script_levenshtein.rb

#!/usr/bin/env ruby

require 'rubygems'
require 'levenshtein'
require 'csv'

# Config
counter = 0
maxError = 3
inFile = 'entrada.csv'
outFile = 'salida.csv'
total = 0

# Extending String class for blank? method
class String
  def blank?
    self.strip.empty?
  end
end

# Formatting strings
def format_string str
  str.upcase.strip
end

# Does name has a "DE" inside?
def has_de? str
  str.include? " DE "
end

# Calculate Distance between two strings (te, ifarhu)
def calculate_distance te, ifarhu
  distance = 99
  ifarhuParts = ifarhu.split(" ")

  if ifarhuParts.length == 4 and !has_de? ifarhu
    # El nombre del IFARHU tiene 4 partes y ningun "DE"
    clearedName = "#{ifarhuParts[0]} #{ifarhuParts[2]}"
    distance = Levenshtein.distance te, clearedName
  elsif ifarhuParts.length == 3 and !has_de? ifarhu
    # El nombre del IFARHU tiene 3 partes y ningun "DE"
    clearedName = "#{ifarhuParts[0]} #{ifarhuParts[1]}"
    distance = Levenshtein.distance te, clearedName
  elsif te.blank? or ifarhu.blank?
    # El nombre del TE o del IFARHU viene vacio
    distance = 99
  elsif has_de? ifarhu
    # El nombre tiene "DE" en algun lado
    teParts = te.split(" ")
    distance = Levenshtein.distance teParts[0], ifarhuParts[0]
  else
    # El resto
    distance = Levenshtein.distance te, ifarhu
  end

  distance
end

# In
lines = CSV.read(inFile)
lines.each do |line|
  id        = format_string line[0]
  tribunal  = format_string line[1]
  ifarhu   	= format_string line[2]

  line[0] = id
  line[1] = tribunal
  line[2] = ifarhu

  distance = calculate_distance tribunal, ifarhu

  line << distance
end

# Out
CSV.open(outFile, 'w') do |csv|
  lines.each do |line|
    total = total + 1
    counter = counter + 1 if line[3] <= maxError
    csv << line
  end
end

# Print
p "Total: #{total}"
p "Corregidos: #{counter}"
p "Con error: #{total - counter}"