Last active
August 14, 2017 15:27
-
-
Save iamcarrico/bc32e546b3a08f77946fecf39c154ba5 to your computer and use it in GitHub Desktop.
A little converter for the pieces I need to change a csv of addresses to their long-form
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
addresses.csv | |
export.csv |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
require 'csv' | |
input_file = "addresses.csv" | |
output_file = "export.csv" | |
word_replacements = [ | |
# States | |
["AK", "Alaska"], | |
["AL", "Alabama"], | |
["AR", "Arkansas"], | |
["AS", "American Samoa"], | |
["AZ", "Arizona"], | |
["CA", "California"], | |
["CO", "Colorado"], | |
["CT", "Connecticut"], | |
["DC", "District of Columbia"], | |
["DE", "Delaware"], | |
["FL", "Florida"], | |
["GA", "Georgia"], | |
["GU", "Guam"], | |
["HI", "Hawaii"], | |
["IA", "Iowa"], | |
["ID", "Idaho"], | |
["IL", "Illinois"], | |
["IN", "Indiana"], | |
["KS", "Kansas"], | |
["KY", "Kentucky"], | |
["LA", "Louisiana"], | |
["MA", "Massachusetts"], | |
["MD", "Maryland"], | |
["ME", "Maine"], | |
["MI", "Michigan"], | |
["MN", "Minnesota"], | |
["MO", "Missouri"], | |
["MS", "Mississippi"], | |
["MT", "Montana"], | |
["NC", "North Carolina"], | |
["ND", "North Dakota"], | |
["NE", "Nebraska"], | |
["NH", "New Hampshire"], | |
["NJ", "New Jersey"], | |
["NM", "New Mexico"], | |
["NV", "Nevada"], | |
["NY", "New York"], | |
["OH", "Ohio"], | |
["OK", "Oklahoma"], | |
["OR", "Oregon"], | |
["PA", "Pennsylvania"], | |
["PR", "Puerto Rico"], | |
["RI", "Rhode Island"], | |
["SC", "South Carolina"], | |
["SD", "South Dakota"], | |
["TN", "Tennessee"], | |
["TX", "Texas"], | |
["UT", "Utah"], | |
["VA", "Virginia"], | |
["VI", "Virgin Islands"], | |
["VT", "Vermont"], | |
["WA", "Washington"], | |
["WI", "Wisconsin"], | |
["WV", "West Virginia"], | |
["WY", "Wyoming"], | |
# Cardinal directions | |
["W", "West"], | |
["E", "East"], | |
["N", "North"], | |
["S", "South"], | |
["SE", "Southeast"], | |
["SW", "Southwest"], | |
["NE", "Northeast"], | |
["NW", "Northwest"], | |
# Street things | |
["DR", "Drive"], | |
["LN", "Lane"], | |
["ST", "Street"], | |
["CT", "Court"], | |
["PL", "Place"], | |
["AVE", "Avenue"], | |
["RD", "Road"], | |
["HL", "Hill"], | |
["BLVD", "Boulevard"], | |
["PL", "Place"], | |
["TER", "Place"], | |
["CIR", "Circle"], | |
["KPN", "Key Peninsula North"], | |
["CV", "Cove"], | |
["BLF", "Bluff"], | |
# Cities | |
["FT", "Fort"], | |
# Apartments and such. | |
["APT", "Apartment"], | |
["STE", "Suite"], | |
] | |
File.delete(output_file) | |
output = [] | |
CSV.foreach(input_file) do |row| | |
# The names | |
names = row.shift | |
column_number = 0 | |
row = row.map do |text| | |
column_number += 1 | |
if text.is_a?(String) | |
text = text.split(/ |\_/).map{ |word| | |
if text.is_a?(String) | |
word_replacements.each do | replace, replacement | | |
word.gsub!(Regexp.new(/^#{Regexp.escape(replace)}$/), replacement) | |
end | |
# Werid thing, CT is both Connecticut and Court— luckily unless we | |
# are on the state box, we don't care about Connecticut | |
if column_number != 4 | |
word.gsub!(/^Connecticut$/, "Court") | |
end | |
word = word.split.map(&:capitalize).join(' ') | |
word.gsub!("Usa", "United States") | |
end | |
word | |
}.join(" ") | |
text.gsub!("Po Box", "PO Box") | |
end | |
text | |
end | |
row.unshift(names) | |
output << row | |
end | |
CSV.open(output_file, "a+") do |csv| | |
output.each do |line| | |
csv << line | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment