WIP towards LCSH detector

The regex is detecting `--` characters surrounded by spaces, but more work
is needed. More tests are needed.

Update annotations

app/graphql/types/standard_identifiers_type.rb

@@ -2,10 +2,10 @@
 
 module Types
   class StandardIdentifiersType < Types::BaseObject
-    description 'A detector for standard identifiers in search terms. Currently supported: ISBN, ISSN, PMID, DOI'
+    description 'A detector for standard identifiers in search terms. Currently supported: DOI, ISBN, ISSN, LCSH, PMID'
 
     field :details, DetailsType, description: 'Additional information about the detected identifier(s)'
-    field :kind, String, null: false, description: 'The type of identifier detected (one of ISBN, ISSN, PMID, DOI)'
+    field :kind, String, null: false, description: 'The type of identifier detected (one of DOI, ISBN, ISSN, LCSH, PMID)'
     field :value, String, null: false, description: 'The identifier detected in the search term'
 
     # details does external lookups and should only be run if the fields
@@ -18,6 +18,8 @@ def details
         LookupIsbn.new.info(@object[:value])
       when :issn
         LookupIssn.new.info(@object[:value])
+      when :lcsh
+        @object[:value]
       when :pmid
         LookupPmid.new.info(@object[:value].split.last)
       end

app/models/detector/standard_identifiers.rb

@@ -1,7 +1,7 @@
 # frozen_string_literal: true
 
 class Detector
-  # Detector::StandardIdentifiers detects the identifiers DOI, ISBN, ISSN, PMID.
+  # Detector::StandardIdentifiers detects the identifiers DOI, ISBN, ISSN, LCSH, PMID.
   # See /docs/reference/pattern_detection_and_enhancement.md for details.
   class StandardIdentifiers
     attr_reader :identifiers
@@ -55,10 +55,12 @@ def match(pattern, term)
     end
 
     # term_patterns are regex patterns to be applied to the basic search box input
+    # The LCSH regex is looking for the separator used in the Bento UI, so this is an area for later improvement.
     def term_patterns
       {
         isbn: /\b(ISBN-*(1[03])* *(: ){0,1})*(([0-9Xx][- ]*){13}|([0-9Xx][- ]*){10})\b/,
         issn: /\b[0-9]{4}-[0-9]{3}[0-9xX]\b/,
+        lcsh: /\s--\s/,
         pmid: /\b((pmid|PMID):\s?(\d{7,8}))\b/,
         doi: %r{\b10\.(\d+\.*)+/(([^\s.])+\.*)+\b}
       }

app/models/metrics/algorithms.rb

@@ -15,6 +15,7 @@
 #  updated_at               :datetime         not null
 #  journal_exact            :integer
 #  suggested_resource_exact :integer
+#  lcsh                     :integer
 #
 module Metrics
   # Algorithms aggregates statistics for matches for all SearchEvents
@@ -48,7 +49,7 @@ def generate(month = nil)
                   count_matches(SearchEvent.includes(:term))
                 end
       Metrics::Algorithms.create(month:, doi: matches[:doi], issn: matches[:issn], isbn: matches[:isbn],
-                                 pmid: matches[:pmid], journal_exact: matches[:journal_exact],
+                                 lcsh: matches[:lcsh], pmid: matches[:pmid], journal_exact: matches[:journal_exact],
                                  suggested_resource_exact: matches[:suggested_resource_exact],
                                  unmatched: matches[:unmatched])
     end
@@ -89,7 +90,7 @@ def event_matches(event, matches)
     # @param matches [Hash] a Hash that keeps track of how many of each algorithm we match
     # @return [Array] an array of matched StandardIdentifiers
     def match_standard_identifiers(event, matches)
-      known_ids = %i[unmatched pmid isbn issn doi]
+      known_ids = %i[unmatched doi isbn issn lcsh pmid]
       ids = Detector::StandardIdentifiers.new(event.term.phrase)
 
       known_ids.each do |id|

db/migrate/20241001205152_add_lcsh_to_metrics_algorithm.rb

@@ -0,0 +1,5 @@
+class AddLcshToMetricsAlgorithm < ActiveRecord::Migration[7.1]
+  def change
+    add_column :metrics_algorithms, :lcsh, :integer
+  end
+end

test/models/detector/standard_identifiers_test.rb

@@ -137,6 +137,34 @@ class StandardIdentifiersTest < ActiveSupport::TestCase
       end
     end
 
+    # LCSH 
+    test 'lcsh detected' do
+      true_samples = [
+        'Geology -- Massachusetts',
+        'Space vehicles -- Materials -- Congresses'
+      ]
+
+      true_samples.each do |term|
+        actual = Detector::StandardIdentifiers.new(term).identifiers
+
+        assert_includes(actual, :lcsh)
+      end
+
+
+      false_samples = [
+        'Geology of Massachusetts',
+        'Geology-Massachusetts',
+        'Geology--Massachusetts'
+      ]
+
+      false_samples.each do |term|
+        actual = Detector::StandardIdentifiers.new(term).identifiers
+
+        refute_includes(actual, :lcsh)
+      end
+    end
+
+    # DOI tests
     test 'doi detected in string' do
       actual = Detector::StandardIdentifiers.new('"Quantum tomography: Measured measurement", Markus Aspelmeyer, nature physics "\
                                        "January 2009, Volume 5, No 1, pp11-12; [ doi:10.1038/nphys1170 ]').identifiers

test/models/metrics/algorithms_test.rb

@@ -15,6 +15,7 @@
 #  updated_at               :datetime         not null
 #  journal_exact            :integer
 #  suggested_resource_exact :integer
+#  lcsh                     :integer
 #
 require 'test_helper'