From fde027fb269214a7e8f71f5717bcf569014b6661 Mon Sep 17 00:00:00 2001 From: Bryan Newbold Date: Tue, 1 May 2018 22:33:52 +0000 Subject: 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 --- pig/hbase-count-rows.pig | 13 +++++++++++++ 1 file changed, 13 insertions(+) create mode 100644 pig/hbase-count-rows.pig (limited to 'pig') 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; -- cgit v1.2.3