deltacat 1.1.29__tar.gz → 1.1.30__tar.gz

{deltacat-1.1.29/deltacat.egg-info → deltacat-1.1.30}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: deltacat
-Version: 1.1.29
+Version: 1.1.30
 Summary: A scalable, fast, ACID-compliant Data Catalog powered by Ray.
 Home-page: https://github.com/ray-project/deltacat
 Author: Ray Team

{deltacat-1.1.29 → deltacat-1.1.30}/deltacat/__init__.py

@@ -44,7 +44,7 @@ from deltacat.types.tables import TableWriteMode
 
 deltacat.logs.configure_deltacat_logger(logging.getLogger(__name__))
 
-__version__ = "1.1.29"
+__version__ = "1.1.30"
 
 
 __all__ = [

{deltacat-1.1.29 → deltacat-1.1.30}/deltacat/tests/utils/test_pyarrow.py

@@ -8,6 +8,7 @@ from deltacat.utils.pyarrow import (
     ReadKwargsProviderPyArrowSchemaOverride,
     RAISE_ON_EMPTY_CSV_KWARG,
     RAISE_ON_DECIMAL_OVERFLOW,
+    OVERRIDE_CONTENT_ENCODING_FOR_PARQUET_KWARG,
 )
 import decimal
 from deltacat.types.media import ContentEncoding, ContentType
@@ -812,3 +813,54 @@ class TestS3FileToTable(TestCase):
         schema = result.schema
         schema_index = schema.get_field_index("n_legs")
         self.assertEqual(schema.field(schema_index).type, "int64")
+
+    def test_s3_file_to_table_when_utsv_gzip_and_content_type_overridden(self):
+        schema = pa.schema(
+            [("is_active", pa.string()), ("ship_datetime_utc", pa.timestamp("us"))]
+        )
+
+        # OVERRIDE_CONTENT_ENCODING_FOR_PARQUET_KWARG has no effect on uTSV files
+        pa_kwargs_provider = lambda content_type, kwargs: {
+            "reader_type": "pyarrow",
+            OVERRIDE_CONTENT_ENCODING_FOR_PARQUET_KWARG: ContentEncoding.IDENTITY.value,
+            **kwargs,
+        }
+
+        result = s3_file_to_table(
+            GZIP_COMPRESSED_FILE_UTSV_PATH,
+            ContentType.UNESCAPED_TSV.value,
+            ContentEncoding.GZIP.value,
+            ["is_active", "ship_datetime_utc"],
+            None,
+            pa_read_func_kwargs_provider=pa_kwargs_provider,
+        )
+
+        self.assertEqual(len(result), 3)
+        self.assertEqual(len(result.column_names), 2)
+        result_schema = result.schema
+        for index, field in enumerate(result_schema):
+            self.assertEqual(field.name, schema.field(index).name)
+
+        self.assertEqual(result.schema.field(0).type, "string")
+
+    def test_s3_file_to_table_when_parquet_gzip_and_encoding_overridden(self):
+        pa_kwargs_provider = lambda content_type, kwargs: {
+            "reader_type": "pyarrow",
+            OVERRIDE_CONTENT_ENCODING_FOR_PARQUET_KWARG: ContentEncoding.IDENTITY.value,
+            **kwargs,
+        }
+
+        result = s3_file_to_table(
+            PARQUET_FILE_PATH,
+            ContentType.PARQUET.value,
+            ContentEncoding.GZIP.value,
+            ["n_legs", "animal"],
+            ["n_legs"],
+            pa_read_func_kwargs_provider=pa_kwargs_provider,
+        )
+
+        self.assertEqual(len(result), 6)
+        self.assertEqual(len(result.column_names), 1)
+        schema = result.schema
+        schema_index = schema.get_field_index("n_legs")
+        self.assertEqual(schema.field(schema_index).type, "int64")

{deltacat-1.1.29 → deltacat-1.1.30}/deltacat/utils/pyarrow.py

@@ -47,6 +47,7 @@ logger = logs.configure_deltacat_logger(logging.getLogger(__name__))
 
 RAISE_ON_EMPTY_CSV_KWARG = "raise_on_empty_csv"
 READER_TYPE_KWARG = "reader_type"
+OVERRIDE_CONTENT_ENCODING_FOR_PARQUET_KWARG = "override_content_encoding_for_parquet"
 
 """
 By default, round decimal values using half_to_even round mode when
@@ -543,6 +544,15 @@ def s3_file_to_table(
     if pa_read_func_kwargs_provider is not None:
         kwargs = pa_read_func_kwargs_provider(content_type, kwargs)
 
+    if OVERRIDE_CONTENT_ENCODING_FOR_PARQUET_KWARG in kwargs:
+        new_content_encoding = kwargs.pop(OVERRIDE_CONTENT_ENCODING_FOR_PARQUET_KWARG)
+        if content_type == ContentType.PARQUET.value:
+            logger.debug(
+                f"Overriding {s3_url} content encoding from {content_encoding} "
+                f"to {new_content_encoding}"
+            )
+            content_encoding = new_content_encoding
+
     if (
         content_type == ContentType.PARQUET.value
         and content_encoding == ContentEncoding.IDENTITY.value

{deltacat-1.1.29 → deltacat-1.1.30/deltacat.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: deltacat
-Version: 1.1.29
+Version: 1.1.30
 Summary: A scalable, fast, ACID-compliant Data Catalog powered by Ray.
 Home-page: https://github.com/ray-project/deltacat
 Author: Ray Team