aboutsummaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2019-11-13 16:43:10 -0800
committerBryan Newbold <bnewbold@archive.org>2019-11-13 16:43:10 -0800
commit9db14e42137e06f41e7c895b097a247be2a5efb7 (patch)
treea5435c6505797d4049061396223d6d90cb3bdf8c
parente74bf1ea577c8d991eebf4174ae1a1932ad9992f (diff)
downloadsandcrawler-9db14e42137e06f41e7c895b097a247be2a5efb7.tar.gz
sandcrawler-9db14e42137e06f41e7c895b097a247be2a5efb7.zip
note that kafka_grobid.py is deprecated
-rwxr-xr-xpython/kafka_grobid.py3
1 files changed, 3 insertions, 0 deletions
diff --git a/python/kafka_grobid.py b/python/kafka_grobid.py
index cde7a2d..8d1bd2e 100755
--- a/python/kafka_grobid.py
+++ b/python/kafka_grobid.py
@@ -1,5 +1,8 @@
#!/usr/bin/env python3
"""
+DEPRECATED: this worker uses old kafka topics and an old schema. Use
+`sandcrawler_worker.py` instead.
+
Kafka worker that does GROBID extraction from one queue and into another.
Based on the ungrobided Hadoop job code. Does not talk to HBase at all, just