Skip to content

[SPARK-42562][CONNECT] UnresolvedNamedLambdaVariable in python do not need unique names #40287

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

Closed
wants to merge 2 commits into from
Closed

[SPARK-42562][CONNECT] UnresolvedNamedLambdaVariable in python do not need unique names #40287

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
91c0790
[SPARK-42562][CONNECT] UnresolvedNamedLambdaVariable in python do not…
beliefer Mar 6, 2023
22837dc
Update code
beliefer Mar 6, 2023
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
19 changes: 0 additions & 19 deletions python/pyspark/sql/connect/expressions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,6 @@
import decimal
import datetime
import warnings
from threading import Lock

import numpy as np

Expand Down Expand Up @@ -686,10 +685,6 @@ def __repr__(self) -> str:


class UnresolvedNamedLambdaVariable(Expression):

_lock: Lock = Lock()
_nextVarNameId: int = 0

def __init__(
self,
name_parts: Sequence[str],
Expand All @@ -712,20 +707,6 @@ def to_plan(self, session: "SparkConnectClient") -> proto.Expression:
def __repr__(self) -> str:
return f"(UnresolvedNamedLambdaVariable({', '.join(self._name_parts)})"

@staticmethod
def fresh_var_name(name: str) -> str:
assert isinstance(name, str) and str != ""

_id: Optional[int] = None

with UnresolvedNamedLambdaVariable._lock:
_id = UnresolvedNamedLambdaVariable._nextVarNameId
UnresolvedNamedLambdaVariable._nextVarNameId += 1

assert _id is not None

return f"{name}_{_id}"


class LambdaFunction(Expression):
def __init__(
Expand Down
5 changes: 1 addition & 4 deletions python/pyspark/sql/connect/functions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -160,10 +160,7 @@ def _create_lambda(f: Callable) -> LambdaFunction:
parameters = _get_lambda_parameters(f)

arg_names = ["x", "y", "z"][: len(parameters)]
arg_exprs = [
UnresolvedNamedLambdaVariable([UnresolvedNamedLambdaVariable.fresh_var_name(arg_name)])
for arg_name in arg_names
]
arg_exprs = [UnresolvedNamedLambdaVariable([arg_name]) for arg_name in arg_names]
arg_cols = [Column(arg_expr) for arg_expr in arg_exprs]

result = f(*arg_cols)
Expand Down