Allow to parse JSON objects into Strings

docs/en/interfaces/formats.md

@@ -1202,6 +1202,7 @@ SELECT * FROM json_each_row_nested
 - [input_format_import_nested_json](../operations/settings/settings.md#input_format_import_nested_json) - map nested JSON data to nested tables (it works for JSONEachRow format). Default value - `false`.
 - [input_format_json_read_bools_as_numbers](../operations/settings/settings.md#input_format_json_read_bools_as_numbers) - allow to parse bools as numbers in JSON input formats. Default value - `true`.
 - [input_format_json_read_numbers_as_strings](../operations/settings/settings.md#input_format_json_read_numbers_as_strings) - allow to parse numbers as strings in JSON input formats. Default value - `false`.
+- [input_format_json_read_objects_as_strings](../operations/settings/settings.md#input_format_json_read_objects_as_strings) - allow to parse JSON objects as strings in JSON input formats. Default value - `false`.
 - [output_format_json_quote_64bit_integers](../operations/settings/settings.md#output_format_json_quote_64bit_integers) - controls quoting of 64-bit integers in JSON output format. Default value - `true`.
 - [output_format_json_quote_64bit_floats](../operations/settings/settings.md#output_format_json_quote_64bit_floats) - controls quoting of 64-bit floats in JSON output format. Default value - `false`.
 - [output_format_json_quote_denormals](../operations/settings/settings.md#output_format_json_quote_denormals) - enables '+nan', '-nan', '+inf', '-inf' outputs in JSON output format. Default value - `false`.

docs/en/operations/settings/settings.md

@@ -3753,6 +3753,28 @@ Allow parsing numbers as strings in JSON input formats.
 
 Disabled by default.
 
+### input_format_json_read_objects_as_strings {#input_format_json_read_objects_as_strings}
+
+Allow parsing JSON objects as strings in JSON input formats.
+
+Example:
+
+```sql
+CREATE TABLE test (obj String) ENGINE=Memory();
+INSERT INTO test FORMAT JSONEachRow {"obj" : {"a" : 1, "b" : "Hello"}};
+SELECT * FROM test;
+```
+
+Result:
+
+```
+┌─obj──────────────────────┐
+│ {"a" : 1, "b" : "Hello"} │
+└──────────────────────────┘
+```
+
+Disabled by default.
+
 ### input_format_json_validate_types_from_metadata {#input_format_json_validate_types_from_metadata}
 
 For JSON/JSONCompact/JSONColumnsWithMetadata input formats, if this setting is set to 1,

src/Core/Settings.h

@@ -546,7 +546,7 @@ static constexpr UInt64 operator""_GiB(unsigned long long value)
     \
     M(Bool, collect_hash_table_stats_during_aggregation, true, "Enable collecting hash table statistics to optimize memory allocation", 0) \
     M(UInt64, max_entries_for_hash_table_stats, 10'000, "How many entries hash table statistics collected during aggregation is allowed to have", 0) \
-    M(UInt64, max_size_to_preallocate_for_aggregation, 10'000'000, "For how many elements it is allowed to preallocate space in all hash tables in total before aggregation", 0) \
+    M(UInt64, max_size_to_preallocate_for_aggregation, 100'000'000, "For how many elements it is allowed to preallocate space in all hash tables in total before aggregation", 0) \
     \
     M(Bool, kafka_disable_num_consumers_limit, false, "Disable limit on kafka_num_consumers that depends on the number of available CPU cores", 0) \
     M(Bool, enable_software_prefetch_in_aggregation, true, "Enable use of software prefetch in aggregation", 0) \
@@ -763,6 +763,7 @@ static constexpr UInt64 operator""_GiB(unsigned long long value)
     M(Bool, input_format_json_try_infer_numbers_from_strings, true, "Try to infer numbers from string fields while schema inference", 0) \
     M(Bool, input_format_json_validate_types_from_metadata, true, "For JSON/JSONCompact/JSONColumnsWithMetadata input formats this controls whether format parser should check if data types from input metadata match data types of the corresponding columns from the table", 0) \
     M(Bool, input_format_json_read_numbers_as_strings, false, "Allow to parse numbers as strings in JSON input formats", 0) \
+    M(Bool, input_format_json_read_objects_as_strings, false, "Allow to parse JSON objects as strings in JSON input formats", 0) \
     M(Bool, input_format_try_infer_integers, true, "Try to infer numbers from string fields while schema inference in text formats", 0) \
     M(Bool, input_format_try_infer_dates, true, "Try to infer dates from string fields while schema inference in text formats", 0) \
     M(Bool, input_format_try_infer_datetimes, true, "Try to infer datetimes from string fields while schema inference in text formats", 0) \

src/DataTypes/Serializations/SerializationString.cpp

@@ -311,13 +311,20 @@ void SerializationString::serializeTextJSON(const IColumn & column, size_t row_n
 
