csv-importer 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 452e11ff0f75dce583a2034fde100790e0327508
+  data.tar.gz: 09230194e20902779a053687122249ea7fd612ef
+SHA512:
+  metadata.gz: 0960dc9c1f6a8880c7ef7bf6ce83f2f38bd0c297be95890a22982fd0e6789f6fbcb4925f078538162c5cfcef0efdcc89bd06b7ff8f74c6e5e40b7b8c6bdb050d
+  data.tar.gz: 419168d5231b7a08a827090fdbed9c0bfe95df8d5d6e5900f024d7e3f736e1671803913ef22ffef3fbba9b8e409bb66852136c70da76b13b1908f179a5d6b6ee

data/.gitignore

@@ -0,0 +1,10 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+.DS_Store

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.travis.yml

@@ -0,0 +1,6 @@
+language: ruby
+rvm:
+  - 2.2.1
+addons:
+  code_climate:
+    repo_token: 0e005c563813539e6d0cdca9a3e95b3c0f1c79f32284f8eaa93b54c57303d427

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,13 @@
+# Contributor Code of Conduct
+
+As contributors and maintainers of this project, we pledge to respect all people who contribute through reporting issues, posting feature requests, updating documentation, submitting pull requests or patches, and other activities.
+
+We are committed to making participation in this project a harassment-free experience for everyone, regardless of level of experience, gender, gender identity and expression, sexual orientation, disability, personal appearance, body size, race, age, or religion.
+
+Examples of unacceptable behavior by participants include the use of sexual language or imagery, derogatory comments or personal attacks, trolling, public or private harassment, insults, or other unprofessional conduct.
+
+Project maintainers have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct. Project maintainers who do not follow the Code of Conduct may be removed from the project team.
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be reported by opening an issue or contacting one or more of the project maintainers.
+
+This Code of Conduct is adapted from the [Contributor Covenant](http:contributor-covenant.org), version 1.0.0, available at [http://contributor-covenant.org/version/1/0/0/](http://contributor-covenant.org/version/1/0/0/)

data/Gemfile

@@ -0,0 +1,10 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in csv-importer.gemspec
+gemspec
+
+gem 'rspec'
+gem 'guard-rspec'
+gem 'activemodel'
+gem 'simplecov', require: nil
+gem "codeclimate-test-reporter", require: nil

data/Guardfile

@@ -0,0 +1,53 @@
+# A sample Guardfile
+# More info at https://github.com/guard/guard#readme
+
+## Uncomment and set this to only include directories you want to watch
+# directories %w(app lib config test spec features)
+
+## Uncomment to clear the screen before every task
+# clearing :on
+
+## Guard internally checks for changes in the Guardfile and exits.
+## If you want Guard to automatically start up again, run guard in a
+## shell loop, e.g.:
+##
+##  $ while bundle exec guard; do echo "Restarting Guard..."; done
+##
+## Note: if you are using the `directories` clause above and you are not
+## watching the project directory ('.'), then you will want to move
+## the Guardfile to a watched dir and symlink it back, e.g.
+#
+#  $ mkdir config
+#  $ mv Guardfile config/
+#  $ ln -s config/Guardfile .
+#
+# and, you'll have to watch "config/Guardfile" instead of "Guardfile"
+
+# Note: The cmd option is now required due to the increasing number of ways
+#       rspec may be run, below are examples of the most common uses.
+#  * bundler: 'bundle exec rspec'
+#  * bundler binstubs: 'bin/rspec'
+#  * spring: 'bin/rspec' (This will use spring if running and you have
+#                          installed the spring binstubs per the docs)
+#  * zeus: 'zeus rspec' (requires the server to be started separately)
+#  * 'just' rspec: 'rspec'
+
+guard :rspec, cmd: "bundle exec rspec" do
+  require "guard/rspec/dsl"
+  dsl = Guard::RSpec::Dsl.new(self)
+
+  # Feel free to open issues for suggestions and improvements
+
+  # RSpec files
+  rspec = dsl.rspec
+  watch(rspec.spec_helper) { rspec.spec_dir }
+  watch(rspec.spec_support) { rspec.spec_dir }
+  watch(rspec.spec_files)
+
+  # Ruby files
+  ruby = dsl.ruby
+  dsl.watch_spec_files_for(ruby.lib_files)
+
+  watch(%r{^lib/(.+)\.rb$}) { |m| "spec/#{m[1]}_spec.rb" }
+
+end

