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

5 files changed, 39 insertions, 22 deletions

diff --git a/scalding/scalastyle-config.xml b/scalding/scalastyle-config.xml
index e2f58a0..adf9b0f 100644
--- a/scalding/scalastyle-config.xml
+++ b/scalding/scalastyle-config.xml
@@ -6,6 +6,13 @@
    <parameter name="maxFileLength"><![CDATA[800]]></parameter>
   </parameters>
  </check>
+<check enabled="true" class="org.scalastyle.file.IndentationChecker" level="warning">
+ <parameters>
+  <parameter name="tabSize">2</parameter>
+  <parameter name="methodParamIndentSize">2</parameter>
+  <parameter name="classParamIndentSize">4</parameter>
+ </parameters>
+</check>
  <check level="warning" class="org.scalastyle.file.HeaderMatchesChecker" enabled="false">
   <parameters>
    <parameter name="header"><![CDATA[// Copyright (C) 2011-2012 the original author or authors.
@@ -50,11 +57,6 @@
   </parameters>
  </check>
  <check level="warning" class="org.scalastyle.scalariform.EqualsHashCodeChecker" enabled="true"></check>
- <check level="warning" class="org.scalastyle.scalariform.IllegalImportsChecker" enabled="true">
-  <parameters>
-   <parameter name="illegalImports"><![CDATA[sun._,java.awt._]]></parameter>
-  </parameters>
- </check>
  <check level="warning" class="org.scalastyle.scalariform.ParameterNumberChecker" enabled="true">
   <parameters>
    <parameter name="maxParameters"><![CDATA[8]]></parameter>
@@ -124,5 +126,10 @@
    <parameter name="maxBlankLines">1</parameter>
    <parameter name="lexicographic">true</parameter>
   </parameters>
+</check>
+<check level="warning" class="org.scalastyle.scalariform.IllegalImportsChecker" enabled="true">
+  <parameters>
+   <parameter name="illegalImports"><![CDATA[sun._,java.awt._]]></parameter>
+  </parameters>
  </check>
 </scalastyle>
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 : _*)}))
   }
 
diff --git a/scalding/src/main/scala/sandcrawler/HBaseCountJob.scala b/scalding/src/main/scala/sandcrawler/HBaseCountJob.scala
index 22e4e86..b12e723 100644
--- a/scalding/src/main/scala/sandcrawler/HBaseCountJob.scala
+++ b/scalding/src/main/scala/sandcrawler/HBaseCountJob.scala
@@ -1,9 +1,10 @@
 package sandcrawler
 
+import java.util.Properties
+
 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.HBaseConstants.SourceMode
 import parallelai.spyglass.hbase.HBasePipeConversions
@@ -14,9 +15,10 @@ class HBaseCountJob(args: Args, colSpec: String) extends JobBase(args) with HBas
   HBaseBuilder.parseColSpec(colSpec)
   val Col: String = colSpec.split(":")(1)
 
-  HBaseCountJob.getHBaseSource(args("hbase-table"),
-                               args("zookeeper-hosts"),
-                               colSpec)
+  HBaseCountJob.getHBaseSource(
+    args("hbase-table"),
+    args("zookeeper-hosts"),
+    colSpec)
     .read
     .fromBytesWritable(Symbol(Col))
     .debug
diff --git a/scalding/src/main/scala/sandcrawler/HBaseRowCountJob.scala b/scalding/src/main/scala/sandcrawler/HBaseRowCountJob.scala
index 6def218..4c3de33 100644
--- a/scalding/src/main/scala/sandcrawler/HBaseRowCountJob.scala
+++ b/scalding/src/main/scala/sandcrawler/HBaseRowCountJob.scala
@@ -1,9 +1,10 @@
 package sandcrawler
 
+import java.util.Properties
+
 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.HBaseConstants.SourceMode
 import parallelai.spyglass.hbase.HBasePipeConversions
@@ -13,8 +14,9 @@ class HBaseRowCountJob(args: Args) extends JobBase(args) with HBasePipeConversio
 
   val output = args("output")
 
-  HBaseRowCountJob.getHBaseSource(args("hbase-table"),
-                                  args("zookeeper-hosts"))
+  HBaseRowCountJob.getHBaseSource(
+    args("hbase-table"),
+    args("zookeeper-hosts"))
     .read
     .debug
     .groupAll { _.size('count) }
@@ -31,5 +33,4 @@ object HBaseRowCountJob {
       List("file:size"),
       SourceMode.SCAN_ALL)
   }
-
 }
diff --git a/scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala b/scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala
index b1dab0e..fd0b4e2 100644
--- a/scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala
+++ b/scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala
@@ -1,18 +1,24 @@
 package sandcrawler
 
-import com.twitter.scalding.Args
+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 HBaseStatusCountJob(args: Args) extends JobBase(args) with HBasePipeConversions {
 
-  val source = HBaseCountJob.getHBaseSource(args("hbase-table"),
-                                            args("zookeeper-hosts"),
-                                            "grobid0:status_code")
+  val source = HBaseCountJob.getHBaseSource(
+    args("hbase-table"),
+    args("zookeeper-hosts"),
+    "grobid0:status_code")
 
   val statusPipe : TypedPipe[Long] = source
     .read