psu_dir 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 38f15c203dbe7e880535a394e06e6cece1299fe19294054e81b12ff531459ffa
+  data.tar.gz: 924167e4aa0e213a501bcab5b8d9b5734029bf79539408b2839d370e0e720f60
+SHA512:
+  metadata.gz: b412309069f1e42f9d6a53d1bb2374ae365610265233dde4a285b9c9b5a73611d453f2c3867bfc543848dbb7e089b7ad433a46d45bd5e77cadac92e8cbdd994e
+  data.tar.gz: 6e74c9007572462b57df8e569c72f1643ccb44ce0e286b0480f705cfdda5c782895b877548f05736dbe4b1f983edf037840327b968d9f96a5e6eab3a4c5ecc71

data/.gitignore

@@ -0,0 +1,13 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
+# rspec failure tracking
+.rspec_status
+Gemfile.lock
+config/hydra-ldap.yml

data/.rspec

@@ -0,0 +1,5 @@
+--color
+--tty
+--format progress
+--profile
+--require spec_helper

data/.rubocop.yml

@@ -0,0 +1,4 @@
+inherit_from: .rubocop_todo.yml
+
+inherit_gem:
+  niftany: niftany_rubocop.yml

data/.rubocop_todo.yml

@@ -0,0 +1,35 @@
+# This configuration was generated by
+# `rubocop --auto-gen-config`
+# on 2018-05-15 10:32:26 -0400 using RuboCop version 0.52.1.
+# 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: 7
+# Configuration parameters: CountComments, ExcludedMethods.
+Metrics/BlockLength:
+  Max: 170
+
+# Offense count: 9
+# Configuration parameters: .
+# SupportedStyles: have_received, receive
+RSpec/MessageSpies:
+  EnforcedStyle: receive
+
+# Offense count: 6
+# Configuration parameters: AggregateFailuresByDefault.
+RSpec/MultipleExpectations:
+  Max: 4
+
+# Offense count: 6
+# Configuration parameters: Max.
+RSpec/NestedGroups:
+  Exclude:
+    - 'spec/psu_dir/ldap_user_spec.rb'
+
+# Offense count: 60
+# Configuration parameters: AllowHeredoc, AllowURI, URISchemes, IgnoreCopDirectives, IgnoredPatterns.
+# URISchemes: http, https
+Metrics/LineLength:
+  Max: 279

data/.travis.yml

@@ -0,0 +1,13 @@
+language: ruby
+cache:
+  bundler: true
+rvm:
+  - 2.4.1
+stages:
+  - rubocop
+  - test
+jobs:
+  include:
+    - script: cp config/travis/hydra-ldap.yml config/hydra-ldap.yml && bundle exec rspec
+    - stage: rubocop
+      script: bundle exec rubocop

data/Gemfile

@@ -0,0 +1,8 @@
+# frozen_string_literal: true
+
+source 'https://rubygems.org'
+
+git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in psu_dir.gemspec
+gemspec

