csv_monster 0.1.0

data/.gitignore

@@ -0,0 +1 @@
+*.gem

data/Gemfile

@@ -0,0 +1,8 @@
+source 'https://rubygems.org'
+
+group :test do
+  gem 'rspec'
+end
+
+# Specify your gem's dependencies in csv_monster.gemspec
+gemspec

data/Gemfile.lock

@@ -0,0 +1,26 @@
+PATH
+  remote: .
+  specs:
+    csv_monster (0.0.1)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    diff-lcs (1.2.4)
+    rake (10.0.4)
+    rspec (2.13.0)
+      rspec-core (~> 2.13.0)
+      rspec-expectations (~> 2.13.0)
+      rspec-mocks (~> 2.13.0)
+    rspec-core (2.13.1)
+    rspec-expectations (2.13.0)
+      diff-lcs (>= 1.1.3, < 2.0)
+    rspec-mocks (2.13.1)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  csv_monster!
+  rake
+  rspec

data/LICENSE

@@ -0,0 +1,22 @@
+Copyright (c) 2012 Jeff Iacono, Joe Prang & Square Inc.
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,18 @@
+# CSVMonster
+
+```ruby
+require './lib/csv_monster'
+
+first  = CSVMonster.new 'first.csv'
+second = CSVMonster.new 'second.csv'
+parts  = CSVMonster.new ['first.csv', 'second.csv']
+whole  = CSVMonster.new 'first_and_second_already_combined.csv'
+
+# using the + operator
+puts (whole == (first + second)) ? "matchy!" : "no matchy!"
+
+# using the initializer
+puts "whole contains #{whole.content_length} records"
+puts "parts contain #{parts.content_length} records"
+puts whole == parts ? "matchy!" : "no matchy!"
+```

data/Rakefile

@@ -0,0 +1,13 @@
+#!/usr/bin/env rake
+require "bundler/gem_tasks"
+begin
+  require 'rspec/core/rake_task'
+
+  RSpec::Core::RakeTask.new(:spec) do |t|
+    t.rspec_opts = '-b'
+  end
+
+  task default: :spec
+rescue LoadError
+  $stderr.puts "rspec not available, spec task not provided"
+end

data/TODO.md

@@ -0,0 +1,17 @@
+# TODO
+
+### add split method
+Add in a #split method that takes an integer and splits its content into that
+many equal parts and writes each.
+
+Example:
+
+```ruby
+e = ExtendedCSV.new 'somefile.csv' # 1 header + 20 rows
+e.split(4)
+#=> wrote 4 different files:
+#     - somefile_1.csv # 1 header + 5 rows
+#     - somefile_2.csv # 1 header + 5 rows
+#     - somefile_3.csv # 1 header + 5 rows
+#     - somefile_4.csv # 1 header + 5 rows
+```

data/csv_monster.gemspec

@@ -0,0 +1,19 @@
+require File.expand_path('../lib/csv_monster/version', __FILE__)
+
+Gem::Specification.new do |gem|
+  gem.authors       = ["Jeff Iacono", "Joe Prang"]
+  gem.email         = ["jeff.iacono@gmail.com", "joseph.prang@gmail.com"]
+  gem.summary       = "A monster of a CSV util"
+  gem.description   = "A set of utils for working with CSV files"
+  gem.homepage      = ''
+  gem.license       = 'MIT'
+  gem.name          = 'csv_monster'
+  gem.date          = '2013-06-19'
+  gem.version       = CSVMonster::VERSION
+  gem.require_paths = ["lib"]
+  gem.files         = `git ls-files`.split($\)
+  gem.test_files    = gem.files.grep(%r{^(test|spec|features)/})
+
+  gem.add_development_dependency "rake"
+  gem.add_development_dependency "rspec", [">= 2"]
+end

