8000 refactor: subclass DerefOp as ResolvedDerefOp by chelsea-lin · Pull Request #1874 · googleapis/python-bigquery-dataframes · GitHub
[go: up one dir, main page]
Skip to content

refactor: subclass DerefOp as ResolvedDerefOp #1874

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
chelsea-lin merged 3 commits into from
Jul 1, 2025
Merged

refactor: subclass DerefOp as ResolvedDerefOp #1874

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
ef6d580
refactor: subclass DerefOp as ResolvedDerefOp
chelsea-lin Jun 30, 2025
294510f
replace the `field` attribute by id, dtype, nullable
chelsea-lin Jun 30, 2025
0f20a6a
final cleanup
chelsea-lin Jul 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions bigframes/core/compile/polars/compiler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -120,9 +120,9 @@ def _(
@compile_expression.register
def _(
self,
expression: ex.SchemaFieldRefExpression,
expression: ex.ResolvedDerefOp,
) -> pl.Expr:
return pl.col(expression.field.id.sql)
return pl.col(expression.id.sql)

@compile_expression.register
def _(
Expand Down
7 changes: 0 additions & 7 deletions bigframes/core/compile/sqlglot/scalar_compiler.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,13 +42,6 @@ def compile_deref_expression(expr: expression.DerefOp) -> sge.Expression:
return sge.ColumnDef(this=sge.to_identifier(expr.id.sql, quoted=True))


@compile_scalar_expression.register
def compile_field_ref_expression(
expr: expression.SchemaFieldRefExpression,
) -> sge.Expression:
return sge.ColumnDef(this=sge.to_identifier(expr.field.id.sql, quoted=True))


@compile_scalar_expression.register
def compile_constant_expression(
expr: expression.ScalarConstantExpression,
Expand Down
52 changes: 12 additions & 40 deletions bigframes/core/expression.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -429,55 +429,27 @@ def transform_children(self, t: Callable[[Expression], Expression]) -> Expressio


@dataclasses.dataclass(frozen=True)
class SchemaFieldRefExpression(Expression):
"""An expression representing a schema field. This is essentially a DerefOp with input schema bound."""
class ResolvedDerefOp(DerefOp):
"""An expression that refers to a column by ID and resolved with schema bound."""

field: field.Field
dtype: dtypes.Dtype
is_nullable: bool

@property
def column_references(self) -> typing.Tuple[ids.ColumnId, ...]:
return (self.field.id,)

@property
def is_const(self) -> bool:
return False

@property
def nullable(self) -> bool:
return self.field.nullable
@classmethod
def from_field(cls, f: field.Field):
return cls(id=f.id, dtype=f.dtype, is_nullable=f.nullable)

@property
def is_resolved(self) -> bool:
return True

@property
def output_type(self) -> dtypes.ExpressionType:
return self.field.dtype

def bind_variables(
self, bindings: Mapping[str, Expression], allow_partial_bindings: bool = False
) -> Expression:
return self

def bind_refs(
self,
bindings: Mapping[ids.ColumnId, Expression],
allow_partial_bindings: bool = False,
) -> Expression:
if self.field.id in bindings.keys():
return bindings[self.field.id]
return self

@property
def is_bijective(self) -> bool:
return True
def nullable(self) -> bool:
return self.is_nullable

@property
def is_identity(self) -> bool:
return True

def transform_children(self, t: Callable[[Expression], Expression]) -> Expression:
return self
def output_type(self) -> dtypes.ExpressionType:
return self.dtype


@dataclasses.dataclass(frozen=True)
Expand Down Expand Up @@ -589,7 +561,7 @@ def bind_schema_fields(
return expr

expr_by_id = {
id: SchemaFieldRefExpression(field) for id, field in field_by_id.items()
id: ResolvedDerefOp.from_field(field) for id, field in field_by_id.items()
}
return expr.bind_refs(expr_by_id)

Expand Down
13 changes: 13 additions & 0 deletions bigframes/core/rewrite/schema_binding.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,4 +52,17 @@ def bind_schema_to_node(

return dataclasses.replace(node, by=tuple(bound_bys))

if isinstance(node, nodes.JoinNode):
conditions = tuple(
(
ex.ResolvedDerefOp.from_field(node.left_child.field_by_id[left.id]),
ex.ResolvedDerefOp.from_field(node.right_child.field_by_id[right.id]),
)
for left, right in node.conditions
)
return dataclasses.replace(
node,
conditions=conditions,
)

return node
4 changes: 2 additions & 2 deletions tests/unit/core/test_expression.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,8 +77,8 @@ def test_deref_op_dtype_resolution():


def test_field_ref_expr_dtype_resolution_short_circuit():
expression = ex.SchemaFieldRefExpression(
field.Field(ids.ColumnId("mycol"), dtype=dtypes.INT_DTYPE)
expression = ex.ResolvedDerefOp(
id=ids.ColumnId("mycol"), dtype=dtypes.INT_DTYPE, is_nullable=True
)
field_bindings = _create_field_bindings({"anotherCol": dtypes.STRING_DTYPE})

Expand Down
0