distinction between status_code and status counting

2 files changed, 36 insertions, 4 deletions

diff --git a/scalding/src/main/scala/sandcrawler/HBaseStatusCodeCountJob.scala b/scalding/src/main/scala/sandcrawler/HBaseStatusCodeCountJob.scala
new file mode 100644
index 0000000..4d9880f
--- /dev/null
+++ b/scalding/src/main/scala/sandcrawler/HBaseStatusCodeCountJob.scala
@@ -0,0 +1,32 @@
+package sandcrawler
+
+import java.util.Properties
+
+import cascading.property.AppProps
+import cascading.tuple.Fields
+import com.twitter.scalding._
+import com.twitter.scalding.typed.TDsl._
+import org.apache.hadoop.hbase.io.ImmutableBytesWritable
+import org.apache.hadoop.hbase.util.Bytes
+import parallelai.spyglass.base.JobBase
+import parallelai.spyglass.hbase.HBaseConstants.SourceMode
+import parallelai.spyglass.hbase.HBasePipeConversions
+import parallelai.spyglass.hbase.HBaseSource
+
+class HBaseStatusCodeCountJob(args: Args) extends JobBase(args) with HBasePipeConversions {
+
+  val source = HBaseCountJob.getHBaseSource(
+    args("hbase-table"),
+    args("zookeeper-hosts"),
+    "grobid0:status_code")
+
+  val statusPipe : TypedPipe[Long] = source
+    .read
+    .toTypedPipe[(ImmutableBytesWritable,ImmutableBytesWritable)]('key, 'status_code)
+    .map { case (key, raw_code) => Bytes.toLong(raw_code.copyBytes()) }
+
+  statusPipe.groupBy { identity }
+    .size
+    .debug
+    .write(TypedTsv[(Long,Long)](args("output")))
+}
diff --git a/scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala b/scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala
index fd0b4e2..1635e03 100644
--- a/scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala
+++ b/scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala
@@ -18,15 +18,15 @@ class HBaseStatusCountJob(args: Args) extends JobBase(args) with HBasePipeConver
   val source = HBaseCountJob.getHBaseSource(
     args("hbase-table"),
     args("zookeeper-hosts"),
-    "grobid0:status_code")
+    "grobid0:status")
 
   val statusPipe : TypedPipe[Long] = source
     .read
-    .toTypedPipe[(ImmutableBytesWritable,ImmutableBytesWritable)]('key, 'status_code)
-    .map { case (key, raw_code) => Bytes.toLong(raw_code.copyBytes()) }
+    .toTypedPipe[(ImmutableBytesWritable,ImmutableBytesWritable)]('key, 'status)
+    .map { case (key, raw_status) => Bytes.toString(raw_code.copyBytes()) }
 
   statusPipe.groupBy { identity }
     .size
     .debug
-    .write(TypedTsv[(Long,Long)](args("output")))
+    .write(TypedTsv[(Long,String)](args("output")))
 }