rialto-etl 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: ce6dc39a28a8eaf343077ff27d0f8c2db190cdde
+  data.tar.gz: 0b0d5f057a895517ddd28948f474938b2bec9684
+SHA512:
+  metadata.gz: da68daa6efc58935ab2506d66a0331dd07806185d763f9eaa907df4280d349d6216264205a1c3e37da501f90a6cbbf11d1be819c08485875521c85f96f5fb417
+  data.tar.gz: 11d1b2a16c38e672a313f98caae41b1f0e43099062fd10af0ae2082d70d17b03974159cebd43d141d7bd43b94694f67ae11bbfa53800501692a6f9cd71fb3b63

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/.rspec

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

data/.rubocop.yml

@@ -0,0 +1,8 @@
+inherit_from: .rubocop_todo.yml
+
+AllCops:
+  TargetRubyVersion: 2.3
+
+Style/MixinUsage:
+  Exclude:
+    - lib/rialto/etl/configs/stanford_organizations.rb

data/.rubocop_todo.yml

@@ -0,0 +1,13 @@
+# This configuration was generated by
+# `rubocop --auto-gen-config`
+# on 2017-12-19 16:17:32 -0800 using RuboCop version 0.52.0.
+# The point is for the user to remove these configuration records
+# one by one as the offenses are removed from the code base.
+# Note that changes in the inspected code, or installation of new
+# versions of RuboCop, may require this file to be generated again.
+
+# Offense count: 15
+# Configuration parameters: AllowHeredoc, AllowURI, URISchemes, IgnoreCopDirectives, IgnoredPatterns.
+# URISchemes: http, https
+Metrics/LineLength:
+  Max: 125

data/.travis.yml

@@ -0,0 +1,8 @@
+language: ruby
+sudo: false
+dist: trusty
+cache:
+  bundler: true
+rvm:
+  - 2.4.2
+before_install: gem install bundler

data/Gemfile

@@ -0,0 +1,9 @@
+# frozen_string_literal: true
+
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in rialto-etl.gemspec
+gemspec
+
+gem 'pry'
+gem 'pry-byebug'

data/README.md

@@ -0,0 +1,64 @@
+# Rialto::Etl
+
+[![Build Status](https://travis-ci.org/sul-dlss-labs/rialto-etl.svg?branch=master)](https://travis-ci.org/sul-dlss-labs/rialto-etl)
+
+Rialto::Etl is a set of ETL tools for RIALTO, Stanford University Libraries' research intelligence project
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'rialto-etl'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install rialto-etl
+
+## Usage
+
+### Extract
+
+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.
+
+### Transform
+
+Run `bin/transform` to run a named transformer, based on [Traject](https://github.com/traject/traject), on a named input file and print output to STDOUT:
+
+    $ bin/transform -s StanfordOrganizationsToVivo -i stanford_organizations.json
+    {"@id":"http://authorities.stanford.edu/orgs#vice-provost-for-undergraduate-education/stanford-introductory-studies/freshman-and-sophomore-programs","@type":"http://vivoweb.org/ontology/core#Division","rdfs:label":"Freshman and Sophomore Programs","vivo:abbreviation":["FFQH"]}
+
+### Load
+
+TBD
+
+## Help
+
+    $ bin/extract -h
+    Usage: bin/extract [options]
+        -n, --name NAME                Name of the extractor to run (REQUIRED)
+
+    $ bin/transform -h
+    Usage: bin/transform [options]
+        -n, --name NAME                Name of the transformer to run (REQUIRED)
+        -i, --input-file FILENAME      Name of file holding data to be transformed (REQUIRED)
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also 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`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/sul-dlss-labs/rialto-etl.

data/Rakefile

@@ -0,0 +1,18 @@
+# frozen_string_literal: true
+
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
+require 'rubocop/rake_task'
+
+desc 'Run style checker'
+RuboCop::RakeTask.new(:rubocop) do |task|
+  task.fail_on_error = true
+end
+
+RSpec::Core::RakeTask.new(:spec)
+
+task ci: [:rubocop] do
+  Rake::Task['spec'].invoke
+end
+
+task default: :ci

data/bin/console

@@ -0,0 +1,15 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require 'bundler/setup'
+require 'rialto/etl'
+
+# 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/extract