data/LICENSE.md

@@ -0,0 +1,177 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS

data/README.md

@@ -0,0 +1,64 @@
+# PsuDir
+
+Directory services integrations at Penn State University.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'psu_dir'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install psu_dir
+
+## Usage
+
+Instantiate the service with a string `PsuDir::Name.new("jbd123")` and then
+call the disambiguate method which returns an array of people in the format `[{:id=>"jbd123", :given_name=>"Jane B", :surname=>"Doe", :email=>"jbd123@psu.edu", :affiliation=>["STAFF"]}]`
+
+What you pass in as the name can vary from an id to a list of names and or emails.
+
+### Basic usage with a id
+
+You can call disambiguate with an id, which then calls ldap and returns a record.
+
+```
+service = PsuDir::Name.new("cam156") # #<PsuDir::Name:0x007fab36190710 @name="cam156", @email_for_name_cache={}, @results=[]>
+service.disambiguate #[{:id=>"cam156", :given_name=>"CAROLYN A", :surname=>"COLE", :email=>"cam156@psu.edu", :affiliation=>["STAFF"]}]
+```
+
+### Basic usage with a name
+
+```
+service = PsuDir::Name.new("Carolyn Cole") # #<PsuDir::Name:0x007fab36190710 @name="Carolyn Cole", @email_for_name_cache={}, @results=[]>
+service.disambiguate #[{:id=>"cam156", :given_name=>"CAROLYN A", :surname=>"COLE", :email=>"cam156@psu.edu", :affiliation=>["STAFF"]}]
+```
+
+### Usage with last name and first name part
+```
+service = PsuDir::Name.new("Carol Cole") # #<PsuDir::Name:0x007fab36190710 @name="Carol Cole", @email_for_name_cache={}, @results=[]>
+service.disambiguate #[{:id=>"cam156", :given_name=>"CAROLYN A", :surname=>"COLE", :email=>"cam156@psu.edu", :affiliation=>["STAFF"]}]
+```
+
+### Usage with last name and first name part
+```
+service = PsuDir::Name.new("Carol Cole, cam156") # #<PsuDir::Name:0x007fab36190710 @name="Carol Cole", @email_for_name_cache={}, @results=[]>
+service.disambiguate #[{:id=>"cam156", :given_name=>"CAROLYN A", :surname=>"COLE", :email=>"cam156@psu.edu", :affiliation=>["STAFF"]}]
+```
+
+### Usage with a list of names
+```
+service = PsuDir::Name.new("Carol Cole; Adam Wead") ##<PsuDir::Name:0x007fab32cf2418 @name="Carol Cole; Adam Wead", @email_for_name_cache={}, @results=[]>
+service.disambiguate #[{:id=>"cam156", :given_name=>"CAROLYN A", :surname=>"COLE", :email=>"cam156@psu.edu", :affiliation=>["STAFF"]}, {:id=>"agw13", :given_name=>"ADAM GARNER", :surname=>"WEAD", :email=>"agw13@psu.edu", :affiliation=>["STAFF"]}]
+```
+
+## Contributing
+
+Bug reports and pull requests are welcome!

data/Rakefile

@@ -0,0 +1,8 @@
+# frozen_string_literal: true
+
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
+
+RSpec::Core::RakeTask.new(:spec)
+
+task default: :spec

data/bin/console

@@ -0,0 +1,15 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require 'bundler/setup'
+require 'psu_dir'
+
+# 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(__FILE__)

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/config/travis/hydra-ldap.yml

@@ -0,0 +1,24 @@
+development:
+  host: ldap.example.com
+  port: 389
+  # username: cn=admin,dc=example,dc=com
+  # password: simple77
+  group_base: dc=psu,dc=edu
+  base: dc=example,dc=com
+  uid: uid
+test:
+  host: ldap.example.com
+  port: 389
+  # username: cn=admin,dc=example,dc=com
+  # password: simple77
+  group_base: dc=psu,dc=edu
+  # base: dc=example,dc=com
+  # uid: uid
+production:
+  host: ldap.example.com
+  port: 389
+  #username: cn=admin,dc=example,dc=com
+  #password: <%= ENV['LDAP_PASSWORD'] %>
+  group_base: dc=psu,dc=edu
+  base: dc=example,dc=com
+  uid: uid

data/lib/psu_dir.rb

@@ -0,0 +1,28 @@
+# frozen_string_literal: true
+
+require 'psu_dir/version'
+require 'net-ldap'
+require 'hydra-ldap'
+require 'namae'
+require 'logger'
+require 'mail'
+
+module PsuDir
+  autoload :Disambiguate, 'psu_dir/disambiguate'
+  autoload :LdapUser, 'psu_dir/ldap_user'
+  autoload :Ldap, 'psu_dir/ldap'
+
+  class << self
+    def logger
+      @logger ||= if Rails.try(:logger)
+                    Rails.logger
+                  else
+                    Logger.new(STDOUT)
+                  end
+    end
+
+    def ldap_unwilling_sleep
+      @ldap_unwilling_sleep ||= ENV.fetch('ldap_unwilling_sleep', 2).to_i
+    end
+  end
+end

