Low cardinality cases moved to the function for its corresponding type

src/Functions/FunctionsJSON.cpp

@@ -23,6 +23,7 @@
 #include <DataTypes/Serializations/SerializationDecimal.h>
 #include <DataTypes/DataTypesNumber.h>
 #include <DataTypes/DataTypeLowCardinality.h>
+#include <DataTypes/DataTypeFixedString.h>
 #include <DataTypes/DataTypeString.h>
 #include <DataTypes/DataTypesDecimal.h>
 #include <DataTypes/DataTypeUUID.h>
@@ -694,9 +695,15 @@ public:
         }
         else
             return false;
-
+ 
-        auto & col_vec = assert_cast<ColumnVector<NumberType> &>(dest);
+        if (dest.getDataType() == TypeIndex::LowCardinality) {
-        col_vec.insertValue(value);
+            ColumnLowCardinality & col_low = assert_cast<ColumnLowCardinality &>(dest);
+            col_low.insertData(reinterpret_cast<const char * >(&value), sizeof(value));
+        }
+        else {
+            auto & col_vec = assert_cast<ColumnVector<NumberType> &>(dest);
+            col_vec.insertValue(value);
+        }
         return true;
     }
 };
@@ -773,8 +780,15 @@ public:
             return JSONExtractRawImpl<JSONParser>::insertResultToColumn(dest, element, {});
 
         auto str = element.getString();
-        ColumnString & col_str = assert_cast<ColumnString &>(dest);
+
-        col_str.insertData(str.data(), str.size());
+        if (dest.getDataType() == TypeIndex::LowCardinality) {
+            ColumnLowCardinality & col_low = assert_cast<ColumnLowCardinality &>(dest);
+            col_low.insertData(str.data(), str.size());
+        }
+        else {
+            ColumnString & col_str = assert_cast<ColumnString &>(dest);
+            col_str.insertData(str.data(), str.size());
+        }
         return true;
     }
 };
@@ -803,25 +817,26 @@ struct JSONExtractTree
         }
     };
 
-    class LowCardinalityNode : public Node
+    class LowCardinalityFixedStringNode : public Node
     {
     public:
-        LowCardinalityNode(DataTypePtr dictionary_type_, std::unique_ptr<Node> impl_)
+        LowCardinalityFixedStringNode(const size_t fixed_length_)
-            : dictionary_type(dictionary_type_), impl(std::move(impl_)) {}
+            : fixed_length(fixed_length_) {}
         bool insertResultToColumn(IColumn & dest, const Element & element) override
         {
-            auto from_col = dictionary_type->createColumn();
+            auto str = element.getString();
-            if (impl->insertResultToColumn(*from_col, element))
+            
-            {
+            if (str.size() > fixed_length)
-                std::string_view value = from_col->getDataAt(0).toView();
+                return false;
-                assert_cast<ColumnLowCardinality &>(dest).insertData(value.data(), value.size());
+
-                return true;
+            auto padded_str = str.data() + std::string(fixed_length - std::min(fixed_length, str.length()), '\0');
-            }
+
-            return false;
+            assert_cast<ColumnLowCardinality &>(dest).insertData(padded_str.data(), padded_str.size());
+            return true;
+
         }
     private:
-        DataTypePtr dictionary_type;
+        const size_t fixed_length;
-        std::unique_ptr<Node> impl;
     };
 
     class UUIDNode : public Node
@@ -833,7 +848,13 @@ struct JSONExtractTree
                 return false;
 
             auto uuid = parseFromString<UUID>(element.getString());
-            assert_cast<ColumnUUID &>(dest).insert(uuid);
+            if (dest.getDataType() == TypeIndex::LowCardinality) {
+                ColumnLowCardinality & col_low = assert_cast<ColumnLowCardinality &>(dest);
+                col_low.insertData(reinterpret_cast<const char * >(&uuid), sizeof(uuid));
+            }
+            else {
+                assert_cast<ColumnUUID &>(dest).insert(uuid);
+            }
             return true;
         }
     };
@@ -873,11 +894,12 @@ struct JSONExtractTree
         {
             if (!element.isString())
                 return false;
-            auto & col_str = assert_cast<ColumnFixedString &>(dest);
             auto str = element.getString();
+            auto & col_str = assert_cast<ColumnFixedString &>(dest);
             if (str.size() > col_str.getN())
                 return false;
             col_str.insertData(str.data(), str.size());
+            
             return true;
         }
     };
@@ -1101,7 +1123,13 @@ struct JSONExtractTree
             {
                 auto dictionary_type = typeid_cast<const DataTypeLowCardinality *>(type.get())->getDictionaryType();
                 auto impl = build(function_name, dictionary_type);
-                return std::make_unique<LowCardinalityNode>(dictionary_type, std::move(impl));
+
+                if ((*dictionary_type).getTypeId() == TypeIndex::FixedString) {
+                    auto fixed_length = typeid_cast<const DataTypeFixedString *>(dictionary_type.get())->getN();
+                    return std::make_unique<LowCardinalityFixedStringNode>(fixed_length); 
+                }
+                else
+                    return impl; 
             }
             case TypeIndex::Decimal256: return std::make_unique<DecimalNode<Decimal256>>(type);
             case TypeIndex::Decimal128: return std::make_unique<DecimalNode<Decimal128>>(type);

