Integrate TACOS with external lambda

.env.test

@@ -3,3 +3,6 @@ LINKRESOLVER_BASEURL=https://mit.primo.exlibrisgroup.com/discovery/openurl?insti
 [email protected]
 LIBKEY_KEY=FAKE_LIBKEY_KEY
 LIBKEY_ID=FAKE_LIBKEY_ID
+DETECTOR_LAMBDA_URL=http://localhost:3000
+DETECTOR_LAMBDA_PATH=/foo
+DETECTOR_LAMBDA_CHALLENGE_SECRET=secret_phrase

app/models/detector/citation.rb

@@ -10,26 +10,11 @@ class Detector
   # hallmarks of being a citation.
   # Phrases whose score is higher than the REQUIRED_SCORE value can be registered as a Detection.
   class Citation
-    attr_reader :score, :subpatterns, :summary
+    attr_reader :features, :score, :patterns, :summary
 
     # shared singleton methods
     extend Detector::BulkChecker
 
-    # Citation patterns are regular expressions which attempt to identify structures that are part of many citations.
-    # This object is used as part of the pattern_checker method. Some of these patterns may get promoted to the Detector
-    # model if they prove useful beyond a Citation context.
-    CITATION_PATTERNS = {
-      apa_volume_issue: /\d+\(\d+\)/,
-      no: /no\.\s\d+/,
-      pages: /\d+-+\d+/,
-      pp: /pp\.\s\d+/,
-      vol: /vol\.\s\d+/,
-      year_parens: /\(\d{4}\)/,
-      brackets: /\[.*?\]/,
-      lastnames: /[A-Z][a-z]+[.,]/,
-      quotes: /".*?"/
-    }.freeze
-
     # The required score value is the threshold needed for a phrase to be officially recorded with a Detection via it's
     # associated Term.
     # Hint: set this to 0 in development environments if you want to temporarily see all output
@@ -55,29 +40,29 @@ def detection?
       @score >= REQUIRED_SCORE
     end
 
-    # The initializer handles the parsing of a phrase, and subsequent population of the @subpatterns, @summary,
-    # and @score instance variables. @subpatterns contains all the citation components which have been flagged by the
+    # The initializer handles the parsing of a phrase, and subsequent population of the @patterns, @summary,
+    # and @score instance variables. @patterns contains all the citation components which have been flagged by the
     # CITATION_PATTERNS hash. @summary contains counts of how often certain characters or words appear in the phrase.
-    # Finally, the @score value is a summary of how many elements in the subpatterns or summary report were detected.
+    # Finally, the @score value is a summary of how many elements in the patterns or summary report were detected.
     #
     # @note This method can be called directly via Detector::Citation.new(phrase). It is also called indirectly via the
     #       Detector::Citation.record(Term) instance method. This method can be called directly when a Detection is not
     #       desired.
     # @param phrase String. Often a `Term.phrase`.
-    # @return Nothing intentional. Data is written to Hashes `@subpatterns`, `@summary`,
+    # @return Nothing intentional. Data is written to Hashes `@patterns`, `@summary`,
     #   and `@score` during processing.
     def initialize(phrase)
-      @subpatterns = {}
-      @summary = {}
-      pattern_checker(phrase)
-      summarize(phrase)
+      f = Detector::Features.new(phrase)
+      @features = f.features
+      @patterns = f.patterns
+      @summary = f.summary
       @score = calculate_score
     end
 
     def detections
       return unless detection?
 
-      [@summary, @subpatterns, @score]
+      [@summary, @patterns, @score]
     end
 
     # The record method first runs all of the parsers by running the initialize method. If the resulting score is higher
@@ -99,7 +84,7 @@ def self.record(term)
 
     private
 
-    # This combines the two reports generated by the Citation detector (subpatterns and summary), and calculates the
+    # This combines the two reports generated by the Citation detector (patterns and summary), and calculates the
     # final score value from their contents.
     #
     # Any detected subpattern is counted toward the score (multiple detections do not get counted twice). For example,
@@ -116,64 +101,7 @@ def calculate_score
         SUMMARY_THRESHOLDS.key?(key) && value >= SUMMARY_THRESHOLDS[key]
       end
 
