Revert changes

Author: Fokko

pyiceberg/table/inspect.py

@@ -559,7 +559,7 @@ def _get_files_from_manifest(
             if data_file_filter and data_file.content not in data_file_filter:
                 continue
             column_sizes = data_file.column_sizes or {}
-            value_counts = data_file.value_counts
+            value_counts = data_file.value_counts or {}
             null_value_counts = data_file.null_value_counts or {}
             nan_value_counts = data_file.nan_value_counts or {}
             lower_bounds = data_file.lower_bounds or {}

pyproject.toml

@@ -19,7 +19,7 @@ name = "pyiceberg"
 version = "0.10.0"
 description = "Apache Iceberg is an open table format for huge analytic datasets"
 authors = [{ name = "Apache Software Foundation", email = "dev@iceberg.apache.org" }]
-requires-python = ">=3.10.0,<=3.13.0"
+requires-python = ">=3.10.0,<4.0.0"
 readme = "README.md"
 license = "Apache-2.0"
 license-files = ["LICENSE", "NOTICE"]
@@ -98,12 +98,6 @@ pyiceberg-core = ["pyiceberg-core>=0.5.1,<0.9.0"]
 datafusion = ["datafusion>=51,<52"]
 gcp-auth = ["google-auth>=2.4.0"]
 
-[[tool.uv.index]]
-name = "testpypi"
-url = "https://test.pypi.org/simple/"
-publish-url = "https://test.pypi.org/legacy/"
-explicit = true
-
 [dependency-groups]
 dev = [
     "pytest==7.4.4",

tests/integration/test_hive_migration.py

@@ -24,7 +24,6 @@
 
 
 @pytest.mark.integration
-@pytest.mark.skip("Waiting on an upstream fix: https://github.com/apache/iceberg/pull/14163")
 def test_migrate_table(
     session_catalog_hive: Catalog,
     spark: SparkSession,

tests/integration/test_inspect_table.py

@@ -129,8 +129,7 @@ def _inspect_files_asserts(df: pa.Table, spark_df: DataFrame) -> None:
             "record_count",
             "file_size_in_bytes",
             "split_offsets",
-            # Fixed in https://github.com/apache/iceberg-rust/pull/1705
-            # "equality_ids",
+            "equality_ids",
             "sort_order_id",
         ]
     ]
@@ -143,19 +142,14 @@ def _inspect_files_asserts(df: pa.Table, spark_df: DataFrame) -> None:
             "record_count",
             "file_size_in_bytes",
             "split_offsets",
-            # Fixed in https://github.com/apache/iceberg-rust/pull/1705
-            # "equality_ids",
+            "equality_ids",
             "sort_order_id",
         ]
     ]
 
     assert_frame_equal(lhs_subset, rhs_subset, check_dtype=False, check_categorical=False)
 
     for column in df.column_names:
-        if column == "equality_ids":
-            # Fixed in https://github.com/apache/iceberg-rust/pull/1705
-            continue
-
         if column == "partition":
             # Spark leaves out the partition if the table is unpartitioned
             continue
@@ -363,10 +357,6 @@ def check_pyiceberg_df_equals_spark_df(df: pa.Table, spark_df: DataFrame) -> Non
                             # Arrow turns dicts into lists of tuple
                             df_lhs = dict(df_lhs)
 
-                        if "equality_ids" == df_column:
-                            # Fixed in https://github.com/apache/iceberg-rust/pull/1705
-                            continue
-
                         assert df_lhs == df_rhs, f"Difference in data_file column {df_column}: {df_lhs} != {df_rhs}"
                 elif column == "readable_metrics":
                     assert list(left.keys()) == [
@@ -887,7 +877,7 @@ def test_inspect_history(spark: SparkSession, session_catalog: Catalog, format_v
             if isinstance(left, float) and math.isnan(left) and isinstance(right, float) and math.isnan(right):
                 # NaN != NaN in Python
                 continue
-            # assert left == right, f"Difference in column {column}: {left} != {right}"
+            assert left == right, f"Difference in column {column}: {left} != {right}"
 
 
 @pytest.mark.integration
@@ -1094,7 +1084,6 @@ def test_inspect_all_files(
 
 
 @pytest.mark.integration
-@pytest.mark.skip("Fixed in https://github.com/apache/iceberg-rust/pull/1682/")
 def test_inspect_files_format_version_3(spark: SparkSession, session_catalog: Catalog, arrow_table_with_null: pa.Table) -> None:
     identifier = "default.table_metadata_files"
 
@@ -1140,9 +1129,7 @@ def test_inspect_files_format_version_3(spark: SparkSession, session_catalog: Ca
 
 
 @pytest.mark.integration
-# @pytest.mark.parametrize("format_version", [1, 2, 3])
-# V3 support in https://github.com/apache/iceberg-rust/pull/1682/
-@pytest.mark.parametrize("format_version", [1, 2])
+@pytest.mark.parametrize("format_version", [1, 2, 3])
 def test_inspect_files_partitioned(spark: SparkSession, session_catalog: Catalog, format_version: int) -> None:
     from pandas.testing import assert_frame_equal
 

tests/utils/test_manifest.py

@@ -58,7 +58,6 @@ def _verify_metadata_with_fastavro(avro_file: str, expected_metadata: dict[str,
             assert metadata[k] == v
 
 
-@pytest.mark.skip("Fix in https://github.com/apache/iceberg-rust/pull/1705")
 def test_read_manifest_entry(generated_manifest_entry_file: str) -> None:
     manifest = ManifestFile.from_args(
         manifest_path=generated_manifest_entry_file,
@@ -308,9 +307,7 @@ def test_write_empty_manifest() -> None:
 
 
 @pytest.mark.parametrize("format_version", [1, 2])
-@pytest.mark.parametrize("compression", ["null", "deflate"])
-# Added in https://github.com/apache/iceberg-rust/pull/1692
-# @pytest.mark.parametrize("compression", ["null", "deflate", "zstd"])
+@pytest.mark.parametrize("compression", ["null", "deflate", "zstd"])
 def test_write_manifest(
     generated_manifest_file_file_v1: str,
     generated_manifest_file_file_v2: str,