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

Jump to bottom

Allow GCSTarget's as input and GCSFlagTarget's as output for Hadoop jobs #1664

Merged
merged 3 commits into from
May 11, 2016
Merged

Allow GCSTarget's as input and GCSFlagTarget's as output for Hadoop jobs #1664

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
2274d90
Allow GCSTarget()'s as Hadoop streaming input and output.
Apr 20, 2016
d9f20f0
Don't GCSFlagTarget doesn't support atomic move at end
Apr 21, 2016
60387b9
Merge remote-tracking branch 'spotify/master' into hadoop-gcs
Apr 21, 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
27 changes: 19 additions & 8 deletions luigi/contrib/hadoop.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,6 +49,7 @@
from luigi import configuration
import luigi
import luigi.task
import luigi.contrib.gcs
import luigi.contrib.hdfs
import luigi.s3
from luigi import mrrunner
Expand Down Expand Up @@ -456,9 +457,11 @@ def run_job(self, job, tracking_url_callback=None):
output_final = job.output().path
# atomic output: replace output with a temporary work directory
if self.end_job_with_atomic_move_dir:
if isinstance(job.output(), luigi.s3.S3FlagTarget):
illegal_targets = (
luigi.s3.S3FlagTarget, luigi.contrib.gcs.GCSFlagTarget)
if isinstance(job.output(), illegal_targets):
raise TypeError("end_job_with_atomic_move_dir is not supported"
" for S3FlagTarget")
" for {}".format(illegal_targets))
output_hadoop = '{output}-temp-{time}'.format(
output=output_final,
time=datetime.datetime.now().isoformat().replace(':', '-'))
Expand Down Expand Up @@ -521,15 +524,23 @@ def run_job(self, job, tracking_url_callback=None):
if self.input_format:
arglist += ['-inputformat', self.input_format]

allowed_input_targets = (
luigi.contrib.hdfs.HdfsTarget,
luigi.s3.S3Target,
luigi.contrib.gcs.GCSTarget)
for target in luigi.task.flatten(job.input_hadoop()):
if not isinstance(target, luigi.contrib.hdfs.HdfsTarget) \
and not isinstance(target, luigi.s3.S3Target):
raise TypeError('target must be an HdfsTarget or S3Target')
if not isinstance(target, allowed_input_targets):
raise TypeError('target must one of: {}'.format(
allowed_input_targets))
arglist += ['-input', target.path]

if not isinstance(job.output(), luigi.contrib.hdfs.HdfsTarget) \
and not isinstance(job.output(), luigi.s3.S3FlagTarget):
raise TypeError('output must be an HdfsTarget or S3FlagTarget')
allowed_output_targets = (
luigi.contrib.hdfs.HdfsTarget,
luigi.s3.S3FlagTarget,
luigi.contrib.gcs.GCSFlagTarget)
if not isinstance(job.output(), allowed_output_targets):
raise TypeError('output must be one of: {}'.format(
allowed_output_targets))
arglist += ['-output', output_hadoop]

# submit job
Expand Down