-      summary_score + @subpatterns.length
-    end
-
-    # This calculates the number of characters in the search phrase. It is called by the summarize method.
-    def characters(phrase)
-      phrase.length
-    end
-
-    # This counts the number of colons that appear in the search phrase, because they tend to appear more often in
-    # citations than in other searches. It is called by the summarize method.
-    def colons(phrase)
-      phrase.count(':')
-    end
-
-    # This counts the number of commas in the search phrase. It is called by the summarize method.
-    def commas(phrase)
-      phrase.count(',')
-    end
-
-    # This builds one of the two main components of the Citation detector - the subpattern report. It uses each of the
-    # regular expressions in the CITATION_PATTERNS constant, extracting all matches using the scan method.
-    #
-    # @return hash
-    def pattern_checker(phrase)
-      CITATION_PATTERNS.each_pair do |type, pattern|
-        @subpatterns[type.to_sym] = scan(pattern, phrase) if scan(pattern, phrase).present?
-      end
-    end
-
-    # This counts the number of periods in the search phrase. It is called by the summarize method.
-    def periods(phrase)
-      phrase.count('.')
-    end
-
-    # This is a convenience method for the scan method, which is used by pattern_checker.
-    def scan(pattern, phrase)
-      phrase.scan(pattern).map(&:strip)
-    end
-
-    # This counts the semicolons in the search phrase. It is called by the summarize method.
-    def semicolons(phrase)
-      phrase.count(';')
-    end
-
-    # This builds one of the two main components of the Citation detector - the summary report. It calls each of the
-    # methods in the first line - which all return integers - and puts the result as a key-value pair in the @summary
-    # instance variable.
-    #
-    # @return hash
-    def summarize(phrase)
-      %w[characters colons commas periods semicolons words].each do |check|
-        @summary[check.to_sym] = send(check, phrase)
-      end
-    end
-
-    # This counts the number of words in the search phrase. It is called by the summarize method.
-    def words(phrase)
-      phrase.split.length
+      summary_score + @patterns.length
     end
   end
 end

app/models/detector/features.rb

@@ -0,0 +1,91 @@
+# frozen_string_literal: true
+
+class Detector
+  class Features
+    attr_reader :features, :patterns, :summary
+
+    # Citation patterns are regular expressions which attempt to identify structures that are part of many citations.
+    # This object is used as part of the pattern_checker method. Some of these patterns may get promoted to the Detector
+    # model if they prove useful beyond a Citation context.
+    CITATION_PATTERNS = {
+      apa_volume_issue: /\d+\(\d+\)/,
+      no: /no\.\s\d+/,
+      pages: /\d+-+\d+/,
+      pp: /pp\.\s\d+/,
+      vol: /vol\.\s\d+/,
+      year_parens: /\(\d{4}\)/,
+      brackets: /\[.*?\]/,
+      lastnames: /[A-Z][a-z]+[.,]/,
+      quotes: /".*?"/
+    }.freeze
+
+    def initialize(phrase)
+      @features = {}
+      @patterns = {}
+      @summary = {}
+      pattern_checker(phrase)
+      summarize(phrase)
+      @features = @patterns.deep_dup.transform_values(&:length).merge(summary)
+      @patterns.delete_if { |_, v| v == [] }
+    end
+
+    private
+
+    # This calculates the number of characters in the search phrase. It is called by the summarize method.
+    def characters(phrase)
+      phrase.length
+    end
+
+    # This counts the number of colons that appear in the search phrase, because they tend to appear more often in
+    # citations than in other searches. It is called by the summarize method.
+    def colons(phrase)
+      phrase.count(':')
+    end
+
+    # This counts the number of commas in the search phrase. It is called by the summarize method.
+    def commas(phrase)
+      phrase.count(',')
+    end
+
+    # This builds one of the two main components of the Citation detector - the subpattern report. It uses each of the
+    # regular expressions in the CITATION_PATTERNS constant, extracting all matches using the scan method.
+    #
+    # @return hash
+    def pattern_checker(phrase)
+      CITATION_PATTERNS.each_pair do |type, pattern|
+        @patterns[type.to_sym] = scan(pattern, phrase)
+      end
+    end
+
+    # This counts the number of periods in the search phrase. It is called by the summarize method.
+    def periods(phrase)
+      phrase.count('.')
+    end
+
+    # This is a convenience method for the scan method, which is used by pattern_checker.
+    def scan(pattern, phrase)
+      phrase.scan(pattern).map(&:strip)
+    end
+
+    # This counts the semicolons in the search phrase. It is called by the summarize method.
+    def semicolons(phrase)
+      phrase.count(';')
+    end
+
+    # This builds one of the two main components of the Citation detector - the summary report. It calls each of the
+    # methods in the first line - which all return integers - and puts the result as a key-value pair in the @summary
+    # instance variable.
+    #
+    # @return hash
+    def summarize(phrase)
+      %w[characters colons commas periods semicolons words].each do |check|
+        @summary[check.to_sym] = send(check, phrase)
+      end
+    end
+
+    # This counts the number of words in the search phrase. It is called by the summarize method.
+    def words(phrase)
+      phrase.split.length
+    end
+  end
+end

