searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2024-11-26 14:54:27 +01:00
Code Issues Releases Wiki Activity

Merge #583

Browse Source 
583: Use BufReader to read datasets in benchmarks r=ManyTheFish a=loiclec

## What does this PR do?
Ensure that the datasets used by the benchmarks are read efficiently by using a `BufReader`.

## Why?
Using a `BufReader` is more representative of how `meilisearch` works. It will also make performance comparisons between different branches of `milli` more  accurate.




Co-authored-by: Loïc Lecrenier <loic@meilisearch.com>
This commit is contained in:
bors[bot] 2022-07-07 08:13:07 +00:00 committed by GitHub
commit ce90fc628a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
benchmarks/benches/utils.rs
View File

@ -140,9 +140,10 @@ pub fn run_benches(c: &mut criterion::Criterion, confs: &[Conf]) {
} }
} }
pub fn documents_from(filename: &str, filetype: &str) -> DocumentBatchReader<impl Read + Seek> { pub fn documents_from(filename: &str, filetype: &str) -> DocumentBatchReader<impl BufRead + Seek> {
let reader = let reader =
File::open(filename).expect(&format!("could not find the dataset in: {}", filename)); File::open(filename).expect(&format!("could not find the dataset in: {}", filename));
let reader = BufReader::new(reader);
let documents = match filetype { let documents = match filetype {
"csv" => documents_from_csv(reader).unwrap(), "csv" => documents_from_csv(reader).unwrap(),
"json" => documents_from_json(reader).unwrap(), "json" => documents_from_json(reader).unwrap(),
@ -152,12 +153,11 @@ pub fn documents_from(filename: &str, filetype: &str) -> DocumentBatchReader<imp
DocumentBatchReader::from_reader(Cursor::new(documents)).unwrap() DocumentBatchReader::from_reader(Cursor::new(documents)).unwrap()
} }
fn documents_from_jsonl(reader: impl Read) -> anyhow::Result<Vec<u8>> { fn documents_from_jsonl(mut reader: impl BufRead) -> anyhow::Result<Vec<u8>> {
let mut writer = Cursor::new(Vec::new()); let mut writer = Cursor::new(Vec::new());
let mut documents = milli::documents::DocumentBatchBuilder::new(&mut writer)?; let mut documents = milli::documents::DocumentBatchBuilder::new(&mut writer)?;
let mut buf = String::new(); let mut buf = String::new();
let mut reader = BufReader::new(reader);
while reader.read_line(&mut buf)? > 0 { while reader.read_line(&mut buf)? > 0 {
documents.extend_from_json(&mut buf.as_bytes())?; documents.extend_from_json(&mut buf.as_bytes())?;
@ -168,7 +168,7 @@ fn documents_from_jsonl(reader: impl Read) -> anyhow::Result<Vec<u8>> {
Ok(writer.into_inner()) Ok(writer.into_inner())
} }
fn documents_from_json(reader: impl Read) -> anyhow::Result<Vec<u8>> { fn documents_from_json(reader: impl BufRead) -> anyhow::Result<Vec<u8>> {
let mut writer = Cursor::new(Vec::new()); let mut writer = Cursor::new(Vec::new());
let mut documents = milli::documents::DocumentBatchBuilder::new(&mut writer)?; let mut documents = milli::documents::DocumentBatchBuilder::new(&mut writer)?;
@ -178,7 +178,7 @@ fn documents_from_json(reader: impl Read) -> anyhow::Result<Vec<u8>> {
Ok(writer.into_inner()) Ok(writer.into_inner())
} }
fn documents_from_csv(reader: impl Read) -> anyhow::Result<Vec<u8>> { fn documents_from_csv(reader: impl BufRead) -> anyhow::Result<Vec<u8>> {
let mut writer = Cursor::new(Vec::new()); let mut writer = Cursor::new(Vec::new());
milli::documents::DocumentBatchBuilder::from_csv(reader, &mut writer)?.finish()?; milli::documents::DocumentBatchBuilder::from_csv(reader, &mut writer)?.finish()?;