From 573fab9526b6720498f7ad060365bfca9afb6680 Mon Sep 17 00:00:00 2001
From: denon1 <gardnerjens@gmail.com>
Date: Sat, 1 Apr 2023 01:52:22 +0200
Subject: [PATCH 1/3] Change Refactor inverted if and changed for comprehension
 to a foldRight with a match on the result

---
 .../scalding/KnownForSources.scala            | 46 +++++++++----------
 1 file changed, 22 insertions(+), 24 deletions(-)

diff --git a/src/scala/com/twitter/simclusters_v2/scalding/KnownForSources.scala b/src/scala/com/twitter/simclusters_v2/scalding/KnownForSources.scala
index 217f521ac..f59968e78 100644
--- a/src/scala/com/twitter/simclusters_v2/scalding/KnownForSources.scala
+++ b/src/scala/com/twitter/simclusters_v2/scalding/KnownForSources.scala
@@ -102,31 +102,29 @@ object KnownForSources {
     TypedPipe
       .from(TextLine(textFile))
       .flatMap { str =>
-        if (!str.startsWith("#")) {
-          try {
-            val tokens = str.trim.split("\\s+")
-            val res = Array.newBuilder[(Int, Float)]
-            val userId = tokens(0).toLong
-            for (i <- 1 until tokens.length) {
-              val Array(cIdStr, scoreStr) = tokens(i).split(":")
-              val clusterId = cIdStr.toInt
-              val score = scoreStr.toFloat
-              val newEntry = (clusterId, score)
-              res += newEntry
-            }
-            val result = res.result
-            if (result.nonEmpty) {
-              Some((userId, res.result()))
-            } else None
-          } catch {
-            case ex: Throwable =>
-              log.warning(
-                s"Error while loading knownFor from $textFile for line <$str>: " +
-                  ex.getMessage
-              )
-              None
+        if (str.startsWith("#")) {none}
+        try {
+          val tokens = str.trim.split("\\s+")
+          val userId = tokens(0).toLong
+          (1 until tokens.length).foldRight(Array.newBuilder[(Int, Float)])((i, r) => {
+            val Array(cIdStr, scoreStr) = tokens(i).split(":")
+            val clusterId = cIdStr.toInt
+            val score = scoreStr.toFloat
+            val newEntry = (clusterId, score)
+            r += newEntry
+          }).result() match {
+            case (res) if res.nonEmpty =>  Some((userId, res.result()))
+              _ => none
           }
-        } else None
+        }
+        catch {
+          case ex: Throwable =>
+            log.warning(
+              s"Error while loading knownFor from $textFile for line <$str>: " +
+                ex.getMessage
+            )
+            None
+        }
       }
   }
 

From 376f35f08f8ee3d2020007380dc04ca30506bc9f Mon Sep 17 00:00:00 2001
From: denon1 <gardnerjens@gmail.com>
Date: Sat, 1 Apr 2023 02:04:07 +0200
Subject: [PATCH 2/3] Change if refactored to match

---
 .../scalding/KnownForSources.scala            | 44 ++++++++++---------
 1 file changed, 23 insertions(+), 21 deletions(-)

diff --git a/src/scala/com/twitter/simclusters_v2/scalding/KnownForSources.scala b/src/scala/com/twitter/simclusters_v2/scalding/KnownForSources.scala
index f59968e78..577faf763 100644
--- a/src/scala/com/twitter/simclusters_v2/scalding/KnownForSources.scala
+++ b/src/scala/com/twitter/simclusters_v2/scalding/KnownForSources.scala
@@ -102,28 +102,30 @@ object KnownForSources {
     TypedPipe
       .from(TextLine(textFile))
       .flatMap { str =>
-        if (str.startsWith("#")) {none}
-        try {
-          val tokens = str.trim.split("\\s+")
-          val userId = tokens(0).toLong
-          (1 until tokens.length).foldRight(Array.newBuilder[(Int, Float)])((i, r) => {
-            val Array(cIdStr, scoreStr) = tokens(i).split(":")
-            val clusterId = cIdStr.toInt
-            val score = scoreStr.toFloat
-            val newEntry = (clusterId, score)
-            r += newEntry
-          }).result() match {
-            case (res) if res.nonEmpty =>  Some((userId, res.result()))
-              _ => none
+        str match {
+          case s"#$_" => none
+          case _ => try {
+            val tokens = str.trim.split("\\s+")
+            val userId = tokens(0).toLong
+            (1 until tokens.length).foldRight(Array.newBuilder[(Int, Float)])((i, r) => {
+              val Array(cIdStr, scoreStr) = tokens(i).split(":")
+              val clusterId = cIdStr.toInt
+              val score = scoreStr.toFloat
+              val newEntry = (clusterId, score)
+              r += newEntry
+            }).result() match {
+              case (res) if res.nonEmpty => Some((userId, res.result()))
+                _ => none
+            }
+          }
+          catch {
+            case ex: Throwable =>
+              log.warning(
+                s"Error while loading knownFor from $textFile for line <$str>: " +
+                  ex.getMessage
+              )
+              None
           }
-        }
-        catch {
-          case ex: Throwable =>
-            log.warning(
-              s"Error while loading knownFor from $textFile for line <$str>: " +
-                ex.getMessage
-            )
-            None
         }
       }
   }

From 645342ba2f4f6dff9b5e69cc5881a97e3b8957b4 Mon Sep 17 00:00:00 2001
From: denon1 <gardnerjens@gmail.com>
Date: Sat, 1 Apr 2023 02:07:36 +0200
Subject: [PATCH 3/3] Fix none was Lowercase fixed for right Option Type

---
 .../com/twitter/simclusters_v2/scalding/KnownForSources.scala | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/src/scala/com/twitter/simclusters_v2/scalding/KnownForSources.scala b/src/scala/com/twitter/simclusters_v2/scalding/KnownForSources.scala
index 577faf763..5f96df6a5 100644
--- a/src/scala/com/twitter/simclusters_v2/scalding/KnownForSources.scala
+++ b/src/scala/com/twitter/simclusters_v2/scalding/KnownForSources.scala
@@ -103,7 +103,7 @@ object KnownForSources {
       .from(TextLine(textFile))
       .flatMap { str =>
         str match {
-          case s"#$_" => none
+          case s"#$_" => None
           case _ => try {
             val tokens = str.trim.split("\\s+")
             val userId = tokens(0).toLong
@@ -115,7 +115,7 @@ object KnownForSources {
               r += newEntry
             }).result() match {
               case (res) if res.nonEmpty => Some((userId, res.result()))
-                _ => none
+                _ => None
             }
           }
           catch {