update test

apache · Mar 24, 2015 · 9651aec · 9651aec
1 parent f96526d
commit 9651aec
Show file tree

Hide file tree

Showing 3 changed files with 13 additions and 13 deletions.
diff --git a/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala b/mllib/src/main/scala/org/apache/spark/ml/feature/Tokenizer.scala
@@ -68,8 +68,8 @@ class RegexTokenizer extends UnaryTransformer[String, Seq[String], RegexTokenize
    * param sets regex as splitting on gaps (true) or matching tokens (false)
    * @group param
    */
-  val gaps: BooleanParam = new BooleanParam(this, "gaps", 
-    "Set regex to match gaps or tokens", Some(false))
+  val gaps: BooleanParam = new BooleanParam(
+    this, "gaps", "Set regex to match gaps or tokens", Some(false))
 
   /** @group setParam */
   def setGaps(value: Boolean): this.type = set(gaps, value)

diff --git a/mllib/src/test/java/org/apache/spark/ml/feature/JavaTokenizerSuite.java b/mllib/src/test/java/org/apache/spark/ml/feature/JavaTokenizerSuite.java
@@ -54,11 +54,11 @@ public void regexTokenizer() {
 			.setGaps(true)
       .setMinTokenLength(3);
 
-		JavaRDD<TextData> rdd = jsc.parallelize(Lists.newArrayList(
-			new TextData("Test of tok.", new String[] {"Test", "tok."}),
-			new TextData("Te,st.  punct", new String[] {"Te,st.", "punct"})
+		JavaRDD<TokenizerTestData> rdd = jsc.parallelize(Lists.newArrayList(
+			new TokenizerTestData("Test of tok.", new String[] {"Test", "tok."}),
+			new TokenizerTestData("Te,st.  punct", new String[] {"Te,st.", "punct"})
 		));
-    DataFrame dataset = jsql.createDataFrame(rdd, TextData.class);
+    DataFrame dataset = jsql.createDataFrame(rdd, TokenizerTestData.class);
 
 		Row[] pairs = myRegExTokenizer.transform(dataset)
 			.select("tokens","wantedTokens")

diff --git a/mllib/src/test/scala/org/apache/spark/ml/feature/TokenizerSuite.scala b/mllib/src/test/scala/org/apache/spark/ml/feature/TokenizerSuite.scala
@@ -25,7 +25,7 @@ import org.apache.spark.mllib.util.MLlibTestSparkContext
 import org.apache.spark.sql.{DataFrame, Row, SQLContext}
 
 @BeanInfo
-case class TextData(rawText: String, wantedTokens: Seq[String]) {
+case class TokenizerTestData(rawText: String, wantedTokens: Seq[String]) {
   /** Constructor used in [[org.apache.spark.ml.feature.JavaTokenizerSuite]] */
   def this(rawText: String, wantedTokens: Array[String]) = this(rawText, wantedTokens.toSeq)
 }
@@ -46,14 +46,14 @@ class RegexTokenizerSuite extends FunSuite with MLlibTestSparkContext {
       .setOutputCol("tokens")
 
     val dataset0 = sqlContext.createDataFrame(Seq(
-      TextData("Test for tokenization.", Seq("Test", "for", "tokenization", ".")),
-      TextData("Te,st. punct", Seq("Te", ",", "st", ".", "punct"))
+      TokenizerTestData("Test for tokenization.", Seq("Test", "for", "tokenization", ".")),
+      TokenizerTestData("Te,st. punct", Seq("Te", ",", "st", ".", "punct"))
     ))
     testRegexTokenizer(tokenizer, dataset0)
 
     val dataset1 = sqlContext.createDataFrame(Seq(
-      TextData("Test for tokenization.", Seq("Test", "for", "tokenization")),
-      TextData("Te,st. punct", Seq("punct"))
+      TokenizerTestData("Test for tokenization.", Seq("Test", "for", "tokenization")),
+      TokenizerTestData("Te,st. punct", Seq("punct"))
     ))
 
     tokenizer.setMinTokenLength(3)
@@ -64,8 +64,8 @@ class RegexTokenizerSuite extends FunSuite with MLlibTestSparkContext {
       .setGaps(true)
       .setMinTokenLength(0)
     val dataset2 = sqlContext.createDataFrame(Seq(
-      TextData("Test for tokenization.", Seq("Test", "for", "tokenization.")),
-      TextData("Te,st.  punct", Seq("Te,st.", "", "punct"))
+      TokenizerTestData("Test for tokenization.", Seq("Test", "for", "tokenization.")),
+      TokenizerTestData("Te,st.  punct", Seq("Te,st.", "", "punct"))
     ))
     testRegexTokenizer(tokenizer, dataset2)
   }