@@ -0,0 +1,19 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require 'bundler/setup'
+require 'optparse'
+require 'rialto/etl'
+
+options = {}
+
+OptionParser.new do |parser|
+  parser.banner = 'Usage: bin/extract [options]'
+  parser.on('-n', '--name NAME', 'Name of the extractor to run (REQUIRED)') do |value|
+    options[:name] = value
+  end
+end.parse!
+
+raise OptionParser::MissingArgument, '-n NAME' unless options[:name]
+
+puts Rialto::Etl::Extractors.const_get(options[:name]).new.extract

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/bin/transform

@@ -0,0 +1,23 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require 'bundler/setup'
+require 'optparse'
+require 'rialto/etl'
+
+options = {}
+
+OptionParser.new do |parser|
+  parser.banner = 'Usage: bin/transform [options]'
+  parser.on('-n', '--name NAME', 'Name of the transformer to run (REQUIRED)') do |value|
+    options[:name] = value
+  end
+  parser.on('-i', '--input-file FILENAME', 'Name of file holding data to be transformed (REQUIRED)') do |value|
+    options[:input] = value
+  end
+end.parse!
+
+raise OptionParser::MissingArgument, '-n NAME' unless options[:name]
+raise OptionParser::MissingArgument, '-i FILENAME' unless options[:input]
+
+Rialto::Etl::Transformers.const_get(options[:name]).new(input: options[:input]).transform

data/lib/rialto/etl.rb

@@ -0,0 +1,11 @@
+# frozen_string_literal: true
+
+require 'rialto/etl/version'
+require 'rialto/etl/extractors'
+require 'rialto/etl/transformers'
+
+module Rialto
+  # The top-level Rialto::Etl module
+  module Etl
+  end
+end

data/lib/rialto/etl/configs/stanford_organizations.rb

@@ -0,0 +1,26 @@
+# frozen_string_literal: true
+
+extend TrajectPlus::Macros
+extend TrajectPlus::Macros::JSON
+
+settings do
+  provide 'writer_class_name', 'JsonWriter'
+  provide 'reader_class_name', 'Rialto::Etl::StanfordOrganizationsJsonReader'
+end
+
+# context_object = {
+#   '@context' => {
+#     obo: 'http://purl.obolibrary.org/obo/',
+#     rdfs: 'http://www.w3.org/2000/01/rdf-schema#',
+#     vcard: 'http://www.w3.org/2006/vcard/ns#',
+#     vivo: 'http://vivoweb.org/ontology/core#',
+#     stanford: 'http://authorities.stanford.edu/orgs#'
+#   }
+# }
+
+# puts context_object.to_json
+to_field '@id', extract_json('$.alias'), transform: transform(prepend: 'http://authorities.stanford.edu/orgs#'), single: true
+to_field '@type', extract_json('$.type', translation_map: 'stanford_organizations_to_vivo_types'), single: true
+to_field 'rdfs:label', extract_json('$.name'), single: true
+to_field 'rdfs:seeAlso', extract_json('$.url'), single: true
+to_field 'vivo:abbreviation', extract_json('$.orgCodes'), single: true

data/lib/rialto/etl/extractors.rb

@@ -0,0 +1,12 @@
+# frozen_string_literal: true
+
+require 'rialto/etl/extractors/stanford_researchers'
+require 'rialto/etl/extractors/stanford_organizations'
+
+module Rialto
+  module Etl
+    # A module to hold extractors
+    module Extractors
+    end
+  end
+end