data/lib/psu_dir/disambiguate.rb

@@ -0,0 +1,9 @@
+# frozen_string_literal: true
+
+module PsuDir::Disambiguate
+  autoload :Base, 'psu_dir/disambiguate/base'
+  autoload :Name, 'psu_dir/disambiguate/name'
+  autoload :Email, 'psu_dir/disambiguate/email'
+  autoload :User, 'psu_dir/disambiguate/user'
+  autoload :MultipleUserError, 'psu_dir/disambiguate/multiple_user_error'
+end

data/lib/psu_dir/disambiguate/base.rb

@@ -0,0 +1,20 @@
+# frozen_string_literal: true
+
+module PsuDir::Disambiguate
+  # This class allows you to use LDAP to disambiguate a text name
+  #
+  class Base
+    class << self
+      private
+
+      def ldap_attributes_for_id(id)
+        users = User.directory_attributes(id, ldap_attrs)
+        users.count < 1 ? nil : users
+      end
+
+      def ldap_attrs
+        %i[uid givenname sn mail eduPersonPrimaryAffiliation displayname]
+      end
+    end
+  end
+end

data/lib/psu_dir/disambiguate/email.rb

@@ -0,0 +1,33 @@
+# frozen_string_literal: true
+
+module PsuDir::Disambiguate
+  # This class allows you to use LDAP to extract user information
+  #  from an email or list of emails
+  #
+  class Email < Base
+    class << self
+      def disambiguate(email)
+        return unless email.include?('@psu.edu')
+        email_in_name(email)
+      end
+
+      private
+
+      def email_in_name(email_list)
+        parts = email_list.split(' ')
+        emails = parts.select { |part| part.include?('@') }
+        results = []
+        Array(emails).each do |email_str|
+          email = Mail::Address.new(email_str)
+          results << (ldap_attributes_for_id(email.local) || ldap_attributes_for_email(email.address) || [User.results_hash(mail: [email.address])]).first
+        end
+        results
+      end
+
+      def ldap_attributes_for_email(email)
+        users = User.query_ldap_by_mail(email, ldap_attrs)
+        users.count < 1 ? nil : users
+      end
+    end
+  end
+end

data/lib/psu_dir/disambiguate/multiple_user_error.rb

@@ -0,0 +1,8 @@
+# frozen_string_literal: true
+
+module PsuDir::Disambiguate
+  # This error is thrown if we get more than one user back from ldap for an input
+  #
+  class MultipleUserError < RuntimeError
+  end
+end

