Copy data only when necessary

funes · funes · commit 64e719843929 · 2014-05-06T17:26:15.000+08:00
diff --git a/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala b/mllib/src/main/scala/org/apache/spark/mllib/linalg/Vectors.scala
@@ -136,7 +136,12 @@ object Vectors {
           new DenseVector(v.toArray)  // Can't use underlying array directly, so make a new one
         }
       case v: BSV[Double] =>
-        new SparseVector(v.length, v.index.slice(0, v.used), v.data.slice(0, v.used))
+        if (v.index.length == v.used) {
+          new SparseVector(v.length, v.index, v.data)
+        }
+        else {
+          new SparseVector(v.length, v.index.slice(0, v.used), v.data.slice(0, v.used))
+        }
       case v: BV[_] =>
         sys.error("Unsupported Breeze vector type: " + v.getClass.getName)
     }

Original file line number	Diff line number	Diff line change
`@@ -136,7 +136,12 @@ object Vectors {`
`136`	`136`	`new DenseVector(v.toArray) // Can't use underlying array directly, so make a new one`
`137`	`137`	`}`
`138`	`138`	`case v: BSV[Double] =>`
`139`		`- new SparseVector(v.length, v.index.slice(0, v.used), v.data.slice(0, v.used))`
	`139`	`+ if (v.index.length == v.used) {`
	`140`	`+ new SparseVector(v.length, v.index, v.data)`
	`141`	`+ }`
	`142`	`+ else {`
	`143`	`+ new SparseVector(v.length, v.index.slice(0, v.used), v.data.slice(0, v.used))`
	`144`	`+ }`
`140`	`145`	`case v: BV[_] =>`
`141`	`146`	`sys.error("Unsupported Breeze vector type: " + v.getClass.getName)`
`142`	`147`	`}`