data/lib/rialto/etl/extractors/abstract_stanford_extractor.rb

@@ -0,0 +1,86 @@
+# frozen_string_literal: true
+
+require 'faraday'
+require 'openssl'
+require 'base64'
+require 'json'
+
+module Rialto
+  module Etl
+    module Extractors
+      # Abstract class hitting Stanford APIs using Stanford authz
+      class AbstractStanfordExtractor
+        attr_reader :access_token_expiry_time
+
+        def extract
+          raise NotImplementedError, 'Implement #extract in a child class'
+        end
+
+        private
+
+        def client
+          connection(uri: 'https://api.stanford.edu').tap do |conn|
+            conn.headers['Authorization'] = access_token
+          end
+        end
+
+        def connection(uri:)
+          Faraday.new(uri, headers: connection_headers) do |connection|
+            connection.request :retry, max: 3, interval: 0.8, interval_randomness: 0.2, backoff_factor: 2
+            connection.ssl.update(verify: true, verify_mode: OpenSSL::SSL::VERIFY_PEER)
+            connection.use Faraday::Response::RaiseError
+            connection.adapter :httpclient
+            connection.options.timeout = 500
+            connection.options.open_timeout = 10
+          end
+        end
+
+        def connection_headers
+          {
+            accept: 'application/json',
+            content_type: 'application/json'
+          }
+        end
+
+        def access_token
+          reset_access_token! if token_expired?
+          @access_token ||= begin
+                              response = auth_client.get '?grant_type=client_credentials'
+                              raise 'Failed to authenticate' unless response.success?
+                              auth_data = JSON.parse(response.body)
+                              reset_expiry_time!(expires_in: auth_data['expires_in'])
+                              "Bearer #{auth_data['access_token']}"
+                            end
+        end
+
+        def reset_access_token!
+          @access_token = nil
+        end
+
+        def token_expired?
+          access_token_expiry_time < current_time
+        rescue NoMethodError
+          true
+        end
+
+        def reset_expiry_time!(expires_in:)
+          @access_token_expiry_time = current_time + expires_in.to_i
+        end
+
+        def current_time
+          Time.local(*Time.now).to_i
+        end
+
+        def auth_client
+          @auth_client ||= connection(uri: 'https://authz.stanford.edu/oauth/token').tap do |conn|
+            conn.headers['Authorization'] = "Basic #{auth_code}"
+          end
+        end
+
+        def auth_code
+          @auth_code ||= Base64.strict_encode64("sul:#{ENV['CAP_TOKEN']}")
+        end
+      end
+    end
+  end
+end

data/lib/rialto/etl/extractors/stanford_organizations.rb

@@ -0,0 +1,18 @@
+# frozen_string_literal: true
+
+require 'rialto/etl/extractors/abstract_stanford_extractor'
+
+module Rialto
+  module Etl
+    module Extractors
+      # Stanford CAP API for orgs
+      class StanfordOrganizations < AbstractStanfordExtractor
+        def extract
+          client.get('/cap/v1/orgs/stanford?p=1&ps=10').body
+        rescue StandardError => exception
+          puts "Error: #{exception.message}"
+        end
+      end
+    end
+  end
+end

data/lib/rialto/etl/extractors/stanford_researchers.rb

@@ -0,0 +1,18 @@
+# frozen_string_literal: true
+
+require 'rialto/etl/extractors/abstract_stanford_extractor'
+
+module Rialto
+  module Etl
+    module Extractors
+      # Stanford Profiles API
+      class StanfordResearchers < AbstractStanfordExtractor
+        def extract
+          client.get('/profiles/v1?p=1&ps=10').body
+        rescue StandardError => exception
+          puts "Error: #{exception.message}"
+        end
+      end
+    end
+  end
+end

data/lib/rialto/etl/stanford_organizations_json_reader.rb

@@ -0,0 +1,27 @@
+# frozen_string_literal: true
+
+module Rialto
+  module Etl
+    # Read JSON that maps to Stanford orgs
+    class StanfordOrganizationsJsonReader < TrajectPlus::JsonReader
+      def each(&block)
+        yield_children(json, block)
+      end
+
+      private
+
+      def yield_children(hash, block)
+        block.call(hash)
+        children = children_path(hash)
+        return if children.blank?
+        children.each do |child|
+          yield_children(child, block)
+        end
+      end
+
+      def children_path(hash)
+        JsonPath.on(hash, '$.children').first
+      end
+    end
+  end
+end

data/lib/rialto/etl/transformers.rb

@@ -0,0 +1,11 @@
+# frozen_string_literal: true
+
+require 'rialto/etl/transformers/stanford_organizations_to_vivo'
+
+module Rialto
+  module Etl
+    # A module to hold transformers
+    module Transformers
+    end
+  end
+end

data/lib/rialto/etl/transformers/stanford_organizations_to_vivo.rb

@@ -0,0 +1,33 @@
+# frozen_string_literal: true
+
+require 'traject_plus'
+require 'rialto/etl/stanford_organizations_json_reader'
+
+module Rialto
+  module Etl
+    module Transformers
+      # Transformer turning Stanford org info into Vivo format
+      class StanfordOrganizationsToVivo
+        attr_reader :input
+
+        def initialize(input:)
+          @input = input
+        end
+
+        def transform
+          File.open(input, 'r') do |stream|
+            transformer.process(stream)
+          end
+        end
+
+        private
+
+        def transformer
+          @transformer ||= Traject::Indexer.new.tap do |indexer|
+            indexer.load_config_file('lib/rialto/etl/configs/stanford_organizations.rb')
+          end
+        end
+      end
+    end
+  end
+end