tests/performance/low_cardinality_from_json.xml

@@ -0,0 +1,73 @@
+<test>
+
+    <substitutions>
+        <substitution>
+            <name>string_json</name>
+            <values>
+                <value>'{"a": "hi", "b": "hello", "c": "hola", "d": "see you, bye, bye"}'</value>
+            </values>
+        </substitution>
+        <substitution>
+            <name>int_json</name>
+            <values>
+                <value>'{"a": 11, "b": 2222, "c": 33333333, "d": 4444444444444444}'</value>
+            </values>
+        </substitution>
+        <substitution>
+            <name>uuid_json</name>
+            <values>
+                <value>'{"a": "2d49dc6e-ddce-4cd0-afb8-790956df54c4", "b": "2d49dc6e-ddce-4cd0-afb8-790956df54c3", "c": "2d49dc6e-ddce-4cd0-afb8-790956df54c1", "d": "2d49dc6e-ddce-4cd0-afb8-790956df54c1"}'</value>
+            </values>
+        </substitution>
+        <substitution>
+            <name>low_cardinality_tuple_string</name>
+            <values>
+                <value>'Tuple(a LowCardinality(String), b LowCardinality(String), c LowCardinality(String), d LowCardinality(String) )'</value>
+            </values>
+        </substitution>
+        <substitution>
+            <name>low_cardinality_tuple_fixed_string</name>
+            <values>
+                <value>'Tuple(a LowCardinality(FixedString(20)), b LowCardinality(FixedString(20)), c LowCardinality(FixedString(20)), d LowCardinality(FixedString(20)) )'</value>
+            </values>
+        </substitution>
+        <substitution>
+            <name>low_cardinality_tuple_int8</name>
+            <values>
+                <value>'Tuple(a LowCardinality(Int8), b LowCardinality(Int8), c LowCardinality(Int8), d LowCardinality(Int8) )'</value>
+            </values>
+        </substitution>
+        <substitution>
+            <name>low_cardinality_tuple_int16</name>
+            <values>
+                <value>'Tuple(a LowCardinality(Int16), b LowCardinality(Int16), c LowCardinality(Int16), d LowCardinality(Int16) )'</value>
+            </values>
+        </substitution>
+        <substitution>
+            <name>low_cardinality_tuple_int32</name>
+            <values>
+                <value>'Tuple(a LowCardinality(Int32), b LowCardinality(Int32), c LowCardinality(Int32), d LowCardinality(Int32) )'</value>
+            </values>
+        </substitution>
+        <substitution>
+            <name>low_cardinality_tuple_int64</name>
+            <values>
+                <value>'Tuple(a LowCardinality(Int64), b LowCardinality(Int64), c LowCardinality(Int64), d LowCardinality(Int64) )'</value>
+            </values>
+        </substitution>
+        <substitution>
+            <name>low_cardinality_tuple_uuid</name>
+            <values>
+                <value>'Tuple(a LowCardinality(UUID), b LowCardinality(UUID), c LowCardinality(UUID), d LowCardinality(UUID) )'</value>
+            </values>
+        </substitution>
+    </substitutions>
+
+    <query>SELECT 'fixed_string_json' FROM zeros(500000) WHERE NOT ignore(JSONExtract(materialize({string_json}), {low_cardinality_tuple_fixed_string})) FORMAT Null </query>
+    <query>SELECT 'string_json' FROM zeros(500000) WHERE NOT ignore(JSONExtract(materialize({string_json}), {low_cardinality_tuple_string})) FORMAT Null </query>
+    <query>SELECT 'int8_json' FROM zeros(500000) WHERE NOT ignore(JSONExtract(materialize({int_json}), {low_cardinality_tuple_int8})) FORMAT Null </query>
+    <query>SELECT 'int16_json' FROM zeros(500000) WHERE NOT ignore(JSONExtract(materialize({int_json}), {low_cardinality_tuple_int16})) FORMAT Null </query>
+    <query>SELECT 'int32_json' FROM zeros(500000) WHERE NOT ignore(JSONExtract(materialize({int_json}), {low_cardinality_tuple_int32})) FORMAT Null </query>
+    <query>SELECT 'int64_json' FROM zeros(500000) WHERE NOT ignore(JSONExtract(materialize({int_json}), {low_cardinality_tuple_int64})) FORMAT Null </query>
+    <query>SELECT 'uuid_json' FROM zeros(500000) WHERE NOT ignore(JSONExtract(materialize({uuid_json}), {low_cardinality_tuple_uuid})) FORMAT Null </query>
+</test>

