csv_piper 0.1.7 → 0.1.8

data/Gemfile

@@ -1,4 +1,6 @@
 source 'https://rubygems.org'
 
+gem 'rubocop', require: false
+
 # Specify your gem's dependencies in csv_piper.gemspec
 gemspec

data/README.md

@@ -1,4 +1,4 @@
-[![Gem Version](https://badge.fury.io/rb/csv_piper.svg)](http://badge.fury.io/rb/csv_piper) [![Build Status](https://travis-ci.org/jazzarati/csv_piper.svg?branch=master)](https://travis-ci.org/jazzarati/csv_piper)
+[![Gem Version](https://badge.fury.io/rb/csv_piper.svg)](http://badge.fury.io/rb/csv_piper) [![Build Status](https://travis-ci.org/jazzarati/csv_piper.svg?branch=master)](https://travis-ci.org/jazzarati/csv_piper) [![Code Climate](https://codeclimate.com/github/jazzarati/csv_piper/badges/gpa.svg)](https://codeclimate.com/github/jazzarati/csv_piper) [![Test Coverage](https://codeclimate.com/github/jazzarati/csv_piper/badges/coverage.svg)](https://codeclimate.com/github/jazzarati/csv_piper/coverage) [![Dependency Status](https://gemnasium.com/jazzarati/csv_piper.svg)](https://gemnasium.com/jazzarati/csv_piper)
 
 # CsvPiper
 
@@ -144,12 +144,24 @@ If you return `nil` instead of `[transformed, errors]` all further processing of
 
 _Return value_ is what will be passed into _source_ and _errors_ of the next pre-processor (and processors). Final pre-processor value of _source_ will be passed to each processor as a frozen hash. Final pre-processor value of _errors_ will be passed to the first processor.
 
-#### Row Errors
-This object is passed into each processor (which must pass it on) and is used to accumulate any and all errors for the particular row. You can access the row number through `row_index`.
+## Error Handling
+
+#### Built-in
+
+The `Errors::Row` object is passed into each processor as the last parameter to process (which must pass it on) and is used to accumulate any and all errors for the particular row being processed. This is useful to collect all errors for display to your users rather than just failing on first error (if this mode matches your use case). You can add the built-in `CollectErrors` processor as one of the final processors and this will allow you to grab all the errors ever occured once processing all rows have finished if desired.
 
 Add errors using `errors.add(error_key, error)`.
 
-#### Builder Options
+You can access the row number being processed through `row_index` which can be useful for displaying or logging errors.
+
+#### Do-it-yourself
+
+You can ignore the `Errors::Row` passed in to each processor and just handle error cases anyway you feel like. You can pass in a logger object in the construction of each of your processors if you want to use it during processing rows to handle errors.
+
+## Builder
+
+CsvPiper provides a builder class to allow nicer creation of the piper object.
+
 All builder options utilise the _fluent interface pattern_ and should be followed by a call to `build` to get the piper instance and then `process` to process the csv.
 
 Eg. `CsvPiper::Builder.new.from(io).with_processors(processors).build.process`

data/Rakefile

@@ -1,6 +1,14 @@
 require "bundler/gem_tasks"
 require "rspec/core/rake_task"
+require 'rubocop/rake_task'
 
 RSpec::Core::RakeTask.new(:spec)
+RuboCop::RakeTask.new
 
-task :default => :spec
+task :default => [:spec, :quality]
+
+task :quality => :rubocop
+
+task :codeclimate do
+  exec('codeclimate analyze')
+end

data/csv_piper.gemspec

@@ -23,6 +23,8 @@ Gem::Specification.new do |spec|
   spec.add_development_dependency "bundler", "~> 1.10"
   spec.add_development_dependency "rake", "~> 10.0"
   spec.add_development_dependency "rspec", "~> 3"
+  spec.add_development_dependency "codeclimate-test-reporter", '~> 0.4'
+  spec.add_development_dependency "rubocop", '~> 0.34'
   spec.add_development_dependency 'sqlite3', '~> 1.3'
   spec.add_development_dependency 'activerecord', '~> 4.2'
 end

data/lib/csv_piper/piper.rb

@@ -1,4 +1,7 @@
 module CsvPiper
+  ###
+  # Catch exceptions on a per processor/row basis (allow other rows to continue processing)?
+  ###
   class Piper
     HEADER_LINE_INDEX = 1
     FIRST_DATA_LINE_INDEX = 2
@@ -37,23 +40,23 @@ module CsvPiper
 
     def process_csv_body
       csv.each.with_index(FIRST_DATA_LINE_INDEX) do |row, index|
-        processed_data, row_errors = process_row(row.to_hash, Errors::Row.new(index))
+        process_row(row.to_hash, Errors::Row.new(index))
       end
     end
 
     def process_row(row, row_errors)
       pre_processed_row, row_errors = pre_processors.reduce([row, row_errors]) do |memo, processor|
         output = processor.process(*memo)
-        return if output.nil?
+        return nil if output.nil?
         output
       end
 
       frozen_row = pre_processed_row.freeze
 
       processed_data = {}
-      processed_data, row_errors = processors.reduce([processed_data, row_errors]) do |memo, processor|
+      processors.reduce([processed_data, row_errors]) do |memo, processor|
         output = processor.process(frozen_row, *memo)
-        return if output.nil?
+        return nil if output.nil?
         output
       end
     end

data/lib/csv_piper/processors/collect_errors.rb

@@ -1,12 +1,16 @@
 module CsvPiper
   module Processors
+    # Collects errors for use after processing.
+    # Instantiate and keep a reference, then once processing complete retrieve errors through #errors
     class CollectErrors
+      # @return[Hash] Holds all of the errors for each row that was processed
+      # { row_index => { errors_key => array_of_errors } }
       attr_reader :errors
       def initialize
         @errors = {}
       end
 