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2015 Philippe Creux
+
+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 +1,117 @@
+# CSVImporter
+
+Importing a CSV file is easy to code until real users attempt to import
+real data.
+
+CSVImporter aims to handle validations, column mapping, actual import
+and reporting.
+
+[![Build
+Status](https://travis-ci.org/BrewhouseTeam/csv-importer.svg)](https://travis-ci.org/BrewhouseTeam/csv-importer)
+[![Code
+Climate](https://codeclimate.com/github/BrewhouseTeam/csv-importer/badges/gpa.svg)](https://codeclimate.com/github/BrewhouseTeam/csv-importer)
+[![Test
+Coverage](https://codeclimate.com/github/BrewhouseTeam/csv-importer/badges/coverage.svg)](https://codeclimate.com/github/BrewhouseTeam/csv-importer/coverage)
+
+## Usage
+
+**This is still a work in progress**
+
+Define your CSVImporter:
+
+```ruby
+class ImportUserCSV
+  include CSVImporter
+
+  model User
+
+  column :email, to: ->(email) { email.downcase }, required: true
+  column :first_name, as: [ /first.?name/i, /pr(é|e)nom/i ]
+  column :last_name,  to: :l_name
+  column :published,  to: ->(published, model) { model.published_at = published ? Time.now : nil }
+
+  identifier :email # will find_or_update via :email
+
+  when_invalid :skip # or :abort
+end
+```
+
+Let's run an new import:
+
+```ruby
+# Import a file (IOStream or file path) and from CSV content
+
+import = ImportUserCSV.new(file: InputStream)
+import = ImportUserCSV.new(path: String)
+import = ImportUserCSV.new(content: String)
+
+# Validate header
+
+import.header.valid?
+  # => true if header is valid
+
+import.header
+  # => returns an instance of `CSVImporter::Header`
+
+import.header.missing_required_columns # => ["email"]
+import.header.missing_columns          # => ["email", "first_name"]
+import.header.extra_columns            # => ["zip_code"]
+import.header.columns                  # => ["last_name", "zip_code"]
+
+# Manipulate rows
+
+import.rows
+  # => return a (lazy?) Array of Rows
+row = rows.first
+
+row.raw_string       # => "bob@example.com,bob,,extra"
+row.raw_array        # => [ "bob@example.com", "bob", "", "extra" ]
+row.csv_attributes   # => { email: "bob@example.com", first_name: "bob" }
+row.model            # => User<email: "bob@example.com", f_name: "bob", id: nil>
+row.valid?           # delegate to model.valid?
+
+# Time to run the import!
+
+report = import.run!
+
+# The following methods return arrays of `Row`
+report.valid_rows
+report.invalid_rows
+report.created_rows
+report.updated_rows
+report.failed_to_create_rows
+report.failed_to_update_rows
+
+report.success? # => true
+report.message # => "Import completed. 4 created, 2 updated, 1 failed to update"
+```
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'csv-importer'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install csv-importer
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release` to create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+1. Fork it ( https://github.com/BrewhouseTeam/csv-importer/fork )
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create a new Pull Request

data/Rakefile

@@ -0,0 +1,8 @@
+require "bundler/gem_tasks"
+
+desc "Run specs"
+task :test do
+  system("bundle exec rspec spec") || exit(-1)
+end
+
+task default: :test

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "csv_importer"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start

data/bin/setup

@@ -0,0 +1,7 @@
+#!/bin/bash
+set -euo pipefail
+IFS=$'\n\t'
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/csv-importer.gemspec

@@ -0,0 +1,25 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'csv_importer/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "csv-importer"
+  spec.version       = CSVImporter::VERSION
+  spec.authors       = ["Philippe Creux"]
+  spec.email         = ["pcreux@gmail.com"]
+
+  spec.summary       = %q{CSV Import for humans}
+  spec.homepage      = "https://github.com/BrewhouseTeam/csv-importer"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_dependency "virtus"
+
+  spec.add_development_dependency "bundler", "~> 1.8"
+  spec.add_development_dependency "rake", "~> 10.0"
+end

data/lib/csv-importer.rb

@@ -0,0 +1 @@
+require "csv_importer"

