From c7e2c4a72f6179814d5f5c0975b6e87506b9e0d5 Mon Sep 17 00:00:00 2001
From: Tricia Jenkins <tricia.g.jenkins@gmail.com>
Date: Thu, 30 Apr 2020 18:07:47 -0600
Subject: [PATCH 1/5] add migration to fix concatenated subjects (part 1)

This will take a subject like ["Cat, Dog, Rabbit"] and make it ["Cat", "Dog", "Rabbit"] in a new deconcatenated_subject column.

We're doing this in two parts to make data cleanup a little more sane than edits in production.

This assumes that at some point in the future this new column will be reviewed and replace the Item's subject.
---
 CHANGELOG.md                                  |   1 +
 ...econcatenate_subject_in_item_and_thesis.rb |  21 +
 db/migrate/ERA_subject_issue.txt              | 628 ++++++++++++++++++
 db/schema.rb                                  |   4 +-
 4 files changed, 653 insertions(+), 1 deletion(-)
 create mode 100644 db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb
 create mode 100644 db/migrate/ERA_subject_issue.txt

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 9d977a545..0d64be0f6 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -19,6 +19,7 @@ and releases in Jupiter project adheres to [Semantic Versioning](http://semver.o
 - Thesis ingest rewrite [PR#1670](https://github.com/ualbertalib/jupiter/pull/1670)
 - Rails 6 sidekiq queues
 - Add stylelint to Jupiter [#1120](https://github.com/ualbertalib/jupiter/issues/1430
+- migration to fix concatenated subjects (part 1) [#1449](https://github.com/ualbertalib/jupiter/issues/1449)
 
 ### Changed
 - bump rubocop-rails to 2.4.1 Rails/FilePath default changed to slashes [PR#1398](https://github.com/ualbertalib/jupiter/pull/1398)
diff --git a/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb b/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb
new file mode 100644
index 000000000..9ea2e6f5b
--- /dev/null
+++ b/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb
@@ -0,0 +1,21 @@
+class DeconcatenateSubjectInItemAndThesis < ActiveRecord::Migration[6.0]
+
+  def change
+    add_column :items, :deconcatenated_subject, :json
+    add_column :theses, :deconcatenated_subject, :json
+
+    concatenated_subject_ids = File.readlines('db/migrate/ERA_subject_issue.txt').collect(&:strip)
+    report = Logger.new('log/concatenatedsubjects.log')
+    (Item.all + Thesis.all).each do |item|
+      item.deconcatenated_subject = if concatenated_subject_ids.include? item.id
+                                      deconcatenated_subject = item.subject.map { |subject| subject.split(%r{,\s*}) }.flatten
+                                      report.info("#{item.id}, \"#{item.title}\", #{item.subject}, #{deconcatenated_subject}")
+                                      deconcatenated_subject
+                                    else
+                                      item.subject
+                                    end
+      item.save!
+    end
+  end
+
+end
diff --git a/db/migrate/ERA_subject_issue.txt b/db/migrate/ERA_subject_issue.txt
new file mode 100644
index 000000000..ba611eb24
--- /dev/null
+++ b/db/migrate/ERA_subject_issue.txt
@@ -0,0 +1,628 @@
+c7b69f61-2404-4eb9-9b4f-ca0e971bde3
+a6de3cc1-9b66-4d29-b287-9ade9a6e8714
+e2306501-bf3b-4ccb-9d07-fdd8520695dd
+e2306501-bf3b-4ccb-9d07-fdd8520695dd
+39d68f48-556c-437d-92fb-164063b7a1e3
+06d3cfb9-f30a-49c5-b3e5-d2d84c6502fc
+4cdc962c-8680-4343-a397-525c21bebcde
+3e4c904f-6381-4748-a3e1-6bd9b61f57c3
+fd8a6b18-b1cf-4e75-8151-3e058d16132d
+e09f6ca5-3a87-41b3-9eba-5f9b60acb845
+7b416312-7d12-4fec-b080-46efd5816c67
+544eed05-55ed-44c4-993e-4104ebbf4717
+1509c801-9ee2-4572-9db4-009480156439
+5c755f81-3721-45a5-98a2-0c749aad741d
+4f1e114f-cfad-4ac9-8e81-dc6327238f4d
+5d591ebe-39df-4af2-979f-23270aff45fd
+1c41e1da-99bc-458f-bcd3-a250e6a2e5c9
+b3855e50-434d-4c46-a0f1-a6c277bda047
+1ca18ec6-3d4d-43ad-8791-52b0b1f5f77a
+622b97e9-d984-4371-9255-8400c74ba76a
+680b0d84-33cf-4235-9461-23490e82e780
+6f239e24-adfe-4cd0-8279-1178f04cdbb8
+db8c424e-817b-403f-a884-9e279b8cce79
+569cabf8-7c0b-479f-9bfc-a430c5cdca33
+357ac655-1d3c-41c0-856d-293c6faa50b9
+070c8f21-8411-45e2-acec-eb1e9a05ba9d
+c55d4fc5-0ae5-48bc-9dba-70237b5afd93
+07e48311-379e-4dd3-a1be-54ddee728c08
+85a965b7-d124-4b1a-a700-ba5b3ff21b13
+7b25779c-baec-42da-943f-13e264449978
+7bb20a40-e257-490f-8947-bd1b28cf11fd
+1df14139-7f3e-4f90-be32-49d84fcd00da
+30690cb1-2555-4c63-baf4-ab32d9098a6d
+bbcc059d-7b86-4be3-bb99-1b1cbeb4c44f
+0d588fc1-74fc-4744-b94f-2b071ee1c6dc
+3002fd33-9c3b-4232-bbf3-363221ec4fc7
+32069b4e-18c9-4be2-8473-416d51d57e71
+2ab9e0f8-46aa-44d4-ab10-26003e13f713
+672dddb0-2d26-4fd9-aa96-4b4d716f66be
+a11848cd-21c3-405a-875b-0737db00da63
+385f8fed-0973-4429-9220-94f7f15ef70c
+381225b6-9893-4178-bb9e-5587e291d4fd
+38ac07da-4bca-4830-b5a3-3c7189f5bf9e
+814145a2-1cb2-4c52-98e2-71874bb7e4e9
+38b45415-8c8e-4134-b78e-0819e7890c3b
+384d5384-c3a6-4a94-89f4-a3a9b591a459
+732b0d5a-44aa-4907-bf49-a854b4455352
+7334d32f-b588-4616-b551-a95ab8adf96b
+739169de-addf-4cd9-9040-2e88a75e1c0a
+73cda2f9-82fc-41f1-af30-67e565348083
+73af6cd9-f58d-4649-866c-1974dc40e656
+3b42c83f-b5e8-435a-9350-7b9b782a4c2e
+73baf8db-5e86-4816-93d8-f8685372a8ec
+087cace6-a269-40c0-b736-3cf0c4d29614
+08327822-fdc5-4dc1-8e0c-af96c4ba3caf
+08f2b72e-685f-4e1c-8b6f-ed7155c3bd88
+caaf058c-2a9d-45ac-aa91-3e47891e18d6
+08efefe2-806b-4ded-9681-fb2901f954c4
+1b9e7aff-349d-4b6d-9f7e-a5550720930c
+63a8df9f-2db6-4f5c-b19c-5a3da0a1a9fa
+b20a0dfc-c697-4c0e-a69c-38ce0c334f3e
+8c713294-0541-4895-9d7a-7bcfa2fde402
+9f549018-abd5-4a85-8120-41c46579c5b7
+5bde8ae3-2c39-4aee-93b8-7703dd0700e7
+ece17cb6-8f6f-497a-bf86-024bb3225736
+d1415b0c-fb44-435c-8550-f83b922ddc71
+d14c25aa-c2b4-4299-9e5f-3e9731d20a50
+8003ca46-3837-4737-83e5-dc85a9e27a72
+5e62f233-e4e0-497d-952b-a357d3a58275
+44092a93-2d77-4867-a69e-6a098a56818f
+84992b09-13a5-4d0b-9641-ba94bb359b7b
+a7111ab9-2b1c-4f4f-a407-f1a9421da77f
+e49509e2-9949-4c33-9a85-271fad7b8533
+a759f7eb-e709-4988-afc6-84dfc46d921b
+0c827f8e-0356-41dd-bcd8-729d5b23479e
+a758a144-c965-42a1-990b-a79295fa82dc
+a7288f44-22ff-4dcf-abee-91eb90299e6b
+641b9a81-6e12-42ba-a4fb-e969419bb44f
+c66decaa-6622-416c-97b2-2b723abc616e
+c6419d00-b8dc-44db-b507-9730fc8aee6a
+c6b109bc-335d-450c-a3cc-0585d285bf44
+c6b14d26-3e40-44c5-8c3d-743bac9ecae1
+c68cc6ae-a664-4336-998a-f6f50ed67147
+2ef024d3-f520-4fd3-ad0b-f2baa3ef4d09
+318a93aa-e9a2-4e8d-9377-93df415fb549
+f12c8e4b-9bae-466c-a9be-68439472f55f
+31df1cac-d364-4479-a420-c43fccce79c3
+316ebe19-5bbe-496a-bb2e-d4b83574efbb
+e6d2a941-008c-4540-8394-fc4af066aee0
+25559e54-165d-4075-8a62-b63c2fc980b4
+be0c0f14-ae89-42de-b66c-45a6f125250b
+2529e08e-f86e-42e3-b617-75eaedda8fd2
+25721b14-1228-490b-bf3d-6cccb56bb735
+25d7b742-3498-4dcb-a260-8db2295bf086
+4661f346-e350-4d1c-9fc9-e382fb0be047
+9a67acaa-8563-4998-97cc-7776de1f164d
+1fcd27a7-ef7a-4f13-9f1d-e602b39ec46b
+95c73a10-49cc-487b-9fbb-a75d9ff15133
+ad861ca5-d535-4161-9871-61fd1619a317
+8912dc58-c60f-4833-84d2-a1d89545bb45
+447d63c8-49c2-4319-bab2-c57ca0171f99
+c1e83cfd-2daf-4b3f-ba3d-1f9e29035c62
+89a2a399-e041-425d-950d-7ff05167660f
+0bee5b13-4208-41f7-8b46-c3f0b0d9f584
+0007b2c2-95c3-477f-9602-801dc6dd0dc7
+1e2207ca-57e8-40bc-ab5a-61b0d5625dbd
+1ea39156-0c7b-43b6-beae-0991a225bee8
+70cbb166-f23b-43cd-a2a6-86beba78abfa
+66c0be2e-892b-4656-bc32-04d929f12806
+66c6ad58-d43b-4b24-9b3a-8007bfad0ce1
+83083024-68b3-471d-978a-99cd6defbc6c
+e50d1872-2411-48e4-b95c-bb6ade3b541d
+2827153c-91aa-4615-8641-4dd12ecab234
+66bff155-f1d2-441b-a9de-cb8f1b1dd2b2
+90d5b06c-e508-45b3-8526-3509bceb930e
+cc28e61c-4c33-4ea2-b372-97c4adb7df3b
+9a4b6d09-eba4-4d1c-ab73-4b8d76de8c22
+cc025e18-3f9a-4a3e-bb41-1f6a30f4e8c4
+6e67c496-e294-4711-823d-b9a3f723f805
+479734c9-f95b-43c2-91fd-a17e4a318ca1
+e024fafb-2842-45a4-b6d3-d1254cc268b5
+58064fb5-1112-4c4a-973e-b6525a64e8ca
+0d9000f4-3c7e-4221-9f26-f5faf0a1d1bb
+82029824-3371-4c6b-87e6-9ef8721be4c4
+ce0c14b5-c5f7-48cf-a8b3-14cd903254d7
+bfd448da-363b-465c-8c1e-6c664dfcd3a4
+0dcf457c-7946-44a4-900d-75e5b99bdf12
+950a9128-f010-4967-a6f1-1c5340ef94de
+aded0c42-97e0-4532-a0af-216d76597a82
+841cccfa-a390-4c85-af67-16516599745c
+729e1b74-c88c-46ac-afcd-657a3d7a3334
+72a543d0-6e0b-4956-b507-7c07eae97b36
+8469e83c-4696-4bc4-b51b-f104ac5ab747
+e7fa80eb-15d0-46aa-8ea9-3ee5a4620b7e
+223682fd-60ec-41e6-b5cb-a308648a218f
+2282d2eb-cb2f-4476-8f1d-35d387d2461b
+e3a5c8ca-8a64-4ee3-bd0f-cd8e10adfd89
+5cc74c66-f747-4c66-960b-c124d3299501
+2228516c-0856-4d17-b9b2-e264cfcf6fe1
+71305aaa-8ef2-426b-8fc3-40480932308c
+7acc3499-05b9-4139-85ea-b94def8e3fbd
+062c4767-80b0-4d8b-8b3e-4a0d28b97529
+e04a1590-2239-4370-b1f9-8217e8149285
+e0ac359c-0a70-4f67-8c5c-e8849d883947
+7681508c-0b0f-4217-a16e-685eab116567
+69c96b9a-3309-4838-b23e-48b38d6ee2cb
+3fce2766-0d73-4a92-8556-6e0476796944
+902e22e6-d19e-46b7-9b1b-3dc754894c7c
+db1a2de2-ce0d-427c-9f3f-5a321c0ccf42
+fe337ecd-3d59-4cb6-be55-fd1cf5cf3c92
+908925e4-04cd-41dd-bff9-eeab5d959802
+a3267506-bc62-430a-ac1c-72500713841c
+a37d1744-ac4c-4db9-a641-2666be10f154
+a37dd506-4295-4cc7-8d8e-fb28560e0a5e
+a3e2b299-2f67-4e3d-826c-e6d44bf0eff3
+a35893ff-09ac-4e61-9bd6-f4762211573a
+f694c8e1-63b5-418f-a67d-733c8324d374
+2462ebf1-bc8d-4a27-b16e-323631a5dfea
+a0269448-05f2-4a80-942d-96103dbdcbe8
+1d613236-53f9-4930-8757-3ab94fe5bb29
+1d43020a-9eda-4da7-bb99-862a8dd331ea
+6abd54c8-dc12-417c-b37d-bc1b6d8c8248
+1df25826-d366-4c23-8513-70d3869702a6
+0007c436-44d6-4966-96a9-330016a46af9
+1dd1157f-c262-4eef-ab6d-a7e7a06db808
+1d330167-e5db-4d78-9888-e4405a3d9d26
+7a4cab33-8fea-44e0-ad19-4891aa75166e
+48471753-39f2-469f-b49d-43d29c7d9ebd
+c2e5d01e-fc1c-4ebd-9583-a5fbd0bea74e
+48d5a915-fbf9-4a66-8faa-28a4a168ccce
+489c0395-45a1-4290-a1ad-210a543d6d25
+488d7590-75f3-44f0-8e18-be41f0174d33
+4810c715-e50e-4f61-bdc8-b4ec7608538f
+7418ecc6-e4e7-4916-a90e-ced7cec58671
+744e075c-d20b-4c88-ab31-d611d5ffabfb
+83a99966-b443-49d3-a2b8-47892b9e20aa
+2f9589d0-6bc8-406a-8df3-cc5f1b344896
+2f8ce94f-4964-4184-86b3-f2236057e215
+3d413094-f82d-483c-8886-57022da94d67
+f155f205-1ac9-4c33-9154-c9de8b8642cc
+54bcb1f5-e558-4e22-884f-3e5169cd8eff
+1697a6d6-937d-46b9-9dee-3bba0ef18331
+54999f4d-b89f-4c21-94bf-db6afd1a0f35
+20e06daf-c8c2-42cb-94b5-33165d1b64e2
+fcc8b2e7-3462-4693-ae72-59c651d90bf9
+6eef459d-21b3-4c59-9438-f9697264817b
+0b87c639-9d32-4415-b7fc-ea7db7b77ecd
+cf522384-0f10-4a65-a512-50a7f23a0267
+d24a4ba2-48fe-4c67-9d26-b8bc7fadcee6
+fbf1bddd-b478-44c6-b708-c09b2c1582f5
+851bf4fc-445f-46f2-8e91-df6f1be95317
+0e967017-d8df-4fd8-800a-f433b76c87d5
+e9799fee-c525-4483-a719-696d7ac78cf8
+d9e1d77c-9088-4695-8d77-0893cde44190
+3474e341-6034-4b60-85c4-776ec7aa6454
+6a0e3441-cfe6-48e1-bceb-19f7ca8025af
+0fa04354-84bd-4372-9e43-a990a21e7e55
+6a3e10a4-319d-4df9-b208-5217aa5c9c4a
+6afbff5c-06b8-4265-b101-07ed497cc31a
+c00362fb-956a-4654-a282-66afa9b39830
+b4558cf4-559f-42d9-8adf-15a8782d6ae0
+a1e460ad-5009-456a-ab7f-5ae1f007e66d
+b49882a3-e386-47c8-8549-18cd01c1a982
+e15b8b8e-3ae2-4645-9e80-c10f9be90b61
+5d11b162-3d97-4a71-ad2e-d06d76b6a70f
+e181961a-0e3f-4c0e-820f-ebe6d8817828
+4e0d90ee-6dbe-424f-be7e-747727c48466
+ff6ebe0a-677b-4b41-882e-0cf53b1639cf
+ff34c97a-3e6d-4610-ba84-5af46ad498ea
+017371a2-a39e-4431-8363-c48886db144f
+2666e9a4-ec9d-4e0d-a37f-7165a69b8434
+72078c56-f989-45e3-9198-9760ad6fb738
+26d9df97-06de-41c7-9a11-33359efa725e
+4edd79b0-eb0d-429c-9bdb-0398358c99d9
+96d1a6a4-13ee-48e5-bbcf-4e30dfcf0cd9
+62f2cb82-a2ab-467d-b448-95a245abb302
+7a9fd82e-6360-40b4-9644-e96f08695090
+b9b449bf-035e-448f-83ba-42a99ae20928
+9dfdff92-1282-4944-9456-c50de5785e6a
+b9ca959c-fbca-4f6d-b03f-bb3a81723794
+6176eb4c-fbf1-4daf-a055-e2b6b04f229b
+b92cfd36-fc0b-44bf-abab-c675470ee6fe
+cf046d5e-d56f-4276-932c-efdd95758c1e
+4f316a8b-7e90-4c38-b796-78b442beff51
+4f38ab93-226b-4cc9-b7ba-6be62f0981c0
+4f2e3e77-1791-4893-843b-a75012c61674
+4f70cf86-47d4-42bf-bc8c-919ee440810a
+52f76c51-8cba-4b86-87d2-f93faa1798aa
+3a4612b8-c577-4f05-900b-6caf0036c3ba
+2c09019d-9e85-47e4-8342-359b07a74d91
+2ccb56b6-74d9-4232-9673-5e9865f42522
+33d064c0-647d-4262-9876-f37ff252edfa
+3ac59350-5e66-4261-a8ed-c44a90bc19eb
+f48b1ce3-5f3b-48e1-bc13-fbb882e15f69
+f48b1ce3-5f3b-48e1-bc13-fbb882e15f69
+f4a715dc-329c-4c9a-9490-591d4735be7e
+da611ad8-1051-451d-bd99-16910e899e12
+e3ca4334-a0c4-430a-a2f4-1fb9deb80866
+f4cdaed6-3dcd-4535-a8b8-45f9df8d1ed9
+f4012ed0-762f-4988-aa80-b5c60b22e933
+c8c57003-5148-4825-b83a-4f15cc4ddc48
+81ac1a49-833d-4edc-bec1-734e434cf7a9
+81b47dc8-b615-45e8-97c2-fc4b2e43d866
+fdcddbb6-3f1f-4911-9e7a-5da824523990
+81d059b6-c448-428e-b501-1fcdeef68ad7
+8137a5f9-8563-4e99-9317-ebd9d2f88e46
+20766212-dc98-42a8-a0ea-05736a56aae2
+193f61d2-dac5-4adf-877e-d236abc1dbf9
+0bcc754d-4053-4baf-aa16-dd2f0b124668
+19db5d1a-0a08-427a-a8be-3f626cd1a1f3
+e5e4d8ee-2eae-4d78-b398-4c288e008bb0
+ee879c4b-8548-4570-912e-7477947c60f9
+cef02516-1d3f-438d-b5e4-613706dc0de4
+039192a3-51e2-4342-806a-f352e18eac61
+2efb3c37-3cbf-4ee6-8306-7a4cca9c4882
+55b4ebbf-4ae3-469a-a5b7-4a54f896a964
+550d2b1d-0ec8-4604-8bb4-bb2f5106ecb9
+469e378c-27fc-42ef-831f-bc1f5b4e33a1
+db9998d5-0ae2-41b4-b657-8b82f2e339af
+db9d533e-dff6-4edc-b938-dd9b8a7b6f9f
+7dfebca7-f652-4d61-aa02-57d4fee54d40
+db314ce0-56b4-4894-b193-5ae5cce8a5c6
+dbf8ed78-5c34-472c-b65a-e71cacbbb819
+dbf8ed78-5c34-472c-b65a-e71cacbbb819
+dbf8ed78-5c34-472c-b65a-e71cacbbb819
+34c72e40-ac42-43d5-8f82-0ad3161a02fe
+21588a9e-ca25-4bb4-a5ad-f12c6ada89bf
+8c2101f6-bb2f-4b6f-8414-7b8b0252dff3
+8f599357-4ffc-494e-9c8b-f27e90ea2f14
+01c45fd9-6ed8-4ea9-8584-af03fdd8f55c
+f9f4986f-98ff-483c-824d-a169b23c1e09
+991db118-a926-4a1e-9246-2a793ee3c43d
+0c6e7d22-037d-4c1f-8b00-37e07a70f85a
+5dfb8ce6-9214-4a4d-a6e9-df128659397c
+5dfb8ce6-9214-4a4d-a6e9-df128659397c
+5dfb8ce6-9214-4a4d-a6e9-df128659397c
+c96eaf69-3276-41b1-804d-52cad49b0569
+daa06320-acfe-49ed-8645-36dc7f49e8d8
+f3ab7fbf-9817-483f-8d7e-1e32146fc571
+f8bce972-f747-40a2-a610-0ec8c83801f0
+70a8acf7-ff3e-4b79-b3b4-f6decae6121a
+36a73314-684b-4c91-b85d-27cb20081937
+369ab3d6-f4a2-4476-873b-52758b54bacb
+365ac02d-252c-4459-b5f4-513c0e354b0a
+ac8db8d4-c13b-41b3-bc5d-4c932e0d1e61
+935d43ad-1a72-484f-9cf3-154d9326adcc
+7f611636-999c-4aec-b26a-1cd6e48eed63
+ec1e13ea-545d-4e17-b7b8-25a6dae6ca49
+f5918f81-9013-487c-961c-1df701d9f2a2
+5a043d04-b944-4ca9-a505-d65d16d812a6
+53ec0fdc-2ea0-4613-9c21-358201a766d5
+5ac3d9ba-870c-4f6d-aef0-c640339eb512
+504e3344-d31e-4c08-8ad9-dd276e79c1bb
+ebdbecc7-1072-4a22-9917-6743d32ed380
+5a9fbf5a-eee3-49c4-8446-8a6f46b5bf23
+dcca8d14-131b-4fe6-a4f8-383f06ba403b
+b8bb677c-3f39-467a-a480-1f985d919f81
+f3b3533b-f3b1-483d-8a20-6f65c655e255
+56aa8754-e7a9-4e9c-a80a-62cd697e23c7
+02275b03-4b0a-4eab-a9fa-708d403391c2
+8ab82b77-ce3e-4ef3-a9ec-03a3582c902d
+d8e18331-365d-4e41-966a-4bb5c9b886ef
+d83cf297-2071-4fc8-ae67-ad093c72777c
+18030dab-1f1a-4098-be18-c7f330596b1b
+1844ac04-7ccf-4fb0-82a0-60a7340a8f7f
+1066d3e3-e32d-4cb9-a867-c666e5efaa9a
+183adc06-687f-40e6-8c80-17933e83e8c8
+18b9ad30-ccfb-4243-8de6-7cbff8653134
+d493aa64-f125-4cbc-abd8-e1ff210ed1f8
+02dceac8-a8b5-4ebe-857f-f52d0ad0236a
+be3bc1f4-438c-4cc2-8c99-996cccbca6a2
+aa592098-6986-4c5a-91e7-b80325887100
+aa14dcb7-253d-4d62-ae9a-0a1a057c0ca8
+3a7f99ad-d2f3-4f5a-b42a-fb0b0b43e160
+a9cce3e1-f0ab-49be-a01b-4c990c15923f
+3d6b31c2-686c-4c62-a598-eda1cf159125
+a5575ac7-faee-4db1-89e5-20c94327d079
+8cad4798-7b94-4e9e-bc75-a408f78627de
+e482ac72-7bad-4e5f-95b7-547df580b22f
+1b49ace7-e95c-4d91-92fe-162b7d69924e
+1b3e3afa-8065-4d13-8dea-fa7629e2aca6
+3fed1567-8be1-4dbd-9e62-801373aedb26
+ecb2db70-a74d-4d42-a49d-f876d7e9a7d8
+414009a4-72da-4487-99b7-357c9d9afa3e
+ab50c96a-71b2-439c-8665-f27c44695e73
+c1114ced-feb1-4576-834c-1f7b15767e89
+c1902f90-0442-40b3-b77f-1edd9003165f
+cb0e0e3b-09a6-47dd-b04d-6f29bc264fef
+8f7d2250-ae9a-49ee-b2db-b1924adb1525
+c45b733d-1896-4202-8b9c-79a2507d69e7
+8f5aae19-56d5-482a-92b9-0c514835ed98
+869d2173-bce1-46e2-8732-798e34b8a27d
+cf5144ad-64dc-4065-8963-abca0ea5abb1
+80bbd647-f9ab-4ec5-abd1-7752c006e9d6
+8ec21525-7dc5-4237-8857-5042e18cee90
+c0ed35c4-e55f-4bfa-bf8e-2a355544ceb3
+32398753-0ed5-4350-ba88-68bcf6d11800
+ebb74a1f-77e4-4a0c-b763-405ad505e847
+2b1242a4-0b0c-4d81-b255-5127fc75088c
+f2481789-c38e-4209-be8d-847ba6c24c87
+281659bb-f5b0-47f5-90d3-b45ea8ae385c
+9ad78f8e-7be3-41e8-a0fb-e1102de7ff88
+fc7eb837-8bd8-4899-bec9-53efc01fd75f
+287dae7c-9bd2-469a-9c4a-b0c16bd6db4d
+23f27c28-f77f-454c-8eca-753a57709d45
+284954cf-20d7-4ec2-9897-3bfda58406fd
+96430153-cf57-4f47-8c82-d7fdeadeda45
+9e34445c-9c8d-497a-873d-4f08d598d510
+79c52f98-9ff9-4828-a6f4-2d0a238c22a3
+e76b170c-1e1f-4f85-8794-8d9654123a2c
+0297e53f-9fb4-4243-8ffc-1f97fd7ae80d
+4ac9543f-f10a-4747-b319-3f617c44d8f5
+4acd2a0c-7d5d-4f4f-acae-4982042b03e6
+4aeaa9c8-364c-46b5-b1da-294201be948c
+9d4d07b9-a62c-4b04-8d0d-30c9d7933ffe
+9dfcb32e-1436-40fd-bed5-96ef18b29f8e
+09dda2a6-60ea-4222-b8ba-c661ceab4d2c
+093575ee-35b9-40b1-81db-ba5486de89e5
+bfdb021d-5e81-4bc5-a2ef-0c5ae27ffbff
+ba9042db-d5d3-436e-9392-e1bad236ada9
+7503d30a-f3f8-4bca-89d3-87a70d3b3e4c
+0c79188b-eba2-492a-8c3b-4fb6dfa7cc2d
+8066671b-ea33-4a99-98fa-3a6c8cd2dfe5
+e57bbdd9-0eb2-4da7-88bc-7c4e7d6c64b1
+164790e8-2bed-4435-a81b-e650348afda7
+f5069237-5309-4a30-af61-b3d9baa54e3c
+d58cc6b1-ba38-44ce-b486-b9abfb1bde4f
+a5a975e2-27cb-4727-a76f-73b9c5517a96
+d0e6a21f-b4ed-480f-8b1b-a4f9f52558e0
+117ac3a3-87c4-44c6-b56c-944b4b013280
+4e9298c0-c74e-4d75-9fd0-5f87cc1a29fd
+dedcd799-5012-4e1f-8725-71023a16386d
+06e3fd74-dde4-450b-a67b-ca86c3883eda
+a9fcb101-3ae1-4ba4-84c9-01584601a650
+29942e1b-b2c9-4116-a2b2-e3b4fb7cf218
+fa579bde-1b44-4af7-b761-4c439b9131b3
+13b7e3cd-be27-40d5-92e8-dcd8065a8298
+1321beb4-f625-4043-87a3-fe206564e364
+23339418-a932-4f02-a055-ad58970161d1
+6cc31add-527e-4471-8680-a7fe3e30b762
+5f884060-e94a-41e8-97e9-93709cde6383
+ad7412ad-832c-46d3-9318-413a96bd90ae
+9427fcd8-9b7d-4f9d-9554-829f1016d13c
+94ebd992-fdec-4be4-bf39-12f42e6fe5e8
+33d28a3d-df74-43f1-8bf3-ac6a584ac819
+33e90f45-2434-4452-bc47-27f452e332f2
+9b31c138-cc9c-4228-a48a-bcaf7f2f2ce9
+b6f63541-a795-4ff6-b92b-b36eeb10323d
+cda6f78a-5967-42b4-b41c-211dfc2511b9
+c0867789-e528-4103-b443-305001be3f98
+d63ecd91-d34b-40fe-aeda-f1a6aad45923
+d63ecd91-d34b-40fe-aeda-f1a6aad45923
+d63ecd91-d34b-40fe-aeda-f1a6aad45923
+d63ecd91-d34b-40fe-aeda-f1a6aad45923
+d63ecd91-d34b-40fe-aeda-f1a6aad45923
+bd14deb7-3c34-4c0f-b3b9-a1f4109bec10
+fc7ef555-ecef-4f1f-8529-74bbae53024e
+430f94d1-a3ea-48e1-81ef-318f05e2922f
+8a26521d-d1b7-4ae9-88e1-b7da07f442f6
+2083a420-ff55-4359-a746-33467e15527c
+508c58df-bc07-4ea5-8870-769518845821
+ca49d2f1-c4a9-431f-b136-99fa48ab380f
+85361c8b-648c-48ce-9844-929a16f3e436
+5701156f-c678-4bd1-a273-17d271802137
+53f52101-902e-400e-92e7-460a61ef26bc
+8d1f9e80-df86-4125-9bd8-bf1723aca3c6
+041baa0f-ef49-4146-bb72-f6f2218c8367
+53b41892-aebb-4070-9e32-fbc283353e57
+7e596c97-b798-4888-a48a-eedf9e363297
+bc676e51-5acc-4461-b63f-bc6f72ca916d
+bc66dd3c-9097-4a0b-9626-942dfa416768
+bc51c1fc-64b2-4d67-a921-0d8cb82448d5
+6b862e65-0034-45b3-bd5d-8669b16d4562
+bfc7c84d-80b7-40fe-a7ad-3b9e1f10656f
+02f54606-8fba-46ae-9331-7954713e8717
+7fc5180a-52f9-404f-893c-5e6c306ebf5e
+91c708fe-fe93-4fec-9620-f9465ebe158e
+4bbf18bf-6ae1-48bd-9c86-e65362ab4e9a
+86178db9-5e8a-42b0-9082-c2c939a44e4b
+facba5c2-c192-4b50-a285-2b58ee128bdb
+7c67afa9-e9b7-4c18-941a-9427b3cddda3
+d6e33c46-9eff-4ccf-ad29-62fdc6022a8e
+06ba647d-5ead-4b3b-b561-073ffe0b658f
+e31eff3a-eb09-4460-9be3-c649f4834f57
+cd93c4e8-74e5-4440-a4d1-30bad3f7359e
+cd93c4e8-74e5-4440-a4d1-30bad3f7359e
+348f3938-ee52-45f7-a2b2-bdeb4f48bbd3
+34423ffc-ea5c-4497-a34c-d43acb09d929
+f3246024-63c8-4911-9382-a0c1910eb687
+7618f77d-34af-4b61-91ab-cd03cca896d7
+c0a2c3e6-3ca9-45cb-83e0-44066fd6dd52
+60afc7a9-d5b4-4c6b-b80e-50ff99d9cb42
+a276581c-baa3-47bd-8196-90228bb78340
+8dc6801f-38ca-42c1-80d8-e7cb21fd9600
+8a97b789-b5b9-44bb-8e96-61fd629b8727
+4da95ece-2cd4-4efd-93a9-a83bc5f9069b
+a04bcaad-286f-4998-a6cd-2136d9f7c2dc
+bb1cc972-ece2-4421-93df-4a52d1ac1ecd
+a8c09ba3-fc76-491b-bce4-3aa2c9ee1e02
+53b65d90-5d32-4ca9-8d8d-d61fc6053c82
+59cf9be2-8ccc-41b3-ad6b-ed913c233f43
+39c4b4c2-0f11-4890-a5a2-33087525b63a
+64a74e82-b78c-4058-8003-5fff33239554
+0007b857-565c-4d6a-9c16-a1e4ef1fc44b
+5126d130-a46a-4fbc-9620-360b3ff3ac36
+511a12a0-5734-4541-b1ec-b41ba516f232
+77c36eeb-1708-4d19-b69f-1d3bb61da93e
+4995d8be-fd4c-40ec-8ac5-08c60a96f141
+625a97da-5ceb-4906-992f-c0fe9b0f7020
+7e71eb35-de19-441a-a1c5-9e8200eac3ae
+7e0f52e0-66a3-4904-9a27-24f0adb69098
+fa2f2b9d-73e6-466a-8637-d7a9e90d8160
+7e3098e1-66d2-4b6c-97a0-10577fd80736
+75226600-5922-4a5d-a22d-9b4867d388fe
+ddfb1c75-cb65-41a5-890e-04fb6bcd2d5d
+86af7796-2b12-4ae6-8ae0-5d806a6e0ce6
+29132845-f20a-4dec-b20b-38000f40c3be
+88560da8-52e5-4d29-975d-2883708bf1ff
+29fcd8d1-9cae-4058-b92c-cc16cbd706ab
+29ddc5e3-f2b6-4311-9887-0690aa3b95a6
+52e1f13b-d7cd-451f-a241-684075d57afc
+52e2d638-cff5-4535-85fb-e4681e27a40d
+df7309ff-994c-4671-b323-a6db7f80a25d
+c4c391ed-a81e-4919-a6be-0302f72e5d6d
+976c7653-1378-4c18-b0b0-9a38d34677e8
+c4d8e1c0-ca60-43cc-b75d-07aa9acf7b8a
+a94a7e5c-4760-4148-841c-a7059fd2da73
+21df9a0a-828a-4855-b0a9-54f7f94a219d
+2d55ad1d-6781-467c-bbce-f0b40a86c907
+cd4b908d-3cff-49a2-a59d-f5acea8bfcd3
+61bba94e-6486-40b7-b8f2-8ea656ed1794
+dae8b502-3634-42ce-81d6-0dba66f14646
+dad1d280-08c7-4928-ad57-077c5c660b98
+dad1d280-08c7-4928-ad57-077c5c660b98
+06016c56-66e6-4636-a2d8-288e58a43bc7
+3c683968-2df0-42f6-aa18-cc9dd0f6d5d1
+ddca0676-719a-445d-940b-7ffab61c9b28
+6b08b744-86c7-469e-9b77-84b354325294
+8bbfd1da-60eb-4308-a846-efdfce5e482e
+e3a3eb67-625c-4337-aafe-ccd147388544
+4d09f28c-6bd1-430d-95e8-822571cbb5d3
+4d09f28c-6bd1-430d-95e8-822571cbb5d3
+4d5671fe-e125-42bd-8c1f-4ca469c391bc
+884e0229-45ab-496d-9571-2230f83dddd8
+6d8c93f9-5742-4e0e-be01-b3bba0eb2029
+9ab8ab60-cb8f-4d7d-9551-3c602956b0ad
+fa2d0fd8-2726-4f35-b518-3ff7f738ac27
+91313dd3-fb17-4ab2-b023-50974bdad7bd
+1680262d-4cc9-42f1-b277-42399570576f
+394cb821-fd29-498b-a977-22326738c4ee
+5905cee6-2f78-4436-aba2-65d619e81953
+39d1c7bb-c762-4c88-80b0-2f429c55b7d4
+64f9a1de-f117-4c68-9a99-523d65ef8c80
+64a64c08-fdea-40d2-9004-33f3aa30e36d
+d24fac9f-2a9e-4aeb-a938-dc601b1897dc
+f1a694fa-9567-4d76-a9ec-e201d994d3f3
+97a2833f-f941-442f-8b3f-49fbc3cb6998
+e63d1504-8875-4d7e-98ae-cb4f1a6b74a9
+8c4b3d35-8b23-424b-9380-b510bb1d202d
+f192f7bf-9af9-424e-b764-b1bc2178972f
+88fa2a34-2b22-4d2b-a450-0e1aceae9ed9
+fc661b2d-649a-48ea-b699-1ce19a813fcb
+fc66c8dd-f357-4b98-b84e-99ea48e56c13
+fc4f1080-7177-4d52-8892-8d662610e1c8
+ed637c70-2d14-4825-93d9-bebf3b6c7cdf
+5efc0723-728c-4a06-a3b8-4ccb3882cbad
+10c22cc6-726f-4bff-8415-ba29edf25976
+401acaf6-956c-46d1-981c-a21fe78d1f1d
+97e4be9f-a48e-4763-86fb-dcebcb0f2504
+a0388e70-1d12-4d0f-b5f3-2256ca51d2ea
+6d4428ae-908f-4d33-b5e8-c0e046cdc3ee
+5b59d653-be0c-440a-91fa-9a546f964977
+d2c9a865-ae99-462b-97f6-ad90626776b8
+d2779b9d-2d81-4edc-aa4f-5d7c23da57eb
+bfc5191c-ed54-491f-9563-a83f3939abb6
+bfad8a01-4384-4816-9992-a7a80c62b7ec
+86b4d007-b099-4ee0-9a83-0653786632b3
+2af583d2-5494-4029-b073-27b0641e53ab
+2ac2173a-02e3-444d-ac78-8e40c15bc02a
+0246eb08-ccf0-4ede-aaf6-adfc3886bd3e
+b13166c1-c08b-4b80-b4e3-85231d9a0c2e
+02c06d86-8153-4751-9ffd-f6b87b9b7053
+023e513c-59db-43d0-b012-7d14dd15281a
+5ddc7acf-928a-4fa2-ad4d-a55c3269365a
+167e9432-85c5-4d14-a9f6-a6afb6cfb2bc
+16e98daf-45a9-46da-8d4c-e8348266693d
+8d2e9ede-8f88-43ec-9bef-6e2f06b202c7
+b1f5e658-57b0-403a-a649-958cd1aca197
+ac847d12-7f50-42a3-9266-447d4a781b55
+425b1a2b-f6fd-4e10-8e4e-4f9130bd358b
+12fc0cb8-c990-4759-8fa1-5e12af33116a
+f17fcced-4df3-4708-8ea9-5e121c968263
+9b104823-e834-42e7-b12b-6e0fcecb8a23
+57c0302d-7ef2-40a3-9628-a2d87871d582
+c7693e7f-a1b3-4e28-88e1-b398a965fdd1
+57e9847d-9b66-453e-a5bd-fdd9ac6c5045
+457f8150-56fb-452d-9f26-ce08b19b8260
+401c2c9e-fd7b-4c14-b4f0-d96913850e26
+3203fa2b-4e07-4422-a603-252a777cd368
+b6747b91-0ba4-406f-952d-da8504e88650
+047f3c18-5929-4c17-a019-f82e9c23dcc3
+a14c43ad-d872-4ccf-8b25-44a34e6a6ebf
+b54a5768-7138-4417-80f1-8907e28d9b73
+5eca2554-84be-46e9-a8de-84624206c5b5
+8defd4d4-8145-4811-8da5-d1b3701874fe
+c89b7eb3-640e-474c-8380-812437deae65
+30927c0a-e183-4b78-8887-22ddd4e275cd
+7d9a2ead-b772-4576-804d-e93b04cddd8f
+04f2125c-c815-4e59-ad03-ce67be7fece8
+578bb8cb-3c43-4d3e-836e-3848187add52
+ebef783e-da83-478b-8467-d5cc99709272
+f44e4332-a503-48cc-a415-c1cb98e96765
+cfd58fa4-72cf-4036-9b44-e371da3739dc
+ab1e1209-eadf-4517-93c1-6351ca8a3487
+453de708-8779-4fc6-9ba3-55d3665f4d07
+8ae6d801-6dca-4d1a-b844-986a9f7f6017
+335ea771-10f6-41cf-898a-4adfbcd9fd08
+be7d39d9-9561-4485-a6f2-0f69f8084f83
+7bf20131-3764-439d-91b3-a418b3346244
+7f9b1521-fba1-425a-8af7-308645c8855e
+fa1235da-fb0a-466c-a3fe-874d09e9c1ff
+9c840025-74c8-4db1-b1d5-dd570dd11e88
+fcc2a413-2fcb-4603-90c4-4420dfb48840
+2fa1b862-dd70-4fb6-a9cb-1a33ba32381e
+f8fb83f0-bf52-498d-aa69-646f485a0147
+13a259d2-934a-4f8f-ad92-d36513044309
+57c59690-4f72-4e81-b006-bceae375fe4f
+f2015a6e-ea8b-4d5c-9c4e-0bf9409f4168
+b665e9a7-5d1e-4a0c-b6a8-f217498684eb
+e47b0ecf-fe57-440f-80a1-bca04a2d59c8
+07f98c62-409d-40e0-897a-a9b5eb10baee
+e20773d5-e98e-479a-8cb6-bc97c5239072
+8a914e39-6430-45af-9156-69a80943f5f4
+c8ee3377-7501-4954-aff5-c92e01f7cf95
+580fa313-d9b7-4b32-a0f6-18017ce9c32a
+b1d9d52d-c628-465f-a74a-2d8a67857a94
+b1d9d52d-c628-465f-a74a-2d8a67857a94
+e98a33a6-6b1e-4500-837b-2ac80c765598
+4ffc6dc3-8903-4467-9387-0741b4e92f33
+fef38a2c-2830-4ee0-afa3-4c645de257c8
+82811161-df7e-41ec-8c2e-a3c9bbaba773
+c132fc69-6b79-4823-8c91-b4661291f1fe
+f5b1aa38-41e2-474c-917d-806b2a43056c
+eaf3a575-537b-467c-9369-8174fdf3f9ce
+2aca2dff-e993-4e26-a51c-d855385c311c
+9ecbb262-6d4b-4644-9acc-6c295743c225
+b2d6e47d-5430-45a4-b70e-4e0f5dba6966
+9fad8da3-9b63-4d79-a448-e87879952110
+ff6d25a3-fe5c-4957-ab42-dbb5190aa3b1
+be290561-9fd3-41c3-98ae-65581b2d7e71
+1bcfa63f-15d6-478b-bfb2-b5160da52d4a
+c132fc69-6b79-4823-8c91-b4661291f1fe
+83d296d5-14e7-47b2-9444-2bd69a843ac8
+bfe4f92a-7f5d-4d84-a44c-3aa30e14bf0b
+6c026b1e-9390-4f73-ad95-0c5a3c1d69d5
+df63f4ef-aa09-4d7b-9306-04a61f7b5cd4
+35e80746-edc4-4ecb-bb71-65534e0feca1
+7a5949f6-72c0-41e2-b937-203cc4f74631
+d63ecd91-d34b-40fe-aeda-f1a6aad45923
+f09b4b2d-0879-4cfe-bbeb-b9b2e27526fb
+4b79b361-4199-4a6b-af92-e4ce86971428
+06ef1b48-1eac-45ba-9578-bd09b1460489
+ebc28a49-2ac6-4ed3-9192-2a38fb4ce8e0
+212392da-916d-4e36-86b8-c43857cb766d
+f746180e-f832-488d-910f-124f160934cd
+610f0c17-6653-44b7-873a-fd1ef5daf65e
+f1480aa2-c8c1-48cd-90b9-54318ee9f95b
+6f6a3f86-dae5-4710-91c9-b3676b000893
+89c80fa3-6d1c-4385-91eb-92088148c9b1
+9240c35d-5eff-4f45-b250-b670fbba00f3
+1c139e50-bf9b-4831-8128-3a68d8a15c88
+070c8f21-8411-45e2-acec-eb1e9a05ba9d
+075590cf-f73c-41e5-8b88-85e6eabb771d
+876c9b59-9e43-4602-83e5-6b05e105e89e
+73fd1b47-a741-49ff-8245-a57acdac132a
+f0cff5a4-d446-407b-9315-e8b64d53b1f2
+b2d6e47d-5430-45a4-b70e-4e0f5dba6966
+048fea6e-a512-435c-8d42-f5630e2b6f43
+32e2eec9-0fc3-4828-839f-e0d1ff745afa
+2405afd3-874e-477b-b518-ae8fdbd71e22
+26a4f01c-3811-49d5-8324-726a001359cd
+56425281-46a6-4ae6-891e-330569b0a0b8
+183e7234-1a3a-4ae6-bd70-9baae352443b
+97c31b37-de2c-48ac-b3a9-bc29f687da03
+595ab3e8-e341-4509-99d5-180f7de90123
+9b3a0453-6c7d-40e2-b2fa-6c8be2a55a9a
+9b3a0453-6c7d-40e2-b2fa-6c8be2a55a9a
+9b3a0453-6c7d-40e2-b2fa-6c8be2a55a9a
\ No newline at end of file
diff --git a/db/schema.rb b/db/schema.rb
index 0a3ade196..863ede1af 100644
--- a/db/schema.rb
+++ b/db/schema.rb
@@ -10,7 +10,7 @@
 #
 # It's strongly recommended that you check this file into your version control system.
 
