[branch-2.1](function) fix error result in auto partition name (#41130) (#43977)

pick https://github.com/apache/doris/pull/41130
https://github.com/apache/doris/pull/41372

---------

Co-authored-by: zhaochangle <zhaochangle@selectdb.com>
This commit is contained in:
Uniqueyou
2024-11-15 19:11:42 +08:00
committed by GitHub
parent 02bb36c281
commit edd9015de3
4 changed files with 75 additions and 28 deletions

View File

@ -532,7 +532,7 @@ public:
String get_name() const override { return name; }
size_t get_number_of_arguments() const override { return 0; }
bool is_variadic() const override { return true; }
bool use_default_implementation_for_nulls() const override { return false; }
DataTypePtr get_return_type_impl(const DataTypes& arguments) const override {
return std::make_shared<DataTypeString>();
}
@ -540,23 +540,36 @@ public:
Status execute_impl(FunctionContext* context, Block& block, const ColumnNumbers& arguments,
size_t result, size_t input_rows_count) const override {
size_t argument_size = arguments.size();
if (argument_size < 2) {
return Status::InvalidArgument(
"auto_partition_name must contains at least two arguments");
}
auto const_null_map = ColumnUInt8::create(input_rows_count, 0);
auto null_map = ColumnUInt8::create(input_rows_count, 0);
std::vector<const ColumnString::Chars*> chars_list(argument_size);
std::vector<const ColumnString::Offsets*> offsets_list(argument_size);
std::vector<bool> is_const_args(argument_size);
std::vector<const ColumnUInt8::Container*> null_list(argument_size);
std::vector<ColumnPtr> argument_null_columns(argument_size);
std::vector<ColumnPtr> argument_columns(argument_size);
for (int i = 0; i < argument_size; ++i) {
argument_columns[i] =
block.get_by_position(arguments[i]).column->convert_to_full_column_if_const();
if (const auto* nullable =
check_and_get_column<const ColumnNullable>(*argument_columns[i])) {
null_list[i] = &nullable->get_null_map_data();
argument_null_columns[i] = nullable->get_null_map_column_ptr();
argument_columns[i] = nullable->get_nested_column_ptr();
} else {
null_list[i] = &const_null_map->get_data();
}
const auto& [col, is_const] =
unpack_if_const(block.get_by_position(arguments[i]).column);
const auto* col_str = assert_cast<const ColumnString*>(col.get());
const auto* col_str = assert_cast<const ColumnString*>(argument_columns[i].get());
chars_list[i] = &col_str->get_chars();
offsets_list[i] = &col_str->get_offsets();
is_const_args[i] = is_const;
}
auto res = ColumnString::create();
auto& res_data = res->get_chars();
auto& res_offset = res->get_offsets();
@ -564,11 +577,11 @@ public:
const char* partition_type = chars_list[0]->raw_data();
// partition type is list|range
if (std::strncmp(partition_type, "list", 4) == 0) {
return _auto_partition_type_of_list(chars_list, offsets_list, is_const_args, res_data,
res_offset, input_rows_count, argument_size, block,
result, res);
} else {
if (!std::strncmp(partition_type, "list", 4)) {
return _auto_partition_type_of_list(chars_list, offsets_list, is_const_args, null_list,
res_data, res_offset, input_rows_count,
argument_size, block, result, res);
} else if (!std::strncmp(partition_type, "range", 5)) {
return _auto_partition_type_of_range(chars_list, offsets_list, is_const_args, res_data,
res_offset, input_rows_count, argument_size, block,
result, res);
@ -615,8 +628,9 @@ private:
}
Status _auto_partition_type_of_list(std::vector<const ColumnString::Chars*>& chars_list,
std::vector<const ColumnString::Offsets*>& offsets_list,
std::vector<bool>& is_const_args, auto& res_data,
auto& res_offset, size_t input_rows_count,
std::vector<bool>& is_const_args,
const std::vector<const ColumnUInt8::Container*>& null_list,
auto& res_data, auto& res_offset, size_t input_rows_count,
size_t argument_size, Block& block, size_t result,
auto& res) const {
int curr_len = 0;
@ -627,16 +641,21 @@ private:
for (int col = 1; col < argument_size; col++) {
const auto& current_offsets = *offsets_list[col];
const auto& current_chars = *chars_list[col];
const auto& current_nullmap = *null_list[col];
auto idx = index_check_const(row, is_const_args[col]);
int size = current_offsets[idx] - current_offsets[idx - 1];
const char* raw_chars =
reinterpret_cast<const char*>(&current_chars[current_offsets[idx - 1]]);
if (current_nullmap[row]) {
res_p += 'X';
} else {
auto idx = index_check_const(row, is_const_args[col]);
// convert string to u16string in order to convert to unicode strings
const std::string raw_str(raw_chars, size);
auto u16string = _string_to_u16string(raw_str);
res_p += _string_to_unicode(u16string) + std::to_string(u16string.size());
int size = current_offsets[idx] - current_offsets[idx - 1];
const char* raw_chars =
reinterpret_cast<const char*>(&current_chars[current_offsets[idx - 1]]);
// convert string to u16string in order to convert to unicode strings
const std::string raw_str(raw_chars, size);
auto u16string = _string_to_u16string(raw_str);
res_p += _string_to_unicode(u16string) + std::to_string(u16string.size());
}
}
// check the name of length

