Skip to content
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
47 commits
Select commit Hold shift + click to select a range
120d2b0
Update to pre-release arrow
alamb Dec 16, 2025
40a6a71
Fix clippy due to UnionFields::new is deprecated
alamb Dec 16, 2025
f50b9c3
Fix real bug in test
alamb Dec 16, 2025
87563d8
Update test for fixed issue upstream
alamb Dec 16, 2025
4afd46f
Update tests for new feature
alamb Dec 18, 2025
70e2841
Update tests for struct casting
alamb Dec 18, 2025
b29b662
Update to latest
alamb Jan 7, 2026
6a2e631
Merge remote-tracking branch 'apache/main' into alamb/update_arrow_57…
alamb Jan 7, 2026
ca11966
Merge branch 'main' into alamb/update_arrow_57.2.0
alamb Jan 8, 2026
63a85eb
Update to pre-release main
alamb Jan 10, 2026
277aac4
Update expected value of make_interval
alamb Jan 10, 2026
bb29b0c
Update expected output
alamb Jan 10, 2026
35b97fa
Update to latest arrow
alamb Jan 10, 2026
d2e8da6
Update rev
Dandandan Jan 16, 2026
1002408
update outputs
Dandandan Jan 16, 2026
c062756
Merge
Dandandan Jan 16, 2026
917a464
Update rev
Dandandan Jan 20, 2026
c1d27d3
Update again
Dandandan Jan 22, 2026
1b979c6
Update rev
Dandandan Jan 23, 2026
c3df7be
Merge branch 'main' into alamb/update_arrow_58
Dandandan Jan 23, 2026
d79a8a0
Merge remote-tracking branch 'apache/main' into alamb/update_arrow_58
alamb Jan 30, 2026
21fabb5
Update to latest
alamb Jan 30, 2026
36cfd5e
Update for deprecated
alamb Jan 30, 2026
c273703
Update to object_store 0.13.0
alamb Jan 30, 2026
855b51b
Update more
alamb Jan 30, 2026
bdd19a6
More updates
alamb Jan 30, 2026
0d0cc96
updates
alamb Jan 30, 2026
ccf7a14
cleanups
alamb Jan 30, 2026
1a65bf7
remove uneeded code
alamb Jan 30, 2026
206de80
Merge remote-tracking branch 'apache/main' into alamb/update_arrow_58
alamb Jan 30, 2026
778ac16
update
alamb Jan 30, 2026
ddd778d
Remove old comments
alamb Jan 30, 2026
afb5ba3
fixup request counting
alamb Jan 30, 2026
0622248
fix delete
alamb Jan 30, 2026
e4449fd
clippy
alamb Jan 30, 2026
987f879
Upate tests and for clippy
alamb Jan 30, 2026
70a958a
more clipy
alamb Jan 30, 2026
5452d50
Update test as now utf8->float is supported
alamb Jan 30, 2026
9276a8a
fmt
alamb Jan 30, 2026
cae9716
Update to latest main
alamb Feb 3, 2026
d568137
Merge remote-tracking branch 'apache/main' into alamb/update_arrow_58
alamb Feb 3, 2026
6762cb7
Fix object store ugprade
alamb Feb 3, 2026
14a3601
Update expected error message
alamb Feb 3, 2026
2ad66f1
fix test
alamb Feb 3, 2026
16d34ad
Merge remote-tracking branch 'apache/main' into alamb/update_arrow_58
alamb Feb 3, 2026
8d7580a
Merge remote-tracking branch 'apache/main' into alamb/update_arrow_58
alamb Feb 8, 2026
70d22da
Update to latest
alamb Feb 8, 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
89 changes: 37 additions & 52 deletions Cargo.lock

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

31 changes: 30 additions & 1 deletion Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -164,7 +164,7 @@ itertools = "0.14"
liblzma = { version = "0.4.4", features = ["static"] }
log = "^0.4"
num-traits = { version = "0.2" }
object_store = { version = "0.12.4", default-features = false }
object_store = { version = "0.13.1", default-features = false }
parking_lot = "0.12"
parquet = { version = "57.2.0", default-features = false, features = [
"arrow",
Expand Down Expand Up @@ -275,3 +275,32 @@ incremental = false
inherits = "release"
debug = true
strip = false

