Reapply "ref: convert big table GzippedDictFields to LegacyTextJSONField (#97380)" (#97493)

This reverts commit f595908.

reapply after the fix in #97478

<!-- Describe your PR here. -->

Author: asottile-sentry

migrations_lockfile.txt

@@ -27,7 +27,7 @@ preprod: 0014_commitcomparisons_fk
 
 replays: 0006_add_bulk_delete_job
 
-sentry: 0964_add_commitcomparison_table
+sentry: 0965_gzippeddict_big_tables
 
 social_auth: 0003_social_auth_json_field
 

src/sentry/migrations/0965_gzippeddict_big_tables.py

@@ -0,0 +1,44 @@
+# Generated by Django 5.2.1 on 2025-08-07 15:00
+
+from django.db import migrations
+
+import sentry.db.models.fields.jsonfield
+from sentry.new_migrations.migrations import CheckedMigration
+
+
+class Migration(CheckedMigration):
+    # This flag is used to mark that a migration shouldn't be automatically run in production.
+    # 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 post deployment:
+    # - Large data migrations. Typically we want these to be run manually 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
+    #   run this outside deployments so that we don't block them. Note that while adding an index
+    #   is a schema change, it's completely safe to run the operation after the code has deployed.
+    # Once deployed, run these manually via: https://develop.sentry.dev/database-migrations/#migration-deployment
+
+    is_post_deployment = False
+
+    dependencies = [
+        ("sentry", "0964_add_commitcomparison_table"),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name="activity",
+            name="data",
+            field=sentry.db.models.fields.jsonfield.LegacyTextJSONField(default=dict, null=True),
+        ),
+        migrations.AlterField(
+            model_name="group",
+            name="data",
+            field=sentry.db.models.fields.jsonfield.LegacyTextJSONField(null=True),
+        ),
+        migrations.AlterField(
+            model_name="rule",
+            name="data",
+            field=sentry.db.models.fields.jsonfield.LegacyTextJSONField(default=dict),
+        ),
+    ]

src/sentry/models/activity.py

@@ -16,12 +16,12 @@
 from sentry.db.models import (
     BoundedPositiveIntegerField,
     FlexibleForeignKey,
-    GzippedDictField,
     Model,
     region_silo_model,
     sane_repr,
 )
 from sentry.db.models.fields.hybrid_cloud_foreign_key import HybridCloudForeignKey
+from sentry.db.models.fields.jsonfield import LegacyTextJSONField
 from sentry.db.models.manager.base import BaseManager
 from sentry.integrations.types import IntegrationProviderSlug
 from sentry.issues.grouptype import get_group_type_by_type_id
@@ -118,7 +118,7 @@ class Activity(Model):
     # if the user is not set, it's assumed to be the system
     user_id = HybridCloudForeignKey(settings.AUTH_USER_MODEL, null=True, on_delete="SET_NULL")
     datetime = models.DateTimeField(default=timezone.now)
-    data: models.Field[dict[str, Any] | None, dict[str, Any]] = GzippedDictField(null=True)
+    data = LegacyTextJSONField(default=dict, null=True)
 
     objects: ClassVar[ActivityManager] = ActivityManager()
 

src/sentry/models/group.py

@@ -29,11 +29,11 @@
     BoundedIntegerField,
     BoundedPositiveIntegerField,
     FlexibleForeignKey,
-    GzippedDictField,
     Model,
     region_silo_model,
     sane_repr,
 )
+from sentry.db.models.fields.jsonfield import LegacyTextJSONField
 from sentry.db.models.manager.base import BaseManager
 from sentry.eventstore.models import GroupEvent
 from sentry.issues.grouptype import GroupCategory, get_group_type_by_type_id
@@ -612,9 +612,7 @@ class Group(Model):
     time_spent_count = BoundedIntegerField(default=0)
     # deprecated, do not use. GroupShare has superseded
     is_public = models.BooleanField(default=False, null=True)
-    data: models.Field[dict[str, Any] | None, dict[str, Any]] = GzippedDictField(
-        blank=True, null=True
-    )
+    data = LegacyTextJSONField(null=True)
     short_id = BoundedBigIntegerField(null=True)
     type = BoundedPositiveIntegerField(
         default=DEFAULT_TYPE_ID, db_default=DEFAULT_TYPE_ID, db_index=True

src/sentry/models/rule.py

@@ -13,12 +13,12 @@
 from sentry.db.models import (
     BoundedPositiveIntegerField,
     FlexibleForeignKey,
-    GzippedDictField,
     Model,
     region_silo_model,
     sane_repr,
 )
 from sentry.db.models.fields.hybrid_cloud_foreign_key import HybridCloudForeignKey
+from sentry.db.models.fields.jsonfield import LegacyTextJSONField
 from sentry.db.models.manager.base import BaseManager
 from sentry.types.actor import Actor
 from sentry.utils.cache import cache
@@ -48,7 +48,7 @@ class Rule(Model):
     environment_id = BoundedPositiveIntegerField(null=True)
     label = models.CharField(max_length=256)
     # `data` contain all the specifics of the rule - conditions, actions, frequency, etc.
-    data: models.Field[dict[str, Any], dict[str, Any]] = GzippedDictField()
+    data = LegacyTextJSONField(default=dict)
     status = BoundedPositiveIntegerField(
         default=ObjectStatus.ACTIVE,
         choices=((ObjectStatus.ACTIVE, "Active"), (ObjectStatus.DISABLED, "Disabled")),

src/sentry/rules/conditions/reappeared_event.py

@@ -36,7 +36,7 @@ def get_activity(
                 group_id=group_id,
                 type=ConditionActivityType.REAPPEARED,
                 timestamp=timestamp,
-                data=data,
+                data=data or {},
             )
             for group_id, timestamp, data in activities
             if group_id is not None

src/sentry/rules/conditions/regression_event.py

@@ -35,7 +35,7 @@ def get_activity(
                 group_id=group_id,
                 type=ConditionActivityType.REGRESSION,
                 timestamp=timestamp,
-                data=data,
+                data=data or {},
             )
             for group_id, timestamp, data in activities
             if group_id is not None

src/sentry/seer/fetch_issues/fetch_issues_given_exception_type.py

@@ -117,7 +117,7 @@ def get_issues_related_to_exception_type(
     date_threshold = datetime.now(tz=UTC) - timedelta(days=num_days_ago)
 
     # Fetch issues where the exception type is the given exception type
-    # Using a bit ofraw SQL since data is GzippedDictField which can't be filtered with Django ORM
+    # Using a bit ofraw SQL since data is LegacyTextJSONField which can't be filtered with Django ORM
     query_set = (
         Group.objects.annotate(metadata_type=RawSQL("(data::json -> 'metadata' ->> 'type')", []))
         .filter(