deltacat 1.1.34__py3-none-any.whl → 1.1.36__py3-none-any.whl

deltacat/__init__.py

@@ -44,7 +44,7 @@ from deltacat.types.tables import TableWriteMode
 
 deltacat.logs.configure_deltacat_logger(logging.getLogger(__name__))
 
-__version__ = "1.1.34"
+__version__ = "1.1.36"
 
 
 __all__ = [

deltacat/compute/compactor_v2/compaction_session.py

@@ -69,14 +69,17 @@ def compact_partition(params: CompactPartitionParams, **kwargs) -> Optional[str]
     assert (
         params.hash_bucket_count is not None and params.hash_bucket_count >= 1
     ), "hash_bucket_count is a required arg for compactor v2"
+    assert type(params.hash_bucket_count) is int, "Hash bucket count must be an integer"
     if params.num_rounds > 1:
         assert (
             not params.drop_duplicates
         ), "num_rounds > 1, drop_duplicates must be False but is True"
 
-    with memray.Tracker(
-        "compaction_partition.bin"
-    ) if params.enable_profiler else nullcontext():
+    with (
+        memray.Tracker("compaction_partition.bin")
+        if params.enable_profiler
+        else nullcontext()
+    ):
         execute_compaction_result: ExecutionCompactionResult = _execute_compaction(
             params,
             **kwargs,

deltacat/compute/compactor_v2/constants.py

@@ -1,4 +1,4 @@
-from deltacat.utils.common import env_bool, env_integer
+from deltacat.utils.common import env_bool, env_integer, env_string
 
 TOTAL_BYTES_IN_SHA1_HASH = 20
 
@@ -92,3 +92,18 @@ DEFAULT_NUM_ROUNDS = 1
 SHA1_HASHING_FOR_MEMORY_OPTIMIZATION_DISABLED = env_bool(
     "SHA1_HASHING_FOR_MEMORY_OPTIMIZATION_DISABLED", False
 )
+
+# This env variable specifies whether to check bucketing spec
+# compliance of the existing compacted table.
+# PRINT_LOG: Enable logging if any partition is found
+# to be non-compliant with the bucketing spec.
+# ASSERT: Fail the job with ValidationError if the
+# current compacted partition is found to be non-compliant
+# with bucketing spec. Note, logging is implicitly enabled
+# in this case.
+BUCKETING_SPEC_COMPLIANCE_PROFILE = env_string(
+    "BUCKETING_SPEC_COMPLIANCE_PROFILE", None
+)
+
+BUCKETING_SPEC_COMPLIANCE_PRINT_LOG = "PRINT_LOG"
+BUCKETING_SPEC_COMPLIANCE_ASSERT = "ASSERT"

deltacat/compute/compactor_v2/model/merge_input.py

@@ -48,6 +48,7 @@ class MergeInput(Dict):
         deltacat_storage_kwargs: Optional[Dict[str, Any]] = None,
         memory_logs_enabled: Optional[bool] = None,
         disable_copy_by_reference: Optional[bool] = None,
+        hash_bucket_count: Optional[int] = None,
     ) -> MergeInput:
 
         result = MergeInput()
@@ -71,6 +72,7 @@ class MergeInput(Dict):
         result["deltacat_storage_kwargs"] = deltacat_storage_kwargs or {}
         result["memory_logs_enabled"] = memory_logs_enabled
         result["disable_copy_by_reference"] = disable_copy_by_reference
+        result["hash_bucket_count"] = hash_bucket_count
         return result
 
     @property
@@ -154,3 +156,7 @@ class MergeInput(Dict):
     @property
     def disable_copy_by_reference(self) -> bool:
         return self["disable_copy_by_reference"]
+
+    @property
+    def hash_bucket_count(self) -> int:
+        return self["hash_bucket_count"]

deltacat/compute/compactor_v2/private/compaction_utils.py

@@ -438,6 +438,7 @@ def _merge(
                 delete_file_envelopes=delete_file_envelopes,
                 memory_logs_enabled=params.memory_logs_enabled,
                 disable_copy_by_reference=params.disable_copy_by_reference,
+                hash_bucket_count=params.hash_bucket_count,
             )
         }
 

deltacat/compute/compactor_v2/steps/merge.py

@@ -32,6 +32,7 @@ from deltacat.utils.resources import (
 )
 from deltacat.compute.compactor_v2.utils.primary_key_index import (
     generate_pk_hash_column,
+    pk_digest_to_hash_bucket_index,
 )
 from deltacat.storage import (
     Delta,
@@ -47,6 +48,9 @@ from deltacat.compute.compactor_v2.constants import (
     MERGE_TIME_IN_SECONDS,
     MERGE_SUCCESS_COUNT,
     MERGE_FAILURE_COUNT,
+    BUCKETING_SPEC_COMPLIANCE_PROFILE,
+    BUCKETING_SPEC_COMPLIANCE_ASSERT,
+    BUCKETING_SPEC_COMPLIANCE_PRINT_LOG,
 )
 from deltacat.exceptions import (
     categorize_errors,
@@ -58,6 +62,10 @@ if importlib.util.find_spec("memray"):
 logger = logs.configure_deltacat_logger(logging.getLogger(__name__))
 
