aboutsummaryrefslogtreecommitdiffstats
path: root/mapreduce
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2018-04-11 05:19:32 +0000
committerBryan Newbold <bnewbold@archive.org>2018-04-11 05:19:34 +0000
commitbe1704a419a1e916bb0055e2b40d2db026976001 (patch)
tree49f805c3089574c05abea4c54f847e0a69231a04 /mapreduce
parent5c93b9a69cf9c01dbc88cc4f42f86dff732300e4 (diff)
downloadsandcrawler-be1704a419a1e916bb0055e2b40d2db026976001.tar.gz
sandcrawler-be1704a419a1e916bb0055e2b40d2db026976001.zip
revert PYTHONPATH in cmdenv
Seemed to break hadoop jobs for some reason
Diffstat (limited to 'mapreduce')
-rw-r--r--mapreduce/mrjob.conf3
1 files changed, 2 insertions, 1 deletions
diff --git a/mapreduce/mrjob.conf b/mapreduce/mrjob.conf
index 8bf1cdd..fc8e427 100644
--- a/mapreduce/mrjob.conf
+++ b/mapreduce/mrjob.conf
@@ -4,6 +4,7 @@ runners:
upload_files:
- common.py
- grobid2json.py
+ setup:
+ - export PYTHONPATH=$PYTHONPATH:venv/lib/python3.5/site-packages/
cmdenv:
- PYTHONPATH: venv/lib/python3.5/site-packages/
SENTRY_DSN: https://63e8a85bbb8948ea9652ee280aa4dee0:f1639d58707c48a0bbc6a14623ba6a47@sentry.io/1186924