View File

@ -20,10 +20,9 @@ package org.apache.doris.nereids.trees.expressions.functions.scalar;
import org.apache.doris.catalog.FunctionSignature;
import org.apache.doris.nereids.exceptions.AnalysisException;
import org.apache.doris.nereids.trees.expressions.Expression;
import org.apache.doris.nereids.trees.expressions.functions.AlwaysNotNullable;
import org.apache.doris.nereids.trees.expressions.functions.ExplicitlyCastableSignature;
import org.apache.doris.nereids.trees.expressions.functions.PropagateNullable;
import org.apache.doris.nereids.trees.expressions.literal.VarcharLiteral;
import org.apache.doris.nereids.trees.expressions.shape.UnaryExpression;
import org.apache.doris.nereids.trees.expressions.visitor.ExpressionVisitor;
import org.apache.doris.nereids.types.StringType;
import org.apache.doris.nereids.types.VarcharType;
@ -40,7 +39,7 @@ import java.util.List;
* GenerateFunction.
*/
public class AutoPartitionName extends ScalarFunction
implements UnaryExpression, ExplicitlyCastableSignature, PropagateNullable {
implements ExplicitlyCastableSignature, AlwaysNotNullable {
public static final List<FunctionSignature> SIGNATURES = ImmutableList.of(
FunctionSignature.ret(VarcharType.SYSTEM_DEFAULT).varArgs(VarcharType.SYSTEM_DEFAULT),
@ -69,11 +68,11 @@ public class AutoPartitionName extends ScalarFunction
throw new AnalysisException("function auto_partition_name must contains at least two arguments");
}
if (!child(0).isLiteral()) {
throw new AnalysisException("auto_partition_name must accept literal for 1nd argument");
throw new AnalysisException("auto_partition_name must accept literal for 1st argument");
}
final String partition_type = ((VarcharLiteral) getArgument(0)).getStringValue().toLowerCase();
if (!Lists.newArrayList("range", "list").contains(partition_type)) {
throw new AnalysisException("function auto_partition_name must accept range|list for 1nd argument");
throw new AnalysisException("function auto_partition_name must accept range|list for 1st argument");
} else if (Lists.newArrayList("range").contains(partition_type)) {
if (!child(1).isLiteral()) {
throw new AnalysisException("auto_partition_name must accept literal for 2nd argument");
@ -93,6 +92,11 @@ public class AutoPartitionName extends ScalarFunction
}
}
@Override
public void checkLegalityBeforeTypeCoercion() {
checkLegalityAfterRewrite();
}
@Override
public List<FunctionSignature> getSignatures() {
return SIGNATURES;