tests/queries/0_stateless/02452_check_low_cardinality.reference

@@ -0,0 +1,7 @@
+('hi','hello','hola','see you, bye, bye')
+('hi\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0','hello\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0','hola\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0','see you, bye, bye\0\0\0')
+(11,0,0,0)
+(11,2222,0,0)
+(11,2222,33333333,0)
+(11,2222,33333333,4444444444444444)
+('2d49dc6e-ddce-4cd0-afb8-790956df54c4','2d49dc6e-ddce-4cd0-afb8-790956df54c3','2d49dc6e-ddce-4cd0-afb8-790956df54c1','2d49dc6e-ddce-4cd0-afb8-790956df54c1')

tests/queries/0_stateless/02452_check_low_cardinality.sql

@@ -0,0 +1,61 @@
+DROP TABLE IF EXISTS test_low_cardinality_string;
+DROP TABLE IF EXISTS test_low_cardinality_uuid;
+DROP TABLE IF EXISTS test_low_cardinality_int;
+CREATE TABLE test_low_cardinality_string (data String) ENGINE MergeTree ORDER BY data;
+CREATE TABLE test_low_cardinality_uuid (data String) ENGINE MergeTree ORDER BY data;
+CREATE TABLE test_low_cardinality_int (data String) ENGINE MergeTree ORDER BY data;
+INSERT INTO test_low_cardinality_string (data) VALUES ('{"a": "hi", "b": "hello", "c": "hola", "d": "see you, bye, bye"}');
+INSERT INTO test_low_cardinality_int (data) VALUES ('{"a": 11, "b": 2222, "c": 33333333, "d": 4444444444444444}');
+INSERT INTO test_low_cardinality_uuid (data) VALUES ('{"a": "2d49dc6e-ddce-4cd0-afb8-790956df54c4", "b": "2d49dc6e-ddce-4cd0-afb8-790956df54c3", "c": "2d49dc6e-ddce-4cd0-afb8-790956df54c1", "d": "2d49dc6e-ddce-4cd0-afb8-790956df54c1"}');
+SELECT JSONExtract(data, 'Tuple(
+                            a LowCardinality(String),
+                            b LowCardinality(String),
+                            c LowCardinality(String),
+                            d LowCardinality(String)
+                            
+                            )') AS json FROM test_low_cardinality_string;
+SELECT JSONExtract(data, 'Tuple(
+                            a LowCardinality(FixedString(20)),
+                            b LowCardinality(FixedString(20)),
+                            c LowCardinality(FixedString(20)),
+                            d LowCardinality(FixedString(20))
+                            
+                            )') AS json FROM test_low_cardinality_string;
+SELECT JSONExtract(data, 'Tuple(
+                            a LowCardinality(Int8),
+                            b LowCardinality(Int8),
+                            c LowCardinality(Int8),
+                            d LowCardinality(Int8)
+                            
+                            )') AS json FROM test_low_cardinality_int;
+SELECT JSONExtract(data, 'Tuple(
+                            a LowCardinality(Int16),
+                            b LowCardinality(Int16),
+                            c LowCardinality(Int16),
+                            d LowCardinality(Int16)
+                            
+                            )') AS json FROM test_low_cardinality_int;
+SELECT JSONExtract(data, 'Tuple(
+                            a LowCardinality(Int32),
+                            b LowCardinality(Int32),
+                            c LowCardinality(Int32),
+                            d LowCardinality(Int32)
+                            
+                            )') AS json FROM test_low_cardinality_int;
+SELECT JSONExtract(data, 'Tuple(
+                            a LowCardinality(Int64),
+                            b LowCardinality(Int64),
+                            c LowCardinality(Int64),
+                            d LowCardinality(Int64)
+                            
+                            )') AS json FROM test_low_cardinality_int;
+SELECT JSONExtract(data, 'Tuple(
+                            a LowCardinality(UUID),
+                            b LowCardinality(UUID),
+                            c LowCardinality(UUID),
+                            d LowCardinality(UUID)
+                            
+                            )') AS json FROM test_low_cardinality_uuid;
+DROP TABLE test_low_cardinality_string;
+DROP TABLE test_low_cardinality_uuid;
+DROP TABLE test_low_cardinality_int;