Java CDK: DV2 tests have separate testcases for safe_cast (#36935)

airbytehq · May 3, 2024 · 4894ad2 · 4894ad2
1 parent 2c0cd6c
commit 4894ad2
Show file tree

Hide file tree

Showing 15 changed files with 218 additions and 104 deletions.
diff --git a/airbyte-cdk/java/airbyte-cdk/README.md b/airbyte-cdk/java/airbyte-cdk/README.md
@@ -174,6 +174,7 @@ corresponds to that version.
 
 | Version | Date       | Pull Request                                               | Subject                                                                                                                                                        |
 | :------ | :--------- | :--------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| 0.33.0  | 2024-05-03 | [\#36935](https://github.com/airbytehq/airbyte/pull/36935) | Destinations: Enable non-safe-casting DV2 tests                                                                                                                |
 | 0.32.0  | 2024-05-03 | [\#36929](https://github.com/airbytehq/airbyte/pull/36929) | Destinations: Assorted DV2 changes for mysql                                                                                                                   |
 | 0.31.7  | 2024-05-02 | [\#36910](https://github.com/airbytehq/airbyte/pull/36910) | changes for destination-snowflake                                                                                                                              |
 | 0.31.6  | 2024-05-02 | [\#37746](https://github.com/airbytehq/airbyte/pull/37746) | debuggability improvements.                                                                                                                                    |

diff --git a/airbyte-cdk/java/airbyte-cdk/core/src/main/resources/version.properties b/airbyte-cdk/java/airbyte-cdk/core/src/main/resources/version.properties
@@ -1 +1 @@
-version=0.32.0
+version=0.33.0
diff --git a/.../airbyte/integrations/base/destination/typing_deduping/BaseSqlGeneratorIntegrationTest.kt b/.../airbyte/integrations/base/destination/typing_deduping/BaseSqlGeneratorIntegrationTest.kt
diff --git a/...byte-cdk/typing-deduping/src/testFixtures/resources/dat/sync1_cursorchange_messages.jsonl b/...byte-cdk/typing-deduping/src/testFixtures/resources/dat/sync1_cursorchange_messages.jsonl
@@ -1,4 +1,4 @@
 {"type": "RECORD", "record": {"emitted_at": 1000, "data": {"id1": 1, "id2": 200, "old_cursor": 0, "_ab_cdc_deleted_at": null, "name": "Alice", "address": {"city": "San Francisco", "state": "CA"}}}}
 {"type": "RECORD", "record": {"emitted_at": 1000, "data": {"id1": 1, "id2": 200, "old_cursor": 1, "_ab_cdc_deleted_at": null, "name": "Alice", "address": {"city": "Los Angeles", "state": "CA"}}}}
 {"type": "RECORD", "record": {"emitted_at": 1000, "data": {"id1": 1, "id2": 201, "old_cursor": 2, "name": "Bob", "address": {"city": "Boston", "state": "MA"}}}}
-{"type": "RECORD", "record": {"emitted_at": 1000, "data": {"id1": 2, "id2": 200, "old_cursor": 3, "name": "Charlie", "age": "this is not an integer", "registration_date": "this is not a date"}}}
+{"type": "RECORD", "record": {"emitted_at": 1000, "data": {"id1": 2, "id2": 200, "old_cursor": 3, "name": "Charlie", "age": 42, "registration_date": "2023-12-23"}}}
diff --git a/...-cdk/java/airbyte-cdk/typing-deduping/src/testFixtures/resources/dat/sync1_messages.jsonl b/...-cdk/java/airbyte-cdk/typing-deduping/src/testFixtures/resources/dat/sync1_messages.jsonl
@@ -8,7 +8,7 @@
 {"type": "RECORD", "record": {"emitted_at": 1000, "data": {"id1": 1, "id2": 200, "updated_at": "2000-01-01T00:01:00Z", "_ab_cdc_deleted_at": null, "name": "Alice", "address": {"city": "Los Angeles", "state": "CA"}}}}
 // Emit a record with no _ab_cdc_deleted_at field. CDC sources typically emit an explicit null, but we should handle both cases.
 {"type": "RECORD", "record": {"emitted_at": 1000, "data": {"id1": 1, "id2": 201, "updated_at": "2000-01-01T00:02:00Z", "name": "Bob", "address": {"city": "Boston", "state": "MA"}}}}
-// Emit a record with an invalid age & address nulled at source.
-{"type": "RECORD", "record": {"emitted_at": 1000, "data": {"id1": 2, "id2": 200, "updated_at": "2000-01-01T00:03:00Z", "name": "Charlie", "age": "this is not an integer", "registration_date": "this is not a date"}, "meta": {"changes": [{"field": "address", "change": "NULLED", "reason": "SOURCE_RETRIEVAL_ERROR"}]}}}
+// Emit a record with address nulled at source.
