Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Better de-duplication of names in the ultrasignup historical facts transformer #1275

Merged
merged 1 commit into from
Nov 27, 2024
Merged

Better de-duplication of names in the ultrasignup historical facts transformer #1275

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 13 additions & 2 deletions lib/etl/transformers/async/ultrasignup_historical_facts_strategy.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,11 +96,14 @@ def record_emergency_contact(struct)
end

def record_previous_names(struct)
previous_names_array = [struct[:Previous_names_1], struct[:Previous_names_2]]
names_1 = struct[:Previous_names_1]
names_2 = struct[:Previous_names_2]
names_2 = nil if names_2.downcase.strip == names_1.downcase.strip
previous_names_array = [names_1, names_2]

previous_names_array.each do |previous_names|
if previous_names.present?
next if previous_names.downcase.strip.in? JUNK_VALUES
next if name_is_junk(previous_names) || name_is_identical(previous_names, struct)

proto_record = base_proto_record.deep_dup
proto_record[:kind] = :previous_name
Expand All @@ -111,6 +114,14 @@ def record_previous_names(struct)
end
end

def name_is_junk(previous_names)
previous_names.downcase.strip.in? JUNK_VALUES
end

def name_is_identical(previous_names, struct)
previous_names.downcase.strip == "#{struct[:First_Name]} #{struct[:Last_Name]}".downcase.strip
end

def record_ever_finished(struct)
reported_ever_finished = struct[:Ever_finished]

Expand Down
6 changes: 3 additions & 3 deletions spec/lib/etl/transformers/async/ultrasignup_historical_facts_strategy_spec.rb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,7 +59,7 @@
:Volunteer_description => "",
:Ever_finished => "No",
:Previous_names_1 => "David Conroy",
:Previous_names_2 => "",
:Previous_names_2 => "david conroy",
:DNS_since_finish => 1,
:Qualifier => "2023 AUG: Bigfoot 200",
:Years_volunteered => 0
Expand All @@ -80,7 +80,7 @@
:emergency_phone => 33682847631,
:Volunteer_description => "",
:Ever_finished => "No",
:Previous_names_1 => "N/A",
:Previous_names_1 => "louis benoit",
:Previous_names_2 => "",
:DNS_since_finish => 0,
:Qualifier => "2023 SEPT: Tor de Geants (Italy)",
Expand Down Expand Up @@ -155,7 +155,7 @@
expect(emergency_contact_proto_records.map { |pr| pr[:comments] }).to match_array(["Carleen Paucek", "Françoise Benoit, 33682847631", "Promo, 27724373177"])
end

it "returns one proto_record for each provided previous name" do
it "returns one proto_record for each provided previous name, ignoring junk and identical names" do
previous_name_proto_records = proto_records.select { |proto_record| proto_record.attributes[:kind] == :previous_name }
expect(previous_name_proto_records.count).to eq(3)
expect(previous_name_proto_records.map { |pr| pr[:comments] }).to match_array(["David Conroy", "Marie Antoinette", "Maria Sanjust"])
Expand Down
Loading