 
+_EXISTING_VARIANT_LOG_PREFIX = "Existing variant "
+_INCREMENTAL_TABLE_LOG_PREFIX = "Incremental table "
+
+
 def _append_delta_type_column(table: pa.Table, value: np.bool_):
     return table.append_column(
         sc._DELTA_TYPE_COLUMN_FIELD,
@@ -108,6 +116,8 @@ def _merge_tables(
     table: pa.Table,
     primary_keys: List[str],
     can_drop_duplicates: bool,
+    hb_index: int,
+    num_buckets: int,
     compacted_table: Optional[pa.Table] = None,
 ) -> pa.Table:
     """
@@ -126,6 +136,20 @@ def _merge_tables(
 
     all_tables.append(table)
 
+    check_bucketing_spec = BUCKETING_SPEC_COMPLIANCE_PROFILE in [
+        BUCKETING_SPEC_COMPLIANCE_PRINT_LOG,
+        BUCKETING_SPEC_COMPLIANCE_ASSERT,
+    ]
+
+    if primary_keys and check_bucketing_spec:
+        _validate_bucketing_spec_compliance(
+            table=all_tables[incremental_idx],
+            num_buckets=num_buckets,
+            primary_keys=primary_keys,
+            hb_index=hb_index,
+            log_prefix=_INCREMENTAL_TABLE_LOG_PREFIX,
+        )
+
     if not primary_keys or not can_drop_duplicates:
         logger.info(
             f"Not dropping duplicates for primary keys={primary_keys} "
@@ -188,9 +212,47 @@ def _merge_tables(
     return final_table
 
 
+def _validate_bucketing_spec_compliance(
+    table: pa.Table,
+    num_buckets: int,
+    hb_index: int,
+    primary_keys: List[str],
+    rcf: RoundCompletionInfo = None,
+    log_prefix=None,
+) -> None:
+    if rcf is not None:
+        message_prefix = f"{log_prefix}{rcf.compacted_delta_locator.namespace}.{rcf.compacted_delta_locator.table_name}.{rcf.compacted_delta_locator.table_version}.{rcf.compacted_delta_locator.partition_id}.{rcf.compacted_delta_locator.partition_values}"
+    else:
+        message_prefix = f"{log_prefix}"
+    pki_table = generate_pk_hash_column(
+        [table], primary_keys=primary_keys, requires_hash=True
+    )[0]
+    is_not_compliant: bool = False
+    for index, hash_value in enumerate(sc.pk_hash_string_column_np(pki_table)):
+        hash_bucket: int = pk_digest_to_hash_bucket_index(hash_value, num_buckets)
+        if hash_bucket != hb_index:
+            is_not_compliant = True
+            logger.info(
+                f"{message_prefix} has non-compliant bucketing spec at index: {index} "
+                f"Expected hash bucket is {hb_index} but found {hash_bucket}."
+            )
+            if BUCKETING_SPEC_COMPLIANCE_PROFILE == BUCKETING_SPEC_COMPLIANCE_ASSERT:
+                raise AssertionError(
+                    f"Hash bucket drift detected at index: {index}. Expected hash bucket index"
+                    f" to be {hb_index} but found {hash_bucket}"
+                )
+            # No further checks necessary
+            break
+    if not is_not_compliant:
+        logger.debug(
+            f"{message_prefix} has compliant bucketing spec for hb_index: {hb_index}"
+        )
+
+
 def _download_compacted_table(
     hb_index: int,
     rcf: RoundCompletionInfo,
+    primary_keys: List[str],
     read_kwargs_provider: Optional[ReadKwargsProvider] = None,
     deltacat_storage=unimplemented_deltacat_storage,
     deltacat_storage_kwargs: Optional[dict] = None,
@@ -214,7 +276,28 @@ def _download_compacted_table(
 
         tables.append(table)
 
-    return pa.concat_tables(tables)
+    compacted_table = pa.concat_tables(tables)
+    check_bucketing_spec = BUCKETING_SPEC_COMPLIANCE_PROFILE in [
+        BUCKETING_SPEC_COMPLIANCE_PRINT_LOG,
+        BUCKETING_SPEC_COMPLIANCE_ASSERT,
+    ]
+
+    logger.debug(
+        f"Value of BUCKETING_SPEC_COMPLIANCE_PROFILE, check_bucketing_spec:"
+        f" {BUCKETING_SPEC_COMPLIANCE_PROFILE}, {check_bucketing_spec}"
+    )
+
+    # Bucketing spec compliance isn't required without primary keys
+    if primary_keys and check_bucketing_spec:
+        _validate_bucketing_spec_compliance(
+            compacted_table,
+            rcf.hash_bucket_count,
+            hb_index,
+            primary_keys,
+            rcf=rcf,
+            log_prefix=_EXISTING_VARIANT_LOG_PREFIX,
+        )
+    return compacted_table
 