-ActiveRecord::Schema.define(version: 2020_04_28_061736) do
+ActiveRecord::Schema.define(version: 2020_04_30_205827) do
 
   # These are extensions that must be enabled in order to support this database
   enable_extension "pgcrypto"
@@ -229,6 +229,7 @@
     t.string "aasm_state"
     t.datetime "created_at", null: false
     t.datetime "updated_at", null: false
+    t.json "deconcatenated_subject"
     t.index ["logo_id"], name: "index_items_on_logo_id"
     t.index ["owner_id"], name: "index_items_on_owner_id"
   end
@@ -289,6 +290,7 @@
     t.string "aasm_state"
     t.datetime "created_at", null: false
     t.datetime "updated_at", null: false
+    t.json "deconcatenated_subject"
     t.index ["logo_id"], name: "index_theses_on_logo_id"
     t.index ["owner_id"], name: "index_theses_on_owner_id"
   end

From 3b15b7dad7e13744d9fa08c75950c3cbd4c6d7cd Mon Sep 17 00:00:00 2001
From: Tricia Jenkins <tricia.g.jenkins@gmail.com>
Date: Fri, 1 May 2020 14:37:55 -0600
Subject: [PATCH 2/5] address pr feedback

- better path handling of files
- use find_each to batch which would reduce memory use
- added headings to the report log
---
 ...subject_issue.txt => ERA_subject_issue.txt |  0
 ...econcatenate_subject_in_item_and_thesis.rb | 32 +++++++++++++------
 2 files changed, 22 insertions(+), 10 deletions(-)
 rename db/migrate/ERA_subject_issue.txt => ERA_subject_issue.txt (100%)

