jqin61 commented on code in PR #453: URL: https://github.com/apache/iceberg-python/pull/453#discussion_r1496926708
########## tests/integration/test_partitioning_key.py: ########## @@ -0,0 +1,722 @@ +# 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. +# pylint:disable=redefined-outer-name +from datetime import date, datetime +from decimal import Decimal +from typing import Any, List + +import pytest +import pytz +from pyspark.sql import SparkSession +from pyspark.sql.utils import AnalysisException + +from pyiceberg.catalog import Catalog, load_catalog +from pyiceberg.exceptions import NamespaceAlreadyExistsError +from pyiceberg.partitioning import PartitionField, PartitionFieldValue, PartitionKey, PartitionSpec +from pyiceberg.schema import Schema +from pyiceberg.transforms import ( + BucketTransform, + DayTransform, + HourTransform, + IdentityTransform, + MonthTransform, + TruncateTransform, + YearTransform, +) +from pyiceberg.typedef import Record +from pyiceberg.types import ( + BinaryType, + BooleanType, + DateType, + DecimalType, + DoubleType, + FixedType, + FloatType, + IntegerType, + LongType, + NestedField, + StringType, + TimestampType, + TimestamptzType, +) + + +@pytest.fixture() +def catalog() -> Catalog: + catalog = load_catalog( + "local", + **{ + "type": "rest", + "uri": "http://localhost:8181";, + "s3.endpoint": "http://localhost:9000";, + "s3.access-key-id": "admin", + "s3.secret-access-key": "password", + }, + ) + + try: + catalog.create_namespace("default") + except NamespaceAlreadyExistsError: + pass + + return catalog + + +@pytest.fixture(scope="session") +def session_catalog() -> Catalog: + return load_catalog( + "local", + **{ + "type": "rest", + "uri": "http://localhost:8181";, + "s3.endpoint": "http://localhost:9000";, + "s3.access-key-id": "admin", + "s3.secret-access-key": "password", + }, + ) + + +@pytest.fixture(scope="session") +def spark() -> SparkSession: + import importlib.metadata + import os + + spark_version = ".".join(importlib.metadata.version("pyspark").split(".")[:2]) + scala_version = "2.12" + iceberg_version = "1.4.3" + + os.environ["PYSPARK_SUBMIT_ARGS"] = ( + f"--packages org.apache.iceberg:iceberg-spark-runtime-{spark_version}_{scala_version}:{iceberg_version}," + f"org.apache.iceberg:iceberg-aws-bundle:{iceberg_version} pyspark-shell" + ) + os.environ["AWS_REGION"] = "us-east-1" + os.environ["AWS_ACCESS_KEY_ID"] = "admin" + os.environ["AWS_SECRET_ACCESS_KEY"] = "password" + + spark = ( + SparkSession.builder.appName("PyIceberg integration test") + .config("spark.sql.extensions", "org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions") + .config("spark.sql.catalog.integration", "org.apache.iceberg.spark.SparkCatalog") + .config("spark.sql.catalog.integration.catalog-impl", "org.apache.iceberg.rest.RESTCatalog") + .config("spark.sql.catalog.integration.uri", "http://localhost:8181";) + .config("spark.sql.catalog.integration.io-impl", "org.apache.iceberg.aws.s3.S3FileIO") + .config("spark.sql.catalog.integration.warehouse", "s3://warehouse/wh/") + .config("spark.sql.catalog.integration.s3.endpoint", "http://localhost:9000";) + .config("spark.sql.catalog.integration.s3.path-style-access", "true") + .config("spark.sql.defaultCatalog", "integration") + .getOrCreate() + ) + + return spark + + +TABLE_SCHEMA = Schema( + NestedField(field_id=1, name="boolean_field", field_type=BooleanType(), required=False), + NestedField(field_id=2, name="string_field", field_type=StringType(), required=False), + NestedField(field_id=3, name="string_long_field", field_type=StringType(), required=False), + NestedField(field_id=4, name="int_field", field_type=IntegerType(), required=False), + NestedField(field_id=5, name="long_field", field_type=LongType(), required=False), + NestedField(field_id=6, name="float_field", field_type=FloatType(), required=False), + NestedField(field_id=7, name="double_field", field_type=DoubleType(), required=False), + NestedField(field_id=8, name="timestamp_field", field_type=TimestampType(), required=False), + NestedField(field_id=9, name="timestamptz_field", field_type=TimestamptzType(), required=False), + NestedField(field_id=10, name="date_field", field_type=DateType(), required=False), + # NestedField(field_id=11, name="time", field_type=TimeType(), required=False), + # NestedField(field_id=12, name="uuid", field_type=UuidType(), required=False), + NestedField(field_id=11, name="binary_field", field_type=BinaryType(), required=False), + NestedField(field_id=12, name="fixed_field", field_type=FixedType(16), required=False), + NestedField(field_id=13, name="decimal", field_type=DecimalType(5, 2), required=False), +) + + +identifier = "default.test_table" + + +@pytest.mark.parametrize( + "partition_fields, partition_values, expected_partition_record, expected_hive_partition_path_slice, spark_create_table_sql_for_justification, spark_data_insert_sql_for_justification", + [ + # Identity Transform + ( + [PartitionField(source_id=1, field_id=1001, transform=IdentityTransform(), name="boolean_field")], + [False], + Record(boolean_field=False), + "boolean_field=False", + # pyiceberg writes False while spark writes false, so justification (compare expected value with spark behavior) would fail. + None, + None, + # f"""CREATE TABLE {identifier} ( + # boolean_field boolean, + # string_field string + # ) + # USING iceberg + # PARTITIONED BY ( + # identity(boolean_field) -- Partitioning by 'boolean_field' + # ) + # """, + # f"""INSERT INTO {identifier} + # VALUES + # (false, 'Boolean field set to false'); + # """ + ), + ( + [PartitionField(source_id=2, field_id=1001, transform=IdentityTransform(), name="string_field")], + ["sample_string"], + Record(string_field="sample_string"), + "string_field=sample_string", + f"""CREATE TABLE {identifier} ( + string_field string, + another_string_field string + ) + USING iceberg + PARTITIONED BY ( + identity(string_field) + ) + """, + f"""INSERT INTO {identifier} + VALUES + ('sample_string', 'Another string value') + """, + ), + ( + [PartitionField(source_id=4, field_id=1001, transform=IdentityTransform(), name="int_field")], + [42], + Record(int_field=42), + "int_field=42", + f"""CREATE TABLE {identifier} ( + int_field int, + string_field string + ) + USING iceberg + PARTITIONED BY ( + identity(int_field) + ) + """, + f"""INSERT INTO {identifier} + VALUES + (42, 'Associated string value for int 42') + """, + ), + ( + [PartitionField(source_id=5, field_id=1001, transform=IdentityTransform(), name="long_field")], + [1234567890123456789], + Record(long_field=1234567890123456789), + "long_field=1234567890123456789", + f"""CREATE TABLE {identifier} ( + long_field bigint, + string_field string + ) + USING iceberg + PARTITIONED BY ( + identity(long_field) + ) + """, + f"""INSERT INTO {identifier} + VALUES + (1234567890123456789, 'Associated string value for long 1234567890123456789') + """, + ), + ( + [PartitionField(source_id=6, field_id=1001, transform=IdentityTransform(), name="float_field")], + [3.14], + Record(float_field=3.14), + "float_field=3.14", + # spark writes differently as pyiceberg, Record[float_field=3.140000104904175], path:float_field=3.14 (Record has difference) + # so justification (compare expected value with spark behavior) would fail. + None, Review Comment: For a partitioned column with float/double value of 3.14, spark-iceberg has the partition in manifest entry as Record[float_field=3.140000104904175] while iceberg has it as [float_field=3.14] -- 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
