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

Fix logical type issues in the Parquet writer #14322

Merged
merged 15 commits into from
Oct 31, 2023
Merged

Fix logical type issues in the Parquet writer #14322

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
028e5f2
default to isAdjustedToUTC = true
vuule Oct 24, 2023
f993f9b
Merge branch 'branch-23.12' into bug-write_parquet-adjusted-to-utc
vuule Oct 24, 2023
f0a967e
Merge branch 'branch-23.12' of https://github.com/rapidsai/cudf into …
vuule Oct 24, 2023
aabe445
Merge branch 'branch-23.12' into bug-write_parquet-adjusted-to-utc
vuule Oct 24, 2023
00f0923
Merge branch 'branch-23.12' of https://github.com/rapidsai/cudf into …
vuule Oct 25, 2023
1f4cd77
exclude UNKNOWN from merged metadata
vuule Oct 25, 2023
eef499c
add utc flag
vuule Oct 25, 2023
7ba4029
Merge branch 'bug-write_parquet-adjusted-to-utc' of https://github.co…
vuule Oct 25, 2023
d5237aa
doc
vuule Oct 25, 2023
5ab1093
Merge branch 'branch-23.12' into bug-write_parquet-adjusted-to-utc
vuule Oct 25, 2023
a5aefa8
Merge branch 'branch-23.12' into bug-write_parquet-adjusted-to-utc
vuule Oct 26, 2023
b1d232f
Merge branch 'branch-23.12' into bug-write_parquet-adjusted-to-utc
vuule Oct 27, 2023
5d66e1f
Merge branch 'branch-23.12' of https://github.com/rapidsai/cudf into …
vuule Oct 27, 2023
5ba2928
uncomment an assert in a dask test
vuule Oct 27, 2023
e245062
Merge branch 'bug-write_parquet-adjusted-to-utc' of https://github.co…
vuule Oct 27, 2023
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
6 changes: 4 additions & 2 deletions cpp/src/io/parquet/parquet.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,13 +58,15 @@ struct TimeUnit {
};

struct TimeType {
bool isAdjustedToUTC = false;
bool isAdjustedToUTC = true;
vuule marked this conversation as resolved.
Show resolved Hide resolved
TimeUnit unit;
explicit TimeType(TimeUnit::Type t = TimeUnit::MILLIS) : unit{t} {}
};

struct TimestampType {
bool isAdjustedToUTC = false;
bool isAdjustedToUTC = true;
TimeUnit unit;
explicit TimestampType(TimeUnit::Type t = TimeUnit::MILLIS) : unit{t} {}
};

struct IntType {
Expand Down
18 changes: 9 additions & 9 deletions cpp/src/io/parquet/writer_impl.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -404,7 +404,7 @@ struct leaf_schema_fn {
col_schema.ts_scale = 1000;
if (not timestamp_is_int96) {
col_schema.converted_type = ConvertedType::TIMESTAMP_MILLIS;
col_schema.logical_type = LogicalType{TimestampType{false, TimeUnit::MILLIS}};
col_schema.logical_type = LogicalType{TimestampType{TimeUnit::MILLIS}};
}
}

Expand All @@ -415,7 +415,7 @@ struct leaf_schema_fn {
col_schema.stats_dtype = statistics_dtype::dtype_timestamp64;
if (not timestamp_is_int96) {
col_schema.converted_type = ConvertedType::TIMESTAMP_MILLIS;
col_schema.logical_type = LogicalType{TimestampType{false, TimeUnit::MILLIS}};
col_schema.logical_type = LogicalType{TimestampType{TimeUnit::MILLIS}};
}
}

Expand All @@ -426,7 +426,7 @@ struct leaf_schema_fn {
col_schema.stats_dtype = statistics_dtype::dtype_timestamp64;
if (not timestamp_is_int96) {
col_schema.converted_type = ConvertedType::TIMESTAMP_MICROS;
col_schema.logical_type = LogicalType{TimestampType{false, TimeUnit::MICROS}};
col_schema.logical_type = LogicalType{TimestampType{TimeUnit::MICROS}};
}
}

Expand All @@ -441,7 +441,7 @@ struct leaf_schema_fn {
}
// set logical type if it's not int96
else {
col_schema.logical_type = LogicalType{TimestampType{false, TimeUnit::NANOS}};
col_schema.logical_type = LogicalType{TimestampType{TimeUnit::NANOS}};
}
}

Expand All @@ -453,7 +453,7 @@ struct leaf_schema_fn {
col_schema.converted_type = ConvertedType::TIME_MILLIS;
col_schema.stats_dtype = statistics_dtype::dtype_int32;
col_schema.ts_scale = 24 * 60 * 60 * 1000;
col_schema.logical_type = LogicalType{TimeType{false, TimeUnit::MILLIS}};
col_schema.logical_type = LogicalType{TimeType{TimeUnit::MILLIS}};
}

template <typename T>
Expand All @@ -463,7 +463,7 @@ struct leaf_schema_fn {
col_schema.converted_type = ConvertedType::TIME_MILLIS;
col_schema.stats_dtype = statistics_dtype::dtype_int32;
col_schema.ts_scale = 1000;
col_schema.logical_type = LogicalType{TimeType{false, TimeUnit::MILLIS}};
col_schema.logical_type = LogicalType{TimeType{TimeUnit::MILLIS}};
}

template <typename T>
Expand All @@ -472,7 +472,7 @@ struct leaf_schema_fn {
col_schema.type = Type::INT32;
col_schema.converted_type = ConvertedType::TIME_MILLIS;
col_schema.stats_dtype = statistics_dtype::dtype_int32;
col_schema.logical_type = LogicalType{TimeType{false, TimeUnit::MILLIS}};
col_schema.logical_type = LogicalType{TimeType{TimeUnit::MILLIS}};
}

template <typename T>
Expand All @@ -481,7 +481,7 @@ struct leaf_schema_fn {
col_schema.type = Type::INT64;
col_schema.converted_type = ConvertedType::TIME_MICROS;
col_schema.stats_dtype = statistics_dtype::dtype_int64;
col_schema.logical_type = LogicalType{TimeType{false, TimeUnit::MICROS}};
col_schema.logical_type = LogicalType{TimeType{TimeUnit::MICROS}};
}

// unsupported outside cudf for parquet 1.0.
Expand All @@ -490,7 +490,7 @@ struct leaf_schema_fn {
{
col_schema.type = Type::INT64;
col_schema.stats_dtype = statistics_dtype::dtype_int64;
col_schema.logical_type = LogicalType{TimeType{false, TimeUnit::NANOS}};
col_schema.logical_type = LogicalType{TimeType{TimeUnit::NANOS}};
}

template <typename T>
Expand Down
Loading