kevinjqliu commented on code in PR #825: URL: https://github.com/apache/iceberg-rust/pull/825#discussion_r1903134096
########## crates/integration_tests/testdata/pyiceberg/Dockerfile: ########## @@ -0,0 +1,22 @@ +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. + +FROM python:3.9-bullseye + +RUN pip install pyiceberg[pyarrow]==0.8 Review Comment: nit: 0.8.1 is the latest version ########## crates/integration_tests/testdata/pyiceberg/provision.py: ########## @@ -0,0 +1,87 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. + +import os +from pyiceberg.catalog import load_catalog +import pyarrow.parquet as pq +import pyarrow as pa +from datetime import datetime, timedelta + +# Generate a table with various types in memory and dump to a Parquet file +rows = 1001 +columns = [ + pa.array([(i % 2 == 1) for i in range(rows)]), + pa.array([(i % 256 - 128) for i in range(rows)]), + pa.array([i for i in range(rows)]), + pa.array([i for i in range(rows)]), + pa.array([i for i in range(rows)]), + pa.array([float(i) for i in range(rows)]), + pa.array([float(i) for i in range(rows)]), + pa.array([round(i / 100, 2) for i in range(rows)]), + pa.array([(datetime(1970, 1, 1) + timedelta(days=i)).date() for i in range(rows)]), + pa.array([(datetime(1970, 1, 1) + timedelta(seconds=i)) for i in range(rows)]), + pa.array([(datetime(1970, 1, 1) + timedelta(seconds=i)) for i in range(rows)]), + pa.array([str(i) for i in range(rows)]), + pa.array([str(i).encode("utf-8") for i in range(rows)]), +] +schema = pa.schema([ + ('cboolean', pa.bool_()), + ('cint8', pa.int8()), + ('cint16', pa.int16()), + ('cint32', pa.int32()), + ('cint64', pa.int64()), + ('cfloat32', pa.float32()), + ('cfloat64', pa.float64()), + ('cdecimal128', pa.decimal128(8, 2)), + ('cdate32', pa.date32()), + ('ctimestamp', pa.timestamp('us')), + ('ctimestamptz', pa.timestamp('us', tz='UTC')), + ('cutf8', pa.utf8()), + ('cbinary', pa.binary()), +]) Review Comment: do we want to include other data types? including complex types? like in https://github.com/apache/iceberg-python/blob/acd6f5a8a19db709e835e2686b87d4db3dca254f/tests/conftest.py#L304-L349 ########## crates/integration_tests/testdata/pyiceberg/provision.py: ########## @@ -0,0 +1,87 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. + +import os +from pyiceberg.catalog import load_catalog +import pyarrow.parquet as pq +import pyarrow as pa +from datetime import datetime, timedelta + +# Generate a table with various types in memory and dump to a Parquet file +rows = 1001 +columns = [ + pa.array([(i % 2 == 1) for i in range(rows)]), + pa.array([(i % 256 - 128) for i in range(rows)]), + pa.array([i for i in range(rows)]), + pa.array([i for i in range(rows)]), + pa.array([i for i in range(rows)]), + pa.array([float(i) for i in range(rows)]), + pa.array([float(i) for i in range(rows)]), + pa.array([round(i / 100, 2) for i in range(rows)]), + pa.array([(datetime(1970, 1, 1) + timedelta(days=i)).date() for i in range(rows)]), + pa.array([(datetime(1970, 1, 1) + timedelta(seconds=i)) for i in range(rows)]), + pa.array([(datetime(1970, 1, 1) + timedelta(seconds=i)) for i in range(rows)]), + pa.array([str(i) for i in range(rows)]), + pa.array([str(i).encode("utf-8") for i in range(rows)]), +] +schema = pa.schema([ + ('cboolean', pa.bool_()), + ('cint8', pa.int8()), + ('cint16', pa.int16()), + ('cint32', pa.int32()), + ('cint64', pa.int64()), + ('cfloat32', pa.float32()), + ('cfloat64', pa.float64()), + ('cdecimal128', pa.decimal128(8, 2)), + ('cdate32', pa.date32()), + ('ctimestamp', pa.timestamp('us')), + ('ctimestamptz', pa.timestamp('us', tz='UTC')), + ('cutf8', pa.utf8()), + ('cbinary', pa.binary()), +]) + +# Convert to a PyArrow table +table = pa.Table.from_arrays(columns, schema=schema) + +# Write to a Parquet file +pq.write_table(table, "types_test.parquet") + +# Output the result +print(f"Created a Parquet file with {rows} rows and schema {table.schema}.") + + +# Load the Parquet file +parquet_file = pq.read_table("./types_test.parquet") + +# Connect to the REST catalog +catalog = load_catalog( + "rest", + **{ + "type": "rest", + "uri": "http://rest:8181";, + "s3.endpoint": "http://minio:9000";, + "s3.access-key-id": os.environ["AWS_ACCESS_KEY_ID"], + "s3.secret-access-key": os.environ["AWS_SECRET_ACCESS_KEY"], + }, +) + +# Create a corresponding Iceberg table and append the file to it +iceberg_table = catalog.create_table_if_not_exists( + identifier=f"default.types_test", + schema=parquet_file.schema, +) +iceberg_table.append(df=parquet_file) Review Comment: `iceberg_table.append(table)` also works, do we need to roundtrip writing to parquet and then reading it back? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org --------------------------------------------------------------------- To unsubscribe, e-mail: issues-unsubscr...@iceberg.apache.org For additional commands, e-mail: issues-h...@iceberg.apache.org
