Merge branch 'main' into b374307132-information_schema

Author: tswast

.pre-commit-config.yaml

@@ -42,3 +42,8 @@ repos:
         additional_dependencies: [types-requests, types-tabulate, types-PyYAML, pandas-stubs<=2.2.3.241126]
         exclude: "^third_party"
         args: ["--check-untyped-defs", "--explicit-package-bases", "--ignore-missing-imports"]
+-   repo: https://github.com/biomejs/pre-commit
+    rev: v2.0.2
+    hooks:
+    -   id: biome-check
+        files: '\.js$'

MANIFEST.in

@@ -17,7 +17,7 @@
 # Generated by synthtool. DO NOT EDIT!
 include README.rst LICENSE
 recursive-include third_party/bigframes_vendored *
-recursive-include bigframes *.json *.proto py.typed
+recursive-include bigframes *.json *.proto *.js py.typed
 recursive-include tests *
 global-exclude *.py[co]
 global-exclude __pycache__

bigframes/core/compile/polars/compiler.py

@@ -487,8 +487,14 @@ def compile_offsets(self, node: nodes.PromoteOffsetsNode):
     def compile_join(self, node: nodes.JoinNode):
         left = self.compile_node(node.left_child)
         right = self.compile_node(node.right_child)
-        left_on = [l_name.id.sql for l_name, _ in node.conditions]
-        right_on = [r_name.id.sql for _, r_name in node.conditions]
+
+        left_on = []
+        right_on = []
+        for left_ex, right_ex in node.conditions:
+            left_ex, right_ex = lowering._coerce_comparables(left_ex, right_ex)
+            left_on.append(self.expr_compiler.compile_expression(left_ex))
+            right_on.append(self.expr_compiler.compile_expression(right_ex))
+
         if node.type == "right":
             return self._ordered_join(
                 right, left, "left", right_on, left_on, node.joins_nulls
@@ -502,8 +508,8 @@ def _ordered_join(
         left_frame: pl.LazyFrame,
         right_frame: pl.LazyFrame,
         how: Literal["inner", "outer", "left", "cross"],
-        left_on: Sequence[str],
-        right_on: Sequence[str],
+        left_on: Sequence[pl.Expr],
+        right_on: Sequence[pl.Expr],
         join_nulls: bool,
     ):
         if how == "right":

bigframes/core/indexes/base.py

@@ -16,8 +16,9 @@
 
 from __future__ import annotations
 
+import functools
 import typing
-from typing import Hashable, Literal, Optional, overload, Sequence, Union
+from typing import cast, Hashable, Literal, Optional, overload, Sequence, Union
 
 import bigframes_vendored.constants as constants
 import bigframes_vendored.pandas.core.indexes.base as vendored_pandas_index
@@ -529,6 +530,29 @@ def isin(self, values) -> Index:
             )
         ).fillna(value=False)
 
+    def __contains__(self, key) -> bool:
+        hash(key)  # to throw for unhashable values
+        if self.nlevels == 0:
+            return False
+
+        if (not isinstance(key, tuple)) or (self.nlevels == 1):
+            key = (key,)
+
+        match_exprs = []
+        for key_part, index_col, dtype in zip(
+            key, self._block.index_columns, self._block.index.dtypes
+        ):
+            key_type = bigframes.dtypes.is_compatible(key_part, dtype)
+            if key_type is None:
+                return False
+            key_expr = ex.const(key_part, key_type)
+            match_expr = ops.eq_null_match_op.as_expr(ex.deref(index_col), key_expr)
+            match_exprs.append(match_expr)
+
+        match_expr_final = functools.reduce(ops.and_op.as_expr, match_exprs)
+        block, match_col = self._block.project_expr(match_expr_final)
+        return cast(bool, block.get_stat(match_col, agg_ops.AnyOp()))
+
     def _apply_unary_expr(
         self,
         op: ex.Expression,

bigframes/core/tools/datetimes.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 from collections.abc import Mapping
-from datetime import datetime
+from datetime import date, datetime
 from typing import Optional, Union
 
