fight_csv 0.1.0

data/.document

@@ -0,0 +1,5 @@
+lib/**/*.rb
+bin/*
+- 
+features/**/*.feature
+LICENSE.txt

data/.rvmrc

@@ -0,0 +1 @@
+rvm use ruby-1.9.2-p180@fight_csv

data/Gemfile

@@ -0,0 +1,16 @@
+source :rubygems
+# Add dependencies required to use your gem here.
+# Example:
+#   gem "activesupport", ">= 2.3.5"
+
+# Add dependencies to develop your gem here.
+# Include everything needed to run rake, tests, features, etc.
+group :development do
+  gem "jeweler", "~> 1.6.0"
+  gem 'awesome_print'
+  gem 'simplecov'
+  gem 'rake'
+end
+
+gem 'constructable'
+gem 'activesupport'

data/Gemfile.lock

@@ -0,0 +1,26 @@
+GEM
+  remote: http://rubygems.org/
+  specs:
+    activesupport (3.0.9)
+    awesome_print (0.4.0)
+    constructable (0.3.4)
+    git (1.2.5)
+    jeweler (1.6.2)
+      bundler (~> 1.0)
+      git (>= 1.2.5)
+      rake
+    rake (0.9.2)
+    simplecov (0.4.2)
+      simplecov-html (~> 0.4.4)
+    simplecov-html (0.4.5)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  activesupport
+  awesome_print
+  constructable
+  jeweler (~> 1.6.0)
+  rake
+  simplecov

data/LICENSE.txt

@@ -0,0 +1,20 @@
+Copyright (c) 2011 Manuel Korfmann
+
+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 +1,160 @@
+# Fight CSV!
+
+It's 2011, and parsing CSV with Ruby still sucks? Enter FightCSV! It
+will take the cumbersome out of your CSV parsing, while keeping the
+awesome! Want some taste of that juicy fresh? Check out this example:
+
+Consider you have a csv file called log_entries.csv which looks like
+this:
+
+```
+Date,Person,Client/Project,Minutes,Tags,Billable
+2011-08-15,John Doe,handsomelabs,60,blogpost,no
+2011-08-15,Max Powers,beerbrewing,60,meeting,yes
+2011-08-15,Tyler Durden,babysitting,180,"concepting, research",yes
+2011-08-15,Hulk Hero,gardening,60,"meeting, research",no
+2011-08-15,John Doe,handsomelabs,60,coding,yes
+2011-08-08,John Doe,handsomelabs,60,"blabla, meeting",yes
+```
+
+## Schema
+
+Now you can define a class representing a row of the file. You only need
+to include ```FightCSV::Record```.
+
+```ruby
+class LogEntry
+  include FightCSV::Record
+end
+```
+
+But of course you want the values from each row to behave like proper
+Ruby objects. This can be easily achieved by defining a schema in the
+```LogEntry``` class:
+
+```ruby
+class LogEntry
+  include FightCSV::Record
+  schema do
+    field "Name"
+    field "Client/Project", {
+      identifier: :project
+    }
+  end
+end
+```
+
+Now the LogEntry objects will have a ```name``` method corresponding to
+the column called "Name" and a ```project``` method corresponding to the
+column called "Client/Project".
+
+But sometimes you don't only want to adjust the field names, but also
+the values. In this case FightCSV offers converters. The "Billable"
+column seems to represent boolean values, so let's tackle that:
+
+```ruby
+class LogEntry
+  include FightCSV::Record
+  schema do
+    field "Name"
+    field "Client/Project", {
+      identifier: :project
+    }
+
+    field "Billable", {
+      converter: ->(string) { string == "yes" ? true : false }
+    }
+  end
+end
+
+```
+
+Often when converting something, we assume that it has a certain format.
+The "Date" column for example should always be of the format
+```/\d{2}\.\d{2}\.\d{4}/```. A validation can easily be added to a column
+with FightCSV:
+
+```ruby
+class LogEntry
+  include FightCSV::Record
+  schema do
+    field "Name"
+    field "Client/Project", {
+      identifier: :project
+    }
+
+    field "Billable", {
+      converter: ->(string) { string == "yes" ? true : false }
+    }
+
+    field "Date", {
+      validate: /\d{2}\.\d{2}\.\d{4}/,
+      converter: ->(string) { Date.parse(string) }
+    }
+  end
+end
+```
+
+The complete schema:
+
+```ruby
+class LogEntry
+  include FightCSV::Record
+  schema do
+    field "Name"
+    field "Client/Project", {
+      identifier: :project
+    }
+
+    field "Billable", {
+      converter: ->(string) { string == "yes" ? true : false }
+    }
+
+    field "Date", {
+      validate: /\d{2}\.\d{2}\.\d{4}/,
+      converter: ->(string) { Date.parse(string) }
+    }
+
+    field "Tags", {
+      converter: ->(string) { string.split(",") }
+    }
+
+    field "Minutes", {
+      validate: /\d+/,
+      converter: ->(string) { string.to_i }
+    }
+  end
+end
+```
+
+## Parsing CSV
+
+With the schema definition you're finally able to parse some CSV. There
+are two possible ways of doing this:
+
+1.  ```LogEntry.records``` will return an array with all rows
+    mapped to instances of ```LogEntry```.
+
+2.  ```LogEntry.import``` will return an enumerator which will pass the same ```LogEntry``` instance with the
+    row changed for every iteration.
+
+    ```ruby
+    LogEntry.import(csv).map(&:minutes).reduce(:+)
+    #=> 780
+    ```
+    Doing so you can avoid memory leaks on big csv documents.
+
+
+## Contributing to fight\_csv
+* Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet
+* Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it
+* Fork the project
+* Commit and push until you are happy with your contribution
+* Make sure to add tests for it. This is important so I don't break it in a future version unintentionally.
+* Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
+
+## Copyright
+
+Copyright (c) 2011 Manuel Korfmann. See LICENSE.txt for
+further details.
+

