Repository: flink
Updated Branches:
  refs/heads/master 273f54ba4 -> 9a2057310


[FLINK-3630] [docs] Little mistake in documentation

This closes #2254


Project: http://git-wip-us.apache.org/repos/asf/flink/repo
Commit: http://git-wip-us.apache.org/repos/asf/flink/commit/9a205731
Tree: http://git-wip-us.apache.org/repos/asf/flink/tree/9a205731
Diff: http://git-wip-us.apache.org/repos/asf/flink/diff/9a205731

Branch: refs/heads/master
Commit: 9a2057310eb22bae2601f2635b201e3a168a0feb
Parents: 273f54b
Author: Greg Hogan <[email protected]>
Authored: Thu Jul 14 14:42:55 2016 -0400
Committer: zentol <[email protected]>
Committed: Fri Jul 15 11:55:21 2016 +0200

----------------------------------------------------------------------
 docs/apis/batch/dataset_transformations.md | 112 +++++++++++++++++++-----
 1 file changed, 88 insertions(+), 24 deletions(-)
----------------------------------------------------------------------


http://git-wip-us.apache.org/repos/asf/flink/blob/9a205731/docs/apis/batch/dataset_transformations.md
----------------------------------------------------------------------
diff --git a/docs/apis/batch/dataset_transformations.md 
b/docs/apis/batch/dataset_transformations.md
index 8e65389..9be9bc0 100644
--- a/docs/apis/batch/dataset_transformations.md
+++ b/docs/apis/batch/dataset_transformations.md
@@ -247,6 +247,13 @@ DataSet<Tuple1<String>> ds2 = 
ds.<Tuple1<String>>project(0).distinct(0);
 ~~~
 
 </div>
+<div data-lang="scala" markdown="1">
+
+~~~scala
+Not supported.
+~~~
+
+</div>
 <div data-lang="python" markdown="1">
 
 ~~~python
@@ -777,11 +784,15 @@ DataSet<Tuple2<String, Integer>> combinedWords = input
   .combineGroup(new GroupCombineFunction<String, Tuple2<String, Integer>() {
 
     public void combine(Iterable<String> words, Collector<Tuple2<String, 
Integer>>) { // combine
+        String key = null;
         int count = 0;
+
         for (String word : words) {
+            key = word;
             count++;
         }
-        out.collect(new Tuple2(word, count));
+        // emit tuple with word and count
+        out.collect(new Tuple2(key, count));
     }
 });
 
@@ -790,11 +801,15 @@ DataSet<Tuple2<String, Integer>> output = combinedWords
   .reduceGroup(new GroupReduceFunction() { // group reduce with full data 
exchange
 
     public void reduce(Iterable<Tuple2<String, Integer>>, 
Collector<Tuple2<String, Integer>>) {
+        String key = null;
         int count = 0;
+
         for (Tuple2<String, Integer> word : words) {
+            key = word;
             count++;
         }
-        out.collect(new Tuple2(word, count));
+        // emit tuple with word and count
+        out.collect(new Tuple2(key, count));
     }
 });
 ~~~
@@ -809,27 +824,40 @@ val combinedWords: DataSet[(String, Int)] = input
   .groupBy(0)
   .combineGroup {
     (words, out: Collector[(String, Int)]) =>
+        var key: String = null
         var count = 0
+
         for (word <- words) {
-            count++
+            key = word
+            count += 1
         }
-        out.collect(word, count)
+        out.collect((key, count))
 }
 
 val output: DataSet[(String, Int)] = combinedWords
   .groupBy(0)
   .reduceGroup {
     (words, out: Collector[(String, Int)]) =>
-        var count = 0
-        for ((word, Int) <- words) {
-            count++
+        var key: String = null
+        var sum = 0
+
+        for ((word, sum) <- words) {
+            key = word
+            sum += count
         }
-        out.collect(word, count)
+        out.collect((key, sum))
 }
 