data/lib/rialto/etl/version.rb

@@ -0,0 +1,7 @@
+# frozen_string_literal: true
+
+module Rialto
+  module Etl
+    VERSION = '0.0.1'
+  end
+end

data/lib/translation_maps/stanford_organizations_to_vivo_types.yaml

@@ -0,0 +1,5 @@
+DIVISION: 'http://vivoweb.org/ontology/core#Division'
+SUB_DIVISION: 'http://vivoweb.org/ontology/core#Division'
+ROOT: 'http://vivoweb.org/ontology/core#University'
+SCHOOL: 'http://vivoweb.org/ontology/core#School'
+DEPARTMENT: 'http://vivoweb.org/ontology/core#Department'

data/mapping.md

@@ -0,0 +1,22 @@
+TODO: wrap below mappings in @graph => {}
+
+each mapping should include: @id, @type, rdfs:label, one or more obo:BFO\_0000050 or obo:BFO\_0000051
+
+alias (string) => @id http://authorities.stanford.edu/orgs#{alias}
+browsable (boolean) => ignore
+children (array) => keep track of parent, iterate over values (for each obo:BFO\_0000050/partOf) and map, keep track of children for obo:BFO\_0000051/hasPart
+name (string) => rdfs:label
+onboarding (boolean) => ignore
+orgCodes (array) => vivo:abbreviation
+type (string) => see type mappings
+url (string) => rdfs:seeAlso
+
+type mappings
+
+DIVISION        @type: http://vivoweb.org/ontology/core#Division
+SUB_DIVISION    @type: http://vivoweb.org/ontology/core#Division
+ROOT            @type: http://vivoweb.org/ontology/core#University
+SCHOOL          @type: http://vivoweb.org/ontology/core#School
+DEPARTMENT      @type: http://vivoweb.org/ontology/core#Department
+
+

data/rialto-etl.gemspec

@@ -0,0 +1,29 @@
+# frozen_string_literal: true
+
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'rialto/etl/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'rialto-etl'
+  spec.version       = Rialto::Etl::VERSION
+  spec.authors       = ['Michael J. Giarlo']
+  spec.email         = ['mjgiarlo@stanford.edu']
+
+  spec.summary       = "ETL tools for RIALTO, Stanford University Libraries' research intelligence project"
+  spec.homepage      = 'https://github.com/sul-dlss-labs/rialto-etl'
+
+  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 'faraday'
+  spec.add_dependency 'httpclient'
+  spec.add_dependency 'traject_plus', '>= 0.0.2'
+
+  spec.add_development_dependency 'bundler', '~> 1.11'
+  spec.add_development_dependency 'rake', '~> 10.0'
+  spec.add_development_dependency 'rspec', '~> 3.0'
+  spec.add_development_dependency 'rubocop', '~> 0.52.0'
+end

metadata

@@ -0,0 +1,167 @@
+--- !ruby/object:Gem::Specification
+name: rialto-etl
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Michael J. Giarlo
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2017-12-22 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: faraday
+  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: httpclient
+  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: traject_plus
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.0.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: 0.0.2
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.11'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.11'
+- !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'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.52.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.52.0
+description: 
+email:
+- mjgiarlo@stanford.edu
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".rubocop.yml"
+- ".rubocop_todo.yml"
+- ".travis.yml"
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/extract
+- bin/setup
+- bin/transform
+- lib/rialto/etl.rb
+- lib/rialto/etl/configs/stanford_organizations.rb
+- lib/rialto/etl/extractors.rb
+- lib/rialto/etl/extractors/abstract_stanford_extractor.rb
+- lib/rialto/etl/extractors/stanford_organizations.rb
+- lib/rialto/etl/extractors/stanford_researchers.rb
+- lib/rialto/etl/stanford_organizations_json_reader.rb
+- lib/rialto/etl/transformers.rb
+- lib/rialto/etl/transformers/stanford_organizations_to_vivo.rb
+- lib/rialto/etl/version.rb
+- lib/translation_maps/stanford_organizations_to_vivo_types.yaml
+- mapping.md
+- rialto-etl.gemspec
+homepage: https://github.com/sul-dlss-labs/rialto-etl
+licenses: []
+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: 2.6.13
+signing_key: 
+specification_version: 4
+summary: ETL tools for RIALTO, Stanford University Libraries' research intelligence
+  project
+test_files: []