aboutsummaryrefslogtreecommitdiffstats
path: root/scalding
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 15:21:33 -0700
commit3c2488978562b34cf60e51546cc71b0cbfbe5eaf (patch)
tree6a2c4d88fd910f040248058667c06ab4b57e1ec6 /scalding
parenta02a10d98759015ee200a456ad13b6143cd7fde6 (diff)
downloadsandcrawler-3c2488978562b34cf60e51546cc71b0cbfbe5eaf.tar.gz
sandcrawler-3c2488978562b34cf60e51546cc71b0cbfbe5eaf.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')
-rw-r--r--scalding/build.sbt6
-rw-r--r--scalding/scalastyle-config.xml26
-rw-r--r--scalding/src/main/scala/sandcrawler/HBaseBuilder.scala4
-rw-r--r--scalding/src/main/scala/sandcrawler/HBaseCountJob.scala13
-rw-r--r--scalding/src/main/scala/sandcrawler/HBaseRowCountJob.scala12
-rw-r--r--scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala18
6 files changed, 54 insertions, 25 deletions
diff --git a/scalding/build.sbt b/scalding/build.sbt
index f333111..ba2a825 100644
--- a/scalding/build.sbt
+++ b/scalding/build.sbt
@@ -13,6 +13,12 @@ lazy val root = (project in file(".")).
test in assembly := {},
)),
+ (scalastyleSources in Compile) := {
+ // all .scala files in "src/main/scala"
+ val scalaSourceFiles = ((scalaSource in Compile).value ** "*.scala").get
+ val dirNameToExclude = "/example/"
+ scalaSourceFiles.filterNot(_.getAbsolutePath.contains(dirNameToExclude))
+ },
name := "sandcrawler",
resolvers += "conjars.org" at "http://conjars.org/repo",
diff --git a/scalding/scalastyle-config.xml b/scalding/scalastyle-config.xml
index 2f20677..23ec993 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>
@@ -114,4 +116,18 @@
<check level="warning" class="org.scalastyle.scalariform.PublicMethodsHaveTypeChecker" enabled="true"></check>
<check level="warning" class="org.scalastyle.file.NewLineAtEofChecker" enabled="true"></check>
<check level="warning" class="org.scalastyle.file.NoNewLineAtEofChecker" enabled="false"></check>
+ <check enabled="true" class="org.scalastyle.scalariform.BlockImportChecker" level="warning"/>
+ <check enabled="true" class="org.scalastyle.scalariform.ImportOrderChecker" level="warning">
+ <parameters>
+ <parameter name="groups">java,scala,others</parameter>
+ <parameter name="group.java">javax?\..+</parameter>
+ <parameter name="group.scala">scala\..+</parameter>
+ <parameter name="group.others">.+</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 b271def..b4ade24 100644
--- a/scalding/src/main/scala/sandcrawler/HBaseBuilder.scala
+++ b/scalding/src/main/scala/sandcrawler/HBaseBuilder.scala
@@ -39,8 +39,8 @@ 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 1ebc261..b12e723 100644
--- a/scalding/src/main/scala/sandcrawler/HBaseCountJob.scala
+++ b/scalding/src/main/scala/sandcrawler/HBaseCountJob.scala
@@ -1,21 +1,24 @@
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.{HBaseSource, HBasePipeConversions}
import parallelai.spyglass.hbase.HBaseConstants.SourceMode
+import parallelai.spyglass.hbase.HBasePipeConversions
+import parallelai.spyglass.hbase.HBaseSource
class HBaseCountJob(args: Args, colSpec: String) extends JobBase(args) with HBasePipeConversions {
val output = args("output")
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 ba3b9cd..4c3de33 100644
--- a/scalding/src/main/scala/sandcrawler/HBaseRowCountJob.scala
+++ b/scalding/src/main/scala/sandcrawler/HBaseRowCountJob.scala
@@ -1,19 +1,22 @@
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.{HBaseSource, HBasePipeConversions}
import parallelai.spyglass.hbase.HBaseConstants.SourceMode
+import parallelai.spyglass.hbase.HBasePipeConversions
+import parallelai.spyglass.hbase.HBaseSource
class HBaseRowCountJob(args: Args) extends JobBase(args) with HBasePipeConversions {
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) }
@@ -30,5 +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 375d155..befb037 100644
--- a/scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala
+++ b/scalding/src/main/scala/sandcrawler/HBaseStatusCountJob.scala
@@ -1,16 +1,17 @@
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 java.util.Properties
-import parallelai.spyglass.base.JobBase
+import org.apache.hadoop.hbase.io.ImmutableBytesWritable
import org.apache.hadoop.hbase.util.Bytes
-import parallelai.spyglass.hbase.{HBaseSource, HBasePipeConversions}
+import parallelai.spyglass.base.JobBase
+import parallelai.spyglass.hbase.BasePipeConversions
import parallelai.spyglass.hbase.HBaseConstants.SourceMode
-import com.twitter.scalding.Args
-import org.apache.hadoop.hbase.io.ImmutableBytesWritable
+import parallelai.spyglass.hbase.HBaseSource
class HBaseStatusCountJob(args: Args) extends JobBase(args) with HBasePipeConversions {
@@ -19,9 +20,10 @@ class HBaseStatusCountJob(args: Args) extends JobBase(args) with HBasePipeConver
HBaseBuilder.parseColSpec(colSpec)
val Col: String = colSpec.split(":")(1)
- val source : TypedPipe[Long] = HBaseCountJob.getHBaseSource(args("hbase-table"),
- args("zookeeper-hosts"),
- colSpec)
+ val source : TypedPipe[Long] = HBaseCountJob.getHBaseSource(
+ args("hbase-table"),
+ args("zookeeper-hosts"),
+ colSpec)
.read
.toTypedPipe[(ImmutableBytesWritable,ImmutableBytesWritable)]('key, 'status_code)
.map { case (key, raw_code) => Bytes.toLong(raw_code.copyBytes()) }