data/Rakefile

@@ -0,0 +1,40 @@
+# encoding: utf-8
+
+require 'rubygems'
+require 'bundler'
+begin
+  Bundler.setup(:default, :development)
+rescue Bundler::BundlerError => e
+  $stderr.puts e.message
+  $stderr.puts "Run `bundle install` to install missing gems"
+  exit e.status_code
+end
+require 'rake'
+
+require 'jeweler'
+Jeweler::Tasks.new do |gem|
+  # gem is a Gem::Specification... see http://docs.rubygems.org/read/chapter/20 for more options
+  gem.name = "fight_csv"
+  gem.homepage = "http://github.com/mkorfmann/fight_csv"
+  gem.license = "MIT"
+  gem.summary = %Q{JSON-Schema + ActiveModel for CSV}
+  gem.description = %Q{
+Provides a nice DSL to describe your CSV document.
+CSV documents can be validated against this description.
+You can easily define types like Integer or Array for CSV through converters.
+  }
+  gem.email = "manu@korfmann.info"
+  gem.authors = ["Manuel Korfmann"]
+  # dependencies defined in Gemfile
+end
+Jeweler::RubygemsDotOrgTasks.new
+
+require 'rake/testtask'
+Rake::TestTask.new(:test) do |test|
+  test.libs << 'lib' << 'test'
+  test.pattern = 'test/**/test_*.rb'
+  test.verbose = true
+end
+
+
+task :default => :test

data/VERSION

@@ -0,0 +1 @@
+0.1.0

data/examples/timetracking.rb

@@ -0,0 +1,46 @@
+require '../lib/fight_csv'
+
+csv = <<-CSV
+Date,Person,Client/Project,Minutes,Tags,Billable
+2011-08-15,John Doe,handsomelabs,60,blogpost,no
+2011-08-15,Max Powers,beerbrewing,60,meeting,yes
+2011-08-15,Tyler Durden,babysitting,180,"concepting, research",yes
+2011-08-15,Hulk Hero,gardening,60,"meeting, research",no
+2011-08-15,John Doe,handsomelabs,60,coding,yes
+2011-08-08,John Doe,handsomelabs,60,"blabla, meeting",yes
+CSV
+
+class LogEntry
+  include FightCSV::Record
+  schema do
+    field "Person"
+    field "Client/Project", {
+      identifier: :project
+    }
+
+    field "Billable", {
+      converter: ->(string) { string == "yes" ? true : false }
+    }
+
+    field "Date", {
+      validate: /\d{2}\.\d{2}\.\d{4}/,
+      converter: ->(string) { Date.parse(string) }
+    }
+
+    field "Tags", {
+      converter: ->(string) { string.split(",") }
+    }
+
+    field "Minutes", {
+      validate: /\d+/,
+      converter: ->(string) { string.to_i }
+    }
+  end
+end
+
+
+records = LogEntry.records csv
+
+# Persons who have worked on billable projects
+billable_entries = records.select(&:billable)
+puts billable_entries.map(&:person).uniq.join(" - ")