diff --git a/db/migrate/ERA_subject_issue.txt b/ERA_subject_issue.txt
similarity index 100%
rename from db/migrate/ERA_subject_issue.txt
rename to ERA_subject_issue.txt
diff --git a/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb b/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb
index 9ea2e6f5b..3bbbbf70f 100644
--- a/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb
+++ b/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb
@@ -4,18 +4,30 @@ def change
     add_column :items, :deconcatenated_subject, :json
     add_column :theses, :deconcatenated_subject, :json
 
-    concatenated_subject_ids = File.readlines('db/migrate/ERA_subject_issue.txt').collect(&:strip)
-    report = Logger.new('log/concatenatedsubjects.log')
-    (Item.all + Thesis.all).each do |item|
-      item.deconcatenated_subject = if concatenated_subject_ids.include? item.id
-                                      deconcatenated_subject = item.subject.map { |subject| subject.split(%r{,\s*}) }.flatten
-                                      report.info("#{item.id}, \"#{item.title}\", #{item.subject}, #{deconcatenated_subject}")
-                                      deconcatenated_subject
-                                    else
-                                      item.subject
-                                    end
+    @concatenated_subject_ids = File.readlines(Rails.root.join('ERA_subject_issue.txt')).collect(&:strip)
+    @report = Logger.new(Rails.root.join('log/concatenated_subjects.log'))
+
+    Item.find_each do |item|
+      item.deconcatenated_subject = deconcatenated_subject(item)
+      item.save!
+    end
+
+    Thesis.find_each do |item|
+      item.deconcatenated_subject = deconcatenated_subject(item)
       item.save!
     end
   end
 
+  def deconcatenated_subject(item)
+    return item.subject unless @concatenated_subject_ids.include? item.id
+
+    deconcatenated_subject = item.subject.map { |subject| subject.split(%r{,\s*}) }.flatten
+    @report.info(
+      "id: #{item.id}, title: \"#{item.title}\", subject: #{item.subject},"\
+      " deconcatenated subject: #{deconcatenated_subject}"
+    )
+
+    deconcatenated_subject
+  end
+
 end

From f83fa72abe6deb738ad52a4f974512fb819df401 Mon Sep 17 00:00:00 2001
From: Tricia Jenkins <tricia.g.jenkins@gmail.com>
Date: Fri, 1 May 2020 15:21:27 -0600
Subject: [PATCH 3/5] further cleanup

- missed array: true for the new columns
- save directly to the database to bypass validations (some objects might need this exception to save)
---
 ...27_deconcatenate_subject_in_item_and_thesis.rb | 15 ++++-----------
 db/schema.rb                                      |  4 ++--
 2 files changed, 6 insertions(+), 13 deletions(-)

diff --git a/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb b/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb
index 3bbbbf70f..4779730d2 100644
--- a/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb
+++ b/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb
@@ -1,21 +1,14 @@
 class DeconcatenateSubjectInItemAndThesis < ActiveRecord::Migration[6.0]
 
   def change
-    add_column :items, :deconcatenated_subject, :json
-    add_column :theses, :deconcatenated_subject, :json
+    add_column :items, :deconcatenated_subject, :json, array: true
+    add_column :theses, :deconcatenated_subject, :json, array: true
 
     @concatenated_subject_ids = File.readlines(Rails.root.join('ERA_subject_issue.txt')).collect(&:strip)
     @report = Logger.new(Rails.root.join('log/concatenated_subjects.log'))
 
-    Item.find_each do |item|
-      item.deconcatenated_subject = deconcatenated_subject(item)
-      item.save!
-    end
-
-    Thesis.find_each do |item|
-      item.deconcatenated_subject = deconcatenated_subject(item)
-      item.save!
-    end
+    Item.find_each {|item| item.update_column deconcatenated_subject: deconcatenated_subject(item) }
+    Thesis.find_each {|item| item.update_column deconcatenated_subject: deconcatenated_subject(item) }
   end
 
   def deconcatenated_subject(item)
diff --git a/db/schema.rb b/db/schema.rb
index 863ede1af..01c5c608d 100644
--- a/db/schema.rb
+++ b/db/schema.rb
@@ -229,7 +229,7 @@
     t.string "aasm_state"
     t.datetime "created_at", null: false
     t.datetime "updated_at", null: false
-    t.json "deconcatenated_subject"
+    t.json "deconcatenated_subject", array: true
     t.index ["logo_id"], name: "index_items_on_logo_id"
     t.index ["owner_id"], name: "index_items_on_owner_id"
   end
@@ -290,7 +290,7 @@
     t.string "aasm_state"
     t.datetime "created_at", null: false
     t.datetime "updated_at", null: false
-    t.json "deconcatenated_subject"
+    t.json "deconcatenated_subject", array: true
     t.index ["logo_id"], name: "index_theses_on_logo_id"
     t.index ["owner_id"], name: "index_theses_on_owner_id"
   end

From 1b48292de83311d84429d3f0a3284947d22e3f91 Mon Sep 17 00:00:00 2001
From: Tricia Jenkins <tricia.g.jenkins@gmail.com>
Date: Thu, 11 Jun 2020 18:05:44 -0600
Subject: [PATCH 4/5] fix typo

update_column takes (key,value) while update_columns takes parameters in the form (key: value)
---
 ...20200430205827_deconcatenate_subject_in_item_and_thesis.rb | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb b/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb
index 4779730d2..842b5f1bc 100644
--- a/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb
+++ b/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb
@@ -7,8 +7,8 @@ def change
     @concatenated_subject_ids = File.readlines(Rails.root.join('ERA_subject_issue.txt')).collect(&:strip)
     @report = Logger.new(Rails.root.join('log/concatenated_subjects.log'))
 
-    Item.find_each {|item| item.update_column deconcatenated_subject: deconcatenated_subject(item) }
-    Thesis.find_each {|item| item.update_column deconcatenated_subject: deconcatenated_subject(item) }
+    Item.find_each {|item| item.update_columns deconcatenated_subject: deconcatenated_subject(item) }
+    Thesis.find_each {|item| item.update_columns deconcatenated_subject: deconcatenated_subject(item) }
   end
 
   def deconcatenated_subject(item)

From 8fe0ad8bc320e92354d1d6fa38625ed4630ab0da Mon Sep 17 00:00:00 2001
From: Tricia Jenkins <tricia.g.jenkins@gmail.com>
Date: Thu, 9 Jul 2020 12:01:28 -0600
Subject: [PATCH 5/5] add some error handling

We want to wrap this in the ability to catch an exception if the file doesn't exist, and then not do the rest of the migration and carry on. That way we can delete the file ERA_subject_issue.txt once this is all fixed instead of having to keep it around forever to avoid breaking migrations.
---
 ...200430205827_deconcatenate_subject_in_item_and_thesis.rb | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb b/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb
index 842b5f1bc..c9d8d3490 100644
--- a/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb
+++ b/db/migrate/20200430205827_deconcatenate_subject_in_item_and_thesis.rb
@@ -4,7 +4,11 @@ def change
     add_column :items, :deconcatenated_subject, :json, array: true
     add_column :theses, :deconcatenated_subject, :json, array: true
 
-    @concatenated_subject_ids = File.readlines(Rails.root.join('ERA_subject_issue.txt')).collect(&:strip)
+    @concatenated_subject_ids = if File.exist?(Rails.root.join('ERA_subject_issue.txt'))
+      File.readlines(Rails.root.join('ERA_subject_issue.txt')).collect(&:strip)
+    else
+      []
+    end
     @report = Logger.new(Rails.root.join('log/concatenated_subjects.log'))
 
     Item.find_each {|item| item.update_columns deconcatenated_subject: deconcatenated_subject(item) }