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

WIP Upgrade to arrow-rs/parquet 54.0.0 #13663

Open
wants to merge 8 commits into
base: main
Choose a base branch
from
Open

WIP Upgrade to arrow-rs/parquet 54.0.0 #13663

Show file tree
Hide file tree
Changes from 6 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
5554b92
Temp patch to new arrow-rs release
alamb Dec 5, 2024
4991cc4
chore: Update for API changes
alamb Dec 5, 2024
f13b588
Update for new pyo3 API
alamb Dec 7, 2024
00a66bd
Allow deprecated methods for dict_id
alamb Dec 16, 2024
2fe785b
remove unused max_statistics_size field
alamb Dec 17, 2024
24fd642
Update docs
alamb Dec 21, 2024
794eb38
chore: remove max_statistics_size
alamb Dec 21, 2024
5e0ea62
Merge remote-tracking branch 'apache/main' into alamb/upgrade_to_arrow
alamb Dec 21, 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
31 changes: 23 additions & 8 deletions Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -77,21 +77,21 @@ version = "43.0.0"
ahash = { version = "0.8", default-features = false, features = [
"runtime-rng",
] }
arrow = { version = "53.3.0", features = [
arrow = { version = "54.0.0", features = [
"prettyprint",
] }
arrow-array = { version = "53.3.0", default-features = false, features = [
arrow-array = { version = "54.0.0", default-features = false, features = [
"chrono-tz",
] }
arrow-buffer = { version = "53.3.0", default-features = false }
arrow-flight = { version = "53.3.0", features = [
arrow-buffer = { version = "54.0.0", default-features = false }
arrow-flight = { version = "54.0.0", features = [
"flight-sql-experimental",
] }
arrow-ipc = { version = "53.3.0", default-features = false, features = [
arrow-ipc = { version = "54.0.0", default-features = false, features = [
"lz4",
] }
arrow-ord = { version = "53.3.0", default-features = false }
arrow-schema = { version = "53.3.0", default-features = false }
arrow-ord = { version = "54.0.0", default-features = false }
arrow-schema = { version = "54.0.0", default-features = false }
async-trait = "0.1.73"
bigdecimal = "0.4.7"
bytes = "1.4"
Expand Down Expand Up @@ -133,7 +133,7 @@ itertools = "0.13"
log = "^0.4"
object_store = { version = "0.11.0", default-features = false }
parking_lot = "0.12"
parquet = { version = "53.3.0", default-features = false, features = [
parquet = { version = "54.0.0", default-features = false, features = [
"arrow",
"async",
"object_store",
Expand Down 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/apache/arrow-rs.git", tag = "54.0.0" }
arrow-array = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
arrow-buffer = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
arrow-cast = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
arrow-data = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
arrow-ipc = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
arrow-schema = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
arrow-select = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
arrow-string = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
arrow-ord = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
arrow-flight = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
parquet = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
88 changes: 35 additions & 53 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.

19 changes: 17 additions & 2 deletions datafusion-cli/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ rust-version = "1.80.1"
readme = "README.md"

[dependencies]
arrow = { version = "53.0.0" }
arrow = { version = "54.0.0" }
async-trait = "0.1.73"
aws-config = "1.5.5"
aws-sdk-sso = "1.43.0"
Expand Down Expand Up @@ -58,7 +58,7 @@ home = "=0.5.9"
mimalloc = { version = "0.1", default-features = false }
object_store = { version = "0.11.0", features = ["aws", "gcp", "http"] }
parking_lot = { version = "0.12" }
parquet = { version = "53.0.0", default-features = false }
parquet = { version = "54.0.0", default-features = false }
regex = "1.8"
rustyline = "14.0"
tokio = { version = "1.24", features = ["macros", "rt", "rt-multi-thread", "sync", "parking_lot", "signal"] }
Expand All @@ -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/apache/arrow-rs.git", tag = "54.0.0" }
arrow-array = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
arrow-buffer = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
arrow-cast = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
arrow-data = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
arrow-ipc = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
arrow-schema = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
arrow-select = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
arrow-string = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
arrow-ord = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
arrow-flight = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
parquet = { git = "https://github.com/apache/arrow-rs.git", tag = "54.0.0" }
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 @@ -61,7 +61,7 @@ log = { workspace = true }
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 @@ -459,10 +459,6 @@ config_namespace! {
/// default parquet writer setting
pub statistics_enabled: Option<String>, transform = str::to_lowercase, 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)
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think simply removing the config option is pretty rough as you end up with errors liek this

External error: query failed: DataFusion error: Invalid or Unsupported Configuration: Config value "max_statistics_size" not found on ParquetOptions

The best thing to do would be to mark the config setting deprecated, but there wasn't an obvious way to do this with the existing macros. I will futz with the macros and see if I can make it deprecated somehow


/// (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 @@ -1653,10 +1649,6 @@ 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
Loading
Loading