[Data] - Upgrade to pyiceberg 0.11.0 (ray-project#61062)

## Description
As title states.

One more note: apache/iceberg-python#2777
removed `FileScanTask`'s length param

## Related issues
> Link related issues: "Fixes ray-project#1234", "Closes ray-project#1234", or "Related to
ray-project#1234".

## Additional information
> Optional: Add implementation details, API changes, usage examples,
screenshots, etc.

---------

Signed-off-by: Goutam <goutam@anyscale.com>
Signed-off-by: peterxcli <peterxcli@gmail.com>

Author: goutamvenkat-anyscale

python/ray/data/_internal/datasource/iceberg_datasource.py

@@ -84,7 +84,7 @@
 
 
 class _IcebergExpressionVisitor(
-    _ExprVisitor["BooleanExpression | UnboundTerm[Any] | Literal[Any]"]
+    _ExprVisitor["BooleanExpression | UnboundTerm | Literal"]
 ):
     """
     Visitor that converts Ray Data expressions to PyIceberg expressions.
@@ -99,11 +99,11 @@ class _IcebergExpressionVisitor(
         >>> # iceberg_expr can now be used with PyIceberg's filter APIs
     """
 
-    def visit_column(self, expr: "ColumnExpr") -> "UnboundTerm[Any]":
+    def visit_column(self, expr: "ColumnExpr") -> "UnboundTerm":
         """Convert a column reference to an Iceberg reference."""
         return Reference(expr.name)
 
-    def visit_literal(self, expr: "LiteralExpr") -> "Literal[Any]":
+    def visit_literal(self, expr: "LiteralExpr") -> "Literal":
         """Convert a literal value to an Iceberg literal."""
         return literal(expr.value)
 
@@ -148,13 +148,11 @@ def visit_unary(self, expr: "UnaryExpr") -> "BooleanExpression":
 
     def visit_alias(
         self, expr: "AliasExpr"
-    ) -> "BooleanExpression | UnboundTerm[Any] | Literal[Any]":
+    ) -> "BooleanExpression | UnboundTerm | Literal":
         """Convert an aliased expression (just unwrap the alias)."""
         return self.visit(expr.expr)
 
-    def visit_udf(
-        self, expr: "UDFExpr"
-    ) -> "BooleanExpression | UnboundTerm[Any] | Literal[Any]":
+    def visit_udf(self, expr: "UDFExpr") -> "BooleanExpression | UnboundTerm | Literal":
         """UDF expressions cannot be converted to Iceberg expressions."""
         raise TypeError(
             "UDF expressions cannot be converted to Iceberg expressions. "
@@ -163,23 +161,23 @@ def visit_udf(
 
     def visit_download(
         self, expr: "DownloadExpr"
-    ) -> "BooleanExpression | UnboundTerm[Any] | Literal[Any]":
+    ) -> "BooleanExpression | UnboundTerm | Literal":
         """Download expressions cannot be converted to Iceberg expressions."""
         raise TypeError(
             "Download expressions cannot be converted to Iceberg expressions."
         )
 
     def visit_star(
         self, expr: "StarExpr"
-    ) -> "BooleanExpression | UnboundTerm[Any] | Literal[Any]":
+    ) -> "BooleanExpression | UnboundTerm | Literal":
         """Star expressions cannot be converted to Iceberg expressions."""
         raise TypeError(
             "Star expressions cannot be converted to Iceberg filter expressions."
         )
 
     def visit_monotonically_increasing_id(
         self, expr: "MonotonicallyIncreasingIdExpr"
-    ) -> "BooleanExpression | UnboundTerm[Any] | Literal[Any]":
+    ) -> "BooleanExpression | UnboundTerm | Literal":
         """Monotonically increasing ID expressions cannot be converted to Iceberg expressions."""
         raise TypeError(
             "monotonically_increasing_id expressions cannot be converted to Iceberg filter expressions."
@@ -490,7 +488,7 @@ def get_read_tasks(
             metadata = BlockMetadata(
                 num_rows=sum(task.file.record_count for task in chunk_tasks)
                 - position_delete_count,
-                size_bytes=sum(task.length for task in chunk_tasks),
+                size_bytes=sum(task.file.file_size_in_bytes for task in chunk_tasks),
                 input_files=[task.file.file_path for task in chunk_tasks],
                 exec_stats=None,
             )

python/ray/data/tests/datasource/test_iceberg.py

@@ -287,7 +287,7 @@ def test_write_basic():
     table_p = (
         ds.to_pandas().sort_values(["col_a", "col_b", "col_c"]).reset_index(drop=True)
     )
-    assert orig_table_p.equals(table_p)
+    assert rows_same(table_p, orig_table_p)
 
 
 @pytest.mark.skipif(

python/requirements/ml/data-test-requirements.txt

@@ -19,7 +19,7 @@ deltalake==0.9.0
 pytest-mock
 decord
 snowflake-connector-python>=3.15.0
-pyiceberg[sql-sqlite]==0.10.0
+pyiceberg[sql-sqlite]==0.11.0
 clickhouse-connect
 kafka-python
 pybase64

python/requirements_compiled.txt

@@ -1656,7 +1656,7 @@ pygments==2.18.0
     #   nbconvert
     #   rich
     #   sphinx
-pyiceberg==0.10.0
+pyiceberg==0.11.0
     # via -r python/requirements/ml/data-test-requirements.txt
 pyjwt==2.8.0
     # via
@@ -2107,7 +2107,6 @@ snowflake-connector-python==3.15.0
 sortedcontainers==2.4.0
     # via
     #   distributed
-    #   pyiceberg
     #   snowflake-connector-python
 soundfile==0.12.1
     # via -r python/requirements/ml/data-test-requirements.txt
@@ -2589,7 +2588,9 @@ zipp==3.19.2
 zoopt==0.4.1
     # via -r python/requirements/ml/tune-test-requirements.txt
 zstandard==0.23.0
-    # via clickhouse-connect
+    # via
+    #   clickhouse-connect
+    #   pyiceberg
 
 # The following packages are considered to be unsafe in a requirements file:
 # pip

python/requirements_compiled_py3.13.txt

@@ -1699,7 +1699,7 @@ pygments==2.18.0
     #   nbconvert
     #   rich
     #   sphinx
-pyiceberg==0.10.0
+pyiceberg==0.11.0
     # via -r python/requirements/ml/data-test-requirements.txt
 pyjwt==2.8.0
     # via