This is an automated email from the ASF dual-hosted git repository.
shahar1 pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/airflow.git
The following commit(s) were added to refs/heads/main by this push:
new dbe4627b307 Fix template-field validation in PapermillOperator (#70435)
dbe4627b307 is described below
commit dbe4627b307e2463fff504d8701e925ca5dac5b9
Author: Bramhanand Lingala <[email protected]>
AuthorDate: Sun Jul 26 04:08:19 2026 -0400
Fix template-field validation in PapermillOperator (#70435)
---
.../src/airflow/providers/papermill/operators/papermill.py | 8 ++++----
.../tests/unit/papermill/operators/test_papermill.py | 13 ++++++++++---
scripts/ci/prek/validate_operators_init_exemptions.txt | 1 -
3 files changed, 14 insertions(+), 8 deletions(-)
diff --git
a/providers/papermill/src/airflow/providers/papermill/operators/papermill.py
b/providers/papermill/src/airflow/providers/papermill/operators/papermill.py
index f41240ab263..f0ce1607afd 100644
--- a/providers/papermill/src/airflow/providers/papermill/operators/papermill.py
+++ b/providers/papermill/src/airflow/providers/papermill/operators/papermill.py
@@ -89,12 +89,8 @@ class PapermillOperator(BaseOperator):
super().__init__(**kwargs)
self.parameters = parameters
- if not input_nb:
- raise ValueError("Input notebook is not specified")
self.input_nb = input_nb
- if not output_nb:
- raise ValueError("Output notebook is not specified")
self.output_nb = output_nb
self.kernel_name = kernel_name
@@ -105,6 +101,10 @@ class PapermillOperator(BaseOperator):
self.nbconvert_args = nbconvert_args
def execute(self, context: Context):
+ if not self.input_nb:
+ raise ValueError("Input notebook is not specified")
+ if not self.output_nb:
+ raise ValueError("Output notebook is not specified")
if not isinstance(self.input_nb, NoteBook):
self.input_nb = NoteBook(url=self.input_nb,
parameters=self.parameters)
if not isinstance(self.output_nb, NoteBook):
diff --git
a/providers/papermill/tests/unit/papermill/operators/test_papermill.py
b/providers/papermill/tests/unit/papermill/operators/test_papermill.py
index f911fb83658..b18c9e84023 100644
--- a/providers/papermill/tests/unit/papermill/operators/test_papermill.py
+++ b/providers/papermill/tests/unit/papermill/operators/test_papermill.py
@@ -42,13 +42,20 @@ class TestNoteBook:
class TestPapermillOperator:
"""Test PapermillOperator."""
+ def test_init_does_not_validate_notebooks(self):
+ """__init__ must not validate template fields; input_nb/output_nb are
rendered after construction."""
+ op = PapermillOperator(task_id="missing_input_nb", output_nb="foo-bar")
+ assert op.input_nb is None
+ op = PapermillOperator(task_id="missing_output_nb", input_nb="foo-bar")
+ assert op.output_nb is None
+
def test_mandatory_attributes(self):
- """Test missing Input or Output notebooks."""
+ """Test missing Input or Output notebooks are validated at execute()
time, after templating."""
with pytest.raises(ValueError, match="Input notebook is not
specified"):
- PapermillOperator(task_id="missing_input_nb", output_nb="foo-bar")
+ PapermillOperator(task_id="missing_input_nb",
output_nb="foo-bar").execute(context={})
with pytest.raises(ValueError, match="Output notebook is not
specified"):
- PapermillOperator(task_id="missing_input_nb", input_nb="foo-bar")
+ PapermillOperator(task_id="missing_output_nb",
input_nb="foo-bar").execute(context={})
@pytest.mark.parametrize(
("output_nb_url", "output_as_object"),
diff --git a/scripts/ci/prek/validate_operators_init_exemptions.txt
b/scripts/ci/prek/validate_operators_init_exemptions.txt
index abf5d8da246..dbe391c48fc 100644
--- a/scripts/ci/prek/validate_operators_init_exemptions.txt
+++ b/scripts/ci/prek/validate_operators_init_exemptions.txt
@@ -51,6 +51,5 @@
providers/microsoft/azure/src/airflow/providers/microsoft/azure/transfers/gcs_to
providers/microsoft/azure/src/airflow/providers/microsoft/azure/transfers/oracle_to_azure_data_lake.py::OracleToAzureDataLakeOperator
providers/microsoft/psrp/src/airflow/providers/microsoft/psrp/operators/psrp.py::PsrpOperator
providers/oracle/src/airflow/providers/oracle/transfers/oracle_to_oracle.py::OracleToOracleOperator
-providers/papermill/src/airflow/providers/papermill/operators/papermill.py::PapermillOperator
providers/standard/src/airflow/providers/standard/operators/bash.py::BashOperator
providers/standard/src/airflow/providers/standard/operators/trigger_dagrun.py::TriggerDagRunOperator
