You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@spark.apache.org by gu...@apache.org on 2022/12/10 00:33:33 UTC
[spark] branch master updated: [SPARK-41329][CONNECT] Resolve circular imports in Spark Connect
This is an automated email from the ASF dual-hosted git repository.
gurwls223 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/spark.git
The following commit(s) were added to refs/heads/master by this push:
new deabae7465d [SPARK-41329][CONNECT] Resolve circular imports in Spark Connect
deabae7465d is described below
commit deabae7465db606b06c8e1cbaddf9cd67df6083c
Author: Hyukjin Kwon <gu...@apache.org>
AuthorDate: Sat Dec 10 09:33:20 2022 +0900
[SPARK-41329][CONNECT] Resolve circular imports in Spark Connect
### What changes were proposed in this pull request?
This PR proposes to resolve the circular imports workarounds
### Why are the changes needed?
For better readability and maintanence.
### Does this PR introduce _any_ user-facing change?
No, dev-only.
### How was this patch tested?
CI in this PR should test it out.
Closes #38994 from HyukjinKwon/SPARK-41329.
Lead-authored-by: Hyukjin Kwon <gu...@apache.org>
Co-authored-by: Hyukjin Kwon <gu...@gmail.com>
Signed-off-by: Hyukjin Kwon <gu...@apache.org>
---
python/pyspark/sql/connect/column.py | 26 +++++++++++---------------
python/pyspark/sql/connect/readwriter.py | 1 -
2 files changed, 11 insertions(+), 16 deletions(-)
diff --git a/python/pyspark/sql/connect/column.py b/python/pyspark/sql/connect/column.py
index f1a909b89fc..b84c27afb15 100644
--- a/python/pyspark/sql/connect/column.py
+++ b/python/pyspark/sql/connect/column.py
@@ -27,14 +27,10 @@ import pyspark.sql.connect.proto as proto
from pyspark.sql.connect.types import pyspark_types_to_proto_types
if TYPE_CHECKING:
- from pyspark.sql.connect._typing import ColumnOrName
+ from pyspark.sql.connect._typing import ColumnOrName, PrimitiveType
from pyspark.sql.connect.client import SparkConnectClient
import pyspark.sql.connect.proto as proto
-# TODO(SPARK-41329): solve the circular import between _typing and this class
-# if we want to reuse _type.PrimitiveType
-PrimitiveType = Union[bool, float, int, str]
-
def _func_op(name: str, doc: str = "") -> Callable[["Column"], "Column"]:
def _(self: "Column") -> "Column":
@@ -554,7 +550,7 @@ class Column:
return _func_op("not")(_bin_op("==")(self, other))
# string methods
- def contains(self, other: Union[PrimitiveType, "Column"]) -> "Column":
+ def contains(self, other: Union["PrimitiveType", "Column"]) -> "Column":
"""
Contains the other element. Returns a boolean :class:`Column` based on a string match.
@@ -698,6 +694,9 @@ class Column:
>>> df.select(df.name.substr(1, 3).alias("col")).collect()
[Row(col='Ali'), Row(col='Bob')]
"""
+ from pyspark.sql.connect.function_builder import functions as F
+ from pyspark.sql.connect.functions import lit
+
if type(startPos) != type(length):
raise TypeError(
"startPos and length must be the same type. "
@@ -706,17 +705,16 @@ class Column:
length_t=type(length),
)
)
- from pyspark.sql.connect.function_builder import functions as F
if isinstance(length, int):
- length_exp = self._lit(length)
+ length_exp = lit(length)
elif isinstance(length, Column):
length_exp = length
else:
raise TypeError("Unsupported type for substr().")
if isinstance(startPos, int):
- start_exp = self._lit(startPos)
+ start_exp = lit(startPos)
else:
start_exp = startPos
@@ -726,8 +724,11 @@ class Column:
"""Returns a binary expression with the current column as the left
side and the other expression as the right side.
"""
+ from pyspark.sql.connect._typing import PrimitiveType
+ from pyspark.sql.connect.functions import lit
+
if isinstance(other, get_args(PrimitiveType)):
- other = self._lit(other)
+ other = lit(other)
return scalar_function("==", self, other)
def to_plan(self, session: "SparkConnectClient") -> proto.Expression:
@@ -779,11 +780,6 @@ class Column:
else:
raise TypeError("unexpected type: %s" % type(dataType))
- # TODO(SPARK-41329): solve the circular import between functions.py and
- # this class if we want to reuse functions.lit
- def _lit(self, x: Any) -> "Column":
- return Column(LiteralExpression(x))
-
def __repr__(self) -> str:
return "Column<'%s'>" % self._expr.__repr__()
diff --git a/python/pyspark/sql/connect/readwriter.py b/python/pyspark/sql/connect/readwriter.py
index 470417b6a28..778509bcf76 100644
--- a/python/pyspark/sql/connect/readwriter.py
+++ b/python/pyspark/sql/connect/readwriter.py
@@ -164,7 +164,6 @@ class DataFrameReader(OptionUtils):
return self._df(plan)
def _df(self, plan: LogicalPlan) -> "DataFrame":
- # The import is needed here to avoid circular import issues.
from pyspark.sql.connect.dataframe import DataFrame
return DataFrame.withPlan(plan, self._client)
---------------------------------------------------------------------
To unsubscribe, e-mail: commits-unsubscribe@spark.apache.org
For additional commands, e-mail: commits-help@spark.apache.org