This is an automated email from the ASF dual-hosted git repository.
zhengruifeng 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 6df95d33fbcc [SPARK-58135][PYTHON] Consolidate VALUE_NOT_TRUE into
VALUE_NOT_ALLOWED
6df95d33fbcc is described below
commit 6df95d33fbcc045c31f1d5d641c76d90f38ca6fe
Author: Ruifeng Zheng <[email protected]>
AuthorDate: Wed Jul 15 16:27:11 2026 +0800
[SPARK-58135][PYTHON] Consolidate VALUE_NOT_TRUE into VALUE_NOT_ALLOWED
### What changes were proposed in this pull request?
Consolidate the specialized PySpark `VALUE_NOT_TRUE` error condition into
`VALUE_NOT_ALLOWED`. Classic and Spark Connect streaming
`DataStreamWriter.trigger` now report the generic condition when `once` or
`availableNow` is not `True`. The shared streaming tests assert the new
condition in both modes.
### Why are the changes needed?
`VALUE_NOT_TRUE` only represents a single allowed argument value and
duplicates the generic allowed-values condition. Removing it reduces narrowly
scoped error conditions and aligns the validation with other PySpark APIs.
### Does this PR introduce _any_ user-facing change?
Yes. Invalid `trigger(once=...)` and `trigger(availableNow=...)` calls now
use `VALUE_NOT_ALLOWED` and its generic message. The exception type remains
`PySparkValueError`.
### How was this patch tested?
Added shared classic and Spark Connect test assertions. The focused PySpark
test suite was not run. The JSON error-condition file was parsed successfully
and no `VALUE_NOT_TRUE` references remain.
### Was this patch authored or co-authored using generative AI tooling?
Generated-by: Codex (GPT-5)
Closes #57268 from zhengruifeng/consolidate-value-not-true-dev4.
Authored-by: Ruifeng Zheng <[email protected]>
Signed-off-by: Ruifeng Zheng <[email protected]>
---
python/pyspark/errors/error-conditions.json | 5 -----
python/pyspark/sql/connect/streaming/readwriter.py | 8 ++++----
python/pyspark/sql/streaming/readwriter.py | 8 ++++----
python/pyspark/sql/tests/streaming/test_streaming.py | 9 +++++++++
4 files changed, 17 insertions(+), 13 deletions(-)
diff --git a/python/pyspark/errors/error-conditions.json
b/python/pyspark/errors/error-conditions.json
index 56a8144b9fae..6c7612da286d 100644
--- a/python/pyspark/errors/error-conditions.json
+++ b/python/pyspark/errors/error-conditions.json
@@ -1223,11 +1223,6 @@
"Value for `<arg_name>` must be positive, got '<arg_value>'."
]
},
- "VALUE_NOT_TRUE": {
- "message": [
- "Value for `<arg_name>` must be True, got '<arg_value>'."
- ]
- },
"VALUE_OUT_OF_BOUNDS": {
"message": [
"Value for `<arg_name>` must be between <lower_bound> and <upper_bound>
(inclusive), got <actual>"
diff --git a/python/pyspark/sql/connect/streaming/readwriter.py
b/python/pyspark/sql/connect/streaming/readwriter.py
index 969fdc322a0b..130844309ae4 100644
--- a/python/pyspark/sql/connect/streaming/readwriter.py
+++ b/python/pyspark/sql/connect/streaming/readwriter.py
@@ -600,8 +600,8 @@ class DataStreamWriter:
elif once is not None:
if once is not True:
raise PySparkValueError(
- errorClass="VALUE_NOT_TRUE",
- messageParameters={"arg_name": "once", "arg_value":
str(once)},
+ errorClass="VALUE_NOT_ALLOWED",
+ messageParameters={"arg_name": "once", "allowed_values":
"[True]"},
)
self._write_proto.once = True
@@ -624,8 +624,8 @@ class DataStreamWriter:
else:
if availableNow is not True:
raise PySparkValueError(
- errorClass="VALUE_NOT_TRUE",
- messageParameters={"arg_name": "availableNow",
"arg_value": str(availableNow)},
+ errorClass="VALUE_NOT_ALLOWED",
+ messageParameters={"arg_name": "availableNow",
"allowed_values": "[True]"},
)
self._write_proto.available_now = True
diff --git a/python/pyspark/sql/streaming/readwriter.py
b/python/pyspark/sql/streaming/readwriter.py
index 5a99f8fce297..6b7faa622207 100644
--- a/python/pyspark/sql/streaming/readwriter.py
+++ b/python/pyspark/sql/streaming/readwriter.py
@@ -1448,8 +1448,8 @@ class DataStreamWriter:
elif once is not None:
if once is not True:
raise PySparkValueError(
- errorClass="VALUE_NOT_TRUE",
- messageParameters={"arg_name": "once", "arg_value":
str(once)},
+ errorClass="VALUE_NOT_ALLOWED",
+ messageParameters={"arg_name": "once", "allowed_values":
"[True]"},
)
jTrigger = getattr(
@@ -1479,8 +1479,8 @@ class DataStreamWriter:
else:
if availableNow is not True:
raise PySparkValueError(
- errorClass="VALUE_NOT_TRUE",
- messageParameters={"arg_name": "availableNow",
"arg_value": str(availableNow)},
+ errorClass="VALUE_NOT_ALLOWED",
+ messageParameters={"arg_name": "availableNow",
"allowed_values": "[True]"},
)
jTrigger = getattr(
self._spark._sc._jvm, "org.apache.spark.sql.streaming.Trigger"
diff --git a/python/pyspark/sql/tests/streaming/test_streaming.py
b/python/pyspark/sql/tests/streaming/test_streaming.py
index 5954501cd4f9..0ca6f6b4bb4f 100644
--- a/python/pyspark/sql/tests/streaming/test_streaming.py
+++ b/python/pyspark/sql/tests/streaming/test_streaming.py
@@ -147,6 +147,15 @@ class StreamingTestsMixin:
except TypeError:
pass
+ for arg_name in ("once", "availableNow"):
+ with self.assertRaises(PySparkValueError) as pe:
+ df.writeStream.trigger(**{arg_name: False})
+ self.check_error(
+ exception=pe.exception,
+ errorClass="VALUE_NOT_ALLOWED",
+ messageParameters={"arg_name": arg_name, "allowed_values":
"[True]"},
+ )
+
def test_stream_real_time_trigger(self):
df =
self.spark.readStream.format("text").load("python/test_support/sql/streaming")
tmpPath = tempfile.mkdtemp()
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
