dictionary_and_postings(docs)

###################
### index AND query
###################
puts "index AND query"

term_1 = "index".stem.to_sym
term_1_hits = index[term_1][:postings]
term_2 = "query".stem.to_sym
term_2_hits = index[term_2][:postings]
document_hits = []
term_1_hits.each do |l_posting|
	term_2_hits.each do |r_posting|
		document_hits << r_posting[:doc_id] if l_posting[:doc_id] == r_posting[:doc_id]
	end
end
puts "hit list: #{document_hits.sort.inspect}"

###################
### (search AND query) OR (search AND retrieve)
###################
puts "(search AND query) OR (search AND retrieve)"

# search AND query
term_1 = "search".stem.to_sym
term_1_hits = index[term_1][:postings]
term_2 = "query".stem.to_sym
term_2_hits = index[term_2][:postings]
document_hits_1 = []
term_1_hits.each do |l_posting|
	term_2_hits.each do |r_posting|
		document_hits_1 << r_posting[:doc_id] if l_posting[:doc_id] == r_posting[:doc_id]
	end
end

# search AND retrieve
term_1 = "search".stem.to_sym
term_1_hits = index[term_1][:postings]
term_2 = "retrieve".stem.to_sym
term_2_hits = index[term_2][:postings]
document_hits_2 = []
term_1_hits.each do |l_posting|
	term_2_hits.each do |r_posting|
		document_hits_2 << r_posting[:doc_id] if l_posting[:doc_id] == r_posting[:doc_id]
	end
end

# (search AND query) OR (search AND retrieve)
document_hits = document_hits_1.concat(document_hits_2).uniq.sort
puts "hit list: #{document_hits.inspect}"

###################
### (search AND engine AND web) OR feedback
###################
puts "(search AND engine AND web) OR feedback"

#search AND engine AND web
term_1 = "search".stem.to_sym
term_1_hits = index[term_1][:postings]
term_2 = "engine".stem.to_sym
term_2_hits = index[term_2][:postings]
term_3 = "web".stem.to_sym
term_3_hits = index[term_3][:postings]
document_hits_1 = []
term_1_hits.each do |l_posting|
	term_2_hits.each do |m_posting|
		if l_posting[:doc_id] == m_posting[:doc_id]
			term_3_hits.each do |r_posting|
				document_hits_1 << r_posting[:doc_id] if m_posting[:doc_id] == r_posting[:doc_id]
			end
		end
	end
end

#feedback
term_1 = "feedback".stem.to_sym
term_1_hits = index[term_1][:postings]
document_hits_2 = []
term_1_hits.each { |posting| document_hits_2 << posting[:doc_id]}

# (search AND engine AND web) OR feedback
document_hits = document_hits_1.concat(document_hits_2).uniq.sort
puts "hit list: #{document_hits.inspect}"

###################
### (index OR cluster) AND (web OR system)
###################
puts "(index OR cluster) AND (web OR system)"

# (index OR cluster)
term_1 = "index".stem.to_sym
term_1_hits = index[term_1][:postings]
document_hits_1 = []
term_1_hits.each { |posting| document_hits_1 << posting[:doc_id]}
term_2 = "cluster".stem.to_sym
term_2_hits = index[term_2][:postings]
document_hits_2 = []
term_2_hits.each { |posting| document_hits_2 << posting[:doc_id]}
document_hits_l = document_hits_1.concat(document_hits_2).uniq.sort

# (web OR system)
term_1 = "web".stem.to_sym
term_1_hits = index[term_1][:postings]
document_hits_1 = []
term_1_hits.each { |posting| document_hits_1 << posting[:doc_id]}
term_2 = "system".stem.to_sym
term_2_hits = index[term_2][:postings]
document_hits_2 = []
term_2_hits.each { |posting| document_hits_2 << posting[:doc_id]}
document_hits_r = document_hits_1.concat(document_hits_2).uniq.sort

# (index OR cluster) AND (web OR system)
document_hits = []
document_hits_l.each do |l_posting|
	document_hits_r.each do |r_posting|
		document_hits << r_posting if l_posting == r_posting
	end
end

document_hits = document_hits.uniq.sort
puts "hit list: #{document_hits.inspect}"