Prune dependency upper bounds

pyproject.toml

@@ -32,18 +32,18 @@ classifiers = [
     "Programming Language :: Python :: 3.14",
 ]
 dependencies = [
-    "mmh3>=4.0.0,<6.0.0",
-    "requests>=2.20.0,<3.0.0",
-    "click>=7.1.1,<9.0.0",
-    "rich>=10.11.0,<16.0.0",
-    "strictyaml>=1.7.0,<2.0.0", # CVE-2020-14343 was fixed in 5.4.
+    "mmh3>=4.0.0",
+    "requests>=2.20.0",
+    "click>=7.1.1",
+    "rich>=10.11.0",
+    "strictyaml>=1.7.0", # CVE-2020-14343 was fixed in 5.4.
     "pydantic>=2.0,<3.0,!=2.4.0,!=2.4.1,!=2.12.0,!=2.12.1", # 2.4.0, 2.4.1, 2.12.0, 2.12.1 has a critical bug
     "fsspec>=2023.1.0",
-    "pyparsing>=3.1.0,<4.0.0",
-    "tenacity>=8.2.3,<10.0.0",
-    "pyroaring>=1.0.0,<2.0.0",
-    "cachetools>=5.5,<8.0",
-    "zstandard>=0.13.0,<1.0.0"
+    "pyparsing>=3.1.0",
+    "tenacity>=8.2.3",
+    "pyroaring>=1.0.0",
+    "cachetools>=5.5",
+    "zstandard>=0.13.0"
 ]
 
 [project.urls]
@@ -62,23 +62,23 @@ pandas = [
     "pyarrow>=17.0.0",
 ]
 duckdb = [
-    "duckdb>=0.5.0,<2.0.0",
+    "duckdb>=0.5.0",
     "pyarrow>=17.0.0",
 ]
 ray = [
-    "ray>=2.10.0,<3.0.0",
+    "ray>=2.10.0",
     "pyarrow>=17.0.0",
     "pandas>=1.0.0",
 ]
 bodo = ["bodo>=2025.7.4"]
 daft = ["daft>=0.7.10"]
-polars = ["polars>=1.21.0,<2"]
-snappy = ["python-snappy>=0.6.0,<1.0.0"]
-hive = ["thrift>=0.13.0,<1.0.0"]
+polars = ["polars>=1.21.0"]
+snappy = ["python-snappy>=0.6.0"]
+hive = ["thrift>=0.13.0"]
 hive-kerberos = [
-    "thrift>=0.13.0,<1.0.0",
+    "thrift>=0.13.0",
     "thrift-sasl>=0.4.3",
-    "kerberos>=1.3.1,<2",
+    "kerberos>=1.3.1",
 ]
 s3fs = ["s3fs>=2023.1.0"]
 glue = ["boto3>=1.24.59"]
@@ -103,18 +103,18 @@ geoarrow = ["geoarrow-pyarrow>=0.2.0"]
 dev = [
     "pytest==9.1.1",
     "pytest-checkdocs==2.14.0",
-    "prek>=0.2.1,<0.5",
+    "prek>=0.2.1",
     "pytest-lazy-fixtures==1.4.0",
     "fastavro==1.12.2",
-    "coverage[toml]>=7.4.2,<8",
+    "coverage[toml]>=7.4.2",
     "requests-mock==1.12.1",
-    "moto[server]>=5.0.2,<6",
+    "moto[server]>=5.0.2",
     "typing-extensions==4.15.0",
     "pytest-mock==3.15.1",
     "pyspark[connect]==4.0.1",
     "protobuf==6.33.5", # match Spark Connect's gencode
     "cython>=3.0.0",
-    "deptry>=0.14,<0.26",
+    "deptry>=0.14",
     "docutils!=0.21.post1",
     "mypy-boto3-glue>=1.28.18",
     "mypy-boto3-dynamodb>=1.28.18",
@@ -178,6 +178,8 @@ filterwarnings = [
   "ignore:subprocess.*is still running:ResourceWarning",
   # Ignore google-crc32c C extension missing warning (common on Python 3.14+)
   "ignore:As the c extension couldn't be imported:RuntimeWarning:google_crc32c",
+  # Ignore Spark 4.0.1 pandas conversion warning under pandas 3.0
+  "ignore:The copy keyword is deprecated and will be removed in a future version.*",
 ]
 
 [tool.mypy]

tests/catalog/test_glue.py

@@ -72,7 +72,7 @@ def _db_as_dict_with_federated(self):  # type: ignore
     # warehouse location.
     _original_table_init = FakeTable.__init__
 
-    def _table_init_with_location(self, database_name, table_name, table_input, catalog_id):  # type: ignore
+    def _table_init_with_location(self, database_name, table_name, table_input, *args, **kwargs):  # type: ignore
         if table_input.get("Parameters", {}).get("format") == "ICEBERG" and "StorageDescriptor" not in table_input:
             table_input = {
                 **table_input,
@@ -84,7 +84,7 @@ def _table_init_with_location(self, database_name, table_name, table_input, cata
                     "SerdeInfo": {},
                 },
             }
-        _original_table_init(self, database_name, table_name, table_input, catalog_id)
+        _original_table_init(self, database_name, table_name, table_input, *args, **kwargs)
 
     monkeypatch.setattr(FakeTable, "__init__", _table_init_with_location)
 

tests/integration/test_writes/test_writes.py

@@ -768,7 +768,7 @@ def test_spark_writes_orc_pyiceberg_reads(spark: SparkSession, session_catalog:
 
     # Verify PyIceberg data types are correct
     assert pyiceberg_df["id"].dtype == "int64"
-    assert pyiceberg_df["name"].dtype == "object"  # string
+    assert pd.api.types.is_string_dtype(pyiceberg_df["name"].dtype)
     assert pyiceberg_df["age"].dtype == "int64"
     assert pyiceberg_df["is_active"].dtype == "bool"