Skip to content

ARROW-10299: [Rust] Use IPC Metadata V5 as default #9122

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.

Sign up for GitHub

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

Closed
nevi-me wants to merge 2 commits into from
Closed

ARROW-10299: [Rust] Use IPC Metadata V5 as default #9122

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f10b4bd
ARROW-10299: [Rust] Add IPC V5 tests, set V5 as default
nevi-me Dec 3, 2020
8ccc5bd
update comments
nevi-me Jan 21, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions rust/arrow/src/array/array_struct.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,6 +69,10 @@ impl StructArray {
}

/// Return child array whose field name equals to column_name
///
/// Note: A schema can currently have duplicate field names, in which case
/// the first field will always be selected.
/// This issue will be addressed in [ARROW-11178](https://issues.apache.org/jira/browse/ARROW-11178)
pub fn column_by_name(&self, column_name: &str) -> Option<&ArrayRef> {
self.column_names()
.iter()
Expand Down
95 changes: 83 additions & 12 deletions rust/arrow/src/ipc/reader.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -919,14 +919,16 @@ impl<R: Read> RecordBatchReader for StreamReader<R> {
mod tests {
use super::*;

use std::fs::File;

use flate2::read::GzDecoder;

use crate::util::integration_util::*;
use std::fs::File;

#[test]
fn read_generated_files() {
fn read_generated_files_014() {
let testdata = crate::util::test_util::arrow_test_data();
let version = "0.14.1";
// the test is repetitive, thus we can read all supported files at once
let paths = vec![
"generated_interval",
Expand All @@ -940,15 +942,15 @@ mod tests {
];
paths.iter().for_each(|path| {
let file = File::open(format!(
"{}/arrow-ipc-stream/integration/0.14.1/{}.arrow_file",
testdata, path
"{}/arrow-ipc-stream/integration/{}/{}.arrow_file",
testdata, version, path
))
.unwrap();

let mut reader = FileReader::try_new(file).unwrap();

// read expected JSON output
let arrow_json = read_gzip_json(path);
let arrow_json = read_gzip_json(version, path);
assert!(arrow_json.equals_reader(&mut reader));
});
}
Expand All @@ -974,6 +976,8 @@ mod tests {
"generated_datetime",
"generated_dictionary",
"generated_nested",
"generated_null_trivial",
"generated_null",
"generated_primitive_no_batches",
"generated_primitive_zerolength",
"generated_primitive",
Expand All @@ -990,8 +994,9 @@ mod tests {
}

#[test]
fn read_generated_streams() {
fn read_generated_streams_014() {
let testdata = crate::util::test_util::arrow_test_data();
let version = "0.14.1";
// the test is repetitive, thus we can read all supported files at once
let paths = vec![
"generated_interval",
Expand All @@ -1005,15 +1010,81 @@ mod tests {
];
paths.iter().for_each(|path| {
let file = File::open(format!(
"{}/arrow-ipc-stream/integration/0.14.1/{}.stream",
testdata, path
"{}/arrow-ipc-stream/integration/{}/{}.stream",
testdata, version, path
))
.unwrap();

let mut reader = StreamReader::try_new(file).unwrap();

// read expected JSON output
let arrow_json = read_gzip_json(version, path);
assert!(arrow_json.equals_reader(&mut reader));
// the next batch must be empty
assert!(reader.next().is_none());
// the stream must indicate that it's finished
assert!(reader.is_finished());
});
}

#[test]
fn read_generated_files_100() {
let testdata = crate::util::test_util::arrow_test_data();
let version = "1.0.0-littleendian";
// the test is repetitive, thus we can read all supported files at once
let paths = vec![
"generated_interval",
"generated_datetime",
"generated_dictionary",
"generated_nested",
"generated_null_trivial",
"generated_null",
"generated_primitive_no_batches",
"generated_primitive_zerolength",
"generated_primitive",
];
paths.iter().for_each(|path| {
let file = File::open(format!(
"{}/arrow-ipc-stream/integration/{}/{}.arrow_file",
testdata, version, path
))
.unwrap();

let mut reader = FileReader::try_new(file).unwrap();

// read expected JSON output
let arrow_json = read_gzip_json(version, path);
assert!(arrow_json.equals_reader(&mut reader));
});
}

#[test]
fn read_generated_streams_100() {
let testdata = crate::util::test_util::arrow_test_data();
let version = "1.0.0-littleendian";
// the test is repetitive, thus we can read all supported files at once
let paths = vec![
"generated_interval",
"generated_datetime",
"generated_dictionary",
"generated_nested",
"generated_null_trivial",
"generated_null",
"generated_primitive_no_batches",
"generated_primitive_zerolength",
"generated_primitive",
];
paths.iter().for_each(|path| {
let file = File::open(format!(
"{}/arrow-ipc-stream/integration/{}/{}.stream",
testdata, version, path
))
.unwrap();

let mut reader = StreamReader::try_new(file).unwrap();

// read expected JSON output
let arrow_json = read_gzip_json(path);
let arrow_json = read_gzip_json(version, path);
assert!(arrow_json.equals_reader(&mut reader));
// the next batch must be empty
assert!(reader.next().is_none());
Expand Down Expand Up @@ -1072,11 +1143,11 @@ mod tests {
}

/// Read gzipped JSON file
fn read_gzip_json(path: &str) -> ArrowJson {
fn read_gzip_json(version: &str, path: &str) -> ArrowJson {
let testdata = crate::util::test_util::arrow_test_data();
let file = File::open(format!(
"{}/arrow-ipc-stream/integration/0.14.1/{}.json.gz",
testdata, path
"{}/arrow-ipc-stream/integration/{}/{}.json.gz",
testdata, version, path
))
.unwrap();
let mut gz = GzDecoder::new(&file);
Expand Down
Loading