aboutsummaryrefslogtreecommitdiffstats
path: root/scalding/src/main/scala
diff options
context:
space:
mode:
authorBryan Newbold <bnewbold@archive.org>2018-08-20 18:56:38 -0700
committerBryan Newbold <bnewbold@archive.org>2018-08-21 21:25:56 -0700
commitcce6047bdcf979729ec286d4c1f37676aeff2707 (patch)
treef6774d360ad1767ddd1afc11e788b52b699eb75c /scalding/src/main/scala
parent9d9ff332fbbaf5194047bbd056d624a5e999b8c7 (diff)
downloadsandcrawler-cce6047bdcf979729ec286d4c1f37676aeff2707.tar.gz
sandcrawler-cce6047bdcf979729ec286d4c1f37676aeff2707.zip
fix bugs/typos in HBaseColCountJob and HBaseStatusCountJob
Diffstat (limited to 'scalding/src/main/scala')
-rw-r--r--scalding/src/main/scala/sandcrawler/HBaseColCountJob.scala2
-rw-r--r--scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala6
2 files changed, 4 insertions, 4 deletions
diff --git a/scalding/src/main/scala/sandcrawler/HBaseColCountJob.scala b/scalding/src/main/scala/sandcrawler/HBaseColCountJob.scala
index a007339..20cc7a1 100644
--- a/scalding/src/main/scala/sandcrawler/HBaseColCountJob.scala
+++ b/scalding/src/main/scala/sandcrawler/HBaseColCountJob.scala
@@ -17,7 +17,7 @@ class HBaseColCountJob(args: Args) extends JobBase(args) with HBasePipeConversio
HBaseColCountJob.getHBaseSource(
args("hbase-table"),
args("zookeeper-hosts"),
- args("column")
+ args("column"))
.read
.debug
.groupAll { _.size('count) }
diff --git a/scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala b/scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala
index 1635e03..f79d672 100644
--- a/scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala
+++ b/scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala
@@ -20,13 +20,13 @@ class HBaseStatusCountJob(args: Args) extends JobBase(args) with HBasePipeConver
args("zookeeper-hosts"),
"grobid0:status")
- val statusPipe : TypedPipe[Long] = source
+ val statusPipe : TypedPipe[String] = source
.read
.toTypedPipe[(ImmutableBytesWritable,ImmutableBytesWritable)]('key, 'status)
- .map { case (key, raw_status) => Bytes.toString(raw_code.copyBytes()) }
+ .map { case (key, raw_status) => Bytes.toString(raw_status.copyBytes()) }
statusPipe.groupBy { identity }
.size
.debug
- .write(TypedTsv[(Long,String)](args("output")))
+ .write(TypedTsv[(String,Long)](args("output")))
}