 
 def _copy_all_manifest_files_from_old_hash_buckets(
@@ -417,12 +500,12 @@ def _compact_tables(
         _group_sequence_by_delta_type(reordered_all_dfes)
     ):
         if delta_type is DeltaType.UPSERT:
-            (
-                table,
-                incremental_len,
-                deduped_records,
-                merge_time,
-            ) = _apply_upserts(input, delta_type_sequence, hb_idx, table)
+            (table, incremental_len, deduped_records, merge_time,) = _apply_upserts(
+                input=input,
+                dfe_list=delta_type_sequence,
+                hb_idx=hb_idx,
+                prev_table=table,
+            )
             logger.info(
                 f" [Merge task index {input.merge_task_index}] Merged"
                 f" record count: {len(table)}, size={table.nbytes} took: {merge_time}s"
@@ -481,6 +564,8 @@ def _apply_upserts(
         primary_keys=input.primary_keys,
         can_drop_duplicates=input.drop_duplicates,
         compacted_table=prev_table,
+        hb_index=hb_idx,
+        num_buckets=input.hash_bucket_count,
     )
     deduped_records = hb_table_record_count - len(table)
     return table, incremental_len, deduped_records, merge_time
@@ -543,6 +628,7 @@ def _timed_merge(input: MergeInput) -> MergeResult:
                 compacted_table = _download_compacted_table(
                     hb_index=merge_file_group.hb_index,
                     rcf=input.round_completion_info,
+                    primary_keys=input.primary_keys,
                     read_kwargs_provider=input.read_kwargs_provider,
                     deltacat_storage=input.deltacat_storage,
                     deltacat_storage_kwargs=input.deltacat_storage_kwargs,

deltacat/compute/compactor_v2/utils/merge.py

@@ -133,4 +133,5 @@ def generate_local_merge_input(
         delete_strategy=delete_strategy,
         delete_file_envelopes=delete_file_envelopes,
         disable_copy_by_reference=params.disable_copy_by_reference,
+        hash_bucket_count=params.hash_bucket_count,
     )

deltacat/tests/compute/compactor_v2/test_compaction_session.py

@@ -4,9 +4,11 @@ import os
 import pyarrow as pa
 import pytest
 import boto3
+import json
 from deltacat.compute.compactor.model.compaction_session_audit_info import (
     CompactionSessionAuditInfo,
 )
+from deltacat.exceptions import ValidationError
 from boto3.resources.base import ServiceResource
 import deltacat.tests.local_deltacat_storage as ds
 from deltacat.types.media import ContentType
@@ -88,6 +90,17 @@ def disable_sha1(monkeypatch):
     )
 
