Use the config gem to manage configuration

Fixes #14

Author: mjgiarlo

.gitignore

@@ -8,3 +8,5 @@
 /spec/reports/
 /tmp/
 /spec/sensitive-fixtures/
+config/settings.local.yml
+config/settings/*.local.yml

README.md

@@ -35,7 +35,12 @@ Run `bin/extract` to run a named extractor and print output to STDOUT:
     $ bin/extract -s StanfordResearchers
     {"count":10,"firstPage":true,"lastPage":false,"page":1,"totalCount":29089,"totalPages":2909,"values":[{"administrativeAppointments":[...
 
-Note: if you need to run any of the extractors that inherit from `AbstractStanfordExtractor`, you will first need to obtain a token for the CAP API and set the `CAP_TOKEN` environment variable in your session.
+Note: if you need to run any of the extractors that inherit from `AbstractStanfordExtractor`, you will first need to obtain a token for the CAP API and set the `Settings.tokens.cap` value to this token. To set this value, either set an environment variable named `SETTINGS__TOKENS__CAP` or add the value for this to `config/settings.local.yml` (which is ignored under version control and should never be checked in), like so:
+
+```yaml
+tokens:
+  cap: 'foobar'
+```
 
 ### Transform
 
@@ -48,6 +53,10 @@ Run `bin/transform` to run a named transformer, based on [Traject](https://githu
 
 TBD
 
+## Configuration
+
+Rialto::Etl uses the [config gem](https://github.com/railsconfig/config) to manage configuration, allowing for flexible variation of configs between environments and hosts. By default, the gem assumes it is running in the `'production'` environment and will look for its configurations per the [config gem documentation](https://github.com/railsconfig/config#accessing-the-settings-object). To explicitly set the environment to `test` or `development`, set an environment variable named `ENV`.
+
 ## Help
 
     $ bin/extract -h

config/settings.yml

@@ -0,0 +1,7 @@
+# These settings can also be provided as environment variables, in the form, e.g.:
+#    SETTINGS__TOKENS__CAP=foobar
+#
+# The mapping is described in `./lib/rialto/etl/configuration.rb`.
+
+tokens:
+  cap: 'dummyvalue'

config/settings/development.yml

@@ -1,11 +1,43 @@
 # frozen_string_literal: true
 
-require 'rialto/etl/version'
+require 'config'
 require 'rialto/etl/extractors'
 require 'rialto/etl/transformers'
+require 'rialto/etl/version'
 
 module Rialto
   # The top-level Rialto::Etl module
   module Etl
+    Config.setup do |config|
+      # Name of the constant exposing loaded settings
+      config.const_name = 'Settings'
+
+      # Load environment variables from the `ENV` object and override any
+      # settings defined in files.
+      config.use_env = true
+
+      # Define ENV variable prefix deciding which variables to load into
+      # config.
+      config.env_prefix = 'SETTINGS'
+
+      # What string to use as level separator for settings loaded from ENV
+      # variables. Default value of '.' works well with Heroku, but you might
+      # want to change it for example for '__' to easy override settings from
+      # command line, where using dots in variable names might not be allowed
+      # (eg. Bash).
+      config.env_separator = '__'
+
+      # Ability to process variables names:
+      #   * nil  - no change
+      #   * :downcase - convert to lower case
+      config.env_converter = :downcase
+
+      # Parse numeric values as integers instead of strings.
+      config.env_parse_values = true
+    end
+
+    Config.load_and_set_settings(
+      Config.setting_files('config', ENV.fetch('ENV', 'production'))
+    )
   end
 end

config/settings/production.yml

@@ -86,7 +86,7 @@ def auth_client
         end
 
         def auth_code
-          @auth_code ||= Base64.strict_encode64("sul:#{ENV['CAP_TOKEN']}")
+          @auth_code ||= Base64.strict_encode64("sul:#{Settings.tokens.cap}")
         end
       end
     end

config/settings/test.yml

@@ -18,6 +18,7 @@ Gem::Specification.new do |spec|
   spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ['lib']
 
+  spec.add_dependency 'config'
   spec.add_dependency 'faraday'
   spec.add_dependency 'httpclient'
   spec.add_dependency 'rdf'

lib/rialto/etl.rb

@@ -86,7 +86,7 @@
 
   describe '#auth_code' do
     before do
-      allow(ENV).to receive(:[]).with('CAP_TOKEN').and_return('')
+      allow(Settings.tokens).to receive(:cap).and_return('')
     end
 
     subject(:code) { described_class.new.send(:auth_code) }

lib/rialto/etl/extractors/abstract_stanford_extractor.rb

@@ -1,9 +1,26 @@
 # frozen_string_literal: true
 
-require 'spec_helper'
-
 describe Rialto::Etl do
   it 'has a version number' do
     expect(Rialto::Etl::VERSION).not_to be nil
   end
+
+  describe 'configuration' do
+    it 'provides a configuration value for CAP token' do
+      expect(Settings.tokens.cap).not_to be_empty
+    end
+
+    describe 'overriding values via environment variables' do
+      let(:overridden_value) { 'dropthebeat' }
+
+      before do
+        ENV['SETTINGS__TOKENS__CAP'] = overridden_value
+        Settings.reload!
+      end
+
+      it 'works as configured' do
+        expect(Settings.tokens.cap).to eq overridden_value
+      end
+    end
+  end
 end