active_importer 0.0.1

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/.rspec

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

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in active_importer.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 Ernesto Garcia
+
+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 +1,61 @@
+# ActiveImporter
+
+Define importers that load tabular data from spreadsheets or CSV files into any ActiveRecord-like ORM.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'active_importer'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install active_importer
+
+## Usage
+
+Define classes that you instruct on how to import data into data models.
+
+```ruby
+class EmployeeImporter < ActiveImporter::Base
+  imports Employee
+
+  column 'First name', :first_name
+  column 'Last name', :last_name
+  column 'Department', :department do |department_name|
+    Department.find_by(name: department_name)
+  end
+end
+```
+
+The importer defines what data model it imports data into, and how columns in
+the data source map to fields in the model.  Also, by providing a block, the
+source value can be processed before being stored, as shown with the
+'Department' column in the example above.
+
+Once defined, importers can be invoked to import a given data file.
+
+```ruby
+EmployeeImporter.import('/path/to/file.xls')
+```
+
+The data file is expected to contain columns with titles corresponding to the
+columns declared.  Any extra columns are ignored.  Any errors while processing
+the data file does not interrupt the whole process.  Instead, errors are
+notified via some callbacks defined in the importer (see below).
+
+### Callbacks
+
+TODO: Document callbacks
+
+## Contributing
+
+1. Fork it
+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 new Pull Request

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/active_importer.gemspec

@@ -0,0 +1,26 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'active_importer/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "active_importer"
+  spec.version       = ActiveImporter::VERSION
+  spec.authors       = ["Ernesto Garcia"]
+  spec.email         = ["gnapse@gmail.com"]
+  spec.description   = %q{Import tabular data from spreadsheets or similar sources into data models}
+  spec.summary       = %q{Import tabular data into data models}
+  spec.homepage      = ""
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_dependency "roo"
+
+  spec.add_development_dependency "bundler", "~> 1.3"
+  spec.add_development_dependency "rake"
+  spec.add_development_dependency "rspec"
+end

data/lib/active_importer/base.rb

@@ -0,0 +1,150 @@
+require 'roo'
+
+module ActiveImporter
+  class Base
+
+    #
+    # DSL and class variables
+    #
+
+    @model_class = nil
+    @columns = {}
+
+    def self.imports(klass)
+      @model_class = klass
+    end
+
+    def self.columns
+      @columns ||= {}
+    end
+
+    def self.model_class
+      @model_class
+    end
+
+    def model_class
+      self.class.model_class
+    end
+
+    def self.column(title, field, &block)
+      if columns[title]
+        raise "Duplicate importer column '#{title}'"
+      end
+      columns[title] = { field_name: field, transform: block }
+    end
+
+    def self.import(file, options = {})
+      new(file, options).import
+    end
+
+    #
+    # Implementation
+    #
+
+    attr_reader :header, :row, :model
+    attr_reader :row_count, :row_index
+    attr_reader :row_errors
+    attr_reader :context
+
+    def initialize(file, options = {})
+      @row_errors = []
+      @context = options.delete(:context)
+
+      @book = Roo::Spreadsheet.open(file, options)
+      @header = @book.row(1)
+      check_header
+
+      @data_row_indices = (2..@book.count)
+      @row_count = @data_row_indices.count
+    rescue => e
+      @book = @header = nil
+      @row_count = 0
+      @row_index = 1
+      import_failed(e.message)
+    end
+
+    def fetch_model
+      model_class.new
+    end
+
+    def import
+      return if @book.nil?
+      @data_row_indices.each do |index|
+        @row_index = index
+        @row = row_to_hash @book.row(index)
+        import_row
+      end
+      import_finished
+    end
+
+    def row_processed_count
+      row_index - 1
+    end
+
+    def row_success_count
+      row_processed_count - row_errors.count
+    end
+
+    def row_error_count
+      row_errors.count
+    end
+
+    def hook
+    end
+
+    def row_success
+    end
+
+    def row_error(error_message)
+    end
+
+    def import_failed(error_message)
+    end
+
+    def import_finished
+    end
+
+    private
+
+    def columns
+      self.class.columns
+    end
+
+    def check_header
+      # Header should contain all columns declared for this importer
+      unless columns.keys.all? { |item| @header.include?(item) }
+        raise 'Spreadsheet does not contain all the expected columns'
+      end
+    end
+
+    def import_row
+      @model = fetch_model
+      build_model
+      model.save!
+      row_success
+    rescue => e
+      @row_errors << { row_index: row_index, error_message: e.message }
+      row_error(e.message)
+    end
+
+    def build_model
+      row.each_pair do |key, value|
+        column_def = columns[key]
+        next if column_def.nil?
+        field_name = column_def[:field_name]
+        transform = column_def[:transform]
+        value = transform.call(value) if transform
+        model[field_name] = value
+      end
+      hook
+    end
+
+    def row_to_hash(row)
+      hash = {}
+      row.each_with_index do |value, index|
+        hash[@header[index]] = value
+      end
+      hash
+    end
+  end
+end

