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

Alamb/test parquet #13820

Draft
wants to merge 7 commits into
base: main
Choose a base branch
from
Draft

Alamb/test parquet #13820

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
ac84d57
Temp patch to new arrow-rs release
alamb Dec 5, 2024
4b75e07
chore: Update for API changes
alamb Dec 5, 2024
8cc13a2
Update for new pyo3 API
alamb Dec 7, 2024
d2317a8
Allow deprecated methods for dict_id
alamb Dec 16, 2024
3d6002a
chore: update datafusion-cli/Cargo.lock
alamb Dec 17, 2024
fb080a2
remove unused max_statistics_size field
alamb Dec 17, 2024
16ca260
update for new branch
alamb Dec 18, 2024
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
15 changes: 15 additions & 0 deletions Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -177,3 +177,18 @@ large_futures = "warn"
[workspace.lints.rust]
unexpected_cfgs = { level = "warn", check-cfg = ["cfg(tarpaulin)"] }
unused_qualifications = "deny"

# Temp patch to main of arrow-rs
[patch.crates-io]
arrow = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-array = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-buffer = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-cast = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-data = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-ipc = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-schema = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-select = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-string = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-ord = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-flight = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
parquet = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
74 changes: 28 additions & 46 deletions datafusion-cli/Cargo.lock
View file
Open in desktop

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

15 changes: 15 additions & 0 deletions datafusion-cli/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,3 +69,18 @@ assert_cmd = "2.0"
ctor = "0.2.0"
predicates = "3.0"
rstest = "0.22"

# Temp patch to main of arrow-rs
[patch.crates-io]
arrow = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-array = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-buffer = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-cast = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-data = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-ipc = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-schema = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-select = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-string = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-ord = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
arrow-flight = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
parquet = { git = "https://github.com/alamb/arrow-rs.git", rev = "78994df5316106b4db2601ba4f641359b2b8084c" }
2 changes: 1 addition & 1 deletion datafusion/common/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -60,7 +60,7 @@ libc = "0.2.140"
object_store = { workspace = true, optional = true }
parquet = { workspace = true, optional = true, default-features = true }
paste = "1.0.15"
pyo3 = { version = "0.22.0", optional = true }
pyo3 = { version = "0.23.3", optional = true }
recursive = { workspace = true }
sqlparser = { workspace = true }
tokio = { workspace = true }
Expand Down
8 changes: 0 additions & 8 deletions datafusion/common/src/config.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -446,10 +446,6 @@ config_namespace! {
/// default parquet writer setting
pub statistics_enabled: Option<String>, default = Some("page".into())

/// (writing) Sets max statistics size for any column. If NULL, uses
/// default parquet writer setting
pub max_statistics_size: Option<usize>, default = Some(4096)

/// (writing) Target maximum number of rows in each row group (defaults to 1M
/// rows). Writing larger row groups requires more memory to write, but
/// can get better compression and be faster to read.
Expand Down Expand Up @@ -1621,10 +1617,6 @@ config_namespace_with_hashmap! {
/// Sets bloom filter number of distinct values. If NULL, uses
/// default parquet options
pub bloom_filter_ndv: Option<u64>, default = None

/// Sets max statistics size for the column path. If NULL, uses
/// default parquet options
pub max_statistics_size: Option<usize>, default = None
}
}

Expand Down
15 changes: 1 addition & 14 deletions datafusion/common/src/file_options/parquet_writer.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,7 +26,7 @@ use parquet::{
basic::{BrotliLevel, GzipLevel, ZstdLevel},
file::properties::{
EnabledStatistics, WriterProperties, WriterPropertiesBuilder, WriterVersion,
DEFAULT_MAX_STATISTICS_SIZE, DEFAULT_STATISTICS_ENABLED,
DEFAULT_STATISTICS_ENABLED,
},
format::KeyValue,
schema::types::ColumnPath,
Expand Down Expand Up @@ -129,11 +129,6 @@ impl TryFrom<&TableParquetOptions> for WriterPropertiesBuilder {
builder =
builder.set_column_bloom_filter_ndv(path.clone(), bloom_filter_ndv);
}

if let Some(max_statistics_size) = options.max_statistics_size {
builder =
builder.set_column_max_statistics_size(path, max_statistics_size);
}
}

Ok(builder)
Expand All @@ -154,7 +149,6 @@ impl ParquetOptions {
dictionary_enabled,
dictionary_page_size_limit,
statistics_enabled,
max_statistics_size,
max_row_group_size,
created_by,
column_index_truncate_length,
Expand Down Expand Up @@ -190,9 +184,6 @@ impl ParquetOptions {
.and_then(|s| parse_statistics_string(s).ok())
.unwrap_or(DEFAULT_STATISTICS_ENABLED),
)
.set_max_statistics_size(
max_statistics_size.unwrap_or(DEFAULT_MAX_STATISTICS_SIZE),
)
.set_max_row_group_size(*max_row_group_size)
.set_created_by(created_by.clone())
.set_column_index_truncate_length(*column_index_truncate_length)
Expand Down Expand Up @@ -395,7 +386,6 @@ mod tests {
compression: Some("zstd(22)".into()),
dictionary_enabled: src_col_defaults.dictionary_enabled.map(|v| !v),
statistics_enabled: Some("none".into()),
max_statistics_size: Some(72),
encoding: Some("RLE".into()),
bloom_filter_enabled: Some(true),
bloom_filter_fpp: Some(0.72),
Expand All @@ -419,7 +409,6 @@ mod tests {
dictionary_enabled: Some(!defaults.dictionary_enabled.unwrap_or(false)),
dictionary_page_size_limit: 42,
statistics_enabled: Some("chunk".into()),
max_statistics_size: Some(42),
max_row_group_size: 42,
created_by: "wordy".into(),
column_index_truncate_length: Some(42),
Expand Down Expand Up @@ -473,7 +462,6 @@ mod tests {
),
bloom_filter_fpp: bloom_filter_default_props.map(|p| p.fpp),
bloom_filter_ndv: bloom_filter_default_props.map(|p| p.ndv),
max_statistics_size: Some(props.max_statistics_size(&col)),
}
}

Expand Down Expand Up @@ -523,7 +511,6 @@ mod tests {
compression: default_col_props.compression,
dictionary_enabled: default_col_props.dictionary_enabled,
statistics_enabled: default_col_props.statistics_enabled,
max_statistics_size: default_col_props.max_statistics_size,
bloom_filter_on_write: default_col_props
.bloom_filter_enabled
.unwrap_or_default(),
Expand Down
Loading
Loading