-
Notifications
You must be signed in to change notification settings - Fork 174
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
[FEAT] connect:
with_columns_renamed
- Loading branch information
1 parent
f2a1799
commit c69c326
Showing
3 changed files
with
74 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
45 changes: 45 additions & 0 deletions
45
src/daft-connect/src/translation/logical_plan/with_columns_renamed.rs
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,45 @@ | ||
use daft_dsl::col; | ||
use eyre::{bail, Context}; | ||
|
||
use crate::translation::Plan; | ||
|
||
pub async fn with_columns_renamed( | ||
with_columns_renamed: spark_connect::WithColumnsRenamed, | ||
) -> eyre::Result<Plan> { | ||
let spark_connect::WithColumnsRenamed { | ||
input, | ||
rename_columns_map, | ||
renames, | ||
} = with_columns_renamed; | ||
|
||
let Some(input) = input else { | ||
bail!("Input is required"); | ||
}; | ||
|
||
let mut plan = Box::pin(crate::translation::to_logical_plan(*input)).await?; | ||
|
||
// todo: do we want to implement this directly into daft? | ||
|
||
// Convert the rename mappings into expressions | ||
let rename_exprs = if !rename_columns_map.is_empty() { | ||
// Use rename_columns_map if provided (legacy format) | ||
rename_columns_map | ||
.into_iter() | ||
.map(|(old_name, new_name)| col(old_name.as_str()).alias(new_name.as_str())) | ||
.collect() | ||
} else { | ||
// Use renames if provided (new format) | ||
renames | ||
.into_iter() | ||
.map(|rename| col(rename.col_name.as_str()).alias(rename.new_col_name.as_str())) | ||
.collect() | ||
}; | ||
|
||
// Apply the rename expressions to the plan | ||
plan.builder = plan | ||
.builder | ||
.select(rename_exprs) | ||
.wrap_err("Failed to apply rename expressions to logical plan")?; | ||
|
||
Ok(plan) | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,24 @@ | ||
from __future__ import annotations | ||
|
||
|
||
def test_with_columns_renamed(spark_session): | ||
# Test withColumnRenamed | ||
df = spark_session.range(5) | ||
renamed_df = df.withColumnRenamed("id", "number") | ||
|
||
collected = renamed_df.collect() | ||
assert len(collected) == 5 | ||
assert "number" in renamed_df.columns | ||
assert "id" not in renamed_df.columns | ||
assert [row["number"] for row in collected] == list(range(5)) | ||
|
||
# todo: this fails but is this expected or no? | ||
# # Test withColumnsRenamed | ||
# df = spark_session.range(2) | ||
# renamed_df = df.withColumnsRenamed({"id": "number", "id": "character"}) | ||
|
||
# collected = renamed_df.collect() | ||
# assert len(collected) == 2 | ||
# assert set(renamed_df.columns) == {"number", "character"} | ||
# assert "id" not in renamed_df.columns | ||
# assert [(row["number"], row["character"]) for row in collected] == [(0, 0), (1, 1)] |