data/lib/csv_importer.rb

@@ -0,0 +1,79 @@
+require "csv"
+require "virtus"
+
+require "csv_importer/version"
+require "csv_importer/csv_reader"
+require "csv_importer/column_definition"
+require "csv_importer/column"
+require "csv_importer/header"
+require "csv_importer/row"
+require "csv_importer/report"
+require "csv_importer/report_message"
+require "csv_importer/runner"
+require "csv_importer/config"
+require "csv_importer/dsl"
+
+# A class that includes CSVImporter inherit its DSL and methods.
+#
+# Example:
+#   class ImportUserCSV
+#     include CSVImporter
+#
+#     model User
+#
+#     column :email
+#   end
+#
+#   report = ImportUserCSV.new(file: my_csv).run!
+#   puts report.message
+#
+module CSVImporter
+  class Error < StandardError; end
+
+  def self.included(klass)
+    klass.extend(Dsl)
+    klass.define_singleton_method(:csv_importer_config) do
+      @csv_importer_config ||= Config.new
+    end
+  end
+
+  # Defines the path, file or content of the csv file.
+  # Also allows you to overwrite the configuration at runtime.
+  #
+  # Example:
+  #
+  #   .new(file: my_csv_file)
+  #   .new(path: "subscribers.csv", model: newsletter.subscribers)
+  #
+  def initialize(*args)
+    @csv = CSVReader.new(*args)
+    @config = self.class.csv_importer_config.dup
+    @config.attributes = args.last
+  end
+
+  attr_reader :csv, :report, :config
+
+  # Initialize and return the `Header` for the current CSV file
+  def header
+    @header ||= Header.new(column_definitions: config.column_definitions, column_names: csv.header)
+  end
+
+  # Initialize and return the `Row`s for the current CSV file
+  def rows
+    csv.rows.map { |row_array| Row.new(header: header, row_array: row_array,
+                                       model_klass: config.model, identifier: config.identifier) }
+  end
+
+  # Run the import. Return a Report.
+  def run!
+    if header.valid?
+      @report = Runner.call(rows: rows, when_invalid: config.when_invalid)
+    else
+      @report = Report.new(status: :invalid_header, missing_columns: header.missing_required_columns)
+    end
+
+  rescue CSV::MalformedCSVError => e
+    @report = Report.new(status: :invalid_csv_file, parser_error: e.message)
+  end
+end
+

data/lib/csv_importer/column.rb

@@ -0,0 +1,10 @@
+module CSVImporter
+  # A Column from a CSV file with a `name` (from the csv file) and a matching
+  # `ColumnDefinition` if any.
+  class Column
+    include Virtus.model
+
+    attribute :name, String
+    attribute :definition, ColumnDefinition
+  end
+end

data/lib/csv_importer/column_definition.rb

@@ -0,0 +1,64 @@
+module CSVImporter
+  # Define a column. Called from the DSL via `column.
+  #
+  # Examples
+  #
+  #   # the csv column "email" will be assigned to the `email` attribute
+  #   column :email
+  #
+  #   # the csv column matching /email/i will be assigned to the `email` attribute
+  #   column :email, as: /email/i
+  #
+  #   # the csv column matching "First name" or "Prénom" will be assigned to the `first_name` attribute
+  #   column :first_name, as: [/first ?name/i, /pr(é|e)nom/i]
+  #
+  #   # the csv column "first_name" will be assigned to the `f_name` attribute
+  #   column :first_name, to: :f_name
+  #
+  #   # email will be downcased
+  #   column :email, to: ->(email) { email.downcase }
+  #
+  #   # transform `confirmed` to `confirmed_at`
+  #   column :confirmed, to: ->(confirmed, model) do
+  #     model.confirmed_at = confirmed == "true" ? Time.new(2012) : nil
+  #   end
+  #
+  class ColumnDefinition
+    include Virtus.model
+
+    attribute :name, Symbol
+    attribute :to # Symbol or Proc
+    attribute :as # Symbol, String, Regexp, Array
+    attribute :required, Boolean
+
+    # The model attribute that this column targets
+    def attribute
+      if to.is_a?(Symbol)
+        to
+      else
+        name
+      end
+    end
+
+    # Return true if column definition matches the column name passed in.
+    def match?(column_name, search_query=(as || name))
+      return false if column_name.nil?
+
+      downcased_column_name = column_name.downcase
+      underscored_column_name = downcased_column_name.gsub(/\s+/, '_')
+
+      case search_query
+      when Symbol
+        underscored_column_name == search_query.to_s
+      when String
+        downcased_column_name == search_query.downcase
+      when Regexp
+        column_name =~ search_query
+      when Array
+        search_query.any? { |query| match?(column_name, query) }
+      else
+        raise Error, "Invalid `as`. Should be a Symbol, String, Regexp or Array - was #{as.inspect}"
+      end
+    end
+  end
+end

