revert: perf: use elements chain materialization (#23934)

PostHog · Jul 24, 2024 · 967eb55 · 967eb55
1 parent 9ee8309
commit 967eb55
Show file tree

Hide file tree

Showing 12 changed files with 285 additions and 1,133 deletions.
diff --git a/ee/clickhouse/materialized_columns/columns.py b/ee/clickhouse/materialized_columns/columns.py
@@ -44,7 +44,6 @@ def get_materialized_columns(
         WHERE database = %(database)s
           AND table = %(table)s
           AND comment LIKE '%%column_materializer::%%'
-          AND comment not LIKE '%%column_materializer::elements_chain::%%'
     """,
         {"database": CLICKHOUSE_DATABASE, "table": table},
     )

diff --git a/mypy-baseline.txt b/mypy-baseline.txt
@@ -256,6 +256,9 @@ posthog/models/property/util.py:0: error: Argument 1 to "append" of "list" has i
 posthog/models/property/util.py:0: error: Argument 1 to "append" of "list" has incompatible type "str | int"; expected "str"  [arg-type]
 posthog/models/property/util.py:0: error: Argument 1 to "append" of "list" has incompatible type "str | int"; expected "str"  [arg-type]
 posthog/queries/trends/util.py:0: error: Argument 1 to "translate_hogql" has incompatible type "str | None"; expected "str"  [arg-type]
+posthog/hogql/property.py:0: error: Argument "chain" to "Field" has incompatible type "list[str]"; expected "list[str | int]"  [arg-type]
+posthog/hogql/property.py:0: note: "List" is invariant -- see https://mypy.readthedocs.io/en/stable/common_issues.html#variance
+posthog/hogql/property.py:0: note: Consider using "Sequence" instead, which is covariant
 posthog/hogql/property.py:0: error: Incompatible type for lookup 'id': (got "str | int | list[str]", expected "str | int")  [misc]
 posthog/hogql/property.py:0: error: Incompatible type for lookup 'pk': (got "str | float", expected "str | int")  [misc]
 posthog/hogql/filters.py:0: error: Incompatible default for argument "team" (default has type "None", argument has type "Team")  [assignment]

diff --git a/posthog/api/test/test_action.py b/posthog/api/test/test_action.py
@@ -136,7 +136,9 @@ def test_update_action(self, patch_capture, *args):
         action = Action.objects.create(
             name="user signed up", team=self.team, steps_json=[{"event": "$autocapture", "text": "sign me up!"}]
         )
+        action.refresh_bytecode()
         action.save()
+        previous_bytecode = action.bytecode
 
         response = self.client.patch(
             f"/api/projects/{self.team.id}/actions/{action.pk}/",
@@ -196,6 +198,8 @@ def test_update_action(self, patch_capture, *args):
         action.refresh_from_db()
         assert action.name == "user signed up 2"
 
+        assert previous_bytecode != action.bytecode
+
         # Assert analytics are sent
         patch_capture.assert_called_with(
             user,

diff --git a/posthog/clickhouse/test/__snapshots__/test_schema.ambr b/posthog/clickhouse/test/__snapshots__/test_schema.ambr
@@ -595,10 +595,6 @@
       , $group_4 VARCHAR COMMENT 'column_materializer::$group_4'
       , $window_id VARCHAR COMMENT 'column_materializer::$window_id'
       , $session_id VARCHAR COMMENT 'column_materializer::$session_id'
-      , elements_chain_href String COMMENT 'column_materializer::elements_chain::href'
-      , elements_chain_texts Array(String) COMMENT 'column_materializer::elements_chain::texts'
-      , elements_chain_ids Array(String) COMMENT 'column_materializer::elements_chain::ids'
-      , elements_chain_elements Array(Enum('a', 'button', 'form', 'input', 'select', 'textarea', 'label')) COMMENT 'column_materializer::elements_chain::elements'
 
