support MergeJoin nullable convertion (right side)

dbms/src/Columns/ColumnNullable.cpp

@@ -156,6 +156,18 @@ void ColumnNullable::insertFrom(const IColumn & src, size_t n)
     getNullMapData().push_back(src_concrete.getNullMapData()[n]);
 }
 
+void ColumnNullable::insertFromNotNullable(const IColumn & src, size_t n)
+{
+    getNestedColumn().insertFrom(src, n);
+    getNullMapData().push_back(0);
+}
+
+void ColumnNullable::insertRangeFromNotNullable(const IColumn & src, size_t start, size_t length)
+{
+    getNestedColumn().insertRangeFrom(src, start, length);
+    getNullMapData().resize_fill(getNullMapData().size() + length, 0);
+}
+
 void ColumnNullable::popBack(size_t n)
 {
     getNestedColumn().popBack(n);

dbms/src/Columns/ColumnNullable.h

@@ -61,6 +61,9 @@ public:
     void insert(const Field & x) override;
     void insertFrom(const IColumn & src, size_t n) override;
 
+    void insertFromNotNullable(const IColumn & src, size_t n);
+    void insertRangeFromNotNullable(const IColumn & src, size_t start, size_t length);
+
     void insertDefault() override
     {
         getNestedColumn().insertDefault();

dbms/src/Interpreters/MergeJoin.cpp

@@ -1,5 +1,6 @@
 #include <Core/NamesAndTypes.h>
 #include <Core/SortCursor.h>
+#include <Columns/ColumnNullable.h>
 #include <Interpreters/MergeJoin.h>
 #include <Interpreters/AnalyzedJoin.h>
 #include <Interpreters/sortBlock.h>
@@ -104,13 +105,16 @@ private:
 namespace
 {
 
-MutableColumns makeMutableColumns(const Block & block)
+MutableColumns makeMutableColumns(const Block & block, size_t rows_to_reserve = 0)
 {
     MutableColumns columns;
     columns.reserve(block.columns());
 
     for (const auto & src_column : block)
+    {
         columns.push_back(src_column.column->cloneEmpty());
+        columns.back()->reserve(rows_to_reserve);
+    }
     return columns;
 }
 
@@ -133,12 +137,8 @@ void copyLeftRange(const Block & block, MutableColumns & columns, size_t start,
 {
     for (size_t i = 0; i < block.columns(); ++i)
     {
-        const auto & src_column = block.getByPosition(i);
+        const auto & src_column = block.getByPosition(i).column;
-        auto & dst_column = columns[i];
+        columns[i]->insertRangeFrom(*src_column, start, rows_to_add);
-
-        size_t row_pos = start;
-        for (size_t row = 0; row < rows_to_add; ++row, ++row_pos)
-            dst_column->insertFrom(*src_column.column, row_pos);
     }
 }
 
@@ -147,11 +147,14 @@ void copyRightRange(const Block & right_block, const Block & right_columns_to_ad
 {
     for (size_t i = 0; i < right_columns_to_add.columns(); ++i)
     {
-        const auto & src_column = right_block.getByName(right_columns_to_add.getByPosition(i).name);
+        const auto & src_column = right_block.getByName(right_columns_to_add.getByPosition(i).name).column;
         auto & dst_column = columns[i];
+        auto * dst_nullable = typeid_cast<ColumnNullable *>(dst_column.get());
 
-        for (size_t row = 0; row < rows_to_add; ++row)
+        if (dst_nullable && !isColumnNullable(*src_column))
-            dst_column->insertFrom(*src_column.column, row_position);
+            dst_nullable->insertRangeFromNotNullable(*src_column, row_position, rows_to_add);
+        else
+            dst_column->insertRangeFrom(*src_column, row_position, rows_to_add);
     }
 }
 
@@ -270,8 +273,9 @@ void MergeJoin::joinBlock(Block & block)
 
     std::shared_lock lock(rwlock);
 
-    MutableColumns left_columns = makeMutableColumns(block);
+    size_t rows_to_reserve = is_left ? block.rows() : 0;
-    MutableColumns right_columns = makeMutableColumns(right_columns_to_add);
+    MutableColumns left_columns = makeMutableColumns(block, (is_all ? rows_to_reserve : 0));
+    MutableColumns right_columns = makeMutableColumns(right_columns_to_add, rows_to_reserve);
     MergeJoinCursor left_cursor(block, left_merge_description);
 
     if (is_left)

