Last active
September 15, 2022 22:03
-
-
Save vdinovi/a75f7145d89468f738a39a64572ca2d2 to your computer and use it in GitHub Desktop.
This file contains hidden or 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
| #!/usr/bin/ruby | |
| require 'set' | |
| require 'csv' | |
| ARGV.count > 2 or raise "Usage: compare_csv <key>:<filename> <key>:<filename> <col:col> ..." | |
| k1, f1 = ARGV[0].split(':') | |
| k2, f2 = ARGV[1].split(':') | |
| cols = ARGV[2..].map { |c| c.split(':') } | |
| rows1, rows2 = [ | |
| [k1, f1], | |
| [k2, f2] | |
| ].map do |(key, filename)| | |
| CSV.foreach(File.expand_path(filename), headers: true).with_index(1).reduce({}) do |rows, (row, lineno)| | |
| if (id = row[key]) | |
| rows[id] = row.to_h | |
| else | |
| #puts "Error: row on line #{lineno} of #{filename} is missing index key #{key}" | |
| nil | |
| end | |
| rows | |
| end | |
| end | |
| def normalize(value) | |
| case value | |
| when String | |
| if value.empty? | |
| nil | |
| elsif value == "0" || value =~ /false/i | |
| false | |
| elsif value == "1" || value =~ /true/i | |
| true | |
| else | |
| value | |
| end | |
| when nil | |
| nil | |
| else | |
| raise NotImplementedError | |
| end | |
| end | |
| (rows1.keys | rows2.keys).each do |key| | |
| if !rows1.has_key?(key) | |
| #puts "Error: file #{f1} has no row with key #{key}" | |
| nil | |
| elsif !rows2.has_key?(key) | |
| #puts "Error: file #{f2} has no row with key #{key}" | |
| nil | |
| else | |
| r1 = rows1[key] | |
| r2 = rows2[key] | |
| diff = cols.reduce({}) do |diff, (c1, c2)| | |
| if (v1 = normalize(r1[c1])) != (v2 = normalize(r2[c2])) | |
| diff[[c1, c2]] = [v1, v2] | |
| end | |
| diff | |
| end | |
| unless diff.empty? | |
| puts "Error: rows for key #{key} differ (#{diff.inspect})" | |
| else | |
| puts "Rows for key #{key} matched" | |
| end | |
| end | |
| end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment