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

Jump to bottom

Optimize remove action apply with early iteration exit #424 #431

Merged
merged 2 commits into from
Sep 18, 2021
Merged

Optimize remove action apply with early iteration exit #424 #431

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
4e09278
Optimize remove action apply using position and remove
akshay26031996 Sep 16, 2021
2919765
Changing remove to swap_remove
akshay26031996 Sep 18, 2021
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
5 changes: 4 additions & 1 deletion rust/src/delta.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1509,7 +1509,10 @@ fn process_action(state: &mut DeltaTableState, action: Action) -> Result<(), App
state.files.push(v);
}
Action::remove(v) => {
state.files.retain(|a| *a.path != v.path);
let index = { state.files.iter().position(|a| *a.path == v.path) };
if let Some(index) = index {
state.files.swap_remove(index);
}
state.tombstones.push(v);
}
Action::protocol(v) => {
Expand Down
19 changes: 11 additions & 8 deletions rust/tests/read_simple_table_test.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,14 +15,15 @@ async fn read_simple_table() {
assert_eq!(table.get_min_writer_version(), 2);
assert_eq!(table.get_min_reader_version(), 1);
assert_eq!(
table.get_files(),
table.get_files().sort(),
Copy link
Contributor

Choose a reason for hiding this comment

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

sort returns ()

Copy link
Member

Choose a reason for hiding this comment

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

good catch, @akshay26031996 could you send a PR to correct the tests?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Noted, let me go through this.

vec![
"part-00000-c1777d7d-89d9-4790-b38a-6ee7e24456b1-c000.snappy.parquet",
"part-00001-7891c33d-cedc-47c3-88a6-abcfb049d3b4-c000.snappy.parquet",
"part-00004-315835fe-fb44-4562-98f6-5e6cfa3ae45d-c000.snappy.parquet",
"part-00007-3a0e4727-de0d-41b6-81ef-5223cf40f025-c000.snappy.parquet",
"part-00000-2befed33-c358-4768-a43c-3eda0d2a499d-c000.snappy.parquet",
]
.sort()
);
let tombstones = table.get_state().all_tombstones();
assert_eq!(tombstones.len(), 31);
Expand All @@ -38,25 +39,25 @@ async fn read_simple_table() {
);
#[cfg(unix)]
{
let paths: Vec<String> = vec![
let mut paths: Vec<String> = vec![
"./tests/data/simple_table/part-00000-c1777d7d-89d9-4790-b38a-6ee7e24456b1-c000.snappy.parquet".to_string(),
"./tests/data/simple_table/part-00001-7891c33d-cedc-47c3-88a6-abcfb049d3b4-c000.snappy.parquet".to_string(),
"./tests/data/simple_table/part-00004-315835fe-fb44-4562-98f6-5e6cfa3ae45d-c000.snappy.parquet".to_string(),
"./tests/data/simple_table/part-00007-3a0e4727-de0d-41b6-81ef-5223cf40f025-c000.snappy.parquet".to_string(),
"./tests/data/simple_table/part-00000-2befed33-c358-4768-a43c-3eda0d2a499d-c000.snappy.parquet".to_string(),
];
assert_eq!(table.get_file_uris(), paths);
assert_eq!(table.get_file_uris().sort(), paths.sort());
}
#[cfg(windows)]
{
let paths: Vec<String> = vec![
let mut paths: Vec<String> = vec![
"./tests/data/simple_table\\part-00000-c1777d7d-89d9-4790-b38a-6ee7e24456b1-c000.snappy.parquet".to_string(),
"./tests/data/simple_table\\part-00001-7891c33d-cedc-47c3-88a6-abcfb049d3b4-c000.snappy.parquet".to_string(),
"./tests/data/simple_table\\part-00004-315835fe-fb44-4562-98f6-5e6cfa3ae45d-c000.snappy.parquet".to_string(),
"./tests/data/simple_table\\part-00007-3a0e4727-de0d-41b6-81ef-5223cf40f025-c000.snappy.parquet".to_string(),
"./tests/data/simple_table\\part-00000-2befed33-c358-4768-a43c-3eda0d2a499d-c000.snappy.parquet".to_string(),
];
assert_eq!(table.get_file_uris(), paths);
assert_eq!(table.get_file_uris().sort(), paths.sort());
}
}

Expand Down Expand Up @@ -87,7 +88,7 @@ async fn read_simple_table_with_version() {
assert_eq!(table.get_min_writer_version(), 2);
assert_eq!(table.get_min_reader_version(), 1);
assert_eq!(
table.get_files(),
table.get_files().sort(),
vec![
"part-00000-c1777d7d-89d9-4790-b38a-6ee7e24456b1-c000.snappy.parquet",
"part-00001-7891c33d-cedc-47c3-88a6-abcfb049d3b4-c000.snappy.parquet",
Expand All @@ -96,6 +97,7 @@ async fn read_simple_table_with_version() {
"part-00006-46f2ff20-eb5d-4dda-8498-7bfb2940713b-c000.snappy.parquet",
"part-00007-3a0e4727-de0d-41b6-81ef-5223cf40f025-c000.snappy.parquet",
]
.sort()
);

table = deltalake::open_table_with_version("./tests/data/simple_table", 3)
Expand All @@ -105,15 +107,16 @@ async fn read_simple_table_with_version() {
assert_eq!(table.get_min_writer_version(), 2);
assert_eq!(table.get_min_reader_version(), 1);
assert_eq!(
table.get_files(),
table.get_files().sort(),
vec![
"part-00000-c1777d7d-89d9-4790-b38a-6ee7e24456b1-c000.snappy.parquet",
"part-00001-7891c33d-cedc-47c3-88a6-abcfb049d3b4-c000.snappy.parquet",
"part-00004-315835fe-fb44-4562-98f6-5e6cfa3ae45d-c000.snappy.parquet",
"part-00007-3a0e4727-de0d-41b6-81ef-5223cf40f025-c000.snappy.parquet",
"part-00000-f17fcbf5-e0dc-40ba-adae-ce66d1fcaef6-c000.snappy.parquet",
"part-00001-bb70d2ba-c196-4df2-9c85-f34969ad3aa9-c000.snappy.parquet",
],
]
.sort(),
);
}

Expand Down