Skip to content

chore: Update to arrow/parquet 59.0.0 #22744

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

Draft
alamb wants to merge 2 commits into
base: main
Choose a base branch
from
+132 −160
Draft

chore: Update to arrow/parquet 59.0.0 #22744

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
350fd91
chore: Update to arrow/parquet 59.0.0
alamb Jun 3, 2026
4d274ef
Update code for API changes
alamb Jun 3, 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
116 changes: 36 additions & 80 deletions Cargo.lock
View file
Open in desktop

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

36 changes: 27 additions & 9 deletions Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,30 +89,30 @@ version = "53.1.0"
#
# See for more details: https://github.com/rust-lang/cargo/issues/11329
apache-avro = { version = "0.21", default-features = false }
arrow = { version = "58.3.0", features = [
arrow = { version = "59.0.0", features = [
"prettyprint",
"chrono-tz",
] }
arrow-avro = { version = "58.3.0", default-features = false, features = [
arrow-avro = { version = "59.0.0", default-features = false, features = [
"deflate",
"snappy",
"zstd",
"bzip2",
"xz",
] }
arrow-buffer = { version = "58.3.0", default-features = false }
arrow-data = { version = "58.3.0", default-features = false }
arrow-flight = { version = "58.3.0", features = [
arrow-buffer = { version = "59.0.0", default-features = false }
arrow-data = { version = "59.0.0", default-features = false }
arrow-flight = { version = "59.0.0", features = [
"flight-sql-experimental",
] }
# Both codecs are required here to make sure that code paths like
# file-spilling have access to all compression codecs.
arrow-ipc = { version = "58.3.0", default-features = false, features = [
arrow-ipc = { version = "59.0.0", default-features = false, features = [
"lz4",
"zstd",
] }
arrow-ord = { version = "58.3.0", default-features = false }
arrow-schema = { version = "58.3.0", default-features = false }
arrow-ord = { version = "59.0.0", default-features = false }
arrow-schema = { version = "59.0.0", default-features = false }
async-trait = "0.1.89"
bigdecimal = "0.4.8"
bytes = "1.11"
Expand Down Expand Up @@ -178,7 +178,7 @@ memchr = "2.8.0"
num-traits = { version = "0.2" }
object_store = { version = "0.13.2", default-features = false }
parking_lot = "0.12"
parquet = { version = "58.3.0", default-features = false, features = [
parquet = { version = "59.0.0", default-features = false, features = [
"arrow",
"async",
"object_store",
Expand Down Expand Up @@ -291,3 +291,21 @@ debug = false
debug-assertions = false
strip = "debuginfo"
incremental = false


## Temporary arrow-rs patch until 59.0.0 is released

[patch.crates-io]
arrow = { git = "https://github.com/apache/arrow-rs.git", rev = "dc765326433b1e2efcf0fb91168b95fb10314ebd" }
arrow-array = { git = "https://github.com/apache/arrow-rs.git", rev = "dc765326433b1e2efcf0fb91168b95fb10314ebd" }
arrow-avro = { git = "https://github.com/apache/arrow-rs.git", rev = "dc765326433b1e2efcf0fb91168b95fb10314ebd" }
arrow-buffer = { git = "https://github.com/apache/arrow-rs.git", rev = "dc765326433b1e2efcf0fb91168b95fb10314ebd" }
arrow-cast = { git = "https://github.com/apache/arrow-rs.git", rev = "dc765326433b1e2efcf0fb91168b95fb10314ebd" }
arrow-data = { git = "https://github.com/apache/arrow-rs.git", rev = "dc765326433b1e2efcf0fb91168b95fb10314ebd" }
arrow-ipc = { git = "https://github.com/apache/arrow-rs.git", rev = "dc765326433b1e2efcf0fb91168b95fb10314ebd" }
arrow-schema = { git = "https://github.com/apache/arrow-rs.git", rev = "dc765326433b1e2efcf0fb91168b95fb10314ebd" }
arrow-select = { git = "https://github.com/apache/arrow-rs.git", rev = "dc765326433b1e2efcf0fb91168b95fb10314ebd" }
arrow-string = { git = "https://github.com/apache/arrow-rs.git", rev = "dc765326433b1e2efcf0fb91168b95fb10314ebd" }
arrow-ord = { git = "https://github.com/apache/arrow-rs.git", rev = "dc765326433b1e2efcf0fb91168b95fb10314ebd" }
arrow-flight = { git = "https://github.com/apache/arrow-rs.git", rev = "dc765326433b1e2efcf0fb91168b95fb10314ebd" }
parquet = { git = "https://github.com/apache/arrow-rs.git", rev = "dc765326433b1e2efcf0fb91168b95fb10314ebd" }
12 changes: 6 additions & 6 deletions datafusion-cli/src/main.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -613,9 +613,9 @@ mod tests {
+-----------------------------------+-----------------+---------------------+------+------------------+
| filename | file_size_bytes | metadata_size_bytes | hits | extra |
+-----------------------------------+-----------------+---------------------+------+------------------+
| alltypes_plain.parquet | 1851 | 8882 | 2 | page_index=false |
| alltypes_tiny_pages.parquet | 454233 | 269074 | 2 | page_index=true |
| lz4_raw_compressed_larger.parquet | 380836 | 1339 | 2 | page_index=false |
| alltypes_plain.parquet | 1851 | 8794 | 2 | page_index=false |
Copy link
Copy Markdown
Contributor Author

@alamb alamb Jun 4, 2026 •
edited
Loading

Choose a reason for hiding this comment

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

I think this changed (smaller in memory size) due to the representation change of CompressionCodec in this pr

It changes from Compression which also carries the compression level: ZSTD(ZstdLevel), GZIP(GzipLevel), BROTLI(BrotliLevel) — and ZstdLevel(i32) / GzipLevel(u32) / BrotliLevel(u32) and are 4-byte wrappers. So Compression = 4-byte discriminant + 4-byte level = 8 bytes.

To a fieldless enum CompressionCodec -- 1 byte

| alltypes_tiny_pages.parquet | 454233 | 268970 | 2 | page_index=true |
| lz4_raw_compressed_larger.parquet | 380836 | 1331 | 2 | page_index=false |
+-----------------------------------+-----------------+---------------------+------+------------------+
");

Expand Down Expand Up @@ -644,9 +644,9 @@ mod tests {
+-----------------------------------+-----------------+---------------------+------+------------------+
| filename | file_size_bytes | metadata_size_bytes | hits | extra |
+-----------------------------------+-----------------+---------------------+------+------------------+
| alltypes_plain.parquet | 1851 | 8882 | 5 | page_index=false |
| alltypes_tiny_pages.parquet | 454233 | 269074 | 2 | page_index=true |
| lz4_raw_compressed_larger.parquet | 380836 | 1339 | 3 | page_index=false |
| alltypes_plain.parquet | 1851 | 8794 | 5 | page_index=false |
| alltypes_tiny_pages.parquet | 454233 | 268970 | 2 | page_index=true |
| lz4_raw_compressed_larger.parquet | 380836 | 1331 | 3 | page_index=false |
+-----------------------------------+-----------------+---------------------+------+------------------+
");

Expand Down
Loading
Loading