 
+@pytest.fixture(scope="function")
+def enable_bucketing_spec_validation(monkeypatch):
+    import deltacat.compute.compactor_v2.steps.merge
+
+    monkeypatch.setattr(
+        deltacat.compute.compactor_v2.steps.merge,
+        "BUCKETING_SPEC_COMPLIANCE_PROFILE",
+        "ASSERT",
+    )
+
+
 class TestCompactionSession:
     """
     This class adds specific tests that aren't part of the parametrized test suite.
@@ -689,3 +702,307 @@ class TestCompactionSession:
             incremental_rcf.compacted_pyarrow_write_result.pyarrow_bytes >= 2300000000
         )
         assert incremental_rcf.compacted_pyarrow_write_result.records == 4
+
+    def test_compact_partition_when_bucket_spec_validation_fails(
+        self,
+        s3_resource,
+        local_deltacat_storage_kwargs,
+        enable_bucketing_spec_validation,
+    ):
+        """
+        A test case which asserts the bucketing spec validation throws an assertion error
+        when the validation has failed.
+        """
+
+        # setup
+        staged_source = stage_partition_from_file_paths(
+            self.NAMESPACE, ["source"], **local_deltacat_storage_kwargs
+        )
+
+        source_delta = commit_delta_to_staged_partition(
+            staged_source, [self.BACKFILL_FILE_PATH], **local_deltacat_storage_kwargs
+        )
+
+        staged_dest = stage_partition_from_file_paths(
+            self.NAMESPACE, ["destination"], **local_deltacat_storage_kwargs
+        )
+        dest_partition = ds.commit_partition(
+            staged_dest, **local_deltacat_storage_kwargs
+        )
+
+        # action
+        rcf_url = compact_partition(
+            CompactPartitionParams.of(
+                {
+                    "compaction_artifact_s3_bucket": TEST_S3_RCF_BUCKET_NAME,
+                    "compacted_file_content_type": ContentType.PARQUET,
+                    "dd_max_parallelism_ratio": 1.0,
+                    "deltacat_storage": ds,
+                    "deltacat_storage_kwargs": local_deltacat_storage_kwargs,
+                    "destination_partition_locator": dest_partition.locator,
+                    "drop_duplicates": True,
+                    "hash_bucket_count": 4,
+                    "last_stream_position_to_compact": source_delta.stream_position,
+                    "list_deltas_kwargs": {
+                        **local_deltacat_storage_kwargs,
+                        **{"equivalent_table_types": []},
+                    },
+                    "primary_keys": ["pk"],
+                    "rebase_source_partition_locator": source_delta.partition_locator,
+                    "rebase_source_partition_high_watermark": source_delta.stream_position,
+                    "records_per_compacted_file": 1,
+                    "s3_client_kwargs": {},
+                    "source_partition_locator": source_delta.partition_locator,
+                }
+            )
+        )
+
+        backfill_rcf = get_rcf(s3_resource, rcf_url)
+        bucket, backfill_key1, backfill_key2 = rcf_url.strip("s3://").split("/")
+        # Move the records to different hash buckets to simulate a validation failure.
+        backfill_rcf["hbIndexToEntryRange"] = {"1": [0, 3]}
+        s3_resource.Bucket(bucket).put_object(
+            Key=f"{backfill_key1}/{backfill_key2}", Body=json.dumps(backfill_rcf)
+        )
+
+        # Now run an incremental compaction and verify if the previous RCF was read properly.
+        new_source_delta = commit_delta_to_partition(
+            source_delta.partition_locator,
+            [self.INCREMENTAL_FILE_PATH],
+            **local_deltacat_storage_kwargs,
+        )
+
+        new_destination_partition = ds.get_partition(
+            dest_partition.stream_locator, [], **local_deltacat_storage_kwargs
+        )
+
+        with pytest.raises(ValidationError) as excinfo:
+            compact_partition(
+                CompactPartitionParams.of(
+                    {
+                        "compaction_artifact_s3_bucket": TEST_S3_RCF_BUCKET_NAME,
+                        "compacted_file_content_type": ContentType.PARQUET,
+                        "dd_max_parallelism_ratio": 1.0,
+                        "deltacat_storage": ds,
+                        "deltacat_storage_kwargs": local_deltacat_storage_kwargs,
+                        "destination_partition_locator": new_destination_partition.locator,
+                        "drop_duplicates": True,
+                        "hash_bucket_count": 4,
+                        "last_stream_position_to_compact": new_source_delta.stream_position,
+                        "list_deltas_kwargs": {
+                            **local_deltacat_storage_kwargs,
+                            **{"equivalent_table_types": []},
+                        },
+                        "primary_keys": ["pk"],
+                        "rebase_source_partition_locator": None,
+                        "rebase_source_partition_high_watermark": None,
+                        "records_per_compacted_file": 4000,
+                        "s3_client_kwargs": {},
+                        "source_partition_locator": new_source_delta.partition_locator,
+                    }
+                )
+            )
+
+        assert (
+            "Hash bucket drift detected at index: 0. Expected hash bucket index to be 1 but found 0"
+            in str(excinfo.value)
+        )
+
+    def test_compact_partition_when_bucket_spec_validation_fails_but_env_variable_disabled(
+        self,
+        s3_resource,
+        local_deltacat_storage_kwargs,
+    ):
+        """
+        A test case which asserts even if bucketing spec validation fails, compaction doesn't
+        throw an error if the feature is not enabled.
+        """
+
+        # setup
+        staged_source = stage_partition_from_file_paths(
+            self.NAMESPACE, ["source"], **local_deltacat_storage_kwargs
+        )
+
+        source_delta = commit_delta_to_staged_partition(
+            staged_source, [self.BACKFILL_FILE_PATH], **local_deltacat_storage_kwargs
+        )
+
+        staged_dest = stage_partition_from_file_paths(
+            self.NAMESPACE, ["destination"], **local_deltacat_storage_kwargs
+        )
+        dest_partition = ds.commit_partition(
+            staged_dest, **local_deltacat_storage_kwargs
+        )
+
+        # action
+        rcf_url = compact_partition(
+            CompactPartitionParams.of(
+                {
+                    "compaction_artifact_s3_bucket": TEST_S3_RCF_BUCKET_NAME,
+                    "compacted_file_content_type": ContentType.PARQUET,
+                    "dd_max_parallelism_ratio": 1.0,
+                    "deltacat_storage": ds,
+                    "deltacat_storage_kwargs": local_deltacat_storage_kwargs,
+                    "destination_partition_locator": dest_partition.locator,
+                    "drop_duplicates": True,
+                    "hash_bucket_count": 4,
+                    "last_stream_position_to_compact": source_delta.stream_position,
+                    "list_deltas_kwargs": {