dbms/tests/queries/0_stateless/01010_partial_merge_join.reference

@@ -122,3 +122,97 @@ all inner
 2	20	2	22
 4	40	4	41
 4	40	4	42
+any left
+0	0	0
+1	10	\N
+2	20	2
+3	30	\N
+4	40	4
+-
+0	0	0
+1	10	\N
+2	20	\N
+3	30	\N
+4	40	\N
+-
+0	0	0
+1	10	\N
+2	20	2
+3	30	\N
+4	40	4
+-
+0	0	0
+1	10	\N
+2	20	\N
+3	30	\N
+4	40	\N
+all left
+0	0	0	0
+1	10	\N	\N
+2	20	2	21
+2	20	2	22
+3	30	\N	\N
+4	40	4	41
+4	40	4	42
+-
+0	0	0	0
+1	10	\N	\N
+2	20	\N	\N
+3	30	\N	\N
+4	40	\N	\N
+-
+0	0	0	0
+1	10	\N	\N
+2	20	\N	\N
+3	30	\N	\N
+4	40	\N	\N
+-
+0	0	0	0
+1	10	\N	\N
+2	20	2	21
+2	20	2	22
+3	30	\N	\N
+4	40	4	41
+4	40	4	42
+-
+0	0	0	0
+1	10	\N	\N
+2	20	2	21
+2	20	2	22
+3	30	\N	\N
+4	40	4	41
+4	40	4	42
+any inner
+0	0	0
+2	20	2
+4	40	4
+-
+0	0	0
+-
+0	0	0
+2	20	2
+4	40	4
+-
+0	0	0
+all inner
+0	0	0	0
+2	20	2	21
+2	20	2	22
+4	40	4	41
+4	40	4	42
+-
+0	0	0	0
+-
+0	0	0	0
+-
+0	0	0	0
+2	20	2	21
+2	20	2	22
+4	40	4	41
+4	40	4	42
+-
+0	0	0	0
+2	20	2	21
+2	20	2	22
+4	40	4	41
+4	40	4	42

dbms/tests/queries/0_stateless/01010_partial_merge_join.sql

@@ -117,7 +117,47 @@ SELECT t1.*, t2.* FROM t1 INNER JOIN t2 ON t1.x = t2.x AND toUInt32(intDiv(t1.y,
 SELECT '-';
 SELECT t1.*, t2.* FROM t1 INNER JOIN t2 ON t1.x = t2.x AND toUInt64(t1.x) = intDiv(t2.y,10) ORDER BY x, t2.y;
 
--- TODO: SET join_use_nulls = 1;
+SET join_use_nulls = 1;
+
+SELECT 'any left';
+SELECT t1.*, t2.x FROM t1 ANY LEFT JOIN t2 USING (x) ORDER BY x;
+SELECT '-';
+SELECT t1.*, t2.x FROM t1 ANY LEFT JOIN t2 USING (x,y) ORDER BY x;
+SELECT '-';
+SELECT t1.*, t2.x FROM t1 ANY LEFT JOIN t2 USING (x) ORDER BY x;
+SELECT '-';
+SELECT t1.*, t2.x FROM t1 ANY LEFT JOIN t2 USING (x,y) ORDER BY x;
+
+SELECT 'all left';
+SELECT t1.*, t2.* FROM t1 LEFT JOIN t2 ON t1.x = t2.x ORDER BY x, t2.y;
+SELECT '-';
+SELECT t1.*, t2.* FROM t1 LEFT JOIN t2 ON t1.y = t2.y ORDER BY x;
+SELECT '-';
+SELECT t1.*, t2.* FROM t1 LEFT JOIN t2 ON t1.x = t2.x AND t1.y = t2.y ORDER BY x;
+SELECT '-';
+SELECT t1.*, t2.* FROM t1 LEFT JOIN t2 ON t1.x = t2.x AND toUInt32(intDiv(t1.y,10)) = t2.x ORDER BY x, t2.y;
+SELECT '-';
+SELECT t1.*, t2.* FROM t1 LEFT JOIN t2 ON t1.x = t2.x AND toUInt64(t1.x) = intDiv(t2.y,10) ORDER BY x, t2.y;
+
+SELECT 'any inner';
+SELECT t1.*, t2.x FROM t1 ANY INNER JOIN t2 USING (x) ORDER BY x;
+SELECT '-';
+SELECT t1.*, t2.x FROM t1 ANY INNER JOIN t2 USING (x,y) ORDER BY x;
+SELECT '-';
+SELECT t1.*, t2.x FROM t1 ANY INNER JOIN t2 USING (x) ORDER BY x;
+SELECT '-';
+SELECT t1.*, t2.x FROM t1 ANY INNER JOIN t2 USING (x,y) ORDER BY x;
+
+SELECT 'all inner';
+SELECT t1.*, t2.* FROM t1 INNER JOIN t2 ON t1.x = t2.x ORDER BY x, t2.y;
+SELECT '-';
+SELECT t1.*, t2.* FROM t1 INNER JOIN t2 ON t1.y = t2.y ORDER BY x;
+SELECT '-';
+SELECT t1.*, t2.* FROM t1 INNER JOIN t2 ON t1.x = t2.x AND t1.y = t2.y ORDER BY x;
+SELECT '-';
+SELECT t1.*, t2.* FROM t1 INNER JOIN t2 ON t1.x = t2.x AND toUInt32(intDiv(t1.y,10)) = t2.x ORDER BY x, t2.y;
+SELECT '-';
+SELECT t1.*, t2.* FROM t1 INNER JOIN t2 ON t1.x = t2.x AND toUInt64(t1.x) = intDiv(t2.y,10) ORDER BY x, t2.y;
 
 DROP TABLE t0;
 DROP TABLE t1;