data/fight_csv.gemspec

@@ -0,0 +1,84 @@
+# Generated by jeweler
+# DO NOT EDIT THIS FILE DIRECTLY
+# Instead, edit Jeweler::Tasks in Rakefile, and run 'rake gemspec'
+# -*- encoding: utf-8 -*-
+
+Gem::Specification.new do |s|
+  s.name = %q{fight_csv}
+  s.version = "0.1.0"
+
+  s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
+  s.authors = ["Manuel Korfmann"]
+  s.date = %q{2011-08-18}
+  s.description = %q{
+Provides a nice DSL to describe your CSV document.
+CSV documents can be validated against this description.
+You can easily define types like Integer or Array for CSV through converters.
+  }
+  s.email = %q{manu@korfmann.info}
+  s.extra_rdoc_files = [
+    "LICENSE.txt",
+    "README.md"
+  ]
+  s.files = [
+    ".document",
+    ".rvmrc",
+    "Gemfile",
+    "Gemfile.lock",
+    "LICENSE.txt",
+    "README.md",
+    "Rakefile",
+    "VERSION",
+    "examples/timetracking.rb",
+    "fight_csv.gemspec",
+    "lib/fight_csv.rb",
+    "lib/fight_csv/data_source.rb",
+    "lib/fight_csv/field.rb",
+    "lib/fight_csv/record.rb",
+    "lib/fight_csv/schema.rb",
+    "tags",
+    "test/fixtures/cocktails.csv",
+    "test/fixtures/prog_lang_schema.rb",
+    "test/fixtures/programming_languages.csv",
+    "test/fixtures/recipes.csv",
+    "test/helper.rb",
+    "test/test_field.rb",
+    "test/test_fight_csv.rb",
+    "test/test_record.rb",
+    "test/test_schema.rb"
+  ]
+  s.homepage = %q{http://github.com/mkorfmann/fight_csv}
+  s.licenses = ["MIT"]
+  s.require_paths = ["lib"]
+  s.rubygems_version = %q{1.3.7}
+  s.summary = %q{JSON-Schema + ActiveModel for CSV}
+
+  if s.respond_to? :specification_version then
+    current_version = Gem::Specification::CURRENT_SPECIFICATION_VERSION
+    s.specification_version = 3
+
+    if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
+      s.add_runtime_dependency(%q<constructable>, [">= 0"])
+      s.add_runtime_dependency(%q<activesupport>, [">= 0"])
+      s.add_development_dependency(%q<jeweler>, ["~> 1.6.0"])
+      s.add_development_dependency(%q<awesome_print>, [">= 0"])
+      s.add_development_dependency(%q<simplecov>, [">= 0"])
+      s.add_development_dependency(%q<rake>, [">= 0"])
+    else
+      s.add_dependency(%q<constructable>, [">= 0"])
+      s.add_dependency(%q<activesupport>, [">= 0"])
+      s.add_dependency(%q<jeweler>, ["~> 1.6.0"])
+      s.add_dependency(%q<awesome_print>, [">= 0"])
+      s.add_dependency(%q<simplecov>, [">= 0"])
+      s.add_dependency(%q<rake>, [">= 0"])
+    end
+  else
+    s.add_dependency(%q<constructable>, [">= 0"])
+    s.add_dependency(%q<activesupport>, [">= 0"])
+    s.add_dependency(%q<jeweler>, ["~> 1.6.0"])
+    s.add_dependency(%q<awesome_print>, [">= 0"])
+    s.add_dependency(%q<simplecov>, [">= 0"])
+    s.add_dependency(%q<rake>, [">= 0"])
+  end
+end
+

data/lib/fight_csv/data_source.rb

@@ -0,0 +1,23 @@
+require 'csv'
+module FightCSV
+  class DataSource
+    include Enumerable
+
+    ALLOWED_OPTIONS = [:col_sep, :row_sep, :quote_char]
+
+    constructable :header, default: ->{true}, readable: true
+    constructable :io, readable: true
+    constructable :csv_options,
+      accessible: true,
+      default: ->{ Hash.new }
+
+    def each
+      csv = CSV.new(self.io, Hash[csv_options.select { |opt| ALLOWED_OPTIONS.include opt }])
+      additions = {}
+      additions[:header] = csv.shift if self.header
+      csv.each do |row|
+        yield row, additions
+      end
+    end
+  end
+end