 import bigframes_vendored.constants as constants
@@ -28,7 +28,7 @@
 
 def to_datetime(
     arg: Union[
-        Union[int, float, str, datetime],
+        Union[int, float, str, datetime, date],
         vendored_pandas_datetimes.local_iterables,
         bigframes.series.Series,
         bigframes.dataframe.DataFrame,
@@ -38,7 +38,7 @@ def to_datetime(
     format: Optional[str] = None,
     unit: Optional[str] = None,
 ) -> Union[pd.Timestamp, datetime, bigframes.series.Series]:
-    if isinstance(arg, (int, float, str, datetime)):
+    if isinstance(arg, (int, float, str, datetime, date)):
         return pd.to_datetime(
             arg,
             utc=utc,
@@ -62,7 +62,11 @@ def to_datetime(
             f"Unit parameter is not supported for non-numerical input types. {constants.FEEDBACK_LINK}"
         )
 
-    if arg.dtype in (bigframes.dtypes.TIMESTAMP_DTYPE, bigframes.dtypes.DATETIME_DTYPE):
+    if arg.dtype in (
+        bigframes.dtypes.TIMESTAMP_DTYPE,
+        bigframes.dtypes.DATETIME_DTYPE,
+        bigframes.dtypes.DATE_DTYPE,
+    ):
         to_type = (
             bigframes.dtypes.TIMESTAMP_DTYPE if utc else bigframes.dtypes.DATETIME_DTYPE
         )

bigframes/dataframe.py

@@ -374,6 +374,9 @@ def __len__(self):
     def __iter__(self):
         return iter(self.columns)
 
+    def __contains__(self, key) -> bool:
+        return key in self.columns
+
     def astype(
         self,
         dtype: Union[
@@ -779,22 +782,7 @@ def _repr_html_(self) -> str:
         if opts.repr_mode == "deferred":
             return formatter.repr_query_job(self._compute_dry_run())
 
-        if opts.repr_mode == "anywidget":
-            import anywidget  # type: ignore
-
-            # create an iterator for the data batches
-            batches = self.to_pandas_batches()
-
-            # get the first page result
-            try:
-                first_page = next(iter(batches))
-            except StopIteration:
-                first_page = pandas.DataFrame(columns=self.columns)
-
-            # Instantiate and return the widget. The widget's frontend will
-            # handle the display of the table and pagination
-            return anywidget.AnyWidget(dataframe=first_page)
-
+        # Process blob columns first, regardless of display mode
         self._cached()
         df = self.copy()
         if bigframes.options.display.blob_display:
@@ -806,7 +794,31 @@ def _repr_html_(self) -> str:
             for col in blob_cols:
                 # TODO(garrettwu): Not necessary to get access urls for all the rows. Update when having a to get URLs from local data.
                 df[col] = df[col].blob._get_runtime(mode="R", with_metadata=True)
+        else:
+            blob_cols = []
 
+        if opts.repr_mode == "anywidget":
+            try:
+                from IPython.display import display as ipython_display
+
+                from bigframes import display
+
+                # Always create a new widget instance for each display call
+                # This ensures that each cell gets its own widget and prevents
+                # unintended sharing between cells
+                widget = display.TableWidget(df.copy())
+
+                ipython_display(widget)
+                return ""  # Return empty string since we used display()
+
+            except (AttributeError, ValueError, ImportError):
+                # Fallback if anywidget is not available
+                warnings.warn(
+                    "Anywidget mode is not available. Please `pip install anywidget traitlets` or `pip install 'bigframes[anywidget]'` to use interactive tables. Falling back to deferred mode."
+                )
+                return formatter.repr_query_job(self._compute_dry_run())
+
+        # Continue with regular HTML rendering for non-anywidget modes
         # TODO(swast): pass max_columns and get the true column count back. Maybe
         # get 1 more column than we have requested so that pandas can add the
         # ... for us?
@@ -815,7 +827,6 @@ def _repr_html_(self) -> str:
         )
 
         self._set_internal_query_job(query_job)
-
         column_count = len(pandas_df.columns)
 
         with display_options.pandas_repr(opts):

bigframes/display/__init__.py

@@ -0,0 +1,24 @@
+# Copyright 2025 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import annotations
+
+try:
+    import anywidget  # noqa
+
+    from bigframes.display.anywidget import TableWidget
+
+    __all__ = ["TableWidget"]
+except Exception:
+    pass