aboutsummaryrefslogtreecommitdiffstats
path: root/pig
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2018-05-01 22:33:52 +0000
committerBryan Newbold <bnewbold@archive.org>2018-07-06 14:48:57 +0000
commitfde027fb269214a7e8f71f5717bcf569014b6661 (patch)
tree1cbbe97e681d3e0420b00a967b1cd89e380992c2 /pig
parent41c26d2b9ac215f2dacd15f6b7433b909cafb552 (diff)
downloadsandcrawler-fde027fb269214a7e8f71f5717bcf569014b6661.tar.gz
sandcrawler-fde027fb269214a7e8f71f5717bcf569014b6661.zip
possibly-broken version of hbase-count-rows.pig
This just worked a minute ago, but now throws: org.apache.hadoop.hbase.DoNotRetryIOException: java.lang.NoClassDefFoundError: org/apache/hadoop/hbase/util/ByteStringer
Diffstat (limited to 'pig')
-rw-r--r--pig/hbase-count-rows.pig13
1 files changed, 13 insertions, 0 deletions
diff --git a/pig/hbase-count-rows.pig b/pig/hbase-count-rows.pig
new file mode 100644
index 0000000..523beb2
--- /dev/null
+++ b/pig/hbase-count-rows.pig
@@ -0,0 +1,13 @@
+
+REGISTER /usr/lib/hbase/hbase-client-0.98.6-cdh5.3.1.jar
+REGISTER /usr/lib/hbase/hbase-common-0.98.6-cdh5.3.1.jar
+
+set hbase.zookeeper.quorum 'mtrcs-zk1.us.archive.org,mtrcs-zk2.us.archive.org,mtrcs-zk3.us.archive.org'
+
+data = LOAD 'hbase://wbgrp-journal-extract-0-qa'
+ USING org.apache.pig.backend.hadoop.hbase.HBaseStorage('grobid0:status_code', '-loadKey true')
+ AS (key:CHARARRAY, status:CHARARRAY);
+
+data_group = GROUP data ALL;
+data_count = FOREACH data_group GENERATE COUNT(data);
+DUMP data_count;