From 6591acdda8b09289fabfa913b2f6bb51642fd38f Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Wed, 21 Nov 2018 17:53:32 -0800 Subject: cherry-pick: correct HBase column filtering --- python/extraction_ungrobided.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/python/extraction_ungrobided.py b/python/extraction_ungrobided.py index af38cea..4b558dd 100755 --- a/python/extraction_ungrobided.py +++ b/python/extraction_ungrobided.py @@ -242,7 +242,7 @@ class MRExtractUnGrobided(MRJob): # Basically, don't overwrite backfill fields. grobid_status_code = info.get('grobid0:status_code', None) for k in list(info.keys()): - if k.encode('utf-8') in ('f:c', 'file:mime', 'file:cdx'): + if k in ('f:c', 'file:mime', 'file:cdx'): info.pop(k) # Convert fields to binary -- cgit v1.2.3