+{"type": "RECORD", "record": {"emitted_at": 1000, "data": {"id1": 2, "id2": 200, "updated_at": "2000-01-01T00:03:00Z", "name": "Charlie", "age": 42, "registration_date": "2023-12-23"}, "meta": {"changes": [{"field": "address", "change": "NULLED", "reason": "SOURCE_RETRIEVAL_ERROR"}]}}}
 // Emit a record with interesting characters in one of the values.
 {"type": "RECORD", "record": {"emitted_at": 1000, "data": {"id1": 3, "id2": 200, "updated_at": "2000-01-01T00:04:00Z", "name": "a\bb\fc\nd\re\tf`~!@#$%^&*()_+-=[]\\{}|'\",./<>?"}}}
diff --git a/...k/typing-deduping/src/testFixtures/resources/sqlgenerator/all_types_v1_inputrecords.jsonl b/...k/typing-deduping/src/testFixtures/resources/sqlgenerator/all_types_v1_inputrecords.jsonl
@@ -1,7 +1,4 @@
 {"_airbyte_ab_id": "14ba7c7f-e398-4e69-ac22-28d578400dbc", "_airbyte_emitted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 1, "id2": 100, "updated_at": "2023-01-01T01:00:00Z", "array": ["foo"], "struct": {"foo": "bar"}, "string": "foo", "number": 42.1, "integer": 42, "boolean": true, "timestamp_with_timezone": "2023-01-23T12:34:56Z", "timestamp_without_timezone": "2023-01-23T12:34:56", "time_with_timezone": "12:34:56Z", "time_without_timezone": "12:34:56", "date": "2023-01-23", "unknown": {}}}
 {"_airbyte_ab_id": "53ce75a5-5bcc-47a3-b45c-96c2015cfe35", "_airbyte_emitted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 2, "id2": 100, "updated_at": "2023-01-01T01:00:00Z", "array": null, "struct": null, "string": null, "number": null, "integer": null, "boolean": null, "timestamp_with_timezone": null, "timestamp_without_timezone": null, "time_with_timezone": null, "time_without_timezone": null, "date": null, "unknown": null}}
 {"_airbyte_ab_id": "7e1fac0c-017e-4ad6-bc78-334a34d64fbe", "_airbyte_emitted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 3, "id2": 100, "updated_at": "2023-01-01T01:00:00Z"}}
-// Note that array and struct have invalid values ({} and [] respectively).
-{"_airbyte_ab_id": "84242b60-3a34-4531-ad75-a26702960a9a", "_airbyte_emitted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 4, "id2": 100, "updated_at": "2023-01-01T01:00:00Z", "array": {}, "struct": [], "string": null, "number": "foo", "integer": "bar", "boolean": "fizz", "timestamp_with_timezone": {}, "timestamp_without_timezone": {}, "time_with_timezone": {}, "time_without_timezone": {}, "date": "airbyte", "unknown": null}}
 {"_airbyte_ab_id": "a4a783b5-7729-4d0b-b659-48ceb08713f1", "_airbyte_emitted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 5, "id2": 100, "updated_at": "2023-01-01T01:00:00Z", "number": 67.174118, "struct": {"nested_number": 67.174118}, "array": [67.174118], "unknown": 67.174118}}
-{"_airbyte_ab_id": "7e1fac0c-017e-4ad6-bc78-334a34d64fce", "_airbyte_emitted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 6, "id2": 100, "updated_at": "2023-01-01T01:00:00Z", "IamACaseSensitiveColumnName": "Case senstive value"}}
diff --git a/...e-cdk/typing-deduping/src/testFixtures/resources/sqlgenerator/alltypes_inputrecords.jsonl b/...e-cdk/typing-deduping/src/testFixtures/resources/sqlgenerator/alltypes_inputrecords.jsonl
@@ -1,7 +1,4 @@
 {"_airbyte_raw_id": "14ba7c7f-e398-4e69-ac22-28d578400dbc", "_airbyte_extracted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 1, "id2": 100, "updated_at": "2023-01-01T01:00:00Z", "array": ["foo"], "struct": {"foo": "bar"}, "string": "foo", "number": 42.1, "integer": 42, "boolean": true, "timestamp_with_timezone": "2023-01-23T12:34:56Z", "timestamp_without_timezone": "2023-01-23T12:34:56", "time_with_timezone": "12:34:56Z", "time_without_timezone": "12:34:56", "date": "2023-01-23", "unknown": {}}}
 {"_airbyte_raw_id": "53ce75a5-5bcc-47a3-b45c-96c2015cfe35", "_airbyte_extracted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 2, "id2": 100, "updated_at": "2023-01-01T01:00:00Z", "array": null, "struct": null, "string": null, "number": null, "integer": null, "boolean": null, "timestamp_with_timezone": null, "timestamp_without_timezone": null, "time_with_timezone": null, "time_without_timezone": null, "date": null, "unknown": null}}
-{"_airbyte_raw_id": "7e1fac0c-017e-4ad6-bc78-334a34d64fbe", "_airbyte_extracted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 3, "id2": 100, "updated_at": "2023-01-01T01:00:00Z"}}
-// Note that array and struct have invalid values ({} and [] respectively).
