aboutsummaryrefslogtreecommitdiffstats
path: root/scalding/src/main/scala
diff options
context:
space:
mode:
authorbnewbold <bnewbold@archive.org>2018-06-07 20:02:42 +0000
committerbnewbold <bnewbold@archive.org>2018-06-07 20:02:42 +0000
commit410c48faf2099de74292e8583fcd2524d6fd1b7c (patch)
tree9684b67ee0b2ac8e7ca3a047fc8368477faf19f5 /scalding/src/main/scala
parent625ef34f957f7f5fdad99c6ce9d84cf7891fbdef (diff)
parent6eca6290aa3fc829f4767023ae075350a0a78192 (diff)
downloadsandcrawler-410c48faf2099de74292e8583fcd2524d6fd1b7c.tar.gz
sandcrawler-410c48faf2099de74292e8583fcd2524d6fd1b7c.zip
Merge branch 'groupby' into 'master'
Added HBaseMimeCount{Job,Test}, which counts the number of rows with each mimetype, as an example of groupby See merge request webgroup/sandcrawler!4
Diffstat (limited to 'scalding/src/main/scala')
-rw-r--r--scalding/src/main/scala/sandcrawler/HBaseMimeCountJob.scala28
-rw-r--r--scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala28
2 files changed, 56 insertions, 0 deletions
diff --git a/scalding/src/main/scala/sandcrawler/HBaseMimeCountJob.scala b/scalding/src/main/scala/sandcrawler/HBaseMimeCountJob.scala
new file mode 100644
index 0000000..819a652
--- /dev/null
+++ b/scalding/src/main/scala/sandcrawler/HBaseMimeCountJob.scala
@@ -0,0 +1,28 @@
+package sandcrawler
+
+import cascading.property.AppProps
+import cascading.tuple.Fields
+import com.twitter.scalding._
+import java.util.Properties
+import parallelai.spyglass.base.JobBase
+import parallelai.spyglass.hbase.{HBaseSource, HBasePipeConversions}
+import parallelai.spyglass.hbase.HBaseConstants.SourceMode
+
+class HBaseMimeCountJob(args: Args) extends JobBase(args) with HBasePipeConversions {
+ val output = args("output")
+
+ HBaseMimeCountJob.getHBaseSource
+ .read
+ .fromBytesWritable(List('mime))
+ .debug
+ .groupBy('mime){group => group.size('count)}
+ .write(Tsv(output))
+}
+
+object HBaseMimeCountJob {
+ def getHBaseSource = HBaseBuilder.build(
+ "wbgrp-journal-extract-0-qa", // HBase Table Name
+ "mtrcs-zk1.us.archive.org:2181", // HBase Zookeeper server (to get runtime config info; can be array?)
+ List("file:mime"),
+ SourceMode.SCAN_ALL)
+}
diff --git a/scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala b/scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala
new file mode 100644
index 0000000..0675efc
--- /dev/null
+++ b/scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala
@@ -0,0 +1,28 @@
+package sandcrawler
+
+import cascading.property.AppProps
+import cascading.tuple.Fields
+import com.twitter.scalding._
+import java.util.Properties
+import parallelai.spyglass.base.JobBase
+import parallelai.spyglass.hbase.{HBaseSource, HBasePipeConversions}
+import parallelai.spyglass.hbase.HBaseConstants.SourceMode
+
+class HBaseStatusCountJob(args: Args) extends JobBase(args) with HBasePipeConversions {
+ val output = args("output")
+
+ HBaseStatusCountJob.getHBaseSource
+ .read
+ .fromBytesWritable(List('status))
+// .debug
+ .groupBy('status){group => group.size('count)}
+ .write(Tsv(output))
+}
+
+object HBaseStatusCountJob {
+ def getHBaseSource = HBaseBuilder.build(
+ "wbgrp-journal-extract-0-qa", // HBase Table Name
+ "mtrcs-zk1.us.archive.org:2181", // HBase Zookeeper server (to get runtime config info; can be array?)
+ List("grobid0:status"),
+ SourceMode.SCAN_ALL)
+}