PyIceberg

Connect

from pyiceberg.catalog.rest import RestCatalog
catalog = RestCatalog(name='lhbox', uri='https://catalog.lakehousebox.com',
                      warehouse='s3://<handle>--<catalog>/', credential='<client_id>:<client_secret>',
                      **{'s3.endpoint': 'https://s3.lakehousebox.com', 's3.path-style-access': 'true'})
table = catalog.load_table(('<namespace>', '<table>'))

# writing: create from an Arrow schema, then append
import pyarrow.parquet as pq
arrow = pq.read_table('cities.parquet')
tbl = catalog.create_table(('demo', 'cities'), schema=arrow.schema)
tbl.append(arrow)

PyIceberg writes one data file per append and a complete snapshot summary; DuckDB splits large writes into several files. Both are read identically by either engine.