data/lib/csv_importer/config.rb

@@ -0,0 +1,12 @@
+module CSVImporter
+  # The configuration of a CSVImporter
+  class Config
+    include Virtus.model
+
+    attribute :model
+    attribute :column_definitions, Array[ColumnDefinition], default: proc { [] }
+    attribute :identifier, Symbol
+    attribute :when_invalid, Symbol, default: proc { :skip }
+  end
+end
+

data/lib/csv_importer/csv_reader.rb

@@ -0,0 +1,65 @@
+module CSVImporter
+
+  # Reads, sanitize and parse a CSV file
+  class CSVReader
+    include Virtus.model
+
+    attribute :content, String
+    attribute :file # IO
+    attribute :path, String
+
+    def csv_rows
+      @csv_rows ||= begin
+        sane_content = sanitize_content(read_content)
+        separator = detect_separator(sane_content)
+        cells = CSV.parse(sane_content, col_sep: separator)
+        sanitize_cells(cells)
+      end
+    end
+
+    # Returns the header as an Array of Strings
+    def header
+      @header ||= csv_rows.first
+    end
+
+    # Returns the rows as an Array of Arrays of Strings
+    def rows
+      @rows ||= csv_rows[1..-1]
+    end
+
+    private
+
+    def read_content
+      if content
+        content
+      elsif file
+        file.read
+      elsif path
+        File.open(path).read
+      else
+        raise Error, "Please provide content, file, or path"
+      end
+    end
+
+    def sanitize_content(csv_content)
+      csv_content
+        .encode(Encoding.find('UTF-8'), {invalid: :replace, undef: :replace, replace: ''}) # Remove invalid byte sequences
+        .gsub(/\r\r?\n?/, "\n") # Replaces windows line separators with "\n"
+    end
+
+    SEPARATORS = [",", ";", "\t"]
+
+    def detect_separator(csv_content)
+      SEPARATORS.sort_by { |separator| csv_content.count(separator) }.last
+    end
+
+    # Strip cells
+    def sanitize_cells(rows)
+      rows.map do |cells|
+        cells.map do |cell|
+          cell.strip if cell
+        end
+      end
+    end
+  end
+end

data/lib/csv_importer/dsl.rb

@@ -0,0 +1,21 @@
+module CSVImporter
+  # This Dsl extends a class that includes CSVImporter
+  # It is a thin proxy to the Config object
+  module Dsl
+    def model(model_klass)
+      csv_importer_config.model = model_klass
+    end
+
+    def column(name, options={})
+      csv_importer_config.column_definitions << options.merge(name: name)
+    end
+
+    def identifier(identifier)
+      csv_importer_config.identifier = identifier
+    end
+
+    def when_invalid(action)
+      csv_importer_config.when_invalid = action
+    end
+  end
+end

data/lib/csv_importer/header.rb

@@ -0,0 +1,61 @@
+module CSVImporter
+
+  # The CSV Header
+  class Header
+    include Virtus.model
+
+    attribute :column_definitions, Array[ColumnDefinition]
+    attribute :column_names, Array[String]
+
+    def columns
+      column_names.map do |column_name|
+        Column.new(
+          name: column_name,
+          definition: find_column_definition(column_name)
+        )
+      end
+    end
+
+    def column_name_for_model_attribute(attribute)
+      if column = columns.find { |column| column.definition.attribute == attribute if column.definition }
+        column.name
+      end
+    end
+
+    def valid?
+      missing_required_columns.empty?
+    end
+
+    # Returns Array[String]
+    def required_columns
+      column_definitions.select(&:required?).map(&:name)
+    end
+
+    # Returns Array[String]
+    def extra_columns
+      columns.reject(&:definition).map(&:name).map(&:to_s)
+    end
+
+    # Returns Array[String]
+    def missing_required_columns
+      (column_definitions.select(&:required?) - columns.map(&:definition)).map(&:name).map(&:to_s)
+    end
+
+    # Returns Array[String]
+    def missing_columns
+      (column_definitions - columns.map(&:definition)).map(&:name).map(&:to_s)
+    end
+
+    private
+
+    def find_column_definition(name)
+      column_definitions.find do |column_definition|
+        column_definition.match?(name)
+      end
+    end
+
+    def column_definition_names
+      column_definitions.map(&:name).map(&:to_s)
+    end
+  end
+end