 ~~~
 
 </div>
+<div data-lang="python" markdown="1">
+
+~~~python
+Not supported.
+~~~
+
+</div>
 </div>
 
 The above alternative WordCount implementation demonstrates how the 
GroupCombine
@@ -1418,10 +1446,35 @@ DataSet<Tuple2<String, Double>>
             ratings.join(weights) // [...]
 ~~~
 
+</div>
+<div data-lang="scala" markdown="1">
+
+~~~scala
+case class Rating(name: String, category: String, points: Int)
+
+val ratings: DataSet[Ratings] = // [...]
+val weights: DataSet[(String, Double)] = // [...]
+
+val weightedRatings = ratings.join(weights).where("category").equalTo(0) {
+  (rating, weight, out: Collector[(String, Double)]) =>
+    if (weight._2 > 0.1) out.collect(rating.name, rating.points * weight._2)
+}
+
+~~~
+
+</div>
+<div data-lang="python" markdown="1">
+Not supported.
+</div>
+</div>
+
 #### Join with Projection (Java/Python Only)
 
 A Join transformation can construct result tuples using a projection as shown 
here:
 
+<div class="codetabs" markdown="1">
+<div data-lang="java" markdown="1">
+
 ~~~java
 DataSet<Tuple3<Integer, Byte, String>> input1 = // [...]
 DataSet<Tuple2<Integer, Double>> input2 = // [...]
@@ -1443,25 +1496,12 @@ The join projection works also for non-Tuple DataSets. 
In this case, `projectFir
 <div data-lang="scala" markdown="1">
 
 ~~~scala
-case class Rating(name: String, category: String, points: Int)
-
-val ratings: DataSet[Ratings] = // [...]
-val weights: DataSet[(String, Double)] = // [...]
-
-val weightedRatings = ratings.join(weights).where("category").equalTo(0) {
-  (rating, weight, out: Collector[(String, Double)]) =>
-    if (weight._2 > 0.1) out.collect(rating.name, rating.points * weight._2)
-}
-
+Not supported.
 ~~~
 
 </div>
 <div data-lang="python" markdown="1">
 
-#### Join with Projection (Java/Python Only)
-
-A Join transformation can construct result tuples using a projection as shown 
here:
-
 ~~~python
  result = input1.join(input2).where(0).equal_to(0) \
   .project_first(0,2).project_second(1).project_first(1);
@@ -1709,6 +1749,23 @@ DataSet<Tuple2<String, Integer>>
             movies.leftOuterJoin(ratings) // [...]
 ~~~
 
+</div>
+<div data-lang="scala" markdown="1">
+
+~~~scala
+Not supported.
+~~~
+
+</div>
+<div data-lang="python" markdown="1">
+
+~~~python
+Not supported.
+~~~
+
+</div>
+</div>
+
 #### Join Algorithm Hints
 
 The Flink runtime can execute outer joins in various ways. Each possible way 
outperforms the others under
@@ -2200,7 +2257,7 @@ DataSet<Tuple2<String, Integer>> in = // [...]
 // in descending order on the first String field.
 // Apply a MapPartition transformation on the sorted partitions.
 DataSet<Tuple2<String, String>> out = in.sortPartition(1, Order.ASCENDING)
-                                          .sortPartition(0, Order.DESCENDING)
+                                        .sortPartition(0, Order.DESCENDING)
                                         .mapPartition(new PartitionMapper());
 ~~~
 
@@ -2213,11 +2270,18 @@ val in: DataSet[(String, Int)] = // [...]
 // in descending order on the first String field.
 // Apply a MapPartition transformation on the sorted partitions.
 val out = in.sortPartition(1, Order.ASCENDING)
-              .sortPartition(0, Order.DESCENDING)
+            .sortPartition(0, Order.DESCENDING)
             .mapPartition { ... }
 ~~~
 
 </div>
+<div data-lang="python" markdown="1">
+
+~~~python
+Not supported.
+~~~
+
+</div>
 </div>
 
 ### First-n

Reply via email to