 
   , _timestamp DateTime
@@ -2177,17 +2173,17 @@
       , $group_4 VARCHAR MATERIALIZED replaceRegexpAll(JSONExtractRaw(properties, '$group_4'), '^"|"$', '') COMMENT 'column_materializer::$group_4'
       , $window_id VARCHAR MATERIALIZED replaceRegexpAll(JSONExtractRaw(properties, '$window_id'), '^"|"$', '') COMMENT 'column_materializer::$window_id'
       , $session_id VARCHAR MATERIALIZED replaceRegexpAll(JSONExtractRaw(properties, '$session_id'), '^"|"$', '') COMMENT 'column_materializer::$session_id'
-      , elements_chain_href String MATERIALIZED extract(elements_chain, '(?::|")href="(.*?)"')
-      , elements_chain_texts Array(String) MATERIALIZED arrayDistinct(extractAll(elements_chain, '(?::|")text="(.*?)"'))
-      , elements_chain_ids Array(String) MATERIALIZED arrayDistinct(extractAll(elements_chain, '(?::|")attr_id="(.*?)"'))
-      , elements_chain_elements Array(Enum('a', 'button', 'form', 'input', 'select', 'textarea', 'label')) MATERIALIZED arrayDistinct(extractAll(elements_chain, '(?:^|;)(a|button|form|input|select|textarea|label)(?:\.|$|:)'))
       , INDEX `minmax_$group_0` `$group_0` TYPE minmax GRANULARITY 1
       , INDEX `minmax_$group_1` `$group_1` TYPE minmax GRANULARITY 1
       , INDEX `minmax_$group_2` `$group_2` TYPE minmax GRANULARITY 1
       , INDEX `minmax_$group_3` `$group_3` TYPE minmax GRANULARITY 1
       , INDEX `minmax_$group_4` `$group_4` TYPE minmax GRANULARITY 1
       , INDEX `minmax_$window_id` `$window_id` TYPE minmax GRANULARITY 1
       , INDEX `minmax_$session_id` `$session_id` TYPE minmax GRANULARITY 1
+      , elements_chain_href String MATERIALIZED extract(elements_chain, '(?::|")href="(.*?)"')
+      , elements_chain_texts Array(String) MATERIALIZED arrayDistinct(extractAll(elements_chain, '(?::|")text="(.*?)"'))
+      , elements_chain_ids Array(String) MATERIALIZED arrayDistinct(extractAll(elements_chain, '(?::|")attr_id="(.*?)"'))
+      , elements_chain_elements Array(Enum('a', 'button', 'form', 'input', 'select', 'textarea', 'label')) MATERIALIZED arrayDistinct(extractAll(elements_chain, '(?:^|;)(a|button|form|input|select|textarea|label)(?:\.|$|:)'))
 
 
   , _timestamp DateTime
@@ -3271,17 +3267,17 @@
       , $group_4 VARCHAR MATERIALIZED replaceRegexpAll(JSONExtractRaw(properties, '$group_4'), '^"|"$', '') COMMENT 'column_materializer::$group_4'
       , $window_id VARCHAR MATERIALIZED replaceRegexpAll(JSONExtractRaw(properties, '$window_id'), '^"|"$', '') COMMENT 'column_materializer::$window_id'
       , $session_id VARCHAR MATERIALIZED replaceRegexpAll(JSONExtractRaw(properties, '$session_id'), '^"|"$', '') COMMENT 'column_materializer::$session_id'
-      , elements_chain_href String MATERIALIZED extract(elements_chain, '(?::|")href="(.*?)"')
-      , elements_chain_texts Array(String) MATERIALIZED arrayDistinct(extractAll(elements_chain, '(?::|")text="(.*?)"'))
-      , elements_chain_ids Array(String) MATERIALIZED arrayDistinct(extractAll(elements_chain, '(?::|")attr_id="(.*?)"'))
-      , elements_chain_elements Array(Enum('a', 'button', 'form', 'input', 'select', 'textarea', 'label')) MATERIALIZED arrayDistinct(extractAll(elements_chain, '(?:^|;)(a|button|form|input|select|textarea|label)(?:\.|$|:)'))
       , INDEX `minmax_$group_0` `$group_0` TYPE minmax GRANULARITY 1
       , INDEX `minmax_$group_1` `$group_1` TYPE minmax GRANULARITY 1
       , INDEX `minmax_$group_2` `$group_2` TYPE minmax GRANULARITY 1
       , INDEX `minmax_$group_3` `$group_3` TYPE minmax GRANULARITY 1
       , INDEX `minmax_$group_4` `$group_4` TYPE minmax GRANULARITY 1
       , INDEX `minmax_$window_id` `$window_id` TYPE minmax GRANULARITY 1
       , INDEX `minmax_$session_id` `$session_id` TYPE minmax GRANULARITY 1
+      , elements_chain_href String MATERIALIZED extract(elements_chain, '(?::|")href="(.*?)"')
+      , elements_chain_texts Array(String) MATERIALIZED arrayDistinct(extractAll(elements_chain, '(?::|")text="(.*?)"'))
+      , elements_chain_ids Array(String) MATERIALIZED arrayDistinct(extractAll(elements_chain, '(?::|")attr_id="(.*?)"'))
+      , elements_chain_elements Array(Enum('a', 'button', 'form', 'input', 'select', 'textarea', 'label')) MATERIALIZED arrayDistinct(extractAll(elements_chain, '(?:^|;)(a|button|form|input|select|textarea|label)(?:\.|$|:)'))
 
