ESQL: Compute infrastruture for LEFT JOIN

x-pack/plugin/esql/compute/src/main/java/org/elasticsearch/compute/data/Block.java

@@ -212,10 +212,46 @@ default boolean mvSortedAscending() {
     /**
      * Expand multivalued fields into one row per value. Returns the same block if there aren't any multivalued
      * fields to expand. The returned block needs to be closed by the caller to release the block's resources.
-     * TODO: pass BlockFactory
      */
     Block expand();
 
+    /**
+     * Build a {@link Block} with a {@code null} inserted {@code before} each
+     * listed position.
+     * <p>
+     *     Note: {@code before} must be non-decreasing.
+     * </p>
+     */
+    default Block insertNulls(IntVector before) {
+        // TODO remove default and scatter to implementation where it can be a lot more efficient
+        int myCount = getPositionCount();
+        int beforeCount = before.getPositionCount();
+        try (Builder builder = elementType().newBlockBuilder(myCount + beforeCount, blockFactory())) {
+            int beforeP = 0;
+            int nextNull = before.getInt(beforeP);
+            for (int mainP = 0; mainP < myCount; mainP++) {
+                while (mainP == nextNull) {
+                    builder.appendNull();
+                    beforeP++;
+                    if (beforeP >= beforeCount) {
+                        builder.copyFrom(this, mainP, myCount);
+                        return builder.build();
+                    }
+                    nextNull = before.getInt(beforeP);
+                }
+                // This line right below this is the super inefficient one.
+                builder.copyFrom(this, mainP, mainP + 1);
+            }
+            assert nextNull == myCount;
+            while (beforeP < beforeCount) {
+                nextNull = before.getInt(beforeP++);
+                assert nextNull == myCount;
+                builder.appendNull();
+            }
+            return builder.build();
+        }
+    }
+
     /**
      * Builds {@link Block}s. Typically, you use one of it's direct supinterfaces like {@link IntBlock.Builder}.
      * This is {@link Releasable} and should be released after building the block or if building the block fails.

x-pack/plugin/esql/compute/src/main/java/org/elasticsearch/compute/data/X-ArrayBlock.java.st

@@ -149,7 +149,7 @@ $endif$
                 int valueCount = getValueCount(pos);
                 int first = getFirstValueIndex(pos);
                 if (valueCount == 1) {
-                    builder.append$Type$(get$Type$(getFirstValueIndex(pos)$if(BytesRef)$, scratch$endif$));
+                    builder.append$Type$(get$Type$(first$if(BytesRef)$, scratch$endif$));
                 } else {
                     builder.beginPositionEntry();
                     for (int c = 0; c < valueCount; c++) {

x-pack/plugin/esql/compute/src/main/java/org/elasticsearch/compute/operator/lookup/MergePositionsOperator.java

@@ -20,28 +20,32 @@
 import java.util.Objects;
 
 /**
- * Combines values at the given blocks with the same positions into a single position for the blocks at the given channels
+ * Combines values at the given blocks with the same positions into a single position
+ * for the blocks at the given channels.
+ * <p>
  * Example, input pages consisting of three blocks:
- * positions    | field-1 | field-2 |
- * -----------------------------------
+ * </p>
+ * <pre>{@code
+ * | positions    | field-1 | field-2 |
+ * ------------------------------------
  * Page 1:
- * 1           |  a,b    |   2020  |
- * 1           |  c      |   2021  |
- * ---------------------------------
+ * | 1            |  a,b    |   2020  |
+ * | 1            |  c      |   2021  |
  * Page 2:
- * 2           |  a,e    |   2021  |
- * ---------------------------------
+ * | 2            |  a,e    |   2021  |
  * Page 3:
- * 4           |  d      |   null  |
- * ---------------------------------
+ * | 4            |  d      |   null  |
+ * }</pre>
  * Output:
+ * <pre>{@code
  * |  field-1   | field-2    |
  * ---------------------------
  * |  null      | null       |
  * |  a,b,c     | 2020,2021  |
  * |  a,e       | 2021       |
  * |  null      | null       |
  * |  d         | 2023       |
+ * }</pre>
  */
 public final class MergePositionsOperator implements Operator {
     private boolean finished = false;