alamb commented on code in PR #4107:
URL: https://github.com/apache/arrow-datafusion/pull/4107#discussion_r1014814305
##########
datafusion/sql/src/planner.rs:
##########
@@ -2671,6 +2673,113 @@ impl<'a, S: ContextProvider> SqlToRel<'a, S> {
Ok(lit(ScalarValue::new_list(Some(values), data_type)))
}
}
+
+ fn convert_data_type(&self, sql_type: &SQLDataType) -> Result<DataType> {
+ match sql_type {
+ SQLDataType::Array(inner_sql_type) => {
+ let data_type = self.convert_simple_data_type(inner_sql_type)?;
+
+ Ok(DataType::List(Box::new(Field::new(
+ "field", data_type, true,
+ ))))
+ }
+ other => self.convert_simple_data_type(other),
+ }
+ }
+ fn convert_simple_data_type(&self, sql_type: &SQLDataType) ->
Result<DataType> {
+ match sql_type {
+ SQLDataType::Boolean => Ok(DataType::Boolean),
+ SQLDataType::TinyInt(_) => Ok(DataType::Int8),
+ SQLDataType::SmallInt(_) => Ok(DataType::Int16),
+ SQLDataType::Int(_) | SQLDataType::Integer(_) =>
Ok(DataType::Int32),
+ SQLDataType::BigInt(_) => Ok(DataType::Int64),
+ SQLDataType::UnsignedTinyInt(_) => Ok(DataType::UInt8),
+ SQLDataType::UnsignedSmallInt(_) => Ok(DataType::UInt16),
+ SQLDataType::UnsignedInt(_) | SQLDataType::UnsignedInteger(_) => {
+ Ok(DataType::UInt32)
+ }
+ SQLDataType::UnsignedBigInt(_) => Ok(DataType::UInt64),
+ SQLDataType::Float(_) => Ok(DataType::Float32),
+ SQLDataType::Real => Ok(DataType::Float32),
+ SQLDataType::Double | SQLDataType::DoublePrecision =>
Ok(DataType::Float64),
+ SQLDataType::Char(_)
+ | SQLDataType::Varchar(_)
+ | SQLDataType::Text
+ | SQLDataType::String => Ok(DataType::Utf8),
+ SQLDataType::Timestamp(tz_info) => {
+ let tz = if matches!(tz_info, TimezoneInfo::Tz)
+ || matches!(tz_info, TimezoneInfo::WithTimeZone)
+ {
+ match
self.schema_provider.get_config_option("datafusion.execution.time_zone") {
+ Some(ScalarValue::Utf8(s)) => {
+ s
+ }
+ Some(_) => {
+ None
+ }
+ None => None
+ }
+ //Some("+00:00".to_string())
+
+ } else {
+ None
+ };
+ Ok(DataType::Timestamp(TimeUnit::Nanosecond, tz))
Review Comment:
I agree the second approach makes sense to me.
Maybe usability wise we can just add enough comments about what is
happening, or maybe add that best practice is to explicitly specify the
timezone in the create table statement / timestamp types.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: github-unsubscr...@arrow.apache.org
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
