Skip to content
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

PySparkTask: handle special characters in name (#2778) #2779

Merged
merged 2 commits into from
Sep 20, 2019
Merged

PySparkTask: handle special characters in name (#2778) #2779

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
ea97908
PySparkTask: special characters in name (#2778)
mrk-its Sep 10, 2019
962c12c
rename name variable (address reviewer comment)
mrk-its Sep 10, 2019
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
6 changes: 4 additions & 2 deletions luigi/contrib/spark.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@

import logging
import os
import re
import sys
import tempfile
import shutil
Expand Down Expand Up @@ -298,8 +299,9 @@ def app_command(self):
return [self.app, pickle_loc] + self.app_options()

def run(self):
self.run_path = tempfile.mkdtemp(prefix=self.name)
self.run_pickle = os.path.join(self.run_path, '.'.join([self.name.replace(' ', '_'), 'pickle']))
path_name_fragment = re.sub(r'[^\w]', '_', self.name)
self.run_path = tempfile.mkdtemp(prefix=path_name_fragment)
self.run_pickle = os.path.join(self.run_path, '.'.join([path_name_fragment, 'pickle']))
with open(self.run_pickle, 'wb') as fd:
# Copy module file to run path.
module_path = os.path.abspath(inspect.getfile(self.__class__))
Expand Down
11 changes: 11 additions & 0 deletions test/contrib/spark_test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,6 +97,10 @@ def main(self, sc, *args):
sc.textFile(self.input().path).saveAsTextFile(self.output().path)


class MessyNamePySparkTask(TestPySparkTask):
name = 'AppName(a,b,c,1:2,3/4)'


@attr('apache')
class SparkSubmitTaskTest(unittest.TestCase):
ss = 'ss-stub'
Expand Down Expand Up @@ -289,3 +293,10 @@ def mock_spark_submit(task):

sc.textFile.assert_called_with('input')
sc.textFile.return_value.saveAsTextFile.assert_called_with('output')

@patch('luigi.contrib.external_program.subprocess.Popen')
def test_name_cleanup(self, proc):
setup_run_process(proc)
job = MessyNamePySparkTask()
job.run()
assert 'AppName_a_b_c_1_2_3_4_' in job.run_path