-
Notifications
You must be signed in to change notification settings - Fork 818
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
parquet: improve BOOLEAN writing logic and report error on encoding fail #443
Merged
Merged
Changes from all commits
Commits
Show all changes
5 commits
Select commit
Hold shift + click to select a range
db8af9b
improve BOOLEAN writing logic and report error on encoding fail
garyanaplan a4ec2d7
only manipulate the bit_writer for BOOLEAN data
garyanaplan eb11b2b
better isolation of changes
garyanaplan 06d9a33
add test for boolean writer
garyanaplan da8c665
fix capacity calculation error in bool encoding
garyanaplan File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,100 @@ | ||
// 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. | ||
|
||
use parquet::column::writer::ColumnWriter; | ||
use parquet::file::properties::WriterProperties; | ||
use parquet::file::reader::FileReader; | ||
use parquet::file::serialized_reader::SerializedFileReader; | ||
use parquet::file::writer::FileWriter; | ||
use parquet::file::writer::SerializedFileWriter; | ||
use parquet::schema::parser::parse_message_type; | ||
use std::fs; | ||
use std::path::Path; | ||
use std::sync::{mpsc, Arc}; | ||
use std::thread; | ||
use std::time::Duration; | ||
|
||
#[test] | ||
fn it_writes_data_without_hanging() { | ||
let path = Path::new("it_writes_data_without_hanging.parquet"); | ||
|
||
let message_type = " | ||
message BooleanType { | ||
REQUIRED BOOLEAN DIM0; | ||
} | ||
"; | ||
let schema = Arc::new(parse_message_type(message_type).expect("parse schema")); | ||
let props = Arc::new(WriterProperties::builder().build()); | ||
let file = fs::File::create(&path).expect("create file"); | ||
let mut writer = | ||
SerializedFileWriter::new(file, schema, props).expect("create parquet writer"); | ||
for _group in 0..1 { | ||
let mut row_group_writer = writer.next_row_group().expect("get row group writer"); | ||
let values: Vec<i64> = vec![0; 2049]; | ||
let my_bool_values: Vec<bool> = values | ||
.iter() | ||
.enumerate() | ||
.map(|(count, _x)| count % 2 == 0) | ||
.collect(); | ||
while let Some(mut col_writer) = | ||
row_group_writer.next_column().expect("next column") | ||
{ | ||
match col_writer { | ||
ColumnWriter::BoolColumnWriter(ref mut typed_writer) => { | ||
typed_writer | ||
.write_batch(&my_bool_values, None, None) | ||
.expect("writing bool column"); | ||
} | ||
_ => { | ||
panic!("only test boolean values"); | ||
} | ||
} | ||
row_group_writer | ||
.close_column(col_writer) | ||
.expect("close column"); | ||
} | ||
let rg_md = row_group_writer.close().expect("close row group"); | ||
println!("total rows written: {}", rg_md.num_rows()); | ||
writer | ||
.close_row_group(row_group_writer) | ||
.expect("close row groups"); | ||
} | ||
writer.close().expect("close writer"); | ||
|
||
let bytes = fs::read(&path).expect("read file"); | ||
assert_eq!(&bytes[0..4], &[b'P', b'A', b'R', b'1']); | ||
|
||
// Now that we have written our data and are happy with it, make | ||
// sure we can read it back in < 5 seconds... | ||
let (sender, receiver) = mpsc::channel(); | ||
let _t = thread::spawn(move || { | ||
let file = fs::File::open(&Path::new("it_writes_data_without_hanging.parquet")) | ||
.expect("open file"); | ||
let reader = SerializedFileReader::new(file).expect("get serialized reader"); | ||
let iter = reader.get_row_iter(None).expect("get iterator"); | ||
for record in iter { | ||
println!("reading: {}", record); | ||
} | ||
println!("finished reading"); | ||
if let Ok(()) = sender.send(true) {} | ||
}); | ||
assert_ne!( | ||
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. You could also check However, I think that is equivalent to what you have here. 👍 thank you |
||
Err(mpsc::RecvTimeoutError::Timeout), | ||
receiver.recv_timeout(Duration::from_millis(5000)) | ||
); | ||
fs::remove_file("it_writes_data_without_hanging.parquet").expect("remove file"); | ||
} |
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Since
put_value
returns false if there isn't enough space, you might be able to avoid errors with something like:Rather than returning an error
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yea, we can either do this or make sure up front that there's enough capacity to write. One minor concern is putting the if branch inside the for loop might hurt the performance.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I found it hard to think of a good way to test this with the fix in place.
I preferred the "don't auto expand memory at the point of failure" approach because I'm fairly conservative and didn't want to make a change that was too wide in impact without a better understanding of the code. i.e.: my fix specifically targeted the error I reported and made it possible to detect in other locations.
I think a better fix would be to (somehow) pre-size the vector or avoid having to size a vector for all the bytes that could be written, but that would be a much bigger scope to the fix.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
leaving the code as is seems fine to me