scan example

iceberg_rust_scan.rs

use std::collections::HashMap;

use futures::TryStreamExt;
use iceberg::{
    io::{S3_ACCESS_KEY_ID, S3_ENDPOINT, S3_SECRET_ACCESS_KEY},
    Catalog, TableIdent,
};
use iceberg_catalog_rest::{RestCatalog, RestCatalogConfig};

#[tokio::main]
async fn main() {
    // Create catalog
    let config = RestCatalogConfig::builder()
        .uri("http://localhost:8181".to_string())
        .warehouse("demo".to_string())
        .props(HashMap::from([
            (S3_ENDPOINT.to_string(), "http://localhost:9000".to_string()),
            (S3_ACCESS_KEY_ID.to_string(), "admin".to_string()),
            (S3_SECRET_ACCESS_KEY.to_string(), "password".to_string()),
        ]))
        .build();

    let catalog = RestCatalog::new(config);

    let table = catalog
        .load_table(&TableIdent::from_strs(["default", "cities"]).unwrap())
        .await
        .unwrap();

    let scan = table.scan().select_all().build().unwrap();
    let batch_stream = scan.to_arrow().await.unwrap();

    dbg!(scan);

    let batches: Vec<_> = batch_stream.try_collect().await.unwrap();

    dbg!(batches.len());
}

py_iceberg_scan.py

from pyiceberg.catalog import load_catalog
from pyiceberg.table import Table

catalog = load_catalog(
    "demo",
    **{
        "type": "rest",
        "uri": "http://localhost:8181/",
        "s3.endpoint": "http://localhost:9000",
        "s3.access-key-id": "admin",
        "s3.secret-access-key": "password",
        "warehouse": "demo",
    },
)

tbl: Table = catalog.load_table("default.cities")

res = tbl.scan().to_arrow()

print(len(res))