+                        **local_deltacat_storage_kwargs,
+                        **{"equivalent_table_types": []},
+                    },
+                    "primary_keys": ["pk"],
+                    "rebase_source_partition_locator": source_delta.partition_locator,
+                    "rebase_source_partition_high_watermark": source_delta.stream_position,
+                    "records_per_compacted_file": 1,
+                    "s3_client_kwargs": {},
+                    "source_partition_locator": source_delta.partition_locator,
+                }
+            )
+        )
+
+        backfill_rcf = get_rcf(s3_resource, rcf_url)
+        bucket, backfill_key1, backfill_key2 = rcf_url.strip("s3://").split("/")
+        # Move the records to different hash buckets to simulate a validation failure.
+        backfill_rcf["hbIndexToEntryRange"] = {"1": [0, 3]}
+        s3_resource.Bucket(bucket).put_object(
+            Key=f"{backfill_key1}/{backfill_key2}", Body=json.dumps(backfill_rcf)
+        )
+
+        # Now run an incremental compaction and verify if the previous RCF was read properly.
+        new_source_delta = commit_delta_to_partition(
+            source_delta.partition_locator,
+            [self.INCREMENTAL_FILE_PATH],
+            **local_deltacat_storage_kwargs,
+        )
+
+        new_destination_partition = ds.get_partition(
+            dest_partition.stream_locator, [], **local_deltacat_storage_kwargs
+        )
+
+        new_rcf = compact_partition(
+            CompactPartitionParams.of(
+                {
+                    "compaction_artifact_s3_bucket": TEST_S3_RCF_BUCKET_NAME,
+                    "compacted_file_content_type": ContentType.PARQUET,
+                    "dd_max_parallelism_ratio": 1.0,
+                    "deltacat_storage": ds,
+                    "deltacat_storage_kwargs": local_deltacat_storage_kwargs,
+                    "destination_partition_locator": new_destination_partition.locator,
+                    "drop_duplicates": True,
+                    "hash_bucket_count": 4,
+                    "last_stream_position_to_compact": new_source_delta.stream_position,
+                    "list_deltas_kwargs": {
+                        **local_deltacat_storage_kwargs,
+                        **{"equivalent_table_types": []},
+                    },
+                    "primary_keys": ["pk"],
+                    "rebase_source_partition_locator": None,
+                    "rebase_source_partition_high_watermark": None,
+                    "records_per_compacted_file": 4000,
+                    "s3_client_kwargs": {},
+                    "source_partition_locator": new_source_delta.partition_locator,
+                }
+            )
+        )
+
+        incremental_rcf = get_rcf(s3_resource, new_rcf)
+        assert incremental_rcf.hash_bucket_count == 4
+        assert len(incremental_rcf.hb_index_to_entry_range) == 2
+
+    def test_compact_partition_when_bucket_spec_validation_succeeds(
+        self,
+        s3_resource,
+        local_deltacat_storage_kwargs,
+        enable_bucketing_spec_validation,
+    ):
+        """
+        A test case which asserts the bucketing spec validation does not throw
+        and error when the validation succeeds.
+        """
+
+        # setup
+        staged_source = stage_partition_from_file_paths(
+            self.NAMESPACE, ["source"], **local_deltacat_storage_kwargs
+        )
+
+        source_delta = commit_delta_to_staged_partition(
+            staged_source, [self.BACKFILL_FILE_PATH], **local_deltacat_storage_kwargs
+        )
+
+        staged_dest = stage_partition_from_file_paths(
+            self.NAMESPACE, ["destination"], **local_deltacat_storage_kwargs
+        )
+        dest_partition = ds.commit_partition(
+            staged_dest, **local_deltacat_storage_kwargs
+        )
+
+        # action
+        rcf_url = compact_partition(
+            CompactPartitionParams.of(
+                {
+                    "compaction_artifact_s3_bucket": TEST_S3_RCF_BUCKET_NAME,
+                    "compacted_file_content_type": ContentType.PARQUET,
+                    "dd_max_parallelism_ratio": 1.0,
+                    "deltacat_storage": ds,
+                    "deltacat_storage_kwargs": local_deltacat_storage_kwargs,
+                    "destination_partition_locator": dest_partition.locator,
+                    "drop_duplicates": True,
+                    "hash_bucket_count": 4,
+                    "last_stream_position_to_compact": source_delta.stream_position,
+                    "list_deltas_kwargs": {
+                        **local_deltacat_storage_kwargs,
+                        **{"equivalent_table_types": []},
+                    },
+                    "primary_keys": ["pk"],
+                    "rebase_source_partition_locator": source_delta.partition_locator,
+                    "rebase_source_partition_high_watermark": source_delta.stream_position,
+                    "records_per_compacted_file": 1,
+                    "s3_client_kwargs": {},
+                    "source_partition_locator": source_delta.partition_locator,
+                }
+            )
+        )
+
+        rcf = get_rcf(s3_resource, rcf_url)
+        assert rcf.hash_bucket_count == 4
+
+        # Now run an incremental compaction and verify if the previous RCF was read properly.
+        new_source_delta = commit_delta_to_partition(
+            source_delta.partition_locator,
+            [self.INCREMENTAL_FILE_PATH],
+            **local_deltacat_storage_kwargs,
+        )
+
+        new_destination_partition = ds.get_partition(
+            dest_partition.stream_locator, [], **local_deltacat_storage_kwargs
+        )
+
+        new_uri = compact_partition(
+            CompactPartitionParams.of(
+                {
+                    "compaction_artifact_s3_bucket": TEST_S3_RCF_BUCKET_NAME,
+                    "compacted_file_content_type": ContentType.PARQUET,
+                    "dd_max_parallelism_ratio": 1.0,
+                    "deltacat_storage": ds,
+                    "deltacat_storage_kwargs": local_deltacat_storage_kwargs,
+                    "destination_partition_locator": new_destination_partition.locator,
+                    "drop_duplicates": True,
+                    "hash_bucket_count": 4,
+                    "last_stream_position_to_compact": new_source_delta.stream_position,
+                    "list_deltas_kwargs": {
+                        **local_deltacat_storage_kwargs,
+                        **{"equivalent_table_types": []},
+                    },
+                    "primary_keys": ["pk"],
+                    "rebase_source_partition_locator": None,
+                    "rebase_source_partition_high_watermark": None,
+                    "records_per_compacted_file": 4000,
+                    "s3_client_kwargs": {},
+                    "source_partition_locator": new_source_delta.partition_locator,
+                }
+            )
+        )
+
+        rcf = get_rcf(s3_resource, new_uri)
+        assert rcf.hash_bucket_count == 4

