Merge pull request #40754 from CurtizJ/fix-fuzzer-with-object

Avoid logical errors in some common operations with `ColumnObject`

src/Columns/ColumnObject.cpp

@@ -12,6 +12,7 @@
 #include <Interpreters/castColumn.h>
 #include <Interpreters/convertFieldToType.h>
 #include <Common/HashTable/HashSet.h>
+#include <Processors/Transforms/ColumnGathererTransform.h>
 
 namespace DB
 {
@@ -823,6 +824,44 @@ MutableColumnPtr ColumnObject::cloneResized(size_t new_size) const
     return applyForSubcolumns([&](const auto & subcolumn) { return subcolumn.cloneResized(new_size); });
 }
 
+void ColumnObject::getPermutation(PermutationSortDirection, PermutationSortStability, size_t, int, Permutation & res) const
+{
+    res.resize(num_rows);
+    std::iota(res.begin(), res.end(), 0);
+}
+
+void ColumnObject::compareColumn(const IColumn & rhs, size_t rhs_row_num,
+                                 PaddedPODArray<UInt64> * row_indexes, PaddedPODArray<Int8> & compare_results,
+                                 int direction, int nan_direction_hint) const
+{
+    return doCompareColumn<ColumnObject>(assert_cast<const ColumnObject &>(rhs), rhs_row_num, row_indexes,
+                                        compare_results, direction, nan_direction_hint);
+}
+
+void ColumnObject::getExtremes(Field & min, Field & max) const
+{
+    if (num_rows == 0)
+    {
+        min = Object();
+        max = Object();
+    }
+    else
+    {
+        get(0, min);
+        get(0, max);
+    }
+}
+
+MutableColumns ColumnObject::scatter(ColumnIndex num_columns, const Selector & selector) const
+{
+    return scatterImpl<ColumnObject>(num_columns, selector);
+}
+
+void ColumnObject::gather(ColumnGathererStream & gatherer)
+{
+    gatherer.gather(*this);
+}
+
 const ColumnObject::Subcolumn & ColumnObject::getSubcolumn(const PathInData & key) const
 {
     if (const auto * node = subcolumns.findLeaf(key))

src/Columns/ColumnObject.h

@@ -15,7 +15,7 @@ namespace DB
 
 namespace ErrorCodes
 {
-    extern const int LOGICAL_ERROR;
+    extern const int NOT_IMPLEMENTED;
 }
 
 /// Info that represents a scalar or array field in a decomposed view.
@@ -224,6 +224,19 @@ public:
     ColumnPtr replicate(const Offsets & offsets) const override;
     MutableColumnPtr cloneResized(size_t new_size) const override;
 
+    /// Order of rows in ColumnObject is undefined.
+    void getPermutation(PermutationSortDirection, PermutationSortStability, size_t, int, Permutation & res) const override;
+    void compareColumn(const IColumn & rhs, size_t rhs_row_num,
+                       PaddedPODArray<UInt64> * row_indexes, PaddedPODArray<Int8> & compare_results,
+                       int direction, int nan_direction_hint) const override;
+
+    void updatePermutation(PermutationSortDirection, PermutationSortStability, size_t, int, Permutation &, EqualRanges &) const override {}
+    int compareAt(size_t, size_t, const IColumn &, int) const override { return 0; }
+    void getExtremes(Field & min, Field & max) const override;
+
+    MutableColumns scatter(ColumnIndex num_columns, const Selector & selector) const override;
+    void gather(ColumnGathererStream & gatherer) override;
+
     /// All other methods throw exception.
 
     StringRef getDataAt(size_t) const override { throwMustBeConcrete(); }
@@ -236,14 +249,7 @@ public:
     void updateWeakHash32(WeakHash32 &) const override { throwMustBeConcrete(); }
     void updateHashFast(SipHash &) const override { throwMustBeConcrete(); }
     void expand(const Filter &, bool) override { throwMustBeConcrete(); }
-    int compareAt(size_t, size_t, const IColumn &, int) const override { throwMustBeConcrete(); }
-    void compareColumn(const IColumn &, size_t, PaddedPODArray<UInt64> *, PaddedPODArray<Int8> &, int, int) const override { throwMustBeConcrete(); }
     bool hasEqualValues() const override { throwMustBeConcrete(); }
-    void getPermutation(PermutationSortDirection, PermutationSortStability, size_t, int, Permutation &) const override { throwMustBeConcrete(); }
-    void updatePermutation(PermutationSortDirection, PermutationSortStability, size_t, int, Permutation &, EqualRanges &) const override { throwMustBeConcrete(); }
-    MutableColumns scatter(ColumnIndex, const Selector &) const override { throwMustBeConcrete(); }
-    void gather(ColumnGathererStream &) override { throwMustBeConcrete(); }
-    void getExtremes(Field &, Field &) const override { throwMustBeConcrete(); }
     size_t byteSizeAt(size_t) const override { throwMustBeConcrete(); }
     double getRatioOfDefaultRows(double) const override { throwMustBeConcrete(); }
     void getIndicesOfNonDefaultRows(Offsets &, size_t, size_t) const override { throwMustBeConcrete(); }
@@ -251,7 +257,7 @@ public:
 private:
     [[noreturn]] static void throwMustBeConcrete()
     {
-        throw Exception("ColumnObject must be converted to ColumnTuple before use", ErrorCodes::LOGICAL_ERROR);
+        throw Exception("ColumnObject must be converted to ColumnTuple before use", ErrorCodes::NOT_IMPLEMENTED);
     }
 
     template <typename Func>

src/DataTypes/Serializations/SerializationObject.cpp

@@ -260,7 +260,12 @@ void SerializationObject<Parser>::serializeBinaryBulkWithMultipleStreams(
     auto * state_object = checkAndGetState<SerializeStateObject>(state);
 
     if (!column_object.isFinalized())
-        throw Exception(ErrorCodes::LOGICAL_ERROR, "Cannot write non-finalized ColumnObject");
+    {
+        auto finalized_object = column_object.clone();
+        assert_cast<ColumnObject &>(*finalized_object).finalize();
+        serializeBinaryBulkWithMultipleStreams(*finalized_object, offset, limit, settings, state);
+        return;
+    }
 
     auto [tuple_column, tuple_type] = unflattenObjectToTuple(column_object);
 

tests/queries/0_stateless/01825_type_json_order_by.reference

@@ -0,0 +1,6 @@
+0
+0
+{"k":"v"}
+
+{"k":"v"}
+{"k":"v"}

tests/queries/0_stateless/01825_type_json_order_by.sql

@@ -0,0 +1,5 @@
+-- Tags: no-fasttest
+
+SELECT dummy FROM system.one ORDER BY materialize('{"k":"v"}'::JSON);
+SELECT dummy FROM system.one ORDER BY materialize('{"k":"v"}'::JSON), dummy;
+SELECT materialize('{"k":"v"}'::JSON) SETTINGS extremes = 1;