data/lib/csv_monster/version.rb

@@ -0,0 +1,3 @@
+class CSVMonster
+  VERSION = "0.1.0"
+end

data/lib/csv_monster.rb

@@ -0,0 +1,75 @@
+require 'csv'
+require 'csv_monster/version'
+
+class CSVMonster
+  attr_reader :filepaths
+
+  def initialize filepaths = nil
+    self.filepaths = filepaths
+  end
+
+  def filepaths= filepaths
+    @filepaths = [*filepaths]
+  end
+
+  def + other_csv_monster
+    self.class.new self.filepaths + other_csv_monster.filepaths
+  end
+
+  def == other_csv_monster
+    content == other_csv_monster.content
+  end
+
+  def content
+    return @content if defined? @content
+
+    @content ||= []
+    @filepaths.each_with_index do |csv_filepath, i|
+      csv = CSV.parse(File.read(csv_filepath))
+      csv.shift unless i == 0
+
+      csv.each do |row|
+        @content << row
+      end
+    end
+
+    @content
+  end
+
+  def content_length
+    content.length
+  end
+
+  def split split_count
+    header, *tail = self.content
+    splits = []
+
+    tail.each_with_index do |row, i|
+      if (i % (tail.length / split_count)).zero? && split_count > splits.length
+        splits << self.class.new
+        splits.last.content << header
+      end
+
+      splits.last.content << row
+    end
+
+    splits
+  end
+
+  def write! outfile = nil
+    outfile ||= default_outfile_name
+    CSV.open(outfile, "wb") do |csv|
+      content.each do |row|
+        csv << row
+      end
+    end
+
+    puts "wrote #{content.length} rows to #{outfile}"
+  end
+
+private
+
+  def default_outfile_name
+    "#{Time.now.strftime("%Y%m%d%H%M%S")}_#{@filepaths.length}_files.csv"
+  end
+end

