rust-data-processing documentation

Browse API reference for the Rust crate (rustdoc), the Python bindings (pdoc), and JVM integration (Markdown → HTML). This site is generated on every push to main.

Minimal examples

Rust

use rust_data_processing::ingestion::{ingest_from_path, IngestionOptions};
use rust_data_processing::types::{DataType, Field, Schema};

let schema = Schema::new(vec![
    Field::new("id", DataType::Int64),
    Field::new("name", DataType::Utf8),
]);
let ds = ingest_from_path("tests/fixtures/people.csv", &schema, &IngestionOptions::default())?;
println!("rows={}", ds.row_count());

Python

import rust_data_processing as rdp

schema = [
    {"name": "id", "data_type": "int64"},
    {"name": "name", "data_type": "utf8"},
]
ds = rdp.ingest_from_path("path/to/data.csv", schema, {"format": "csv"})
print("rows", ds.row_count())

Java (parity JSON over Panama)

// After rdp_jvm_sys is on the classpath (rdp-jvm-sys classifier) — see java/examples.html
JSONObject root = RdpNativeJson.invokeParityExport(
    linker, lookup, arena, "rdp_parity_watermark_mirror");
PytestMirrorAssertions.validateMirrorExport(
    "rdp_parity_watermark_mirror", root);