data/lib/csv_importer/report.rb

@@ -0,0 +1,60 @@
+module CSVImporter
+  # The Report you get back from an import.
+  #
+  # * It has a status (pending, invalid_csv_file, invalid_header, in_progress, done, aborted)
+  # * It lists out missing columns
+  # * It reports parser_error
+  # * It lists out (created / updated) * (success / failed) records
+  # * It provides a human readable message
+  #
+  class Report
+    include Virtus.model
+
+    attribute :status, Symbol, default: proc { :pending }
+
+    attribute :missing_columns, Array[Symbol], default: proc { [] }
+
+    attribute :parser_error, String
+
+    attribute :created_rows, Array[Row], default: proc { [] }
+    attribute :updated_rows, Array[Row], default: proc { [] }
+    attribute :failed_to_create_rows, Array[Row], default: proc { [] }
+    attribute :failed_to_update_rows, Array[Row], default: proc { [] }
+
+    attribute :message_generator, Class, default: proc { ReportMessage }
+
+    def valid_rows
+      created_rows + updated_rows
+    end
+
+    def invalid_rows
+      failed_to_create_rows + failed_to_update_rows
+    end
+
+    def all_rows
+      valid_rows + invalid_rows
+    end
+
+    def success?
+      done? && invalid_rows.empty?
+    end
+
+    def pending?;     status == :pending;         end
+    def in_progress?; status == :in_progress;     end
+    def done?;        status == :done;            end
+    def aborted?;     status == :aborted;         end
+    def invalid_header?; status == :invalid_header; end
+    def invalid_csv_file?; status == :invalid_csv_file; end
+
+    def pending!;     self.status = :pending;     self; end
+    def in_progress!; self.status = :in_progress; self; end
+    def done!;        self.status = :done;        self; end
+    def aborted!;     self.status = :aborted;     self; end
+    def invalid_header!; self.status = :invalid_header; self; end
+    def invalid_csv_file!; self.status = :invalid_csv_file; self; end
+
+    def message
+      message_generator.call(self)
+    end
+  end
+end

data/lib/csv_importer/report_message.rb

@@ -0,0 +1,54 @@
+module CSVImporter
+  # Generate a human readable message for the given report.
+  class ReportMessage
+    def self.call(report)
+      new(report).to_s
+    end
+
+    def initialize(report)
+      @report = report
+    end
+
+    attr_accessor :report
+
+    def to_s
+      send("report_#{report.status}")
+    end
+
+    private
+
+    def report_pending
+      "Import hasn't started yet"
+    end
+
+    def report_in_progress
+      "Import in progress"
+    end
+
+    def report_done
+      "Import completed: " + import_details
+    end
+
+    def report_invalid_header
+      "The following columns are required: #{report.missing_columns.join(", ")}"
+    end
+
+    def report_invalid_csv_file
+      report.parser_error
+    end
+
+    def report_aborted
+      "Import aborted"
+    end
+
+    # Generate something like: "3 created. 4 updated. 1 failed to create. 2 failed to update."
+    def import_details
+      report.attributes
+        .select { |name, _| name["_rows"] }
+        .select { |_, instances| instances.size > 0 }
+        .map { |bucket, instances| "#{instances.size} #{bucket.to_s.gsub('_rows', '').gsub('_', ' ')}" }
+        .join(", ")
+    end
+
+  end # class ReportMessage
+end