data/spec/csv_monster_spec.rb

@@ -0,0 +1,214 @@
+require './lib/csv_monster'
+
+def sample_csv_filepath
+  File.expand_path(File.join("..", "support", "sample.csv"), __FILE__)
+end
+
+def another_sample_csv_filepath
+  File.expand_path(File.join("..", "support", "another_sample.csv"), __FILE__)
+end
+
+def odd_number_of_records_csv_filepath
+  File.expand_path(File.join("..", "support", "odd_number_of_records.csv"), __FILE__)
+end
+
+def safely_rm file
+  FileUtils.rm file if File.exists? file
+end
+
+describe CSVMonster do
+  describe "#+" do
+    let(:csv_monster)         { described_class.new sample_csv_filepath }
+    let(:another_csv_monster) { described_class.new another_sample_csv_filepath }
+
+    subject { csv_monster +  another_csv_monster }
+
+    it "yields a new instance with the combination of the two's content" do
+      expect(csv_monster.content).to eq [["header_1", "header_2"],
+                                          ["row_1_column_1_entry", "row_1_column_2_entry"],
+                                          ["row_2_column_1_entry", "row_2_column_2_entry"]]
+
+      expect(another_csv_monster.content).to eq [["header_1", "header_2"],
+                                                  ["row_1_column_1_entry_diff_content", "row_1_column_2_entry_diff_content"],
+                                                  ["row_2_column_1_entry_diff_content", "row_2_column_2_entry_diff_content"]]
+
+      result = subject
+
+      expect(csv_monster.content).to eq [["header_1", "header_2"],
+                                          ["row_1_column_1_entry", "row_1_column_2_entry"],
+                                          ["row_2_column_1_entry", "row_2_column_2_entry"]]
+
+      expect(another_csv_monster.content).to eq [["header_1", "header_2"],
+                                                  ["row_1_column_1_entry_diff_content", "row_1_column_2_entry_diff_content"],
+                                                  ["row_2_column_1_entry_diff_content", "row_2_column_2_entry_diff_content"]]
+
+      expect(result.content).to eq [["header_1", "header_2"],
+                                    ["row_1_column_1_entry", "row_1_column_2_entry"],
+                                    ["row_2_column_1_entry", "row_2_column_2_entry"],
+                                    ["row_1_column_1_entry_diff_content", "row_1_column_2_entry_diff_content"],
+                                    ["row_2_column_1_entry_diff_content", "row_2_column_2_entry_diff_content"]]
+    end
+  end
+
+  describe "#==" do
+    let(:csv_monster)         { described_class.new }
+    let(:another_csv_monster) { described_class.new }
+
+    context "when the content is the same" do
+      before do
+        csv_monster.filepaths         = sample_csv_filepath
+        another_csv_monster.filepaths = sample_csv_filepath
+      end
+
+      subject { csv_monster == another_csv_monster }
+      it      { expect(subject).to be_true }
+    end
+
+    context "when the content is different" do
+      before do
+        csv_monster.filepaths         = sample_csv_filepath
+        another_csv_monster.filepaths = another_sample_csv_filepath
+      end
+
+      subject { csv_monster == another_csv_monster }
+      it      { expect(subject).to be_false }
+    end
+  end
+
+  describe "#content" do
+    let(:csv_monster) { described_class.new }
+
+    context "with a single csv file" do
+      before  { csv_monster.filepaths = sample_csv_filepath }
+      subject { csv_monster.content }
+      it      { expect(subject).to eq [["header_1", "header_2"],
+                                       ["row_1_column_1_entry", "row_1_column_2_entry"],
+                                       ["row_2_column_1_entry", "row_2_column_2_entry"]] }
+    end
+
+    context "with multiple csv files" do
+      before  { csv_monster.filepaths = [sample_csv_filepath, another_sample_csv_filepath] }
+      subject { csv_monster.content }
+
+      it "combines the content, removing headers from all but the first" do
+        expect(subject).to eq [["header_1", "header_2"],
+                               ["row_1_column_1_entry", "row_1_column_2_entry"],
+                               ["row_2_column_1_entry", "row_2_column_2_entry"],
+                               ["row_1_column_1_entry_diff_content", "row_1_column_2_entry_diff_content"],
+                               ["row_2_column_1_entry_diff_content", "row_2_column_2_entry_diff_content"]]
+      end
+    end
+  end
+
+  describe "#content_length" do
+    let(:csv_monster) { described_class.new sample_csv_filepath }
+    subject            { csv_monster.content_length }
+
+    it "equals the number of entries" do
+      expect(subject).to eq 3
+    end
+  end
+
+  describe "#split" do
+    let(:number_of_splits) { 2 }
+
+    context "with an even number of records (excluding header)" do
+      let(:csv_monster) { described_class.new sample_csv_filepath }
+
+      subject { csv_monster.split(number_of_splits) }
+
+      it "leaves the original instance unchanged" do
+        expect(csv_monster.content).to eq [["header_1", "header_2"],
+                                            ["row_1_column_1_entry", "row_1_column_2_entry"],
+                                            ["row_2_column_1_entry", "row_2_column_2_entry"]]
+
+        subject
+
+        expect(csv_monster.content).to eq [["header_1", "header_2"],
+                                            ["row_1_column_1_entry", "row_1_column_2_entry"],
+                                            ["row_2_column_1_entry", "row_2_column_2_entry"]]
+      end
+
+      it "returns the specified number of objects of the same type" do
+        result = subject
+
+        expect(result.length).to eq number_of_splits
+
+        expect(result[0]).to be_an_instance_of described_class
+        expect(result[1]).to be_an_instance_of described_class
+      end
+
+
+      it "splits the content amongst the parts evenly" do
+        result = subject
+
+        expect(result[0].content).to eq [["header_1", "header_2"],
+                                         ["row_1_column_1_entry", "row_1_column_2_entry"]]
+
+        expect(result[1].content).to eq [["header_1", "header_2"],
+                                         ["row_2_column_1_entry", "row_2_column_2_entry"]]
+      end
+    end
+
+    context "with an odd number of records (excluding header)" do
+      let(:csv_monster) { described_class.new odd_number_of_records_csv_filepath }
+
+      subject { csv_monster.split(number_of_splits) }
+
+      it "leaves the original instance unchanged" do
+        expect(csv_monster.content).to eq [["header_1", "header_2"],
+                                            ["odd_row_1_column_1_entry", "odd_row_1_column_2_entry"],
+                                            ["odd_row_2_column_1_entry", "odd_row_2_column_2_entry"],
+                                            ["odd_row_3_column_1_entry", "odd_row_3_column_2_entry"],
+                                            ["odd_row_4_column_1_entry", "odd_row_4_column_2_entry"],
+                                            ["odd_row_5_column_1_entry", "odd_row_5_column_2_entry"]]
+
+        subject
+
+        expect(csv_monster.content).to eq [["header_1", "header_2"],
+                                           ["odd_row_1_column_1_entry", "odd_row_1_column_2_entry"],
+                                           ["odd_row_2_column_1_entry", "odd_row_2_column_2_entry"],
+                                           ["odd_row_3_column_1_entry", "odd_row_3_column_2_entry"],
+                                           ["odd_row_4_column_1_entry", "odd_row_4_column_2_entry"],
+                                           ["odd_row_5_column_1_entry", "odd_row_5_column_2_entry"]]
+      end
+
+      it "returns the specified number of objects of the same type" do
+        result = subject
+        expect(result.length).to eq number_of_splits
+        expect(result[0]).to be_an_instance_of described_class
+        expect(result[1]).to be_an_instance_of described_class
+      end
+
+      it "splits the content amongst the parts approximately evenly" do
+        result = subject
+
+        expect(result[0].content).to eq [["header_1", "header_2"],
+                                         ["odd_row_1_column_1_entry", "odd_row_1_column_2_entry"],
+                                         ["odd_row_2_column_1_entry", "odd_row_2_column_2_entry"]]
+
+        expect(result[1].content).to eq [["header_1", "header_2"],
+                                         ["odd_row_3_column_1_entry", "odd_row_3_column_2_entry"],
+                                         ["odd_row_4_column_1_entry", "odd_row_4_column_2_entry"],
+                                         ["odd_row_5_column_1_entry", "odd_row_5_column_2_entry"]]
+      end
+    end
+  end
+
+  describe "#write!" do
+    let(:infile)      { sample_csv_filepath }
+    let(:outfile)     { File.expand_path(File.join("..", "support", "test", "write_sample.csv"), __FILE__) }
+    let(:csv_monster) { described_class.new infile }
+
+    before  { safely_rm outfile }
+    after   { safely_rm outfile }
+
+    subject { csv_monster.write! outfile }
+
+    it "writes the file to the specified location" do
+      expect(File.exists? outfile).to be_false
+      subject
+      expect(FileUtils.identical? infile, outfile).to be_true
+    end
+  end
+end

