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

Add the archive parameters to HadoopJobRunner #1649

Merged
merged 2 commits into from
Apr 12, 2016
Merged

Add the archive parameters to HadoopJobRunner #1649

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0bc6ddf
Add the archive parameters to HadoopJobRunner
Apr 12, 2016
78f21bb
move archives paramter to the end. use instance variable directly.
Apr 12, 2016
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
7 changes: 6 additions & 1 deletion luigi/contrib/hadoop.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -401,14 +401,15 @@ class HadoopJobRunner(JobRunner):
def __init__(self, streaming_jar, modules=None, streaming_args=None,
libjars=None, libjars_in_hdfs=None, jobconfs=None,
input_format=None, output_format=None,
end_job_with_atomic_move_dir=True):
end_job_with_atomic_move_dir=True, archives=None):
def get(x, default):
return x is not None and x or default
self.streaming_jar = streaming_jar
self.modules = get(modules, [])
self.streaming_args = get(streaming_args, [])
self.libjars = get(libjars, [])
self.libjars_in_hdfs = get(libjars_in_hdfs, [])
self.archives = get(archives, [])
self.jobconfs = get(jobconfs, {})
self.input_format = input_format
self.output_format = output_format
Expand Down Expand Up @@ -478,6 +479,10 @@ def run_job(self, job, tracking_url_callback=None):
if libjars:
arglist += ['-libjars', ','.join(libjars)]

# 'archives' is also a generic option
if self.archives:
arglist += ['-archives', ','.join(self.archives)]

# Add static files and directories
extra_files = get_extra_files(job.extra_files())

Expand Down