Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Support partition value string deserialization for timestamp/binary #371

Merged
merged 5 commits into from
Sep 15, 2021
Merged

Support partition value string deserialization for timestamp/binary #371

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
54c2598
Add partition value string deserialization for timestamp.
zijie0 Aug 10, 2021
fae8fa5
Add partition value string deserialization for binary.
zijie0 Aug 10, 2021
081df68
Fix write out binary values to parquet.
zijie0 Aug 13, 2021
a4f71c8
Parse timestamp partition value to micro seconds.
zijie0 Sep 15, 2021
4729109
Bump up Arrow version.
zijie0 Sep 15, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
38 changes: 37 additions & 1 deletion rust/src/checkpoints.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -291,7 +291,7 @@ fn typed_partition_value_from_string(
) -> Result<Value, CheckpointError> {
match data_type {
SchemaDataType::primitive(primitive_type) => match primitive_type.as_str() {
"string" => Ok(string_value.to_owned().into()),
"string" | "binary" => Ok(string_value.to_owned().into()),
"long" | "integer" | "short" | "byte" => Ok(string_value
.parse::<i64>()
.map_err(|_| CheckpointError::PartitionValueNotParseable(string_value.to_owned()))?
Expand All @@ -312,6 +312,14 @@ fn typed_partition_value_from_string(
// day 0 is 1970-01-01 (719163 days from ce)
Ok((d.num_days_from_ce() - 719_163).into())
}
"timestamp" => {
let ts =
chrono::naive::NaiveDateTime::parse_from_str(string_value, "%Y-%m-%d %H:%M:%S")
.map_err(|_| {
CheckpointError::PartitionValueNotParseable(string_value.to_owned())
})?;
Ok((ts.timestamp_millis() * 1000).into())
}
s => unimplemented!(
"Primitive type {} is not supported for partition column values.",
s
Expand Down Expand Up @@ -462,6 +470,34 @@ mod tests {
.unwrap()
);
}

for (s, v) in [
("2021-08-08 01:00:01", 1628384401000000i64),
("1970-01-02 12:59:59", 133199000000i64),
("1970-01-01 13:00:01", 46801000000i64),
("1969-12-31 00:00:00", -86400000000i64),
("1677-09-21 00:12:44", -9223372036000000i64),
] {
let timestamp_value: Value = v.into();
assert_eq!(
timestamp_value,
typed_partition_value_from_option_string(
&Some(s.to_string()),
&SchemaDataType::primitive("timestamp".to_string()),
)
.unwrap()
);
}

let binary_value: Value = "\u{2081}\u{2082}\u{2083}\u{2084}".into();
assert_eq!(
binary_value,
typed_partition_value_from_option_string(
&Some("₁₂₃₄".to_string()),
&SchemaDataType::primitive("binary".to_string()),
)
.unwrap()
);
}

#[test]
Expand Down
3 changes: 2 additions & 1 deletion rust/src/delta_arrow.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,8 @@ impl TryFrom<&schema::SchemaDataType> for ArrowDataType {
"float" => Ok(ArrowDataType::Float32),
"double" => Ok(ArrowDataType::Float64),
"boolean" => Ok(ArrowDataType::Boolean),
"binary" => Ok(ArrowDataType::Binary),
// Change to binary type after https://github.com/apache/arrow-rs/pull/702 is released
"binary" => Ok(ArrowDataType::Utf8),
houqp marked this conversation as resolved.
Show resolved Hide resolved
decimal if DECIMAL_REGEX.is_match(decimal) => {
let extract = DECIMAL_REGEX.captures(decimal).ok_or_else(|| {
ArrowError::SchemaError(format!(
Expand Down