def run(self,
test_runner_api=True,
runner=None,
options=None,
interactive=None):
"""Runs the pipeline. Returns whatever our runner returns after running.
If another runner instance and options are provided, that runner will
execute the pipeline with the given options. If either of them is not set,
a ValueError is raised. The usage is similar to directly invoking
`runner.run_pipeline(pipeline, options)`.
Additionally, an interactive field can be set to override the pipeline's
self.interactive field to mark current pipeline as being initiated from an
interactive environment.
"""
from apache_beam.runners.interactive import interactive_runner
if interactive:
self.interactive = interactive
elif isinstance(self.runner, interactive_runner.InteractiveRunner):
self.interactive = True
else:
self.interactive = False
runner_in_use = self.runner
options_in_use = self._options
if runner and options:
runner_in_use = runner
options_in_use = options
elif not runner and options:
raise ValueError(
'Parameter runner is not given when parameter options '
'is given.')
elif not options and runner:
raise ValueError(
'Parameter options is not given when parameter runner '
'is given.')
# When possible, invoke a round trip through the runner API.
if test_runner_api and self._verify_runner_api_compatible():
return Pipeline.from_runner_api(
self.to_runner_api(use_fake_coders=True), runner_in_use,
options_in_use).run(test_runner_api=False,
interactive=self.interactive)
if options_in_use.view_as(TypeOptions).runtime_type_check:
from apache_beam.typehints import typecheck
self.visit(typecheck.TypeCheckVisitor())
if options_in_use.view_as(SetupOptions).save_main_session:
# If this option is chosen, verify we can pickle the main session early.
tmpdir = tempfile.mkdtemp()
try:
pickler.dump_session(
os.path.join(tmpdir, 'main_session.pickle'))
finally:
shutil.rmtree(tmpdir)
return runner_in_use.run_pipeline(self, options_in_use)
def run(self, test_runner_api=True):
"""Runs the pipeline. Returns whatever our runner returns after running."""
# When possible, invoke a round trip through the runner API.
if test_runner_api and self._verify_runner_api_compatible():
return Pipeline.from_runner_api(
self.to_runner_api(), self.runner, self._options).run(False)
if self._options.view_as(TypeOptions).runtime_type_check:
from apache_beam.typehints import typecheck
self.visit(typecheck.TypeCheckVisitor())
if self._options.view_as(SetupOptions).save_main_session:
# If this option is chosen, verify we can pickle the main session early.
tmpdir = tempfile.mkdtemp()
try:
pickler.dump_session(os.path.join(tmpdir, 'main_session.pickle'))
finally:
shutil.rmtree(tmpdir)
return self.runner.run_pipeline(self)
