Skip to content

Read/write Parquet IEEE 754 nan_count and column order fields #24752

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

Closed
mhaseeb123 wants to merge 2 commits into from
Closed

Read/write Parquet IEEE 754 nan_count and column order fields #24752

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6958ae2
Read and write Parquet IEEE 754 NaN count and column order fields
mhaseeb123 Oct 21, 2026
48d1412
Merge remote-tracking branch 'upstream/main' into claude/parquet-nan-…
mhaseeb123 Oct 22, 2026
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
4 changes: 4 additions & 0 deletions cpp/include/cudf/io/parquet_schema.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -667,6 +667,8 @@ struct Statistics {
std::optional<bool> is_max_value_exact;
/// If true, min_value is the actual minimum value for a column
std::optional<bool> is_min_value_exact;
/// count of NaN values in a floating point column. NaNs may be present if absent
std::optional<int64_t> nan_count;
};

/**
Expand Down Expand Up @@ -737,6 +739,8 @@ struct ColumnIndex {
std::optional<std::vector<int64_t>> repetition_level_histogram;
/// Definition level histogram for the column chunk
std::optional<std::vector<int64_t>> definition_level_histogram;
/// Optional count of NaN values per page of a floating point column
std::optional<std::vector<int64_t>> nan_counts;
};

/**
Expand Down
6 changes: 4 additions & 2 deletions cpp/src/io/parquet/compact_protocol_reader.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1040,7 +1040,8 @@ void CompactProtocolReader::read(ColumnIndex* c)
parquet_field_enum<BoundaryOrder>(4, c->boundary_order),
optional_list_i64(5, c->null_counts),
optional_list_i64(6, c->repetition_level_histogram),
optional_list_i64(7, c->definition_level_histogram));
optional_list_i64(7, c->definition_level_histogram),
optional_list_i64(8, c->nan_counts));
function_builder(this, op);
}

Expand All @@ -1057,7 +1058,8 @@ void CompactProtocolReader::read(Statistics* s)
optional_binary(5, s->max_value),
optional_binary(6, s->min_value),
optional_bool(7, s->is_max_value_exact),
optional_bool(8, s->is_min_value_exact));
optional_bool(8, s->is_min_value_exact),
optional_int64(9, s->nan_count));
function_builder(this, op);
}

Expand Down
1 change: 1 addition & 0 deletions cpp/src/io/parquet/compact_protocol_writer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -258,6 +258,7 @@ size_t CompactProtocolWriter::write(Statistics const& s)
if (s.min_value.has_value()) { c.field_binary(6, s.min_value.value()); }
if (s.is_max_value_exact.has_value()) { c.field_bool(7, s.is_max_value_exact.value()); }
if (s.is_min_value_exact.has_value()) { c.field_bool(8, s.is_min_value_exact.value()); }
if (s.nan_count.has_value()) { c.field_int(9, s.nan_count.value()); }
return c.value();
}

Expand Down
12 changes: 8 additions & 4 deletions cpp/tests/io/experimental/parquet_footer_facade_test.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@ FileMetaData const& make_test_footer()
.repetition_type = FieldRepetitionType::REQUIRED,
.name = "schema",
.num_children = 3},
{.type = Type::INT32,
{.type = Type::DOUBLE,
.repetition_type = FieldRepetitionType::OPTIONAL,
.name = "a",
.field_id = 1},
Expand All @@ -66,7 +66,7 @@ FileMetaData const& make_test_footer()

ColumnChunk const cc[] = {
{.file_offset = 4,
.meta_data = {.type = Type::INT32,
.meta_data = {.type = Type::DOUBLE,
.encodings = {Encoding::PLAIN, Encoding::RLE_DICTIONARY},
.path_in_schema = {"a"},
.codec = Compression::SNAPPY,
Expand All @@ -75,7 +75,8 @@ FileMetaData const& make_test_footer()
.total_compressed_size = 500,
.data_page_offset = 8,
// non-zero exercises the dictionary_page_offset field
.dictionary_page_offset = 4}},
.dictionary_page_offset = 4,
.statistics = {.null_count = 0, .nan_count = 3}}},
{.file_offset = 504,
.meta_data = {.type = Type::BYTE_ARRAY,
.encodings = {Encoding::PLAIN},
Expand All @@ -99,7 +100,8 @@ FileMetaData const& make_test_footer()
{"empty", std::string("")},
{"novalue", std::nullopt},
};
meta.column_orders = {{{ColumnOrder::TYPE_ORDER}, {ColumnOrder::TYPE_ORDER}}};
meta.column_orders = {
{{ColumnOrder::IEEE_754_TOTAL_ORDER}, {ColumnOrder::TYPE_ORDER}, {ColumnOrder::TYPE_ORDER}}};

return meta;
}();
Expand Down Expand Up @@ -137,6 +139,8 @@ void expect_column_meta_equal(ColumnChunkMetaData const& e, ColumnChunkMetaData
EXPECT_EQ(e.data_page_offset, a.data_page_offset);
EXPECT_EQ(e.index_page_offset, a.index_page_offset);
EXPECT_EQ(e.dictionary_page_offset, a.dictionary_page_offset);
EXPECT_EQ(e.statistics.null_count, a.statistics.null_count);
EXPECT_EQ(e.statistics.nan_count, a.statistics.nan_count);
}

void expect_column_chunk_equal(ColumnChunk const& e, ColumnChunk const& a)
Expand Down
Loading