View File

@ -484,6 +484,16 @@ pchar116varchar119
pchar126varchar129
pchar136varchar139
-- !sql_auto_partition_name_list_column --
pchar116Xvarchar119
pchar126Xvarchar129
pchar136Xvarchar139
-- !sql_auto_partition_name_list_column --
pXstring17XX
pXstring27XX
pXstring37XX
-- !sql_auto_partition_name_list_literal_empty --
p0
@ -496,6 +506,12 @@ p_2dhello6
-- !sql_auto_partition_name_list_literal_mixed --
p4023ffe5257e7cworld111112e2e2e2e20
-- !sql_auto_partition_name_list_literal_mixed --
plist4X11X
-- !sql_auto_partition_name_list_literal_null --
pXXX
-- !sql_auto_partition_name_range_literal_notnull --
p20221212000000

View File

@ -83,10 +83,14 @@ suite("nereids_scalar_fn_A") {
qt_sql_auto_partition_name_list_column_type_mixed "select auto_partition_name('list', kchrs1, kbool) from fn_test_not_nullable where id < 3 order by kchrs1"
qt_sql_auto_partition_name_list_column_literal_mixed "select auto_partition_name('list', kstr, 'hello') from fn_test_not_nullable where id < 3 order by kstr"
qt_sql_auto_partition_name_list_column "select auto_partition_name('list', kchrs1, kvchrs1) from fn_test_not_nullable where id < 3 order by kchrs1"
qt_sql_auto_partition_name_list_column "select auto_partition_name('list', kchrs1, null, kvchrs1) from fn_test where id < 3 order by kchrs1"
qt_sql_auto_partition_name_list_column "select auto_partition_name('list', null, kstr, null, null) from fn_test where id < 3 order by kstr"
qt_sql_auto_partition_name_list_literal_empty "select auto_partition_name('list', '')"
qt_sql_auto_partition_name_list_literal_mixed "select auto_partition_name('list', '你好', true, false)"
qt_sql_auto_partition_name_list_literal_mixed "select auto_partition_name('list', '-hello')"
qt_sql_auto_partition_name_list_literal_mixed "select auto_partition_name('list', '@#¥%~|world11111....')"
qt_sql_auto_partition_name_list_literal_mixed "select auto_partition_name('list', 'list', null, true, null)"
qt_sql_auto_partition_name_list_literal_null "select auto_partition_name('list', null, null, null);"
qt_sql_auto_partition_name_range_literal_notnull "select auto_partition_name('range', 'day', '2022-12-12 19:20:30')"
qt_sql_auto_partition_name_range_literal_notnull "select auto_partition_name('range', 'month', '2022-12-12 19:20:30')"
qt_sql_auto_partition_name_range_literal_notnull "select auto_partition_name('range', 'year', '2022-12-12 19:20:30')"
@ -110,7 +114,7 @@ suite("nereids_scalar_fn_A") {
}
test{
sql """select auto_partition_name(kdt, 'day', kdt) from fn_test_not_nullable order by kdt"""
exception "auto_partition_name must accept literal for 1nd argument"
exception "auto_partition_name must accept literal for 1st argument"
}
test{
sql """select auto_partition_name('range', kdt, kdt) from fn_test_not_nullable order by kdt"""
@ -142,7 +146,11 @@ suite("nereids_scalar_fn_A") {
}
test{
sql """select auto_partition_name('ranges', 'year', 'hello');"""
exception "function auto_partition_name must accept range|list for 1nd argument"
exception "function auto_partition_name must accept range|list for 1st argument"
}
test{
sql """select auto_partition_name('lists', 'year', 'hello');"""
exception "function auto_partition_name must accept range|list for 1st argument"
}
test{
sql """select auto_partition_name('range', 'years', 'hello');"""