Merge pull request #14586 from Avogar/Custom-null-representation-in-TCV

Custom null representation in tsv

src/Core/Settings.h

@@ -439,6 +439,7 @@ class IColumn;
     M(String, output_format_avro_codec, "", "Compression codec used for output. Possible values: 'null', 'deflate', 'snappy'.", 0) \
     M(UInt64, output_format_avro_sync_interval, 16 * 1024, "Sync interval in bytes.", 0) \
     M(Bool, output_format_tsv_crlf_end_of_line, false, "If it is set true, end of line in TSV format will be \\r\\n instead of \\n.", 0) \
+    M(String, output_format_tsv_null_representation, "\\N", "Custom NULL representation in TSV format", 0) \
     \
     M(UInt64, input_format_allow_errors_num, 0, "Maximum absolute amount of errors while reading text formats (like CSV, TSV). In case of error, if at least absolute or relative amount of errors is lower than corresponding value, will skip until next line and continue.", 0) \
     M(Float, input_format_allow_errors_ratio, 0, "Maximum relative amount of errors while reading text formats (like CSV, TSV). In case of error, if at least absolute or relative amount of errors is lower than corresponding value, will skip until next line and continue.", 0) \

src/DataTypes/DataTypeNullable.cpp

@@ -217,7 +217,7 @@ void DataTypeNullable::serializeTextEscaped(const IColumn & column, size_t row_n
     const ColumnNullable & col = assert_cast<const ColumnNullable &>(column);
 
     if (col.isNullAt(row_num))
-        writeCString("\\N", ostr);
+        writeString(settings.tsv.null_representation, ostr);
     else
         nested_data_type->serializeAsTextEscaped(col.getNestedColumn(), row_num, ostr, settings);
 }

src/Formats/FormatFactory.cpp

@@ -111,6 +111,7 @@ static FormatSettings getOutputFormatSetting(const Settings & settings, const Co
     format_settings.template_settings.row_format = settings.format_template_row;
     format_settings.template_settings.row_between_delimiter = settings.format_template_rows_between_delimiter;
     format_settings.tsv.crlf_end_of_line = settings.output_format_tsv_crlf_end_of_line;
+    format_settings.tsv.null_representation = settings.output_format_tsv_null_representation;
     format_settings.write_statistics = settings.output_format_write_statistics;
     format_settings.parquet.row_group_size = settings.output_format_parquet_row_group_size;
     format_settings.schema.format_schema = settings.format_schema;

src/Formats/FormatSettings.h

@@ -78,6 +78,7 @@ struct FormatSettings
     {
         bool empty_as_default = false;
         bool crlf_end_of_line = false;
+        String null_representation = "\\N";
     };
 
     TSV tsv;

tests/queries/0_stateless/01474_custom_null_tsv.reference

+MyNull

tests/queries/0_stateless/01474_custom_null_tsv.sh

+#!/usr/bin/env bash
+
+CURDIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
+. "$CURDIR"/../shell_config.sh
+
+$CLICKHOUSE_CLIENT --query="DROP TABLE IF EXISTS tsv_custom_null";
+$CLICKHOUSE_CLIENT --query="CREATE TABLE tsv_custom_null (id Nullable(UInt32)) ENGINE = Memory";
+
+$CLICKHOUSE_CLIENT --query="INSERT INTO tsv_custom_null VALUES (NULL)";
+
+$CLICKHOUSE_CLIENT --output_format_tsv_null_representation='MyNull' --query="SELECT * FROM tsv_custom_null FORMAT TSV";
+
+$CLICKHOUSE_CLIENT --query="DROP TABLE tsv_custom_null";
+