 
   , _timestamp DateTime

diff --git a/posthog/hogql/database/schema/events.py b/posthog/hogql/database/schema/events.py
@@ -3,7 +3,6 @@
     StringDatabaseField,
     DateTimeDatabaseField,
     StringJSONDatabaseField,
-    StringArrayDatabaseField,
     IntegerDatabaseField,
     Table,
     LazyJoin,
@@ -115,10 +114,6 @@ class EventsTable(Table):
             join_table=SessionsTableV1(),
             join_function=join_events_table_to_sessions_table,
         ),
-        "elements_chain_href": StringDatabaseField(name="elements_chain_href"),
-        "elements_chain_texts": StringArrayDatabaseField(name="elements_chain_texts"),
-        "elements_chain_ids": StringArrayDatabaseField(name="elements_chain_ids"),
-        "elements_chain_elements": StringArrayDatabaseField(name="elements_chain_elements"),
     }
 
     def to_printed_clickhouse(self, context):

diff --git a/posthog/hogql/database/test/__snapshots__/test_database.ambr b/posthog/hogql/database/test/__snapshots__/test_database.ambr
@@ -377,42 +377,6 @@
                   "schema_valid": true,
                   "table": "sessions",
                   "type": "lazy_table"
-              },
-              "elements_chain_href": {
-                  "chain": null,
-                  "fields": null,
-                  "hogql_value": "elements_chain_href",
-                  "name": "elements_chain_href",
-                  "schema_valid": true,
-                  "table": null,
-                  "type": "string"
-              },
-              "elements_chain_texts": {
-                  "chain": null,
-                  "fields": null,
-                  "hogql_value": "elements_chain_texts",
-                  "name": "elements_chain_texts",
-                  "schema_valid": true,
-                  "table": null,
-                  "type": "array"
-              },
-              "elements_chain_ids": {
-                  "chain": null,
-                  "fields": null,
-                  "hogql_value": "elements_chain_ids",
-                  "name": "elements_chain_ids",
-                  "schema_valid": true,
-                  "table": null,
-                  "type": "array"
-              },
-              "elements_chain_elements": {
-                  "chain": null,
-                  "fields": null,
-                  "hogql_value": "elements_chain_elements",
-                  "name": "elements_chain_elements",
-                  "schema_valid": true,
-                  "table": null,
-                  "type": "array"
               }
           },
           "id": "events",
@@ -748,11 +712,7 @@
                       "group_3",
                       "$group_4",
                       "group_4",
-                      "session",
-                      "elements_chain_href",
-                      "elements_chain_texts",
-                      "elements_chain_ids",
-                      "elements_chain_elements"
+                      "session"
                   ],
                   "hogql_value": "events",
                   "name": "events",
@@ -1734,42 +1694,6 @@
                   "schema_valid": true,
                   "table": "sessions",
                   "type": "lazy_table"
-              },
-              "elements_chain_href": {
-                  "chain": null,
-                  "fields": null,
-                  "hogql_value": "elements_chain_href",
-                  "name": "elements_chain_href",
-                  "schema_valid": true,
-                  "table": null,
-                  "type": "string"
-              },
-              "elements_chain_texts": {
-                  "chain": null,
-                  "fields": null,
-                  "hogql_value": "elements_chain_texts",
-                  "name": "elements_chain_texts",
-                  "schema_valid": true,
-                  "table": null,
-                  "type": "array"
-              },
-              "elements_chain_ids": {
-                  "chain": null,
-                  "fields": null,
-                  "hogql_value": "elements_chain_ids",
-                  "name": "elements_chain_ids",
-                  "schema_valid": true,
-                  "table": null,
-                  "type": "array"
-              },
-              "elements_chain_elements": {
-                  "chain": null,
-                  "fields": null,
-                  "hogql_value": "elements_chain_elements",
-                  "name": "elements_chain_elements",
-                  "schema_valid": true,
-                  "table": null,
-                  "type": "array"
               }
           },
           "id": "events",
@@ -2105,11 +2029,7 @@
                       "group_3",
                       "$group_4",
                       "group_4",
-                      "session",
-                      "elements_chain_href",
-                      "elements_chain_texts",
-                      "elements_chain_ids",
-                      "elements_chain_elements"
+                      "session"
                   ],
                   "hogql_value": "events",
                   "name": "events",