Merge pull request #25169 from nikitamikhaylov/csv-with-names-bug

Fix insert a subset of columns using CSVWithNames

src/Processors/Formats/IInputFormat.h

@@ -12,7 +12,7 @@ struct ColumnMapping
 {
     /// Non-atomic because there is strict `happens-before` between read and write access
     /// See InputFormatParallelParsing
-    bool is_set;
+    bool is_set{false};
     /// Maps indexes of columns in the input file to indexes of table columns
     using OptionalIndexes = std::vector<std::optional<size_t>>;
     OptionalIndexes column_indexes_for_input_fields;
@@ -22,6 +22,11 @@ struct ColumnMapping
     /// read the file header, and never changed afterwards.
     /// For other columns, it is updated on each read() call.
     std::vector<UInt8> read_columns;
+
+
+    /// Whether we have any columns that are not read from file at all,
+    /// and must be always initialized with defaults.
+    bool have_always_default_columns{false};
 };
 
 using ColumnMappingPtr = std::shared_ptr<ColumnMapping>;

src/Processors/Formats/Impl/CSVRowInputFormat.cpp

@@ -193,7 +193,7 @@ void CSVRowInputFormat::readPrefix()
             {
                 if (!read_column)
                 {
-                    have_always_default_columns = true;
+                    column_mapping->have_always_default_columns = true;
                     break;
                 }
             }
@@ -221,7 +221,7 @@ bool CSVRowInputFormat::readRow(MutableColumns & columns, RowReadExtension & ext
     /// Track whether we have to fill any columns in this row with default
     /// values. If not, we return an empty column mask to the caller, so that
     /// it doesn't have to check it.
-    bool have_default_columns = have_always_default_columns;
+    bool have_default_columns = column_mapping->have_always_default_columns;
 
     ext.read_columns.assign(column_mapping->read_columns.size(), true);
     const auto delimiter = format_settings.csv.delimiter;
@@ -416,7 +416,7 @@ void CSVRowInputFormat::resetParser()
     RowInputFormatWithDiagnosticInfo::resetParser();
     column_mapping->column_indexes_for_input_fields.clear();
     column_mapping->read_columns.clear();
-    have_always_default_columns = false;
+    column_mapping->have_always_default_columns = false;
 }
 
 

src/Processors/Formats/Impl/CSVRowInputFormat.h

@@ -31,17 +31,13 @@ public:
     void resetParser() override;
 
 private:
+    /// There fields are computed in constructor.
     bool with_names;
     const FormatSettings format_settings;
     DataTypes data_types;
-
     using IndexesMap = std::unordered_map<String, size_t>;
     IndexesMap column_indexes_by_names;
 
-    /// Whether we have any columns that are not read from file at all,
-    /// and must be always initialized with defaults.
-    bool have_always_default_columns = false;
-
     void addInputColumn(const String & column_name);
 
     void setupAllColumnsByTableSchema();

tests/queries/0_stateless/01903_csvwithnames_subset_of_columns.reference

@@ -0,0 +1,3 @@
+1000000
+2000000
+3000000

tests/queries/0_stateless/01903_csvwithnames_subset_of_columns.sh

@@ -0,0 +1,23 @@
+#!/usr/bin/env bash
+
+CUR_DIR=$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)
+# shellcheck source=../shell_config.sh
+. "$CUR_DIR"/../shell_config.sh
+
+$CLICKHOUSE_CLIENT -q "DROP TABLE IF EXISTS test_01903"
+
+$CLICKHOUSE_CLIENT -q "CREATE TABLE test_01903 (col0 Date, col1 Nullable(UInt8)) ENGINE MergeTree() PARTITION BY toYYYYMM(col0) ORDER BY col0;"
+
+(echo col0,col1; for _ in `seq 1 1000000`; do echo '2021-05-05',1; done) | $CLICKHOUSE_CLIENT -q "INSERT INTO test_01903 FORMAT CSVWithNames"
+
+$CLICKHOUSE_CLIENT -q "SELECT count() FROM test_01903"
+
+(echo col0; for _ in `seq 1 1000000`; do echo '2021-05-05'; done) | $CLICKHOUSE_CLIENT -q "INSERT INTO test_01903 (col0) FORMAT CSVWithNames"
+
+$CLICKHOUSE_CLIENT -q "SELECT count() FROM test_01903"
+
+(echo col0; for _ in `seq 1 1000000`; do echo '2021-05-05'; done) | $CLICKHOUSE_CLIENT -q "INSERT INTO test_01903 (col0) FORMAT TSVWithNames"
+
+$CLICKHOUSE_CLIENT -q "SELECT count() FROM test_01903"
+
+$CLICKHOUSE_CLIENT -q "DROP TABLE IF EXISTS test_01903"