app/models/lookup_citation.rb

@@ -0,0 +1,97 @@
+# frozen_string_literal: true
+
+class LookupCitation
+  # The info method is the way to return information about whether a given phrase is a citation. It consults an
+  # external lambda service (address in env) and returns either a true or a false. The default if anything goes wrong
+  # is to return false.
+  #
+  # @return Boolean or nil
+  def info(phrase)
+    return unless expected_env?
+
+    external_data = fetch(phrase)
+    return if external_data == 'Error'
+
+    external_data
+  end
+
+  private
+
+  def lambda_path
+    ENV.fetch('DETECTOR_LAMBDA_PATH', nil)
+  end
+
+  def lambda_secret
+    ENV.fetch('DETECTOR_LAMBDA_CHALLENGE_SECRET', nil)
+  end
+
+  def lambda_url
+    ENV.fetch('DETECTOR_LAMBDA_URL', nil)
+  end
+
+  # define_lambda connects to the detector lambda.
+  #
+  # @return Faraday connection
+  def define_lambda
+    Faraday.new(
+      url: lambda_url,
+      params: {}
+    )
+  end
+
+  # define_payload defines the Hash that will be sent to the lambda.
+  #
+  # @return Hash
+  def define_payload(phrase)
+    {
+      action: 'predict',
+      features: extract_features(phrase),
+      challenge_secret: lambda_secret
+    }
+  end
+
+  # expected_env? confirms that all three required environment variables are defined.
+  #
+  # @return Boolean
+  def expected_env?
+    Rails.logger.error('No lambda URL defined') if lambda_url.nil?
+
+    Rails.logger.error('No lambda path defined') if lambda_path.nil?
+
+    Rails.logger.error('No lambda secret defined') if lambda_secret.nil?
+
+    [lambda_url, lambda_path, lambda_secret].all?(&:present?)
+  end
+
+  # extract_features passes the search phrase through the citation detector, and massages the resulting features object
+  # to correspond with what the lambda expects.
+  #
+  # @return Hash
+  def extract_features(phrase)
+    features = Detector::Citation.new(phrase).features
+    features[:apa] = features.delete :apa_volume_issue
+    features[:year] = features.delete :year_parens
+    features.delete :characters
+    features
+  end
+
+  # Fetch handles the communication with the detector lambda: defining the connection, building the payload, and any
+  # error handling with the response.
+  #
+  # @return Boolean or 'Error'
+  def fetch(phrase)
+    lambda = define_lambda
+    payload = define_payload(phrase)
+
+    response = lambda.post(lambda_path, payload.to_json)
+
+    if response.status == 200
+      JSON.parse(response.body)['response'] == 'true'
+    else
+      Rails.logger.error(response.body)
+      Rails.logger.error(response.body['error'])
+
+      'Error'
+    end
+  end
+end