datazone-sdk 6.0.1.dev5__tar.gz → 6.0.1.dev7__tar.gz

{datazone_sdk-6.0.1.dev5 → datazone_sdk-6.0.1.dev7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datazone-sdk
-Version: 6.0.1.dev5
+Version: 6.0.1.dev7
 Summary: Database and Delta storage client library for working with Delta Lake tables
 Author: Team Enigma
 Author-email: enigma@energinet.dk

{datazone_sdk-6.0.1.dev5 → datazone_sdk-6.0.1.dev7}/datazone/__init__.py

@@ -1,13 +1,6 @@
 from datazone.backtesting import backtest
 from datazone.caching import ParquetCache
 from datazone.db import DatabaseClient, SnapshotDatabaseClient
-from datazone.deltastorage import (
-    DeltaOverwriteFallbackWarning,
-    Field,
-    HyperSlice,
-    Schema,
-    Store,
-    Table,
-)
+from datazone.deltastorage import Field, HyperSlice, Schema, Store, Table
 
 from . import testing

{datazone_sdk-6.0.1.dev5 → datazone_sdk-6.0.1.dev7}/datazone/deltastorage/__init__.py

@@ -1,4 +1,4 @@
 from .schema import Field, Schema
 from .slicing import HyperSlice
 from .store import Store
-from .table import DeltaOverwriteFallbackWarning, Table
+from .table import Table

{datazone_sdk-6.0.1.dev5 → datazone_sdk-6.0.1.dev7}/datazone/deltastorage/table.py

@@ -1,11 +1,9 @@
 import datetime as dt
-import warnings
 from typing import Any, Optional
 
 import deltalake as dl
 import polars as pl
 import pyarrow as pa
-from deltalake.exceptions import CommitFailedError
 
 from .schema import Schema
 from .slicing import HyperSlice
@@ -48,14 +46,6 @@ def _dnf_to_sql(dnf: list[tuple]) -> str:
     return " AND ".join(sql_parts)
 
 
-def _is_arrow_cast_commit_failure(error: CommitFailedError) -> bool:
-    return "arrow_cast should have been simplified to cast" in str(error)
-
-
-def _is_safe_partition_filter(filter_: tuple) -> bool:
-    return filter_[1] in ["=", "in"]
-
-
 def _empty_to_none(filters: list[tuple]) -> list[tuple] | None:
     return filters if len(filters) > 0 else None
 
@@ -77,10 +67,6 @@ def _filter_to_polars_expr(filter_: tuple) -> pl.Expr:
     raise ValueError(f"Unsupported operation: {op}")
 
 
-class DeltaOverwriteFallbackWarning(RuntimeWarning):
-    pass
-
-
 class Table:
     def __init__(
         self,
@@ -140,9 +126,9 @@ class Table:
         if hyper_slice is None:
             hyper_slice = []
 
-        # Generated filters are an optimization for partition pruning. Keep them out
-        # of row filters because partition values may be represented as strings by
-        # PyArrow even when the Delta schema has a richer logical type.
+        # Generated filters are an optimization for partition pruning. Keep all
+        # partition filters out of row filters because partition values may be
+        # represented differently by PyArrow than by Delta's partition pruning.
         partition_hyper_slice = self.schema().add_generated_filters(hyper_slice)
 
         delta_table = self.delta_table
@@ -157,16 +143,12 @@ class Table:
                 [f for f in hyper_slice if f[0] not in partition_cols]
             )
             partition_filters = _empty_to_none(
-                [
-                    f
-                    for f in partition_hyper_slice
-                    if f[0] in partition_cols and _is_safe_partition_filter(f)
-                ]
+                [f for f in partition_hyper_slice if f[0] in partition_cols]
             )
             post_filters = [
                 f
                 for f in hyper_slice
-                if f[0] in partition_cols and not _is_safe_partition_filter(f)
+                if f[0] in partition_cols and f not in partition_hyper_slice
             ]
 
         pyarrow_table_existing_data = delta_table.to_pyarrow_table(
@@ -239,21 +221,7 @@ class Table:
         else:
             predicate = _dnf_to_sql(hyper_slice)
 
-        try:
-            self._write_deltalake(data=data, mode="overwrite", predicate=predicate)
-        except CommitFailedError as error:
-            if predicate is None or not _is_arrow_cast_commit_failure(error):
-                raise
-
-            warnings.warn(
-                "Delta predicate overwrite failed with the DataFusion arrow_cast bug. "
-                "Falling back to delete followed by append; this is not atomic as a "
-                "single overwrite commit.",
-                DeltaOverwriteFallbackWarning,
-                stacklevel=2,
-            )
-            self.delta_table.delete(predicate)
-            self._write_deltalake(data=data, mode="append", predicate=None)
+        self._write_deltalake(data=data, mode="overwrite", predicate=predicate)
 
     def append(self, df: pl.DataFrame) -> None:
         """Append rows to Delta Lake. This will write data to the Delta Lake.

{datazone_sdk-6.0.1.dev5 → datazone_sdk-6.0.1.dev7}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "datazone-sdk"
-version = "6.0.1.dev5"
+version = "6.0.1.dev7"
 description = "Database and Delta storage client library for working with Delta Lake tables"
 authors = [{ name = "Team Enigma", email = "enigma@energinet.dk" }]
 requires-python = ">=3.10"