data/lib/psu_dir/disambiguate/name.rb

@@ -0,0 +1,125 @@
+# frozen_string_literal: true
+
+module PsuDir::Disambiguate
+  # This class allows you to use LDAP to disambiguate a text name
+  #
+  class Name < Base
+    class << self
+      def disambiguate(name)
+        return if name.blank?
+        results = ldap_attributes_for_id(name) # text includes login id
+        results ||= Email.disambiguate(name) # text includes email(s)
+        results ||= lookup_text_only_names(name) # straight text we need to query ldap
+        results
+      end
+
+      def clear_cache
+        @email_for_name_cache = {}
+      end
+
+      private
+
+      def lookup_text_only_names(multi_name)
+        results = separate_names(multi_name).map do |name|
+          lookup_name(clean_name(name))
+        end
+        results.reject(&:blank?)
+      end
+
+      def lookup_name(name)
+        query_result = email_for_name(name)
+        query_result ||= title_after_name(name) # try again without the titles
+        query_result
+      rescue MultipleUserError
+        return nil
+      end
+
+      def email_for_name(text_name)
+        return '' if text_name.blank? || word_count(text_name) < 2
+        return email_for_name_cache[text_name] if email_for_name_cache.key?(text_name)
+
+        email_for_name_cache[text_name] = translate_name_to_email(text_name)
+      end
+
+      # titles after the name that namae had trouble parsing
+      def title_after_name(text_name)
+        email_for_name(remove_titles(text_name))
+      end
+
+      def translate_name_to_email(text_name)
+        parsed = Namae::Name.parse(text_name)
+
+        result = try_name(parsed.given, parsed.family)
+        result ||= title_before_name(parsed)
+        result ||= two_words_in_last_name(text_name)
+        result
+      end
+
+      def try_name(given, family)
+        return nil if family.blank?
+
+        possible_users = User.query_ldap_by_name(given, family, ldap_attrs)
+        raise(MultipleUserError, "too name results for #{given} #{family}") if possible_users.count > 1
+        possible_users.first
+      end
+
+      def title_before_name(parsed)
+        return unless parsed.given && multi_word?(parsed.given)
+
+        parts = name_parts(parsed.given, 1)
+        return if only_initial?(parts[:family])
+
+        try_name(parts[:family], parsed.family)
+      end
+
+      def two_words_in_last_name(text_name)
+        return unless word_count(text_name) > 2
+
+        parts = name_parts(text_name, 2)
+        try_name(parts[:given], parts[:family])
+      end
+
+      def name_parts(text_name, last_name_count)
+        return if word_count(text_name) < (last_name_count + 1)
+
+        parts = split_name_parts(text_name)
+        first_name_count = parts.count - last_name_count
+        { given: parts.first(first_name_count).join(' '), family: parts.last(last_name_count).join(' ') }
+      end
+
+      def clean_name(name)
+        name.gsub(/\([^)]*\)/, '')
+          .gsub(/[^\w\s,']/, ' ')
+          .strip.squeeze(' ')
+      end
+
+      def multi_word?(name)
+        word_count(name) > 1
+      end
+
+      def word_count(name)
+        name.squeeze(' ').count(' ') + 1
+      end
+
+      def split_name_parts(name)
+        name.split(' ')
+      end
+
+      def only_initial?(name)
+        name.size <= 1
+      end
+
+      def separate_names(multi_name)
+        multi_name.split(/ and |;/)
+      end
+
+      def remove_titles(name)
+        name.split(',')[0]
+      end
+
+      def email_for_name_cache
+        @email_for_name_cache ||= {}
+      end
+    end
+  end
+end

data/lib/psu_dir/disambiguate/user.rb

@@ -0,0 +1,114 @@
+# frozen_string_literal: true
+
+module PsuDir::Disambiguate
+  # This class provides an api for querying LDAP with different portions of the user's
+  # information (name parts or id)
+  class User < PsuDir::Ldap
+    class << self
+      def directory_attributes(login, attrs = [])
+        filter = Net::LDAP::Filter.eq('uid', login)
+        result = get_users(filter, attrs)
+        format_users(result, attrs)
+      end
+
+      def query_ldap_by_mail(email, attrs = [])
+        filter = Net::LDAP::Filter.construct(email_filter(email))
+        users  = get_filtered_users(filter, attrs)
+        format_users(users, attrs)
+      end
+
+      def query_ldap_by_name(given_name, surname, attrs = [])
+        return [] if given_name.blank? # this method only work if we have a first name to play with
+
+        first_names = given_name.split(/[\s.]+/)
+        users = []
+        name_filters(first_names[0], first_names[1], surname).each do |filter|
+          users = get_filtered_users(filter, attrs)
+          break if users.count.positive? # stop running through the filters if we get results
+        end
+        format_users(users, attrs)
+      end
+
+      def get_filtered_users(name_filter, attrs = [])
+        attrs = (attrs + default_attributes).uniq
+        filter = Net::LDAP::Filter.construct("(& (& #{name_filter}) #{person_filter})")
+        get_users(filter, attrs)
+      end
+
+      def results_hash(opts)
+        {
+          id:          fetch(opts, :uid).first,
+          given_name:  fetch(opts, :givenname).first,
+          surname:     fetch(opts, :sn).first,
+          email:       fetch(opts, :mail).first,
+          affiliation: fetch(opts, :eduPersonPrimaryAffiliation, []),
+          displayname: fetch(opts, :displayname).first
+        }
+      end
+
+      private
+
+      def fetch(opts, key, default = [''])
+        opts[key].presence || default
+      end
+
+      def format_users(users, attrs)
+        user_attrs = attrs - default_attributes
+        users.map { |u| format_user(u, user_attrs) }
+      end
+
+      def format_user(user, extra_attrs)
+        hash = results_hash(user)
+        extra_attrs.each { |attr| hash[attr] = user[attr].first }
+        hash
+      end
+
+      def size_limit_exceeded?
+        Hydra::LDAP.connection.get_operation_result[:message] == 'Size Limit Exceeded'
+      end
+
+      def email_filter(email)
+        '(& (|'\
+        "  (psmailid=#{email})"\
+        "  (mail=#{email})"\
+        "  (psmailbox=#{email})"\
+        "  (edupersonprincipalname=#{email})"\
+        ") #{person_filter})"
+      end
+
+      def person_filter
+        '(|'\
+        '  (eduPersonPrimaryAffiliation=STUDENT)'\
+        '  (eduPersonPrimaryAffiliation=FACULTY)'\
+        '  (eduPersonPrimaryAffiliation=STAFF)'\
+        '  (eduPersonPrimaryAffiliation=EMPLOYEE)'\
+        '  (eduPersonPrimaryAffiliation=RETIREE)'\
+        '  (eduPersonPrimaryAffiliation=EMERITUS)'\
+        '  (eduPersonPrimaryAffiliation=MEMBER)'\
+        '))'
+      end
+
+      def name_filters(first_name, middle_name, surname)
+        filters = []
+        if middle_name.blank?
+          filters << "(givenname=#{first_name}) (sn=#{surname})"
+          filters << "(givenname=#{first_name}*) (sn=#{surname})"
+        else
+          filters << "(givenname=#{first_name}*) (givenname=* #{middle_name}*) (sn=#{surname})"
+          middle_initial = middle_name[0]
+          filters << "(givenname=#{first_name}* #{middle_initial}*) (sn=#{surname})"
+        end
+        filters << "(givenname=#{first_name}) (sn=#{surname})"
+        filters
+      end
+
+      def default_attributes
+        %i[uid givenname sn mail eduPersonPrimaryAffiliation displayname]
+      end
+
+      def cache
+        @cache ||= {}
+      end
+    end
+  end
+end

data/lib/psu_dir/ldap.rb

@@ -0,0 +1,39 @@
+# frozen_string_literal: true
+
+module PsuDir
+  class Ldap
+    class << self
+      def get_users(filter, fields = [])
+        retry_if { Hydra::LDAP.get_user(filter, fields) } || []
+      end
+
+      # Retries the LDAP command up to .tries times, or catches any other kind of LDAP error without retrying.
+      # return [block or nil]
+      def retry_if
+        tries.times.each do
+          result = yield
+          return result unless unwilling?
+          sleep(PsuDir.ldap_unwilling_sleep)
+        end
+        PsuDir.logger.warn 'LDAP is unwilling to perform this operation, try upping the number of tries'
+        nil
+      rescue Net::LDAP::Error => e
+        PsuDir.logger.warn "Error getting LDAP response: #{ldap_error_message(e)}"
+        nil
+      end
+
+      def tries
+        7
+      end
+
+      # Numeric code returned by LDAP if it is feeling "unwilling"
+      def unwilling?
+        Hydra::LDAP.connection.get_operation_result.code == 53
+      end
+
+      def ldap_error_message(e)
+        "#{Hydra::LDAP.connection.get_operation_result.message}\nException: #{e.exception}\n#{e.backtrace.join("\n")}"
+      end
+    end
+  end
+end