-{"_airbyte_raw_id": "84242b60-3a34-4531-ad75-a26702960a9a", "_airbyte_extracted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 4, "id2": 100, "updated_at": "2023-01-01T01:00:00Z", "array": {}, "struct": [], "string": null, "number": "foo", "integer": "bar", "boolean": "fizz", "timestamp_with_timezone": {}, "timestamp_without_timezone": {}, "time_with_timezone": {}, "time_without_timezone": {}, "date": "airbyte", "unknown": null}, "_airbyte_meta": {"changes": [{"field": "string", "change": "NULLED", "reason": "SOURCE_SERIALIZATION_ERROR"}]}}
+{"_airbyte_raw_id": "7e1fac0c-017e-4ad6-bc78-334a34d64fbe", "_airbyte_extracted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 3, "id2": 100, "updated_at": "2023-01-01T01:00:00Z"}, "_airbyte_meta": {"changes": [{"field": "string", "change": "NULLED", "reason": "SOURCE_SERIALIZATION_ERROR"}]}}
 {"_airbyte_raw_id": "a4a783b5-7729-4d0b-b659-48ceb08713f1", "_airbyte_extracted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 5, "id2": 100, "updated_at": "2023-01-01T01:00:00Z", "number": 67.174118, "struct": {"nested_number": 67.174118}, "array": [67.174118], "unknown": 67.174118}}
-{"_airbyte_raw_id": "7e1fac0c-017e-4ad6-bc78-334a34d64fce", "_airbyte_extracted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 6, "id2": 100, "updated_at": "2023-01-01T01:00:00Z", "IamACaseSensitiveColumnName": "Case senstive value"}}
diff --git a/...yping-deduping/src/testFixtures/resources/sqlgenerator/alltypes_unsafe_inputrecords.jsonl b/...yping-deduping/src/testFixtures/resources/sqlgenerator/alltypes_unsafe_inputrecords.jsonl
diff --git a/.../typing-deduping/src/testFixtures/resources/sqlgenerator/cdcupdate_inputrecords_raw.jsonl b/.../typing-deduping/src/testFixtures/resources/sqlgenerator/cdcupdate_inputrecords_raw.jsonl
@@ -12,5 +12,3 @@
 {"_airbyte_raw_id": "4d8674a5-eb6e-41ca-a310-69c64c88d101", "_airbyte_extracted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 0, "id2": 100, "updated_at": "2023-01-01T05:00:00Z", "_ab_cdc_deleted_at": null, "string": "zombie_returned"}}
 // CDC generally outputs an explicit null for deleted_at, but verify that we can also handle the case where deleted_at is unset.
 {"_airbyte_raw_id": "f0b59e49-8c74-4101-9f14-cb4d1193fd5a", "_airbyte_extracted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 4, "id2": 100, "updated_at": "2023-01-01T06:00:00Z", "string": "charlie"}}
-// Invalid values in _ab_cdc_deleted_at result in the record NOT being deleted. This behavior is up for debate, but it's an extreme edge case so not a high priority.
