datazone-sdk 6.0.1.dev1__tar.gz → 6.0.1.dev3__tar.gz

{datazone_sdk-6.0.1.dev1 → datazone_sdk-6.0.1.dev3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: datazone-sdk
-Version: 6.0.1.dev1
+Version: 6.0.1.dev3
 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.dev1 → datazone_sdk-6.0.1.dev3}/datazone/deltastorage/generated_columns.py

@@ -97,18 +97,23 @@ class DateBucket(GeneratedColumn):
         Returns:
             tuple[str, dt.date]: List of conditions on the generated column
         """
-        timestamp = copy.copy(value)
-        if self.as_tz is not None:
-            timestamp = timestamp.astimezone(ZoneInfo(self.as_tz))
-        date = timestamp.date()
+
+        def date_from_timestamp(timestamp: dt.datetime) -> dt.date:
+            timestamp = copy.copy(timestamp)
+            if self.as_tz is not None:
+                timestamp = timestamp.astimezone(ZoneInfo(self.as_tz))
+            return timestamp.date()
 
         match op:
             case "=":
-                return [("=", date)]
+                return [("=", date_from_timestamp(value))]
             case ("<" | "<="):
-                return [("<=", date)]
+                return [("<=", date_from_timestamp(value))]
             case (">" | ">="):
-                return [(">=", date)]
+                return [(">=", date_from_timestamp(value))]
+            case "in":
+                dates = [date_from_timestamp(timestamp) for timestamp in value]
+                return [("in", list(dict.fromkeys(dates)))]
             case _:
                 # for other operations, we cannot make any
                 # useful filters on the generated column

{datazone_sdk-6.0.1.dev1 → datazone_sdk-6.0.1.dev3}/datazone/deltastorage/table.py

@@ -4,6 +4,7 @@ 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
@@ -46,6 +47,10 @@ 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)
+
+
 class Table:
     def __init__(
         self,
@@ -178,13 +183,19 @@ class Table:
         schema = self.schema()
         data = self._to_writable_pyarrow_table(df=df, schema=schema)
 
-        hyper_slice = schema.add_generated_filters(hyper_slice)
         if len(hyper_slice) == 0:
             predicate = None
         else:
             predicate = _dnf_to_sql(hyper_slice)
 
-        self._write_deltalake(data=data, mode="overwrite", predicate=predicate)
+        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
+
+            self.delta_table.delete(predicate)
+            self._write_deltalake(data=data, mode="append", predicate=None)
 
     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.dev1 → datazone_sdk-6.0.1.dev3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "datazone-sdk"
-version = "6.0.1.dev1"
+version = "6.0.1.dev3"
 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"