elusion 8.3.0

Elusion is a modern DataFrame / Data Engineering / Data Analysis library that combines the familiarity of DataFrame operations (like those in PySpark, Pandas, and Polars) with the power of SQL query building. It provides flexible query construction without enforcing strict operation ordering, enabling developers to write intuitive and maintainable data transformations.
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46

use crate::prelude::*;

// The registry key - just a name
pub type NodeName = String;

// What layer is this node in
#[derive(Debug, Clone, PartialEq)]
pub enum NodeLayer {
    Source,
    Bronze,
    Silver,
    Gold,
}

// A resolved node after execution - holds the materialized DataFrame
#[derive(Clone)]
pub struct ResolvedNode {
    pub name: NodeName,
    pub layer: NodeLayer,
    pub df: CustomDataFrame,
}

// The async closure type each node holds
pub type NodeFn = Box<
    dyn Fn(NodeRegistry) -> Pin<Box<dyn Future<Output = ElusionResult<CustomDataFrame>> + Send>>
    + Send
    + Sync
>;

// A registered but not yet executed node
pub struct Node {
    pub name: NodeName,
    pub layer: NodeLayer,
    pub dependencies: Vec<NodeName>,  // populated by ref_* calls
    pub execute: NodeFn,
}

impl std::fmt::Debug for Node {
    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
        f.debug_struct("Node")
            .field("name", &self.name)
            .field("layer", &self.layer)
            .field("dependencies", &self.dependencies)
            .finish()
    }
}