-      def process(source, transformed, row_errors)
+      def process(_source, transformed, row_errors)
         @errors[row_errors.row_index] = row_errors.errors unless row_errors.empty?
         [transformed, errors]
       end

data/lib/csv_piper/processors/collect_output.rb

@@ -1,13 +1,17 @@
 module CsvPiper
   module Processors
+    # Collects transformed objects for use after processing.
+    # Instantiate and keep a reference, then once processing complete retrieve transformed objects through #output
     class CollectOutput
+      # @return[Array] Holds all of the transformed objects for each row that was processed
+      # { row_index => { errors_key => array_of_error } }
       attr_reader :output
       def initialize(collect_when_invalid: true)
         @output = []
         @collect_when_invalid = collect_when_invalid
       end
 
-      def process(source, transformed, errors)
+      def process(_source, transformed, errors)
         @output << transformed if @collect_when_invalid || errors.empty?
         [transformed, errors]
       end

data/lib/csv_piper/processors/copy.rb

@@ -1,6 +1,12 @@
 module CsvPiper
   module Processors
+    # Use to copy data from source row to transformed hash. Does not add any errors.
     class Copy
+      # @param mapping: [nil, Array, Hash{source_key => new_key}] (Defaults to +nil+)
+      #     - When +nil+: All contents of the source hash will be copied across to the transformed hash
+      #     - When an +Array+: Only the matching keys will be copied to the transformed hash
+      #     - When a +Hash+: Only the matching keys will be copied to the transformed hash but they will be copied onto the transformed hash with a new key value (mapping = +{ source_key => new_key }+ )
+      #
       def initialize(mapping = nil)
         mapping = Hash[ mapping.map { |val| [val, val] } ] if mapping.is_a?(Array)
         @mapping = mapping

data/lib/csv_piper/processors/create_active_model.rb

@@ -5,15 +5,16 @@ module CsvPiper
         @model_class = model_class
       end
 
-      def process(source, transformed, errors)
+      def process(_source, transformed, errors)
         model = @model_class.new(transformed)
 
         model.save if model.valid? && errors.empty?
 
-        errors.errors.merge!(model.errors.to_hash) do |key, old_val, new_val|
+        errors.errors.merge!(model.errors.to_hash) do |_key, old_val, new_val|
           old_val + new_val
         end
 
+        transformed["#{@model_class.name.underscore}_model".to_sym] = model
         [transformed, errors]
       end
     end

data/lib/csv_piper/processors/translate.rb

@@ -0,0 +1,31 @@
+module CsvPiper
+  module Processors
+    # Used to convert the values in the transformed hash according a provided mapping hash. { key => { 'value' => 'new_value', 'value2' => 'new_value2' } }
+    class Translate
+
+      # @param mapping: [Hash] Mapping to use for translation: { key => { 'value' => 'new_value', 'value2' => 'new_value2' } }
+      # @param add_error_on_missing_translation: [Boolean] By default errors are not added when there is no matching
+      #    value found in the mapping. When set to +true+ errors will be added to the key if no matching value found.
+      # @param pass_through_on_no_match: By default when there is no matching value the value will become +nil+.
+      #    When set to +true+, the value will remain unchanged if there is no matching value to translate using.
+      def initialize(mapping: , add_error_on_missing_translation: false, pass_through_on_no_match: false)
+        @add_error = add_error_on_missing_translation
+        @pass_through =  pass_through_on_no_match
+        @mapping = mapping
+      end
+
+      def process(_source, transformed, errors)
+        mappings_to_apply = @mapping.select { |key,_| transformed.has_key?(key) }
+
+        transformed = mappings_to_apply.each_with_object(transformed) do |(key, translation), memo|
+          new_value = translation[memo[key]]
+          errors.add(key, "No mapping for value #{memo[key]}") if @add_error && new_value.nil?
+          new_value = new_value || memo[key] if @pass_through
+          memo[key] = new_value
+        end
+
+        [transformed, errors]
+      end
+    end
+  end
+end

data/lib/csv_piper/version.rb

@@ -1,3 +1,3 @@
 module CsvPiper
-  VERSION = "0.1.7"
+  VERSION = "0.1.8"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: csv_piper
 version: !ruby/object:Gem::Version
-  version: 0.1.7
+  version: 0.1.8
 platform: ruby
 authors:
 - Jarrod Sibbison
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2015-09-19 00:00:00.000000000 Z
+date: 2015-09-27 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -52,6 +52,34 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '3'
+- !ruby/object:Gem::Dependency
+  name: codeclimate-test-reporter
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.4'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.4'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.34'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.34'
 - !ruby/object:Gem::Dependency
   name: sqlite3
   requirement: !ruby/object:Gem::Requirement
@@ -87,8 +115,10 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".codeclimate.yml"
 - ".gitignore"
 - ".rspec"
+- ".rubocop.yml"
 - ".travis.yml"
 - Gemfile
 - LICENSE.txt
@@ -106,6 +136,7 @@ files:
 - lib/csv_piper/processors/collect_output.rb
 - lib/csv_piper/processors/copy.rb
 - lib/csv_piper/processors/create_active_model.rb
+- lib/csv_piper/processors/translate.rb
 - lib/csv_piper/test_support/csv_mock_file.rb
 - lib/csv_piper/version.rb
 homepage: https://github.com/jazzarati/csv_piper
@@ -133,3 +164,4 @@ signing_key:
 specification_version: 4
 summary: CSV processing pipeline
 test_files: []
+has_rdoc: