concordance

concordance.rb

TEXT = 'Given an arbitrary text document written in English, write a program
that will generate a concordance, i.e. an alphabetical list of all word
occurrences, labeled with word frequencies. Bonus: label each word with the
sentence numbers in which each occurrence appeared.'

def concordance1(string)
  result = {}
  string.split(".").each_with_index do |sentence, index|
    sentence.gsub(",", "").split(" ").each do |word|
      word = word.downcase
      result[word] ||= [0, []]
      result[word][0] += 1
      result[word][1] << index + 1
    end
  end
  result
end

def concordance2(string)
  result = {}
  string.gsub(/(i)\.(e)\./, 'i{dot}e{dot}').split('.').each_with_index do |sentence, index|
    sentence.gsub(',','').split(' ').each do |word|
      word = word.gsub(/{dot}/, '.').downcase
      result[word] ||= [0, []]
      result[word][0] += 1
      result[word][1] << index + 1
    end
  end
  result
end

def concordance3(string)
  result = {}
  string.gsub(/[.,\/#!$%,;]/, '').split('.').each_with_index do |sentence, index|
    sentence.split(' ').each do |word|
      word = word.downcase
      result[word] ||= [0, []]
      result[word][0] += 1
      result[word][1] << index + 1
    end
  end
  result
end

def format(collection)
  result = ''
  collection.sort_by { |k, _| k }.each do |pair|
    result << "#{pair[0]} {#{pair[1][0]}:#{pair[1][1].join(',')}}\n" if pair
  end
  result
end

puts
result = concordance1(TEXT)
puts format(result)
=begin

a {2:1,1}
all {1:3}
alphabetical {1:3}
an {2:1,3}
appeared {1:4}
arbitrary {1:1}
bonus: {1:4}
concordance {1:1}
document {1:1}
e {1:2}
each {2:4,4}
english {1:1}
frequencies {1:3}
generate {1:1}
given {1:1}
i {1:1}
in {2:1,4}
label {1:4}
labeled {1:3}
list {1:3}
numbers {1:4}
occurrence {1:4}
occurrences {1:3}
of {1:3}
program {1:1}
sentence {1:4}
text {1:1}
that {1:1}
the {1:4}
which {1:4}
will {1:1}
with {2:3,4}
word {3:3,3,4}
write {1:1}
written {1:1}

=end

puts
result = concordance2(TEXT)
puts format(result)
=begin

a {2:1,1}
all {1:1}
alphabetical {1:1}
an {2:1,1}
appeared {1:2}
arbitrary {1:1}
bonus: {1:2}
concordance {1:1}
document {1:1}
each {2:2,2}
english {1:1}
frequencies {1:1}
generate {1:1}
given {1:1}
i.e. {1:1}
in {2:1,2}
label {1:2}
labeled {1:1}
list {1:1}
numbers {1:2}
occurrence {1:2}
occurrences {1:1}
of {1:1}
program {1:1}
sentence {1:2}
text {1:1}
that {1:1}
the {1:2}
which {1:2}
will {1:1}
with {2:1,2}
word {3:1,1,2}
write {1:1}
written {1:1}

=end

puts
result = concordance3(TEXT)
puts format(result)
=begin

a {2:1,1}
all {1:1}
alphabetical {1:1}
an {2:1,1}
appeared {1:1}
arbitrary {1:1}
bonus: {1:1}
concordance {1:1}
document {1:1}
each {2:1,1}
english {1:1}
frequencies {1:1}
generate {1:1}
given {1:1}
ie {1:1}
in {2:1,1}
label {1:1}
labeled {1:1}
list {1:1}
numbers {1:1}
occurrence {1:1}
occurrences {1:1}
of {1:1}
program {1:1}
sentence {1:1}
text {1:1}
that {1:1}
the {1:1}
which {1:1}
will {1:1}
with {2:1,1}
word {3:1,1,1}
write {1:1}
written {1:1}

=end