## Temporary arrow-rs patch until 58 is released

[patch.crates-io]
arrow = { git = "https://github.com/apache/arrow-rs.git", branch = "main" }
arrow-array = { git = "https://github.com/apache/arrow-rs.git", branch = "main" }
arrow-buffer = { git = "https://github.com/apache/arrow-rs.git", branch = "main" }
arrow-cast = { git = "https://github.com/apache/arrow-rs.git", branch = "main" }
arrow-data = { git = "https://github.com/apache/arrow-rs.git", branch = "main" }
arrow-ipc = { git = "https://github.com/apache/arrow-rs.git", branch = "main" }
arrow-schema = { git = "https://github.com/apache/arrow-rs.git", branch = "main" }
arrow-select = { git = "https://github.com/apache/arrow-rs.git", branch = "main" }
arrow-string = { git = "https://github.com/apache/arrow-rs.git", branch = "main" }
arrow-ord = { git = "https://github.com/apache/arrow-rs.git", branch = "main" }
arrow-flight = { git = "https://github.com/apache/arrow-rs.git", branch = "main" }
parquet = { git = "https://github.com/apache/arrow-rs.git", branch = "main" }

#arrow = { path= "/Users/andrewlamb/Software/arrow-rs2/arrow" }
#arrow-array = { path= "/Users/andrewlamb/Software/arrow-rs2/arrow-array" }
#arrow-buffer = { path= "/Users/andrewlamb/Software/arrow-rs2/arrow-buffer" }
#arrow-cast = { path= "/Users/andrewlamb/Software/arrow-rs2/arrow-cast" }
#arrow-data = { path= "/Users/andrewlamb/Software/arrow-rs2/arrow-data" }
#arrow-ipc = { path= "/Users/andrewlamb/Software/arrow-rs2/arrow-ipc" }
#arrow-schema = { path= "/Users/andrewlamb/Software/arrow-rs2/arrow-schema" }
#arrow-select = { path= "/Users/andrewlamb/Software/arrow-rs2/arrow-select" }
#arrow-string = { path= "/Users/andrewlamb/Software/arrow-rs2/arrow-string" }
#arrow-ord = { path= "/Users/andrewlamb/Software/arrow-rs2/arrow-ord" }
#arrow-flight = { path= "/Users/andrewlamb/Software/arrow-rs2/arrow-flight" }
#parquet = { path= "/Users/andrewlamb/Software/arrow-rs2/parquet" }
10 changes: 5 additions & 5 deletions datafusion-cli/src/exec.rs
Original file line number Diff line number Diff line change
Expand Up @@ -521,6 +521,7 @@ mod tests {
use datafusion::common::plan_err;

use datafusion::prelude::SessionContext;
use datafusion_common::assert_contains;
use url::Url;

async fn create_external_table_test(location: &str, sql: &str) -> Result<()> {
Expand Down Expand Up @@ -714,25 +715,24 @@ mod tests {
let err = create_external_table_test(location, &sql)
.await
.unwrap_err();
assert!(err.to_string().contains("os error 2"));
assert_contains!(err.to_string(), "os error 2");

// for service_account_key
let sql = format!(
"CREATE EXTERNAL TABLE test STORED AS PARQUET OPTIONS('gcp.service_account_key' '{service_account_key}') LOCATION '{location}'"
);
let err = create_external_table_test(location, &sql)
.await
.unwrap_err()
.to_string();
assert!(err.contains("No RSA key found in pem file"), "{err}");
.unwrap_err();
assert_contains!(err.to_string(), "Error reading pem file: no items found");

// for application_credentials_path
let sql = format!("CREATE EXTERNAL TABLE test STORED AS PARQUET
OPTIONS('gcp.application_credentials_path' '{application_credentials_path}') LOCATION '{location}'");
let err = create_external_table_test(location, &sql)
.await
.unwrap_err();
assert!(err.to_string().contains("os error 2"));
assert_contains!(err.to_string(), "os error 2");

Ok(())
}
Expand Down
8 changes: 4 additions & 4 deletions datafusion-cli/src/main.rs
Original file line number Diff line number Diff line change
Expand Up @@ -617,8 +617,8 @@ 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 | 269266 | 2 | page_index=true |
| lz4_raw_compressed_larger.parquet | 380836 | 1347 | 2 | page_index=false |
| alltypes_tiny_pages.parquet | 454233 | 269074 | 2 | page_index=true |
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 this reduction in metadata size is a direct consequence of @WaterWhisperer's PR to improve PageEncoding representation

| lz4_raw_compressed_larger.parquet | 380836 | 1339 | 2 | page_index=false |
+-----------------------------------+-----------------+---------------------+------+------------------+
");

Expand Down Expand Up @@ -648,8 +648,8 @@ 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 | 269266 | 2 | page_index=true |
| lz4_raw_compressed_larger.parquet | 380836 | 1347 | 3 | page_index=false |
| alltypes_tiny_pages.parquet | 454233 | 269074 | 2 | page_index=true |
| lz4_raw_compressed_larger.parquet | 380836 | 1339 | 3 | page_index=false |
+-----------------------------------+-----------------+---------------------+------+------------------+
");

Expand Down
Loading