deltacat/tests/compute/test_compact_partition_incremental.py

@@ -119,6 +119,21 @@ def offer_local_deltacat_storage_kwargs(request: pytest.FixtureRequest):
         os.remove(DATABASE_FILE_PATH_VALUE)
 
 
+@pytest.fixture(autouse=True, scope="function")
+def enable_bucketing_spec_validation(monkeypatch):
+    """
+    Enable the bucketing spec validation for all tests.
+    This will help catch hash bucket drift in testing.
+    """
+    import deltacat.compute.compactor_v2.steps.merge
+
+    monkeypatch.setattr(
+        deltacat.compute.compactor_v2.steps.merge,
+        "BUCKETING_SPEC_COMPLIANCE_PROFILE",
+        "ASSERT",
+    )
+
+
 @pytest.mark.parametrize(
     [
         "test_name",

deltacat/tests/compute/test_compact_partition_multiple_rounds.py

@@ -114,6 +114,21 @@ def local_deltacat_storage_kwargs(request: pytest.FixtureRequest):
         os.remove(DATABASE_FILE_PATH_VALUE)
 
 
+@pytest.fixture(autouse=True, scope="function")
+def enable_bucketing_spec_validation(monkeypatch):
+    """
+    Enable the bucketing spec validation for all tests.
+    This will help catch hash bucket drift in testing.
+    """
+    import deltacat.compute.compactor_v2.steps.merge
+
+    monkeypatch.setattr(
+        deltacat.compute.compactor_v2.steps.merge,
+        "BUCKETING_SPEC_COMPLIANCE_PROFILE",
+        "ASSERT",
+    )
+
+
 @pytest.mark.parametrize(
     [
         "test_name",

deltacat/tests/compute/test_compact_partition_rebase.py

@@ -114,6 +114,21 @@ def local_deltacat_storage_kwargs(request: pytest.FixtureRequest):
         os.remove(DATABASE_FILE_PATH_VALUE)
 
 
+@pytest.fixture(autouse=True, scope="function")
+def enable_bucketing_spec_validation(monkeypatch):
+    """
+    Enable the bucketing spec validation for all tests.
+    This will help catch hash bucket drift in testing.
+    """
+    import deltacat.compute.compactor_v2.steps.merge
+
+    monkeypatch.setattr(
+        deltacat.compute.compactor_v2.steps.merge,
+        "BUCKETING_SPEC_COMPLIANCE_PROFILE",
+        "ASSERT",
+    )
+
+
 @pytest.mark.parametrize(
     [
         "test_name",

deltacat/tests/compute/test_compact_partition_rebase_then_incremental.py

@@ -118,6 +118,21 @@ def local_deltacat_storage_kwargs(request: pytest.FixtureRequest):
         os.remove(DATABASE_FILE_PATH_VALUE)
 
 
+@pytest.fixture(autouse=True, scope="function")
+def enable_bucketing_spec_validation(monkeypatch):
+    """
+    Enable the bucketing spec validation for all tests.
+    This will help catch hash bucket drift in testing.
+    """
+    import deltacat.compute.compactor_v2.steps.merge
+
+    monkeypatch.setattr(
+        deltacat.compute.compactor_v2.steps.merge,
+        "BUCKETING_SPEC_COMPLIANCE_PROFILE",
+        "ASSERT",
+    )
+
+
 @pytest.mark.parametrize(
     [
         "test_name",

{deltacat-1.1.34.dist-info → deltacat-1.1.36.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: deltacat
-Version: 1.1.34
+Version: 1.1.36
 Summary: A scalable, fast, ACID-compliant Data Catalog powered by Ray.
 Home-page: https://github.com/ray-project/deltacat
 Author: Ray Team

