migration: backfill apitoken last characters (#63342)

Backfills the `token_last_characters` column on existing `ApiToken` entries.

As of #62972, new `ApiToken` entries
are being created with this column already populated with the correct
values. This backfill will only impact old tokens created prior.

Tracking Issue: #58918
Related RFC: getsentry/rfcs#32

Author: mdtro

migrations_lockfile.txt

@@ -9,5 +9,5 @@ feedback: 0003_feedback_add_env
 hybridcloud: 0009_make_user_id_optional_for_slug_reservation_replica
 nodestore: 0002_nodestore_no_dictfield
 replays: 0003_add_size_to_recording_segment
-sentry: 0631_add_priority_columns_to_groupedmessage
+sentry: 0632_apitoken_backfill_last_chars
 social_auth: 0002_default_auto_field

src/sentry/migrations/0632_apitoken_backfill_last_chars.py

@@ -0,0 +1,46 @@
+# Generated by Django 3.2.23 on 2024-01-17 16:06
+
+from django.db import migrations
+
+from sentry.new_migrations.migrations import CheckedMigration
+from sentry.utils.query import RangeQuerySetWrapperWithProgressBar
+
+
+def backfill_last_token_characters(apps, _):
+    from sentry.models.apitoken import ApiToken
+
+    for api_token in RangeQuerySetWrapperWithProgressBar(ApiToken.objects.all()):
+        if api_token.token_last_characters is None:
+            last_four = api_token.token[-4:]
+            api_token.token_last_characters = last_four
+            api_token.save()
+
+
+class Migration(CheckedMigration):
+    # This flag is used to mark that a migration shouldn't be automatically run in production. For
+    # the most part, this should only be used for operations where it's safe to run the migration
+    # after your code has deployed. So this should not be used for most operations that alter the
+    # schema of a table.
+    # Here are some things that make sense to mark as dangerous:
+    # - Large data migrations. Typically we want these to be run manually by ops so that they can
+    #   be monitored and not block the deploy for a long period of time while they run.
+    # - Adding indexes to large tables. Since this can take a long time, we'd generally prefer to
+    #   have ops run this and not block the deploy. Note that while adding an index is a schema
+    #   change, it's completely safe to run the operation after the code has deployed.
+    is_dangerous = True
+
+    dependencies = [
+        ("sentry", "0631_add_priority_columns_to_groupedmessage"),
+    ]
+
+    operations = [
+        migrations.RunPython(
+            backfill_last_token_characters,
+            migrations.RunPython.noop,
+            hints={
+                "tables": [
+                    "sentry_apitoken",
+                ]
+            },
+        ),
+    ]

tests/sentry/migrations/test_0632_apitoken_backfill_last_chars.py

@@ -0,0 +1,37 @@
+from django.db import router
+
+from sentry.silo import unguarded_write
+from sentry.testutils.cases import TestMigrations
+from sentry.testutils.helpers import override_options
+
+
+class LastCharsApiTokenMigrationTest(TestMigrations):
+    migrate_from = "0631_add_priority_columns_to_groupedmessage"
+    migrate_to = "0632_apitoken_backfill_last_chars"
+    connection = "control"
+
+    def setUp(self):
+        from sentry.models.apitoken import ApiToken
+
+        with unguarded_write(using=router.db_for_write(ApiToken)):
+            super().setUp()
+
+    @override_options({"apitoken.auto-add-last-chars": False})
+    def setup_before_migration(self, apps):
+        ApiToken = apps.get_model("sentry", "ApiToken")
+
+        self.api_token = ApiToken.objects.create(
+            user_id=self.user.id,
+            refresh_token=None,
+        )
+        self.api_token.save()
+
+        assert self.api_token.token_last_characters is None
+
+    def test(self):
+        from sentry.models.apitoken import ApiToken
+
+        api_tokens = ApiToken.objects.all()
+        for api_token in api_tokens:
+            assert api_token.name is None
+            assert api_token.token_last_characters == api_token.token[-4:]