data/lib/csv_importer/row.rb

@@ -0,0 +1,91 @@
+module CSVImporter
+  # A Row from the CSV file.
+  #
+  # Using the header, the model_klass and the identifier it builds the model
+  # to be persisted.
+  class Row
+    include Virtus.model
+
+    attribute :header, Header
+    attribute :row_array, Array[String]
+    attribute :model_klass
+    attribute :identifier
+
+    # The model to be persisted
+    def model
+      @model ||= begin
+        model = if identifier
+          find_or_build_model
+        else
+          build_model
+        end
+
+        set_attributes(model)
+      end
+    end
+
+    # A hash with this row's attributes
+    def csv_attributes
+      @csv_attributes ||= Hash[header.column_names.zip(row_array)]
+    end
+
+    # Set attributes
+    def set_attributes(model)
+      header.columns.each do |column|
+        value = csv_attributes[column.name]
+        column_definition = column.definition
+
+        next if column_definition.nil?
+
+        set_attribute(model, column_definition, value)
+      end
+
+      model
+    end
+
+    # Set the attribute using the column_definition and the csv_value
+    def set_attribute(model, column_definition, csv_value)
+      if column_definition.to && column_definition.to.is_a?(Proc)
+        to_proc = column_definition.to
+
+        case to_proc.arity
+        when 1 # to: ->(email) { email.downcase }
+          model.public_send("#{column_definition.name}=", to_proc.call(csv_value))
+        when 2 # to: ->(published, post) { post.published_at = Time.now if published == "true" }
+          to_proc.call(csv_value, model)
+        else
+          raise ArgumentError, "`to` proc can only have 1 or 2 arguments"
+        end
+      else
+        attribute = column_definition.attribute
+        model.public_send("#{attribute}=", csv_value)
+      end
+
+      model
+    end
+
+    # Error from the model mapped back to the CSV header if we can
+    def errors
+      Hash[
+        model.errors.map do |attribute, errors|
+          if column_name = header.column_name_for_model_attribute(attribute)
+            [column_name, errors]
+          else
+            [attribute, errors]
+          end
+        end
+      ]
+    end
+
+    def find_or_build_model
+      model = build_model
+      set_attributes(model)
+      value = model.public_send(identifier)
+      model_klass.public_send("find_by_#{identifier}", value) || build_model
+    end
+
+    def build_model
+      model_klass.new
+    end
+  end
+end

data/lib/csv_importer/runner.rb

@@ -0,0 +1,88 @@
+module CSVImporter
+  # Do the actual import.
+  #
+  # It iterates over the rows' models and persist them. It returns a `Report`.
+  class Runner
+    def self.call(*args)
+      new(*args).call
+    end
+
+    include Virtus.model
+
+    attribute :rows, Array[Row]
+    attribute :when_invalid, Symbol
+
+    attribute :report, Report, default: proc { Report.new }
+
+    ImportAborted = Class.new(StandardError)
+
+    # Persist the rows' model and return a `Report`
+    def call
+      if rows.empty?
+        report.done!
+        return report
+      end
+
+      report.in_progress!
+
+      persist_rows!
+
+      report.done!
+      report
+    rescue ImportAborted
+      report.aborted!
+      report
+    end
+
+    private
+
+    def abort_when_invalid?
+      when_invalid == :abort
+    end
+
+    def persist_rows!
+      transaction do
+        rows.each do |row|
+          tags = []
+
+          if row.model.persisted?
+            tags << :update
+          else
+            tags << :create
+          end
+
+          if row.model.save
+            tags << :success
+          else
+            tags << :failure
+          end
+
+          add_to_report(row, tags)
+        end
+      end
+    end
+
+    def add_to_report(row, tags)
+      bucket = case tags
+      when [ :create, :success ]
+        report.created_rows
+      when [ :create, :failure ]
+        report.failed_to_create_rows
+      when [ :update, :success ]
+        report.updated_rows
+      when [ :update, :failure ]
+        report.failed_to_update_rows
+      else
+        raise "Invalid tags #{tags.inspect}"
+      end
+
+      bucket << row
+
+      raise ImportAborted if abort_when_invalid? && tags[1] == :failure
+    end
+
+    def transaction(&block)
+      rows.first.model.class.transaction(&block)
+    end
+  end
+end

data/lib/csv_importer/version.rb

@@ -0,0 +1,3 @@
+module CSVImporter
+  VERSION = "0.1.0"
+end

metadata

@@ -0,0 +1,111 @@
+--- !ruby/object:Gem::Specification
+name: csv-importer
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Philippe Creux
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2015-06-12 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: virtus
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.8'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.8'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+description: 
+email:
+- pcreux@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- CODE_OF_CONDUCT.md
+- Gemfile
+- Guardfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- csv-importer.gemspec
+- lib/csv-importer.rb
+- lib/csv_importer.rb
+- lib/csv_importer/column.rb
+- lib/csv_importer/column_definition.rb
+- lib/csv_importer/config.rb
+- lib/csv_importer/csv_reader.rb
+- lib/csv_importer/dsl.rb
+- lib/csv_importer/header.rb
+- lib/csv_importer/report.rb
+- lib/csv_importer/report_message.rb
+- lib/csv_importer/row.rb
+- lib/csv_importer/runner.rb
+- lib/csv_importer/version.rb
+homepage: https://github.com/BrewhouseTeam/csv-importer
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.5
+signing_key: 
+specification_version: 4
+summary: CSV Import for humans
+test_files: []