data/spec/support/another_sample.csv

@@ -0,0 +1,3 @@
+header_1,header_2
+row_1_column_1_entry_diff_content,row_1_column_2_entry_diff_content
+row_2_column_1_entry_diff_content,row_2_column_2_entry_diff_content

data/spec/support/odd_number_of_records.csv

@@ -0,0 +1,6 @@
+header_1,header_2
+odd_row_1_column_1_entry,odd_row_1_column_2_entry
+odd_row_2_column_1_entry,odd_row_2_column_2_entry
+odd_row_3_column_1_entry,odd_row_3_column_2_entry
+odd_row_4_column_1_entry,odd_row_4_column_2_entry
+odd_row_5_column_1_entry,odd_row_5_column_2_entry

data/spec/support/sample.csv

@@ -0,0 +1,3 @@
+header_1,header_2
+row_1_column_1_entry,row_1_column_2_entry
+row_2_column_1_entry,row_2_column_2_entry

metadata

@@ -0,0 +1,100 @@
+--- !ruby/object:Gem::Specification
+name: csv_monster
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+  prerelease: 
+platform: ruby
+authors:
+- Jeff Iacono
+- Joe Prang
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-06-19 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '2'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '2'
+description: A set of utils for working with CSV files
+email:
+- jeff.iacono@gmail.com
+- joseph.prang@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- Gemfile.lock
+- LICENSE
+- README.md
+- Rakefile
+- TODO.md
+- csv_monster.gemspec
+- lib/csv_monster.rb
+- lib/csv_monster/version.rb
+- spec/csv_monster_spec.rb
+- spec/support/another_sample.csv
+- spec/support/odd_number_of_records.csv
+- spec/support/sample.csv
+- spec/support/test/.gitkeep
+homepage: ''
+licenses:
+- MIT
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.21
+signing_key: 
+specification_version: 3
+summary: A monster of a CSV util
+test_files:
+- spec/csv_monster_spec.rb
+- spec/support/another_sample.csv
+- spec/support/odd_number_of_records.csv
+- spec/support/sample.csv
+- spec/support/test/.gitkeep