adapta 4.0.2a596.dev6__tar.gz → 4.0.4__tar.gz

{adapta-4.0.2a596.dev6 → adapta-4.0.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: adapta
-Version: 4.0.2a596.dev6
+Version: 4.0.4
 Summary: Logging, data connectors, monitoring, secret handling and general lifehacks to make data people lives easier.
 License: Apache-2.0
 License-File: LICENSE
@@ -52,7 +52,7 @@ Requires-Dist: mlflow-skinny (>=2.17.0,<2.18.0) ; extra == "ml"
 Requires-Dist: openpyxl (>=3.0,<4.0) ; extra == "excel"
 Requires-Dist: pandas[performance] (>=2.0.0,<3.0)
 Requires-Dist: pandera (>=0.20.3,<1.0)
-Requires-Dist: polars (>=1.7,<1.34)
+Requires-Dist: polars (>=1.7)
 Requires-Dist: pyarrow (>=7.0)
 Requires-Dist: pyiceberg (>=0.11.1,<0.12.0) ; extra == "storage-iceberg"
 Requires-Dist: pyodbc (>=4.0,<4.1) ; extra == "databases"

adapta-4.0.4/adapta/_version.py

@@ -0,0 +1 @@
+__version__ = '4.0.4'

{adapta-4.0.2a596.dev6 → adapta-4.0.4}/adapta/storage/delta_lake/v3/_functions.py

@@ -98,9 +98,7 @@ def load(  # pylint: disable=R0913
 
     if batch_size:
         if limit is not None:
-            pyarrow_table: Table = pyarrow_ds.filter(filter=row_filter).head(
-                int_num_rows=limit, columns=columns, batch_size=batch_size
-            )
+            pyarrow_table: Table = pyarrow_ds.filter(row_filter).head(limit, columns=columns, batch_size=batch_size)
         else:
             pyarrow_table: Table = pyarrow_ds.to_table(filter=row_filter, columns=columns, batch_size=batch_size)
 
@@ -115,7 +113,7 @@ def load(  # pylint: disable=R0913
         )
 
     if limit is not None:
-        pyarrow_table: Table = pyarrow_ds.filter(row_filter).head(int_num_rows=limit, columns=columns)
+        pyarrow_table: Table = pyarrow_ds.filter(row_filter).head(limit, columns=columns)
     else:
         pyarrow_table: Table = pyarrow_ds.to_table(filter=row_filter, columns=columns)
 

{adapta-4.0.2a596.dev6 → adapta-4.0.4}/adapta/storage/iceberg/v1/_functions.py

@@ -98,8 +98,18 @@ def load_using_native_scan(
     This method relies on **UNSTABLE** API to ensure compatibility with S3 implementations outside AWS.
     Use of `load_using_catalog` is recommended for production applications.
     """
+    table = catalog.load_table(identifier=(schema, table_name))
+    if "ADAPTA__ICEBERG_REST_CATALOG__S3_ENDPOINT_OVERRIDE" in os.environ:
+        # FileIO's endpoint is taken directly from the catalog response
+        # In case it differs from `s3.endpoint` set in catalog config, align them
+        # Note that when vended credentials are used, table.config will take preference over client setting
+        # thus endpoint is updated after catalog returns creds
+        # this is necessary if your S3 service has multiple endpoints and client doesn't have access to the one used by catalog
+        table.io.properties["s3.endpoint"] = os.environ["ADAPTA__ICEBERG_REST_CATALOG__S3_ENDPOINT_OVERRIDE"]
+        table.config["s3.endpoint"] = os.environ["ADAPTA__ICEBERG_REST_CATALOG__S3_ENDPOINT_OVERRIDE"]
+
     return MetaFrame(
-        data=catalog.load_table(identifier=(schema, table_name)),
+        table,
         # use built-in DataScan converters
         convert_to_polars=lambda table: polars.scan_iceberg(
             table,

{adapta-4.0.2a596.dev6 → adapta-4.0.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "adapta"
-version = "v4.0.2a596.dev6"
+version = "4.0.4"
 description = "Logging, data connectors, monitoring, secret handling and general lifehacks to make data people lives easier."
 authors = ["ECCO Sneaks & Data <esdsupport@ecco.com>"]
 maintainers = ['GZU <gzu@ecco.com>', 'JRB <ext-jrb@ecco.com>']
@@ -17,7 +17,7 @@ pandas = { version = ">=2.0.0,<3.0", extras = ["performance"] }
 pyarrow = ">=7.0"
 dataclasses-json = "~0.6"
 limits = "^5.8"
-polars = ">=1.7 <1.34"
+polars = ">=1.7"
 pandera = ">=0.20.3 <1.0"
 xlsxwriter = { version = "^3.0", optional = true }
 fastexcel = { version = "^0.14.0", optional = true }

adapta-4.0.2a596.dev6/adapta/_version.py

@@ -1 +0,0 @@
-__version__ = 'v4.0.2a596.dev6'