Merge pull request #72 from MITLibraries/tco52-import-hints

Create rake task for bulk reloading of SuggestedResource records

README.md

@@ -6,6 +6,26 @@ There is a `Makefile` that contains some useful command shortcuts for typical de
 
 To see a current list of commands, run `make help`.
 
+### Generating cassettes for tests
+
+We use [VCR](https://github.com/vcr/vcr) to record transactions with remote systems for testing. This includes the rake
+task for reloading Detector::SuggestedResource records, which do not yet have a standard provider. For the initial
+feature development, we have used a Lando environment with the following definition:
+
+```yml
+name: static
+recipe: lamp
+config:
+  webroot: .
+```
+
+If you need to regenerate these cassettes, the following procedure should be sufficient:
+
+1. Use the configuration above to ensure the needed files are visible at `http://static.lndo.site/filename.ext`.
+2. Delete any existing cassette files which need to be regenerated.
+3. Run the test(s).
+4. Commit the resulting files along with your other work.
+
 ## Environment Variables
 
 ### Required

app/models/detector/suggested_resource.rb

@@ -53,5 +53,28 @@ def calculate_fingerprint(old_phrase)
       # Rejoin tokens
       tokens.join(' ')
     end
+
+    # This replaces all current Detector::SuggestedResource records with a new set from an imported CSV.
+    #
+    # @note This method is called by the suggested_resource:reload rake task.
+    #
+    # @param input [CSV::Table] An imported CSV file containing all Suggested Resource records. The CSV file must have
+    #                           at least three headers, named "Title", "URL", and "Phrase". Please note: these values
+    #                           are case sensitive.
+    def self.bulk_replace(input)
+      raise ArgumentError.new, 'Tabular CSV is required' unless input.instance_of?(CSV::Table)
+
+      # Need to check what columns exist in input
+      required_headers = %w[Title URL Phrase]
+      missing_headers = required_headers - input.headers
+      raise ArgumentError.new, "Some CSV columns missing: #{missing_headers}" unless missing_headers.empty?
+
+      Detector::SuggestedResource.delete_all
+
+      input.each do |line|
+        record = Detector::SuggestedResource.new({ title: line['Title'], url: line['URL'], phrase: line['Phrase'] })
+        record.save
+      end
+    end
   end
 end

lib/tasks/suggested_resources.rake

@@ -0,0 +1,28 @@
+# frozen_string_literal: true
+
+# These define tasks for managing our SuggestedResource records.
+namespace :suggested_resources do
+  # While we intend to use Dataclips for exporting these records when needed,
+  # we do need a way to import records from a CSV file.
+  desc 'Replace all Suggested Resources from CSV'
+  task :reload, [:addr] => :environment do |_task, args|
+    raise ArgumentError.new, 'URL is required' unless args.addr.present?
+
+    raise ArgumentError.new, 'Local files are not supported yet' unless URI(args.addr).scheme
+
+    Rails.logger.info('Reloading all Suggested Resource records from CSV')
+
+    url = URI.parse(args.addr)
+
+    raise ArgumentError.new, 'HTTP/HTTPS scheme is required' unless url.scheme.in?(%w[http https])
+
+    file = url.open.read.gsub("\xEF\xBB\xBF", '').force_encoding('UTF-8').encode
+    data = CSV.parse(file, headers: true)
+
+    Rails.logger.info("Record count before we reload: #{Detector::SuggestedResource.count}")
+
+    Detector::SuggestedResource.bulk_replace(data)
+
+    Rails.logger.info("Record count after we reload: #{Detector::SuggestedResource.count}")
+  end
+end

test/fixtures/files/suggested_resources.csv

@@ -0,0 +1,3 @@
+Title,URL,Phrase
+New Example,https://example.org,new example search
+Web of Science,https://libraries.mit.edu/webofsci,web of Science

test/tasks/suggested_resource_rake_test.rb

@@ -0,0 +1,68 @@
+# frozen_string_literal: true
+
+require 'test_helper'
+require 'rake'
+
+class SuggestedResourceRakeTest < ActiveSupport::TestCase
+  def setup
+    Tacos::Application.load_tasks if Rake::Task.tasks.empty?
+    Rake::Task['suggested_resources:reload'].reenable
+  end
+
+  test 'reload can accept a url' do
+    records_before = Detector::SuggestedResource.count # We have three fixtures at the moment
+    first_record_before = Detector::SuggestedResource.first
+    VCR.use_cassette('suggested_resource:reload from remote csv') do
+      remote_file = 'http://static.lndo.site/suggested_resources.csv'
+      Rake::Task['suggested_resources:reload'].invoke(remote_file)
+    end
+    refute_equal records_before, Detector::SuggestedResource.count
+    refute_equal first_record_before, Detector::SuggestedResource.first
+  end
+
+  test 'reload task errors without a file argument' do
+    error = assert_raises(ArgumentError) do
+      Rake::Task['suggested_resources:reload'].invoke
+    end
+    assert_equal 'URL is required', error.message
+  end
+
+  test 'reload errors on a local file' do
+    error = assert_raises(ArgumentError) do
+      local_file = Rails.root.join('test', 'fixtures', 'files', 'suggested_resources.csv').to_s
+      Rake::Task['suggested_resources:reload'].invoke(local_file)
+    end
+    assert_equal 'Local files are not supported yet', error.message
+  end
+
+  test 'reload fails with a non-CSV file' do
+    assert_raises(CSV::MalformedCSVError) do
+      VCR.use_cassette('suggested_resource:reload from remote non-csv') do
+        remote_file = 'http://static.lndo.site/suggested_resources.xlsx'
+        Rake::Task['suggested_resources:reload'].invoke(remote_file)
+      end
+    end
+  end
+
+  test 'reload fails unless all three columns are present: title, url, phrase' do
+    error = assert_raises(ArgumentError) do
+      VCR.use_cassette('suggested_resource:reload with missing field') do
+        remote_file = 'http://static.lndo.site/suggested_resources_missing_field.csv'
+        Rake::Task['suggested_resources:reload'].invoke(remote_file)
+      end
+    end
+    assert_equal 'Some CSV columns missing: ["Phrase"]', error.message
+  end
+
+  # assert_nothing_raised is viewed as an anti-pattern, but I'm leery of a test
+  # with no assertions. As a result, we use a single assertion to confirm
+  # something happened.
+  test 'reload succeeds if extra columns are present' do
+    records_before = Detector::SuggestedResource.count # We have three fixtures at the moment
+    VCR.use_cassette('suggested_resource:reload with extra field') do
+      remote_file = 'http://static.lndo.site/suggested_resources_extra.csv'
+      Rake::Task['suggested_resources:reload'].invoke(remote_file)
+    end
+    refute_equal records_before, Detector::SuggestedResource.count
+  end
+end