data/lib/psu_dir/ldap_user.rb

@@ -0,0 +1,35 @@
+# frozen_string_literal: true
+
+class PsuDir::LdapUser < PsuDir::Ldap
+  class << self
+    def get_groups(login)
+      return [] if login.blank?
+      retry_if { parse_ldap_groups(group_response_from_ldap(login)) } || []
+    end
+
+    def check_ldap_exist!(login)
+      return false if login.blank?
+      retry_if { Hydra::LDAP.does_user_exist?(Net::LDAP::Filter.eq('uid', login)) } || false
+    end
+
+    def filter_for(*people)
+      return '' if people.empty?
+      '(| ' + people.map { |p| "(eduPersonPrimaryAffiliation=#{p.to_s.upcase})" }.join(' ') + ')))'
+    end
+
+    private
+
+      def parse_ldap_groups(result)
+        return [] if result.empty?
+        result.first[:psmemberof].select { |y| y.start_with? 'cn=umg/' }.map do |x|
+          x.sub(/^cn=/, '').sub(/,dc=psu,dc=edu/, '')
+        end
+      end
+
+      # Response from LDAP
+      # We have to pass a block, see https://github.com/projecthydra-labs/hydra-ldap/issues/8
+      def group_response_from_ldap(login)
+        Hydra::LDAP.groups_for_user(Net::LDAP::Filter.eq('uid', login)) { |r| r }
+      end
+  end
+end

data/lib/psu_dir/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module PsuDir
+  VERSION = '0.1.0'
+end

data/psu_dir.gemspec

@@ -0,0 +1,35 @@
+# frozen_string_literal: true
+
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'psu_dir/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'psu_dir'
+  spec.version       = PsuDir::VERSION
+  spec.authors       = ['Carolyn Cole', 'Adam Wead']
+  spec.email         = ['cam156@psu.edu', 'amsterdamos@gmail.com']
+
+  spec.summary       = 'Directory services at Penn State University.'
+  spec.description   = "Performs queries against Penn State's directory services to find users and return preferred"\
+                       ' names, email address, and other information.'
+  spec.homepage      = 'https://github.com/psu-stewardship/psu_dir'
+  spec.licenses      = ['Apache-2.0']
+
+  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 'hydra-ldap'
+  spec.add_dependency 'mail', '~> 2.6'
+  spec.add_dependency 'namae', '0.9.3'
+  spec.add_dependency 'net-ldap', '~> 0.16.0'
+
+  spec.add_development_dependency 'bundler', '~> 1.16'
+  spec.add_development_dependency 'byebug', '~> 9.1'
+  spec.add_development_dependency 'niftany', '~> 0.0.2'
+  spec.add_development_dependency 'rake', '~> 10.0'
+  spec.add_development_dependency 'rspec', '~> 3.0'
+  spec.add_development_dependency 'rspec-its', '~> 1.2'
+end

metadata

@@ -0,0 +1,210 @@
+--- !ruby/object:Gem::Specification
+name: psu_dir
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Carolyn Cole
+- Adam Wead
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2018-05-15 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: hydra-ldap
+  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: mail
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.6'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.6'
+- !ruby/object:Gem::Dependency
+  name: namae
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 0.9.3
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 0.9.3
+- !ruby/object:Gem::Dependency
+  name: net-ldap
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.16.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.16.0
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+- !ruby/object:Gem::Dependency
+  name: byebug
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '9.1'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '9.1'
+- !ruby/object:Gem::Dependency
+  name: niftany
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.0.2
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.0.2
+- !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: rspec-its
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.2'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.2'
+description: Performs queries against Penn State's directory services to find users
+  and return preferred names, email address, and other information.
+email:
+- cam156@psu.edu
+- amsterdamos@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".rubocop.yml"
+- ".rubocop_todo.yml"
+- ".travis.yml"
+- Gemfile
+- LICENSE.md
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- config/travis/hydra-ldap.yml
+- lib/psu_dir.rb
+- lib/psu_dir/disambiguate.rb
+- lib/psu_dir/disambiguate/base.rb
+- lib/psu_dir/disambiguate/email.rb
+- lib/psu_dir/disambiguate/multiple_user_error.rb
+- lib/psu_dir/disambiguate/name.rb
+- lib/psu_dir/disambiguate/user.rb
+- lib/psu_dir/ldap.rb
+- lib/psu_dir/ldap_user.rb
+- lib/psu_dir/version.rb
+- psu_dir.gemspec
+homepage: https://github.com/psu-stewardship/psu_dir
+licenses:
+- Apache-2.0
+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: 2.7.6
+signing_key: 
+specification_version: 4
+summary: Directory services at Penn State University.
+test_files: []