From 076efd653d04cc6701b6c0da326eb0242a6de5d4 Mon Sep 17 00:00:00 2001
From: Maikel Linke <maikel@email.org.au>
Date: Thu, 2 Jun 2022 12:13:34 +1000
Subject: [PATCH] Correct checksum of big files stored on AWS S3

---
 ...0602013938_compute_checksum_for_big_files.rb | 17 +++++++++++++++++
 db/schema.rb                                    |  2 +-
 2 files changed, 18 insertions(+), 1 deletion(-)
 create mode 100644 db/migrate/20220602013938_compute_checksum_for_big_files.rb

diff --git a/db/migrate/20220602013938_compute_checksum_for_big_files.rb b/db/migrate/20220602013938_compute_checksum_for_big_files.rb
new file mode 100644
index 0000000000..697f731e5d
--- /dev/null
+++ b/db/migrate/20220602013938_compute_checksum_for_big_files.rb
@@ -0,0 +1,17 @@
+# When migrating to Active Storage, we used Amazon's ETag for the blob
+# checksum. But big files have been uploaded in chunks and then the checksum
+# differs. We need to recalculate the checksum for large files.
+class ComputeChecksumForBigFiles < ActiveRecord::Migration[6.1]
+  def up
+    blobs_with_incorrect_checksum.find_each do |blob|
+      md5 = Digest::MD5.base64digest(blob.download)
+      blob.update(checksum: md5)
+    end
+  end
+
+  def blobs_with_incorrect_checksum
+    ActiveStorage::Blob.
+      where(service_name: "amazon").
+      where("byte_size >= 20000000")
+  end
+end
diff --git a/db/schema.rb b/db/schema.rb
index 0ad1f12db3..010059c3d6 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: 2022_04_10_162955) do
+ActiveRecord::Schema.define(version: 2022_06_02_013938) do
 
   # These are extensions that must be enabled in order to support this database
   enable_extension "plpgsql"