aboutsummaryrefslogtreecommitdiffstats
path: root/scalding/src/main/scala/sandcrawler/HBaseBuilder.scala
diff options
context:
space:
mode:
authorEllen Spertus <ellen.spertus@gmail.com>2018-07-19 15:21:33 -0700
committerEllen Spertus <ellen.spertus@gmail.com>2018-07-19 15:55:43 -0700
commitce5cbe4a581ae0a41e988dd3b396ee667b2e63ce (patch)
tree3d0ee185b19b785825350de9c371549919c02ab6 /scalding/src/main/scala/sandcrawler/HBaseBuilder.scala
parent2f39ba88482ba47a03fc52edcae891755ecb2b4d (diff)
downloadsandcrawler-ce5cbe4a581ae0a41e988dd3b396ee667b2e63ce.tar.gz
sandcrawler-ce5cbe4a581ae0a41e988dd3b396ee667b2e63ce.zip
Improved style and style checking.
- Excludes checking of files in /example directories. - Warns about block imports, which have been removed. - Checks indenting. Parameters should be indented 2 spaces. See https://docs.scala-lang.org/style/indentation.html#methods-with-numerous-arguments - Imports should be grouped (java.*, scala.*, other), with a blank line between groups
Diffstat (limited to 'scalding/src/main/scala/sandcrawler/HBaseBuilder.scala')
-rw-r--r--scalding/src/main/scala/sandcrawler/HBaseBuilder.scala11
1 files changed, 6 insertions, 5 deletions
diff --git a/scalding/src/main/scala/sandcrawler/HBaseBuilder.scala b/scalding/src/main/scala/sandcrawler/HBaseBuilder.scala
index fd04f2e..431860c 100644
--- a/scalding/src/main/scala/sandcrawler/HBaseBuilder.scala
+++ b/scalding/src/main/scala/sandcrawler/HBaseBuilder.scala
@@ -1,11 +1,12 @@
package sandcrawler
-import cascading.tuple.Fields
-import parallelai.spyglass.base.JobBase
+import scala._
+
import cascading.tap.SinkMode
+import cascading.tuple.Fields
import parallelai.spyglass.hbase.HBaseConstants.SourceMode
import parallelai.spyglass.hbase.HBaseSource
-import scala._
+import parallelai.spyglass.base.JobBase
object HBaseBuilder {
// map from column families to column names
@@ -41,8 +42,8 @@ object HBaseBuilder {
val groupMap: Map[String, List[String]] = colSpecs.groupBy(c => (c split ":")(0))
val families = groupMap.keys.toList
val groupedColNames : List[List[String]] = families map {fam => {
- val cols = {groupMap(fam).map(v => v.split(":")(1))}
- cols}}
+ val cols = {groupMap(fam).map(v => v.split(":")(1))}
+ cols}}
(families, groupedColNames.map({fields => new Fields(fields : _*)}))
}