maxdebayser commented on code in PR #7831: URL: https://github.com/apache/iceberg/pull/7831#discussion_r1258886052
########## python/pyiceberg/utils/file_stats.py: ########## @@ -0,0 +1,333 @@ +# 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 struct +from typing import ( + Any, + Dict, + List, + Union, +) + +import pyarrow.lib +import pyarrow.parquet as pq + +from pyiceberg.manifest import DataFile, FileFormat +from pyiceberg.schema import Schema, SchemaVisitor, visit +from pyiceberg.types import ( + IcebergType, + ListType, + MapType, + NestedField, + PrimitiveType, + StructType, +) + +BOUND_TRUNCATED_LENGHT = 16 + +# Serialization rules: https://iceberg.apache.org/spec/#binary-single-value-serialization +# +# Type Binary serialization +# boolean 0x00 for false, non-zero byte for true +# int Stored as 4-byte little-endian +# long Stored as 8-byte little-endian +# float Stored as 4-byte little-endian +# double Stored as 8-byte little-endian +# date Stores days from the 1970-01-01 in an 4-byte little-endian int +# time Stores microseconds from midnight in an 8-byte little-endian long +# timestamp without zone Stores microseconds from 1970-01-01 00:00:00.000000 in an 8-byte little-endian long +# timestamp with zone Stores microseconds from 1970-01-01 00:00:00.000000 UTC in an 8-byte little-endian long +# string UTF-8 bytes (without length) +# uuid 16-byte big-endian value, see example in Appendix B +# fixed(L) Binary value +# binary Binary value (without length) +# + + +def bool_to_avro(value: bool) -> bytes: + return struct.pack("?", value) + + +def int32_to_avro(value: int) -> bytes: + return struct.pack("<i", value) + + +def int64_to_avro(value: int) -> bytes: + return struct.pack("<q", value) + + +def float_to_avro(value: float) -> bytes: + return struct.pack("<f", value) + + +def double_to_avro(value: float) -> bytes: + return struct.pack("<d", value) + + +def bytes_to_avro(value: Union[bytes, str]) -> bytes: + if type(value) == str: + return value.encode() + else: + assert isinstance(value, bytes) # appeases mypy + return value + + +class StatsAggregator: + def __init__(self, type_string: str): + self.current_min: Any = None + self.current_max: Any = None + self.serialize: Any = None + + if type_string == "BOOLEAN": + self.serialize = bool_to_avro + elif type_string == "INT32": + self.serialize = int32_to_avro + elif type_string == "INT64": + self.serialize = int64_to_avro + elif type_string == "INT96": + raise NotImplementedError("Statistics not implemented for INT96 physical type") + elif type_string == "FLOAT": + self.serialize = float_to_avro + elif type_string == "DOUBLE": + self.serialize = double_to_avro + elif type_string == "BYTE_ARRAY": + self.serialize = bytes_to_avro + elif type_string == "FIXED_LEN_BYTE_ARRAY": + self.serialize = bytes_to_avro + else: + raise AssertionError(f"Unknown physical type {type_string}") + + def add_min(self, val: bytes) -> None: + if not self.current_min: + self.current_min = val + elif val < self.current_min: + self.current_min = val + + def add_max(self, val: bytes) -> None: + if not self.current_max: + self.current_max = val + elif self.current_max < val: + self.current_max = val + + def get_min(self) -> bytes: + return self.serialize(self.current_min)[:BOUND_TRUNCATED_LENGHT] + + def get_max(self) -> bytes: + return self.serialize(self.current_max)[:BOUND_TRUNCATED_LENGHT] + + +def fill_parquet_file_metadata( + df: DataFile, metadata: pq.FileMetaData, col_path_2_iceberg_id: Dict[str, int], file_size: int +) -> None: + """ + Computes and fills the following fields of the DataFile object. + + - file_format + - record_count + - file_size_in_bytes + - column_sizes + - value_counts + - null_value_counts + - nan_value_counts + - lower_bounds + - upper_bounds + - split_offsets + + Args: + df (DataFile): A DataFile object representing the Parquet file for which metadata is to be filled. + metadata (pyarrow.parquet.FileMetaData): A pyarrow metadata object. + col_path_2_iceberg_id: A mapping of column paths as in the `path_in_schema` attribute of the colum Review Comment: Yes, this is why I've added the `parquet_schema_to_ids` function that uses the SchemaVisitor. If you prefer we can pass the schema to the `fill_parquet_file_metadata` and compute the mapping internally instead of making the caller of the function do it. The reason I decomposed it was to make testing easier. The `parquet_schema_to_ids` uses the `path_in_schema` column metadata attribute instead of the position because I'm not 100% sure if I can assume anything about the position, whereas using the full column path should be safe. -- 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: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