data/lib/fight_csv/field.rb

@@ -0,0 +1,64 @@
+module FightCSV
+	class Field
+		constructable :converter, validate_type: Proc, accessible: true
+		constructable :identifier, validate_type: Symbol, accessible: true
+		constructable :validator, accessible: true, default: ->{/.*/}
+
+		attr_accessor :matcher
+
+		def initialize(matcher, options = {})
+			@matcher = matcher
+		end
+
+    def identifier
+      if super
+        super
+      else
+        case self.matcher
+        when String
+          self.matcher.downcase.to_sym
+        else
+          raise ArgumentError, "Please specify an identifier"
+        end
+      end
+    end
+
+		def validate(row, header = nil)
+			match = self.match(row, header).to_s
+			if self.validator.respond_to?(:call) 
+				result = self.validator.call(match)
+				verb = "pass"
+			else
+				result = (self.validator === match)
+				verb = "match"
+			end
+
+			unless result
+				{ valid: false, error: "#{self.identifier.inspect} must #{verb} #{self.validator}, but was #{match.inspect}"}
+			else
+				{ valid: true }
+			end
+		end
+
+		def match(row, header = nil)
+			case self.matcher
+			when Integer
+				row[matcher-1]
+			else
+				raise ArgumentError, 'No header is provided, but a matcher other than an Integer requires one' unless header
+				index = header.index  { |n| self.matcher === n }
+				index ? row[index] : nil
+			end
+		end
+
+		def process(row, header = nil)
+			if match = self.match(row, header)
+				self.converter ? self.converter.call(match) : match
+			end
+		end
+
+		def ivar_symbol
+			:"@#{self.identifier}"
+		end
+	end
+end

data/lib/fight_csv/record.rb

@@ -0,0 +1,91 @@
+module FightCSV
+  module Record
+    extend ActiveSupport::Concern
+
+    module ClassMethods
+      def schema=(schema)
+        @schema = schema
+      end
+
+      def records(io)
+        data_source = DataSource.new(io: io)
+        data_source.map { |row,additions|self.new(row, additions) }
+      end
+
+      def import(io)
+        Enumerator.new do |yielder|
+          record = self.new
+          data_source = DataSource.new(io: io)
+          data_source.each do |row, additions|
+            record.header = additions[:header]
+            record.row = row
+            yielder << record
+          end
+        end
+      end
+
+      def schema(filename = nil, &block)
+        if filename || block
+          @schema = Schema.new(filename, &block) 
+        else
+          @schema
+        end
+      end
+    end
+
+    module InstanceMethods
+      constructable :schema, validate_type: Schema, accessible: true
+      constructable :header, accessible: true
+
+      attr_accessor :row
+      attr_reader :errors
+
+
+      def initialize(row = nil,options = {})
+        @schema ||= self.class.schema
+        self.row = row if row
+      end
+
+      def row=(raw_row)
+        @raw_row = raw_row
+        @row = Hash[self.schema.fields.map { |field| [field.identifier,field.process(@raw_row, @header)] }]
+      end
+
+      def fields
+        Hash[schema.fields.map { |field| [field.identifier, self.send(field.identifier)] }]
+      end
+
+      def schema=(schema)
+        super
+        self.row = @raw_row
+      end
+
+      def valid?
+        validation = self.validate
+        @errors = validate[:errors]
+        validation[:valid]
+      end
+
+      def validate
+        self.schema.fields.inject({valid: true, errors: []}) do |validation_hash, field|
+          validation_of_field = field.validate(@raw_row, @header)
+          validation_hash[:valid] &&= validation_of_field[:valid]
+          validation_hash[:errors] << validation_of_field[:error] if validation_of_field[:error]
+          validation_hash
+        end
+      end
+
+      def method_missing(meth, *args, &block)
+        if field = schema.fields.find { |field| /#{field.identifier}(=)?/ === meth }
+          if $1 == '='
+            @row[field.identifier] = args.first
+          else
+            @row[field.identifier]
+          end
+        else
+          super
+        end
+      end
+    end
+  end
+end

data/lib/fight_csv/schema.rb

@@ -0,0 +1,17 @@
+module FightCSV
+  class Schema
+    attr_accessor :fields
+    def initialize(filename = nil, &block)
+      self.fields = Array.new
+      if String === filename
+        self.instance_eval { eval(File.read(filename)) }
+      elsif block
+        self.instance_eval &block
+      end
+    end
+
+    def field(fieldname, constructor_hash = {})
+      self.fields << Field.new(fieldname, constructor_hash)
+    end
+  end
+end

data/lib/fight_csv.rb

@@ -0,0 +1,10 @@
+$LOAD_PATH << File.dirname(File.expand_path(__FILE__))
+require 'constructable'
+require 'active_support'
+require 'fight_csv/schema'
+require 'fight_csv/data_source'
+require 'fight_csv/field'
+require 'fight_csv/record'
+
+module FightCSV
+end