data/lib/active_importer/version.rb

@@ -0,0 +1,3 @@
+module ActiveImporter
+  VERSION = "0.0.1"
+end

data/lib/active_importer.rb

@@ -0,0 +1,5 @@
+require "active_importer/version"
+
+module ActiveImporter
+  autoload :Base, 'active_importer/base'
+end

data/spec/active_importer/base_spec.rb

@@ -0,0 +1,96 @@
+require 'spec_helper'
+require 'stubs/employee'
+
+describe ActiveImporter::Base do
+  let(:spreadsheet_data) do
+    [
+      ['Name', 'Birth Date', 'Department'],
+      ['John Doe', '2013-10-25', 'IT'],
+      ['Jane Doe', '2013-10-26', 'Sales'],
+    ]
+  end
+
+  let(:importer) { EmployeeImporter.new('/dummy/file') }
+
+  before do
+    expect(Roo::Spreadsheet).to receive(:open).and_return { Spreadsheet.new(spreadsheet_data) }
+  end
+
+  it 'imports all data from the spreadsheet into the model' do
+    expect { EmployeeImporter.import('/dummy/file') }.to change(Employee, :count).by(2)
+  end
+
+  it 'notifies when each row has been imported successfully' do
+    expect(EmployeeImporter).to receive(:new).once.and_return(importer)
+    expect(importer).not_to receive(:row_error)
+    expect(importer).to receive(:row_success).twice
+    EmployeeImporter.import('/dummy/file')
+  end
+
+  it 'notifies when the import process has finished' do
+    expect(EmployeeImporter).to receive(:new).once.and_return(importer)
+    expect(importer).to receive(:import_finished).once
+    EmployeeImporter.import('/dummy/file')
+  end
+
+  context 'when there are rows with errors' do
+    let(:spreadsheet_data) do
+      [
+        ['Name', 'Birth Date', 'Department'],
+        ['John Doe', '2013-10-25', 'IT'],
+        ['Invalid', '2013-10-24', 'Management'],
+        ['Invalid', '2013-10-24', 'Accounting'],
+        ['Jane Doe', '2013-10-26', 'Sales'],
+      ]
+    end
+
+    it 'does not import those rows' do
+      expect { EmployeeImporter.import('/dummy/file') }.to change(Employee, :count).by(2)
+    end
+
+    it 'notifies about each error' do
+      expect(EmployeeImporter).to receive(:new).once.and_return(importer)
+      expect(importer).to receive(:row_error).twice
+      expect(importer).to receive(:row_success).twice
+      EmployeeImporter.import('/dummy/file')
+    end
+
+    it 'keeps track of each error' do
+      expect(EmployeeImporter).to receive(:new).once.and_return(importer)
+      expect { EmployeeImporter.import('/dummy/file') }.to change(importer.row_errors, :count).by(2)
+    end
+  end
+
+  context 'when the import fails' do
+    let(:spreadsheet_data) do
+      [
+        ['Name', 'Birth Date'],
+        ['John Doe', '2013-10-25'],
+        ['Jane Doe', '2013-10-26'],
+      ]
+    end
+
+    it 'notifies the failure' do
+      expect_any_instance_of(EmployeeImporter).to receive(:import_failed)
+      EmployeeImporter.import('/dummy/file')
+    end
+  end
+
+  describe '.fetch_model' do
+    let(:model) { Employee.new }
+
+    it 'controls what model instance is loaded for each given row' do
+      expect(EmployeeImporter).to receive(:new).once.and_return(importer)
+      expect(importer).to receive(:fetch_model).twice.and_return(model)
+      expect { EmployeeImporter.import('/dummy/file') }.to change(Employee, :count).by(1)
+    end
+  end
+
+  describe '.hook' do
+    it 'allows the importer to modify the model for each row' do
+      expect(EmployeeImporter).to receive(:new).once.and_return(importer)
+      expect(importer).to receive(:hook).twice
+      EmployeeImporter.import('/dummy/file')
+    end
+  end
+end

data/spec/spec_helper.rb

@@ -0,0 +1,23 @@
+require 'active_importer'
+
+# This file was generated by the `rspec --init` command. Conventionally, all
+# specs live under a `spec` directory, which RSpec adds to the `$LOAD_PATH`.
+# Require this file using `require "spec_helper"` to ensure that it is only
+# loaded once.
+#
+# See http://rubydoc.info/gems/rspec-core/RSpec/Core/Configuration
+RSpec.configure do |config|
+  config.treat_symbols_as_metadata_keys_with_true_values = true
+  config.run_all_when_everything_filtered = true
+  config.filter_run :focus
+
+  config.expect_with :rspec do |c|
+    c.syntax = :expect
+  end
+
+  # Run specs in random order to surface order dependencies. If you find an
+  # order dependency and want to debug it, you can fix the order by providing
+  # the seed, which is printed after each run.
+  #     --seed 1234
+  config.order = 'random'
+end

data/spec/stubs/data_model.rb

@@ -0,0 +1,52 @@
+class DataModel
+  @@count = 0
+
+  def self.count
+    @@count
+  end
+
+  attr_reader :errors
+
+  def initialize(attributes = {})
+    @new_record = true
+    @errors = []
+    attributes.each_pair do |key, value|
+      self[key] = value
+    end
+  end
+
+  def []=(field, value)
+    send("#{field}=", value)
+  end
+
+  def to_s
+    "#{self.class.name}(#{attributes})"
+  end
+
+  def save
+    if valid?
+      @@count += 1 if @new_record
+      @new_record = false
+      true
+    else
+      false
+    end
+  end
+
+  def save!
+    raise 'Invalid model' unless save
+  end
+
+  def new_record?
+    @new_record
+  end
+
+  def valid?
+    validate
+    @errors.empty?
+  end
+
+  def validate
+    # ...
+  end
+end

data/spec/stubs/employee.rb

@@ -0,0 +1,20 @@
+require 'stubs/data_model'
+require 'stubs/spreadsheet'
+
+class Employee < DataModel
+  attr_accessor :name, :birth_date, :department, :department_id
+
+  def validate
+    @errors << 'Invalid name' if name == 'Invalid'
+  end
+end
+
+class EmployeeImporter < ActiveImporter::Base
+  imports Employee
+
+  column 'Name', :name
+  column 'Birth Date', :birth_date
+  column 'Department', :department_id do |value|
+    value.length # Quick dummy way to get an integer out of a string
+  end
+end

data/spec/stubs/spreadsheet.rb

@@ -0,0 +1,13 @@
+class Spreadsheet
+  def initialize(data)
+    @data = data
+  end
+
+  def count
+    @data.count
+  end
+
+  def row(index)
+    @data[index-1]
+  end
+end

metadata

@@ -0,0 +1,136 @@
+--- !ruby/object:Gem::Specification
+name: active_importer
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease: 
+platform: ruby
+authors:
+- Ernesto Garcia
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-11-06 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: roo
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !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: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Import tabular data from spreadsheets or similar sources into data models
+email:
+- gnapse@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- .rspec
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- active_importer.gemspec
+- lib/active_importer.rb
+- lib/active_importer/base.rb
+- lib/active_importer/version.rb
+- spec/active_importer/base_spec.rb
+- spec/spec_helper.rb
+- spec/stubs/data_model.rb
+- spec/stubs/employee.rb
+- spec/stubs/spreadsheet.rb
+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'
+      segments:
+      - 0
+      hash: -168044513201808942
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+      segments:
+      - 0
+      hash: -168044513201808942
+requirements: []
+rubyforge_project: 
+rubygems_version: 1.8.23
+signing_key: 
+specification_version: 3
+summary: Import tabular data into data models
+test_files:
+- spec/active_importer/base_spec.rb
+- spec/spec_helper.rb
+- spec/stubs/data_model.rb
+- spec/stubs/employee.rb
+- spec/stubs/spreadsheet.rb