 void SerializationString::deserializeTextJSON(IColumn & column, ReadBuffer & istr, const FormatSettings & settings) const
 {
-    if (settings.json.read_numbers_as_strings && !istr.eof() && *istr.position() != '"')
+    if (settings.json.read_objects_as_strings && !istr.eof() && *istr.position() == '{')
+    {
+        String field;
+        readJSONObjectPossiblyInvalid(field, istr);
+        ReadBufferFromString buf(field);
+        read(column, [&](ColumnString::Chars & data) { data.insert(field.begin(), field.end()); });
+    }
+    else if (settings.json.read_numbers_as_strings && !istr.eof() && *istr.position() != '"')
     {
         String field;
         readJSONField(field, istr);
         Float64 tmp;
         ReadBufferFromString buf(field);
-        if (tryReadFloatText(tmp, buf))
+        if (tryReadFloatText(tmp, buf) && buf.eof())
             read(column, [&](ColumnString::Chars & data) { data.insert(field.begin(), field.end()); });
         else
             throw Exception(ErrorCodes::INCORRECT_DATA, "Cannot parse JSON String value here: {}", field);

src/Formats/EscapingRuleUtils.cpp

@@ -394,6 +394,7 @@ void transformInferredTypesIfNeededImpl(DataTypes & types, const FormatSettings
 
         bool have_maps = false;
         bool have_objects = false;
+        bool have_strings = false;
         bool are_maps_equal = true;
         DataTypePtr first_map_type;
         for (const auto & type : data_types)
@@ -414,6 +415,10 @@ void transformInferredTypesIfNeededImpl(DataTypes & types, const FormatSettings
             {
                 have_objects = true;
             }
+            else if (isString(type))
+            {
+                have_strings = false;
+            }
         }
 
         if (have_maps && (have_objects || !are_maps_equal))
@@ -424,6 +429,15 @@ void transformInferredTypesIfNeededImpl(DataTypes & types, const FormatSettings
                     type = std::make_shared<DataTypeObject>("json", true);
             }
         }
+
+        if (settings.json.read_objects_as_strings && have_strings && (have_maps || have_objects))
+        {
+            for (auto & type : data_types)
+            {
+                if (isMap(type) || isObject(type))
+                    type = std::make_shared<DataTypeString>();
+            }
+        }
     };
 
     transformTypesRecursively(types, transform_simple_types, transform_complex_types);

src/Formats/FormatFactory.cpp

@@ -98,6 +98,7 @@ FormatSettings getFormatSettings(ContextPtr context, const Settings & settings)
     format_settings.json.quote_decimals = settings.output_format_json_quote_decimals;
     format_settings.json.read_bools_as_numbers = settings.input_format_json_read_bools_as_numbers;
     format_settings.json.read_numbers_as_strings = settings.input_format_json_read_numbers_as_strings;
+    format_settings.json.read_objects_as_strings = settings.input_format_json_read_objects_as_strings;
     format_settings.json.try_infer_numbers_from_strings = settings.input_format_json_try_infer_numbers_from_strings;
     format_settings.json.validate_types_from_metadata = settings.input_format_json_validate_types_from_metadata;
     format_settings.json.validate_utf8 = settings.output_format_json_validate_utf8;

src/Formats/FormatSettings.h

@@ -152,6 +152,7 @@ struct FormatSettings
         bool serialize_as_strings = false;
         bool read_bools_as_numbers = true;
         bool read_numbers_as_strings = true;
+        bool read_objects_as_strings = true;
         bool try_infer_numbers_from_strings = false;
         bool validate_types_from_metadata = true;
         bool validate_utf8 = false;

src/Formats/JSONUtils.cpp

@@ -235,7 +235,12 @@ namespace JSONUtils
                     /// If we couldn't infer nested type and Object type is not enabled,
                     /// we can't determine the type of this JSON field.
                     if (!settings.json.try_infer_objects)
+                    {
+                        /// If read_objects_as_strings is enabled, we can read objects into strings.
+                        if (settings.json.read_objects_as_strings)
+                            return makeNullable(std::make_shared<DataTypeString>());
                         return nullptr;
+                    }
 
                     continue;
                 }
@@ -257,7 +262,12 @@ namespace JSONUtils
             if (!are_types_equal)
             {
                 if (!settings.json.try_infer_objects)
+                {
+                    /// If read_objects_as_strings is enabled, we can read objects into strings.
+                    if (settings.json.read_objects_as_strings)
+                        return makeNullable(std::make_shared<DataTypeString>());
                     return nullptr;
+                }
                 return std::make_shared<DataTypeObject>("json", true);
             }
 

tests/queries/0_stateless/02499_read_json_objects_as_strings.reference

@@ -0,0 +1,3 @@
+x	Nullable(String)					
+abc
+{"a" : 10, "b" : "abc"}

tests/queries/0_stateless/02499_read_json_objects_as_strings.sql

@@ -0,0 +1,4 @@
+set input_format_json_read_objects_as_strings=1;
+desc format(JSONEachRow, '{"x" : "abc"}, {"x" : {"a" : 10, "b" : "abc"}}');
+select * from format(JSONEachRow, '{"x" : "abc"}, {"x" : {"a" : 10, "b" : "abc"}}');
+