{deltacat-1.1.34.dist-info → deltacat-1.1.36.dist-info}/RECORD

@@ -1,4 +1,4 @@
-deltacat/__init__.py,sha256=g15eDSUMw0XN1VLww6GpBKnKFtB4WGCcMnJe4SlGOqg,1778
+deltacat/__init__.py,sha256=9vJMHGceWew6atD_3VqKurlBJ3crD5mwAQIgSB1yjNY,1778
 deltacat/constants.py,sha256=TUJLXUJ9xq1Ryil72yLkKR8EDH_Irp5wUg56QstbRNE,2181
 deltacat/exceptions.py,sha256=7sjk3BuMY5Oo-6OvAfHncZx_OcvtEL47BblWr2F7waE,12740
 deltacat/logs.py,sha256=EQSDin1deehzz5xlLV1_TrFJrO_IBZ9Ahp7MdL-4cK8,9363
@@ -50,8 +50,8 @@ deltacat/compute/compactor/utils/round_completion_file.py,sha256=fFevhUuveCvrU3g
 deltacat/compute/compactor/utils/sort_key.py,sha256=oK6otg-CSsma6zlGPaKg-KNEvcZRG2NqBlCw1X3_FBc,2397
 deltacat/compute/compactor/utils/system_columns.py,sha256=CNIgAGos0xAGEpdaQIH7KfbSRrGZgjRbItXMararqXQ,9399
 deltacat/compute/compactor_v2/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-deltacat/compute/compactor_v2/compaction_session.py,sha256=COtol2s63DRPbd-AN9KCiWr4exLX8x5Tvxea_7cOGEQ,8078
-deltacat/compute/compactor_v2/constants.py,sha256=wvd34d7RGdniGbbiJcMljxRrRas4_uy9F9UaqXfS_Ag,3034
+deltacat/compute/compactor_v2/compaction_session.py,sha256=RbO_du0qX7nlyXO-ZSksX8RqWuRwfdvWddpTJjLDVNk,8185
+deltacat/compute/compactor_v2/constants.py,sha256=F5Phrh-2JgnWvtjHXacxOG5Z2ivKcHnboerI12rc1zk,3632
 deltacat/compute/compactor_v2/deletes/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 deltacat/compute/compactor_v2/deletes/delete_file_envelope.py,sha256=AeuH9JRMwp6mvQf6P2cqL92hUEtResQq6qUTS0kIKac,3111
 deltacat/compute/compactor_v2/deletes/delete_strategy.py,sha256=SMEJOxR-5r92kvKNqtu2w6HmwtmhljcZX1wcNEuS-4w,2833
@@ -63,19 +63,19 @@ deltacat/compute/compactor_v2/model/evaluate_compaction_result.py,sha256=XAaEEAd
 deltacat/compute/compactor_v2/model/hash_bucket_input.py,sha256=iJy8kLi1dIpFIyfoAjkaAtZvg8Np1z7BsUNGAcWfFm4,3042
 deltacat/compute/compactor_v2/model/hash_bucket_result.py,sha256=EsY9BPPywhmxlcLKn3kGWzAX4s4BTR2vYyPUB-wAEOc,309
 deltacat/compute/compactor_v2/model/merge_file_group.py,sha256=1o86t9lc3K6ZvtViVO1SVljCj6f0B3MfB3hqtGm2S0s,7410
-deltacat/compute/compactor_v2/model/merge_input.py,sha256=-SxTE0e67z2V7MiMEVz5aMu4E0k8h3-vqohvUUOC0do,5659
+deltacat/compute/compactor_v2/model/merge_input.py,sha256=D-6WuHK4X7m9-P6Hskz6RRemeWrNf6IPdhc14O3KDAg,5860
 deltacat/compute/compactor_v2/model/merge_result.py,sha256=_IZTCStpb4UKiRCJYA3g6EhAqjrw0t9vmoDAN8kIK-Y,436
 deltacat/compute/compactor_v2/private/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-deltacat/compute/compactor_v2/private/compaction_utils.py,sha256=fMWXg1SCIIgjk9p_OFYrcm760dOKNbFO1Lj3_JI3GCY,30929
+deltacat/compute/compactor_v2/private/compaction_utils.py,sha256=nz2N3YZVE9bNwOqRXoQYkArJhyUJRis2s9BweZ3tad8,30989
 deltacat/compute/compactor_v2/steps/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 deltacat/compute/compactor_v2/steps/hash_bucket.py,sha256=1R5xLUkl7GqL1nY-apAgY1czKDEHjIVYSRi9qLOMass,6726
-deltacat/compute/compactor_v2/steps/merge.py,sha256=LliCkWxWZ5Yh7UxVGSDJ1aRViw5hUZhEzlWxoXftbxA,22909
+deltacat/compute/compactor_v2/steps/merge.py,sha256=4rKQ__SeWO_QLZl2btcFrYHCMOn-8R3kja74UrWOMgg,26225
 deltacat/compute/compactor_v2/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 deltacat/compute/compactor_v2/utils/content_type_params.py,sha256=t2j9H9IdFRH9EfpL-9g5XvZs9WK9HybqBGA7fDi82EM,8310
 deltacat/compute/compactor_v2/utils/dedupe.py,sha256=Jz1QbBOdZJwT8K1vD9q01eOn7hdLNZ_AF7bJ0wficr0,1949
 deltacat/compute/compactor_v2/utils/delta.py,sha256=I7Yvda8NVbpKXG3nM2Ku1utvR2r2OpHvUMqUL2ja3aw,3626
 deltacat/compute/compactor_v2/utils/io.py,sha256=Xjs7_D-0xKSetvllIe4o96aM1elfdjt1Ii7YfsHPvZs,6108
-deltacat/compute/compactor_v2/utils/merge.py,sha256=EV_iKhNc3WflgfLW1Q46dXUvyClx8VebWHGtninEfsI,5311
+deltacat/compute/compactor_v2/utils/merge.py,sha256=fAzEYwQYH2ia8MLdEFdZFivWHpi6qZu8AyyEK0H0vwE,5363
 deltacat/compute/compactor_v2/utils/primary_key_index.py,sha256=SbQ97M1Cxld-zZik2QMSzlj20g6JlENaQx_0PhlCIP8,12034
 deltacat/compute/compactor_v2/utils/task_options.py,sha256=0GoB_DLkCN1q8CVKTlWlDYt55qnpTDIa9fPyXJwB-cU,13801
