Fokko commented on code in PR #4920: URL: https://github.com/apache/iceberg/pull/4920#discussion_r897261489
########## python/src/iceberg/avro/decoder.py: ########## @@ -0,0 +1,193 @@ +# 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 datetime +import decimal +import struct + +from iceberg.io.base import InputStream + +STRUCT_FLOAT = struct.Struct("<f") # little-endian float +STRUCT_DOUBLE = struct.Struct("<d") # little-endian double +STRUCT_SIGNED_SHORT = struct.Struct(">h") # big-endian signed short +STRUCT_SIGNED_INT = struct.Struct(">i") # big-endian signed int +STRUCT_SIGNED_LONG = struct.Struct(">q") # big-endian signed long + + +class BinaryDecoder: + """Read leaf values.""" + + _input_stream: InputStream + + def __init__(self, input_stream: InputStream) -> None: + """ + reader is a Python object on which we can call read, seek, and tell. + """ + self._input_stream = input_stream + + def read(self, n: int) -> bytes: + """ + Read n bytes. + """ + if n < 0: + raise ValueError(f"Requested {n} bytes to read, expected positive integer.") + read_bytes = self._input_stream.read(n) + if len(read_bytes) != n: Review Comment: Alright, I tried to implement this which isn't that hard, but we also have other interfaces that might not have implemented the `read_fully`, breaking the protocol of InputStream. This happens with PyArrows NativeFile as well: ```python def test_pyarrow_input_file(): """Test reading a file using PyArrowFile""" with tempfile.TemporaryDirectory() as tmpdirname: file_location = os.path.join(tmpdirname, "foo.txt") with open(file_location, "wb") as f: f.write(b"foo") # Confirm that the file initially exists assert os.path.exists(file_location) # Instantiate the input file absolute_file_location = os.path.abspath(file_location) input_file = PyArrowFile(location=f"{absolute_file_location}") # Test opening and reading the file f = input_file.open() > assert isinstance(f, InputStream) # Test that the file object abides by the InputStream protocol E assert False E + where False = isinstance(<pyarrow.lib.NativeFile object at 0x111bbf6f0>, InputStream) ``` Looks like pyarrow does return the exact number of bytes, and also has a `read1` method fwiw: <img width="1530" alt="image" src="https://user-images.githubusercontent.com/1134248/173676133-4f8aac53-9d49-4c93-bcb7-d32a3cd52c93.png";> -- 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]
![https://user-images.githubusercontent.com/1134248/173676133-4f8aac53-9d49-4c93-bcb7-d32a3cd52c93.png"](https://user-images.githubusercontent.com/1134248/173676133-4f8aac53-9d49-4c93-bcb7-d32a3cd52c93.png"){kind=link}