-{"_airbyte_raw_id": "d4e1d989-c115-403c-9e68-5d320e6376bb", "_airbyte_extracted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 5, "id2": 100, "updated_at": "2023-01-01T07:00:00Z", "_ab_cdc_deleted_at": {}, "string": "david1"}}
diff --git a/...ping-deduping/src/testFixtures/resources/sqlgenerator/incrementaldedup_inputrecords.jsonl b/...ping-deduping/src/testFixtures/resources/sqlgenerator/incrementaldedup_inputrecords.jsonl
@@ -1,3 +1,3 @@
 {"_airbyte_raw_id": "d7b81af0-01da-4846-a650-cc398986bc99", "_airbyte_extracted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 1, "id2": 100, "updated_at": "2023-01-01T01:00:00Z", "string": "Alice", "struct": {"city": "San Francisco", "state": "CA"}, "integer": 42}}
 {"_airbyte_raw_id": "80c99b54-54b4-43bd-b51b-1f67dafa2c52", "_airbyte_extracted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 1, "id2": 100, "updated_at": "2023-01-01T02:00:00Z", "string": "Alice", "struct": {"city": "San Diego", "state": "CA"}, "integer": 84}}
-{"_airbyte_raw_id": "ad690bfb-c2c2-4172-bd73-a16c86ccbb67", "_airbyte_extracted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 2, "id2": 100, "updated_at": "2023-01-01T03:00:00Z", "string": "Bob", "integer": "oops"}}
+{"_airbyte_raw_id": "ad690bfb-c2c2-4172-bd73-a16c86ccbb67", "_airbyte_extracted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 2, "id2": 100, "updated_at": "2023-01-01T03:00:00Z", "string": "Bob", "integer": 126}}
diff --git a/...g-deduping/src/testFixtures/resources/sqlgenerator/mixedcasecolumnname_inputrecords.jsonl b/...g-deduping/src/testFixtures/resources/sqlgenerator/mixedcasecolumnname_inputrecords.jsonl
@@ -0,0 +1 @@
+{"_airbyte_raw_id": "7e1fac0c-017e-4ad6-bc78-334a34d64fce", "_airbyte_extracted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 6, "id2": 100, "updated_at": "2023-01-01T01:00:00Z", "IamACaseSensitiveColumnName": "Case senstive value"}}
diff --git a/...eduping/src/testFixtures/resources/sqlgenerator/safe_cast/all_types_v1_inputrecords.jsonl b/...eduping/src/testFixtures/resources/sqlgenerator/safe_cast/all_types_v1_inputrecords.jsonl
@@ -0,0 +1,2 @@
+// Note that array and struct have invalid values ({} and [] respectively).
+{"_airbyte_ab_id": "84242b60-3a34-4531-ad75-a26702960a9a", "_airbyte_emitted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 4, "id2": 100, "updated_at": "2023-01-01T01:00:00Z", "array": {}, "struct": [], "string": null, "number": "foo", "integer": "bar", "boolean": "fizz", "timestamp_with_timezone": {}, "timestamp_without_timezone": {}, "time_with_timezone": {}, "time_without_timezone": {}, "date": "airbyte", "unknown": null}}
diff --git a/...ng-deduping/src/testFixtures/resources/sqlgenerator/safe_cast/alltypes_inputrecords.jsonl b/...ng-deduping/src/testFixtures/resources/sqlgenerator/safe_cast/alltypes_inputrecords.jsonl
@@ -0,0 +1,2 @@
+// Note that array and struct have invalid values ({} and [] respectively).
+{"_airbyte_raw_id": "84242b60-3a34-4531-ad75-a26702960a9a", "_airbyte_extracted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 4, "id2": 100, "updated_at": "2023-01-01T01:00:00Z", "array": {}, "struct": [], "string": null, "number": "foo", "integer": "bar", "boolean": "fizz", "timestamp_with_timezone": {}, "timestamp_without_timezone": {}, "time_with_timezone": {}, "time_without_timezone": {}, "date": "airbyte", "unknown": null}}
diff --git a/...duping/src/testFixtures/resources/sqlgenerator/safe_cast/cdcupdate_inputrecords_raw.jsonl b/...duping/src/testFixtures/resources/sqlgenerator/safe_cast/cdcupdate_inputrecords_raw.jsonl
@@ -0,0 +1,2 @@
+// Invalid values in _ab_cdc_deleted_at result in the record NOT being deleted. This behavior is up for debate, but it's an extreme edge case so not a high priority.
+{"_airbyte_raw_id": "d4e1d989-c115-403c-9e68-5d320e6376bb", "_airbyte_extracted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 5, "id2": 100, "updated_at": "2023-01-01T07:00:00Z", "_ab_cdc_deleted_at": {}, "string": "david1"}}
diff --git a/...ing/src/testFixtures/resources/sqlgenerator/safe_cast/incrementaldedup_inputrecords.jsonl b/...ing/src/testFixtures/resources/sqlgenerator/safe_cast/incrementaldedup_inputrecords.jsonl
@@ -0,0 +1,2 @@
+// This record verifies that we can update an existing record, with a new record where one column has an invalid value.
+{"_airbyte_raw_id": "b9ac9f01-abc1-4e7c-89e5-eac9223d5726", "_airbyte_extracted_at": "2023-01-01T00:00:00Z", "_airbyte_data": {"id1": 2, "id2": 100, "updated_at": "2023-01-01T03:00:01Z", "string": "Bob", "integer": "oops"}}