Merge pull request #1157 from MITLibraries/timx-211-nil-date-handling

Better error handling for dates

Author: jazairi

app/models/normalize_timdex.rb

@@ -38,17 +38,18 @@ def extract_title(record)
   end
 
   def extract_dates(dates)
-    # It is unlikely for a record to have more than one creation date, but just in case...
-    relevant_dates = dates.select { |date| date['kind'] == 'creation' }
+    # It is unlikely for a record to have more than one creation or publication date, but just in case...
+    relevant_dates = dates.select { |date| date['kind'] == 'creation' || date['kind'] == 'publication' }
 
-    # If the record *does* have more than one creation date, it's probably not worth determining which to display.
-    return if relevant_dates.count > 1
+    # If the record has no creation or publication date, stop here.
+    return if relevant_dates.empty?
 
+    # If the record *does* have more than one creation/pub date, just take the first one.
     relevant_date = relevant_dates.first
 
-    # We are only concerned with creation dates that are ranges, since we harvest ASpace metadata at the collection
+    # We are only concerned with creation/pub dates that are ranges, since we harvest ASpace metadata at the collection
     # level.
-    return unless relevant_date['kind'] == 'creation' && relevant_date['range'].present?
+    return unless relevant_date['range'].present?
 
     "#{relevant_date['range']['gte']}-#{relevant_date['range']['lte']}"
   end

test/models/normalize_timdex_test.rb

@@ -36,4 +36,46 @@ def aspace_records
     assert_match 'The Paul Earls archives contains a large number of music manuscript',
                  aspace_records['results'][0].blurb
   end
+
+  # Some ASpace records have a publication date range rather than a creation date range. The following regression test
+  # ensures that the NormalizeTimdex model does not error for such records.
+  test 'records with no creation date do not error' do
+    VCR.use_cassette('aspace publication date',
+                     allow_playback_repeats: true) do
+      raw_query = SearchTimdex.new.search('SOVEREIGN INTIMACY: PRIVATE MEDIA AND THE TRACES OF COLONIAL VIOLENCE')
+      assert_not raw_query['data']['search']['records'].first['dates'].first['kind'] == 'creation'
+      assert_nothing_raised do
+        NormalizeTimdex.new.to_result(raw_query, 'SOVEREIGN INTIMACY: PRIVATE MEDIA AND THE TRACES OF COLONIAL VIOLENCE')
+      end
+    end
+  end
+
+  # This is another regression test. Now that we know that records with no creation date will not error, we also want
+  # to ensure that records with a publication date will be normalized accordingly.
+  test 'publication dates are normalized' do
+    VCR.use_cassette('aspace publication date',
+                     allow_playback_repeats: true) do
+      raw_query = SearchTimdex.new.search('SOVEREIGN INTIMACY: PRIVATE MEDIA AND THE TRACES OF COLONIAL VIOLENCE')
+      normalized = NormalizeTimdex.new.to_result(raw_query, 'SOVEREIGN INTIMACY: PRIVATE MEDIA AND THE TRACES OF COLONIAL VIOLENCE')
+
+      assert_equal 'publication', raw_query['data']['search']['records'].first['dates'].first['kind']
+      assert_equal '1940', raw_query['data']['search']['records'].first['dates'].first['range']['gte']
+      assert_equal '1983', raw_query['data']['search']['records'].first['dates'].first['range']['lte']
+      assert_equal '1940-1983', normalized['results'][0].year
+    end
+  end
+
+  test 'normalizer selects the first of two relevant dates' do
+    VCR.use_cassette('aspace multiple creation dates') do
+      raw_query = SearchTimdex.new.search('Timurid Architecture Research Archive')
+      assert raw_query['data']['search']['records'].first['dates'].count > 1
+      assert_not_equal raw_query['data']['search']['records'].first['dates'].first,
+                       raw_query['data']['search']['records'].first['dates'].second
+
+      start_date = raw_query['data']['search']['records'].first['dates'].first['range']['gte']
+      end_date = raw_query['data']['search']['records'].first['dates'].first['range']['lte']
+      normalized = NormalizeTimdex.new.to_result(raw_query, 'Timurid Architecture Research Archive')
+      assert_equal "#{start_date}-#{end_date}", normalized['results'][0].year
+    end
+  end
 end