tustvold commented on code in PR #1682:
URL: https://github.com/apache/arrow-rs/pull/1682#discussion_r872193044
##########
parquet/src/arrow/schema.rs:
##########
@@ -385,34 +349,54 @@ fn arrow_to_parquet_type(field: &Field) -> Result<Type> {
DataType::Float64 => Type::primitive_type_builder(name,
PhysicalType::DOUBLE)
.with_repetition(repetition)
.build(),
- DataType::Timestamp(time_unit, zone) => Type::primitive_type_builder(
- name,
- PhysicalType::INT64,
- )
- .with_logical_type(Some(LogicalType::Timestamp {
- is_adjusted_to_u_t_c: matches!(zone, Some(z) if
!z.as_str().is_empty()),
- unit: match time_unit {
- TimeUnit::Second =>
ParquetTimeUnit::MILLIS(Default::default()),
- TimeUnit::Millisecond =>
ParquetTimeUnit::MILLIS(Default::default()),
- TimeUnit::Microsecond =>
ParquetTimeUnit::MICROS(Default::default()),
- TimeUnit::Nanosecond =>
ParquetTimeUnit::NANOS(Default::default()),
- },
- }))
- .with_repetition(repetition)
- .build(),
+ DataType::Timestamp(TimeUnit::Second, _) => {
+ // Cannot represent seconds in LogicalType
+ Type::primitive_type_builder(name, PhysicalType::INT64)
+ .with_repetition(repetition)
+ .build()
+ }
+ DataType::Timestamp(time_unit, _) => {
+ Type::primitive_type_builder(name, PhysicalType::INT64)
+ .with_logical_type(Some(LogicalType::Timestamp {
+ is_adjusted_to_u_t_c: false,
+ unit: match time_unit {
+ TimeUnit::Second => unreachable!(),
+ TimeUnit::Millisecond => {
+ ParquetTimeUnit::MILLIS(Default::default())
+ }
+ TimeUnit::Microsecond => {
+ ParquetTimeUnit::MICROS(Default::default())
+ }
+ TimeUnit::Nanosecond => {
+ ParquetTimeUnit::NANOS(Default::default())
+ }
+ },
+ }))
+ .with_repetition(repetition)
+ .build()
+ }
DataType::Date32 => Type::primitive_type_builder(name,
PhysicalType::INT32)
.with_logical_type(Some(LogicalType::Date))
.with_repetition(repetition)
.build(),
- // date64 is cast to date32
+ // date64 is cast to date32 (#1666)
DataType::Date64 => Type::primitive_type_builder(name,
PhysicalType::INT32)
.with_logical_type(Some(LogicalType::Date))
.with_repetition(repetition)
.build(),
- DataType::Time32(_) => Type::primitive_type_builder(name,
PhysicalType::INT32)
+ DataType::Time32(TimeUnit::Second) => {
+ // Cannot represent seconds in LogicalType
Review Comment:
Yes, TBC this wouldn't be wrong if the writer coerced the types to match.
The problem is it does not
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
