From 9514b6a3620a98e4fc069ca31b77eac6f9c98bec Mon Sep 17 00:00:00 2001
From: Bryan Newbold <bnewbold@archive.org>
Date: Mon, 20 Aug 2018 18:45:21 -0700
Subject: add dedicated job for counting GrobidMetadata column

---
 .../scala/sandcrawler/GrobidMetadataCountJob.scala | 36 ++++++++++++++++++++++
 1 file changed, 36 insertions(+)
 create mode 100644 scalding/src/main/scala/sandcrawler/GrobidMetadataCountJob.scala

(limited to 'scalding/src')

diff --git a/scalding/src/main/scala/sandcrawler/GrobidMetadataCountJob.scala b/scalding/src/main/scala/sandcrawler/GrobidMetadataCountJob.scala
new file mode 100644
index 0000000..08f3340
--- /dev/null
+++ b/scalding/src/main/scala/sandcrawler/GrobidMetadataCountJob.scala
@@ -0,0 +1,36 @@
+package sandcrawler
+
+import java.util.Properties
+
+import cascading.property.AppProps
+import cascading.tuple.Fields
+import com.twitter.scalding._
+import parallelai.spyglass.base.JobBase
+import parallelai.spyglass.hbase.HBaseConstants.SourceMode
+import parallelai.spyglass.hbase.HBasePipeConversions
+import parallelai.spyglass.hbase.HBaseSource
+
+class GrobidMetadataCountJob(args: Args) extends JobBase(args) with HBasePipeConversions {
+
+  val output = args("output")
+
+  GrobidMetadataCountJob.getHBaseSource(
+    args("hbase-table"),
+    args("zookeeper-hosts"))
+    .read
+    .debug
+    .groupAll { _.size('count) }
+    .write(Tsv(output))
+}
+
+object GrobidMetadataCountJob {
+
+  // eg, "wbgrp-journal-extract-0-qa",7 "mtrcs-zk1.us.archive.org:2181"
+  def getHBaseSource(hbaseTable: String, zookeeperHosts: String) : HBaseSource = {
+    HBaseBuilder.build(
+      hbaseTable,
+      zookeeperHosts,
+      List("grobid0:metadata"),
+      SourceMode.SCAN_ALL)
+  }
+}
-- 
cgit v1.2.3