 deltacat/compute/merge_on_read/__init__.py,sha256=ckbgngmqPjYBYz_NySsR1vNTOb_hNpeL1sYkZKvBI9M,214
@@ -137,11 +137,11 @@ deltacat/tests/compute/compact_partition_multiple_rounds_test_cases.py,sha256=kW
 deltacat/tests/compute/compact_partition_rebase_test_cases.py,sha256=8HVr3EIFYFqNaJoqeCuj9xIBjM4Ch2bx-mJcO4BRrLo,16839
 deltacat/tests/compute/compact_partition_rebase_then_incremental_test_cases.py,sha256=l_6-pAKOsRY3NbtfHsYmEaJEkq6IJueYuLsjyJxNgz4,81564
 deltacat/tests/compute/compact_partition_test_cases.py,sha256=HJ15Xyawv8ImFju8wDwt22fH5okoPhyS-QAygkXDb7Q,27422
-deltacat/tests/compute/test_compact_partition_incremental.py,sha256=lkfAraOJmEmieesf7b1BqlfTS26YjYM5xXOXoTMrsos,14989
-deltacat/tests/compute/test_compact_partition_multiple_rounds.py,sha256=xXBA66TTfARR90m5KQs31nmiokuMy9iGQt7Z9evyG7M,12950
+deltacat/tests/compute/test_compact_partition_incremental.py,sha256=8hUqnzeGIhAENcBxLL0R_yfjAaNTmRds6OWxQOmVqD8,15416
+deltacat/tests/compute/test_compact_partition_multiple_rounds.py,sha256=6d3F9E_4eO2Okh97v8NWFbEptPkzKoO0Qq8O6yAXrIs,13377
 deltacat/tests/compute/test_compact_partition_params.py,sha256=Dm5eLyHo8oGMeO3XBbpj1rZqHtPZ1hAB7z2qvzc4Lxk,8497
-deltacat/tests/compute/test_compact_partition_rebase.py,sha256=DNcpmnBo5QoZ23BiIhJCC3zaDK0xClZLUb2-ZEEp5s4,13108
-deltacat/tests/compute/test_compact_partition_rebase_then_incremental.py,sha256=Rxen3QGIaxVPa8lcO7NDMRxQ0aBjrOKn46LK5ZsfQTo,15073
+deltacat/tests/compute/test_compact_partition_rebase.py,sha256=vOF8wgTpdaWJKo47mK9aii3NKtwVwWgujoQyS8C3YyA,13535
+deltacat/tests/compute/test_compact_partition_rebase_then_incremental.py,sha256=BimvU-iHiF78WlE4xbfk4dzHm0a-frwpE7H7Kh4XkbE,15500
 deltacat/tests/compute/test_util_common.py,sha256=0mEHo38bgH64y0XZ_zgUL_aZgQMgJOSTlOYvIJxG_MM,11825
 deltacat/tests/compute/test_util_constant.py,sha256=4o-W3E7r7jhFl1A3OFLLrdKnwcF46zx4lEIDY8ONJ3c,929
 deltacat/tests/compute/test_util_create_table_deltas_repo.py,sha256=Q3HJj1fjoe2JwRUOW8KEjbTqPIIoP2o_T3ZGH6SJnCM,13244
@@ -152,7 +152,7 @@ deltacat/tests/compute/compactor/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JC
 deltacat/tests/compute/compactor/utils/test_io.py,sha256=st5mlU4cVU-eQl7B4mvPgNA3izuNwbVawYOp-NcoyrI,4326
 deltacat/tests/compute/compactor/utils/test_round_completion_file.py,sha256=LAQ4usiRF4oTx4cA85L0eOcBa_Z-febc-CuzUijSGrI,7439
 deltacat/tests/compute/compactor_v2/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-deltacat/tests/compute/compactor_v2/test_compaction_session.py,sha256=y8nNHq9ADHENzUKMQYguB45zOD7F2lZgcBYYTvbTsdM,28957
+deltacat/tests/compute/compactor_v2/test_compaction_session.py,sha256=F1DFaranHekHB7HSNH-0_hV5ovdR5HfF9JqTVDw6Vh8,42575
 deltacat/tests/compute/compactor_v2/test_hashlib.py,sha256=8csF2hFWtBvY2MbX3-6iphCsVXxRp0zP1NTnKhfdmkg,328
 deltacat/tests/compute/compactor_v2/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 deltacat/tests/compute/compactor_v2/utils/test_content_type_params.py,sha256=eoiDuBUhgCmc3DYKCXL1g4QWtmROhZ0RJCQgePMY9as,9959
@@ -212,8 +212,8 @@ deltacat/utils/ray_utils/concurrency.py,sha256=JDVwMiQWrmuSlyCWAoiq9ctoJ0XADEfDD
 deltacat/utils/ray_utils/dataset.py,sha256=waHdtH0c835a-2t51HYRHnulfC0_zBxx8mFSAPvPSPM,3274
 deltacat/utils/ray_utils/performance.py,sha256=d7JFM7vTXHzkGx9qNQcZzUWajnqINvYRwaM088_FpsE,464
 deltacat/utils/ray_utils/runtime.py,sha256=rB0A-tU9WZHz0J11LzJdANYtL397YyuemcA1l-K9dAw,5029
-deltacat-1.1.34.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-deltacat-1.1.34.dist-info/METADATA,sha256=tndXv3uFRcc8PbYdaLMj9sZp9_uW7g94WGZBaNKFcUw,1733
-deltacat-1.1.34.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
-deltacat-1.1.34.dist-info/top_level.txt,sha256=RWdIcid4Bv2i2ozLVh-70kJpyB61xEKXod9XXGpiono,9
-deltacat-1.1.34.dist-info/RECORD,,
+deltacat-1.1.36.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+deltacat-1.1.36.dist-info/METADATA,sha256=wIZbEGHnJWq_TBKi0u463p4-PgG9R_0MApw7IIwmnRc,1733
+deltacat-1.1.36.dist-info/WHEEL,sha256=tZoeGjtWxWRfdplE7E3d45VPlLNQnvbKiYnx7gwAy8A,92
+deltacat-1.1.36.dist-info/top_level.txt,sha256=RWdIcid4Bv2i2ozLVh-70kJpyB61xEKXod9XXGpiono,9
+deltacat-1.1.36.dist-info/RECORD,,