Skip to content

Commit

Permalink
Merge pull request #61 from epage/overhead
Browse files Browse the repository at this point in the history 
Look into processing overhead
  • Loading branch information
@epage
epage committed Oct 25, 2019
2 parents af49b6a + a60ab52 commit a1a8ba2
Show file tree
Hide file tree
Showing 5 changed files with 339 additions and 49 deletions.
1 change: 1 addition & 0 deletions Cargo.lock
View file

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

1 change: 1 addition & 0 deletions Cargo.toml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -37,3 +37,4 @@ env_logger = "0.6"

[dev-dependencies]
assert_fs = "0.11"
bstr = "0.2"
303 changes: 296 additions & 7 deletions benches/file.rs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -4,10 +4,11 @@ extern crate test;

mod data;

pub use assert_fs::prelude::*;
use assert_fs::prelude::*;
use bstr::ByteSlice;

#[bench]
fn process_empty(b: &mut test::Bencher) {
fn check_file_empty(b: &mut test::Bencher) {
let temp = assert_fs::TempDir::new().unwrap();
let sample_path = temp.child("sample");
sample_path.write_str(data::EMPTY).unwrap();
Expand All @@ -21,7 +22,7 @@ fn process_empty(b: &mut test::Bencher) {
}

#[bench]
fn process_no_tokens(b: &mut test::Bencher) {
fn check_file_no_tokens(b: &mut test::Bencher) {
let temp = assert_fs::TempDir::new().unwrap();
let sample_path = temp.child("sample");
sample_path.write_str(data::NO_TOKENS).unwrap();
Expand All @@ -35,7 +36,7 @@ fn process_no_tokens(b: &mut test::Bencher) {
}

#[bench]
fn process_single_token(b: &mut test::Bencher) {
fn check_file_single_token(b: &mut test::Bencher) {
let temp = assert_fs::TempDir::new().unwrap();
let sample_path = temp.child("sample");
sample_path.write_str(data::SINGLE_TOKEN).unwrap();
Expand All @@ -49,7 +50,7 @@ fn process_single_token(b: &mut test::Bencher) {
}

#[bench]
fn process_sherlock(b: &mut test::Bencher) {
fn check_file_sherlock(b: &mut test::Bencher) {
let temp = assert_fs::TempDir::new().unwrap();
let sample_path = temp.child("sample");
sample_path.write_str(data::SHERLOCK).unwrap();
Expand All @@ -63,7 +64,7 @@ fn process_sherlock(b: &mut test::Bencher) {
}

#[bench]
fn process_code(b: &mut test::Bencher) {
fn check_file_code(b: &mut test::Bencher) {
let temp = assert_fs::TempDir::new().unwrap();
let sample_path = temp.child("sample");
sample_path.write_str(data::CODE).unwrap();
Expand All @@ -77,7 +78,7 @@ fn process_code(b: &mut test::Bencher) {
}

#[bench]
fn process_corpus(b: &mut test::Bencher) {
fn check_file_corpus(b: &mut test::Bencher) {
let temp = assert_fs::TempDir::new().unwrap();
let sample_path = temp.child("sample");
sample_path.write_str(data::CORPUS).unwrap();
Expand All @@ -89,3 +90,291 @@ fn process_corpus(b: &mut test::Bencher) {

temp.close().unwrap();
}

#[bench]
fn read_empty(b: &mut test::Bencher) {
let temp = assert_fs::TempDir::new().unwrap();
let sample_path = temp.child("sample");
sample_path.write_str(data::EMPTY).unwrap();

b.iter(|| std::fs::read(sample_path.path()));

temp.close().unwrap();
}

#[bench]
fn read_no_tokens(b: &mut test::Bencher) {
let temp = assert_fs::TempDir::new().unwrap();
let sample_path = temp.child("sample");
sample_path.write_str(data::NO_TOKENS).unwrap();

b.iter(|| std::fs::read(sample_path.path()));

temp.close().unwrap();
}

#[bench]
fn read_single_token(b: &mut test::Bencher) {
let temp = assert_fs::TempDir::new().unwrap();
let sample_path = temp.child("sample");
sample_path.write_str(data::SINGLE_TOKEN).unwrap();

b.iter(|| std::fs::read(sample_path.path()));

temp.close().unwrap();
}

#[bench]
fn read_sherlock(b: &mut test::Bencher) {
let temp = assert_fs::TempDir::new().unwrap();
let sample_path = temp.child("sample");
sample_path.write_str(data::SHERLOCK).unwrap();

b.iter(|| std::fs::read(sample_path.path()));

temp.close().unwrap();
}

#[bench]
fn read_code(b: &mut test::Bencher) {
let temp = assert_fs::TempDir::new().unwrap();
let sample_path = temp.child("sample");
sample_path.write_str(data::CODE).unwrap();

b.iter(|| std::fs::read(sample_path.path()));

temp.close().unwrap();
}

#[bench]
fn read_corpus(b: &mut test::Bencher) {
let temp = assert_fs::TempDir::new().unwrap();
let sample_path = temp.child("sample");
sample_path.write_str(data::CORPUS).unwrap();

b.iter(|| std::fs::read(sample_path.path()));

temp.close().unwrap();
}

#[bench]
fn split_lines_empty(b: &mut test::Bencher) {
b.iter(|| data::EMPTY.as_bytes().lines().enumerate().last());
}

#[bench]
fn split_lines_no_tokens(b: &mut test::Bencher) {
b.iter(|| data::NO_TOKENS.as_bytes().lines().enumerate().last());
}

#[bench]
fn split_lines_single_token(b: &mut test::Bencher) {
b.iter(|| data::SINGLE_TOKEN.as_bytes().lines().enumerate().last());
}

#[bench]
fn split_lines_sherlock(b: &mut test::Bencher) {
b.iter(|| data::SHERLOCK.as_bytes().lines().enumerate().last());
}

#[bench]
fn split_lines_code(b: &mut test::Bencher) {
b.iter(|| data::CODE.as_bytes().lines().enumerate().last());
}

#[bench]
fn split_lines_corpus(b: &mut test::Bencher) {
b.iter(|| data::CORPUS.as_bytes().lines().enumerate().last());
}

#[bench]
fn parse_empty(b: &mut test::Bencher) {
let parser = typos::tokens::Parser::new();
b.iter(|| {
data::EMPTY
.as_bytes()
.lines()
.enumerate()
.for_each(|(_idx, l)| {
parser.parse_bytes(l).last();
()
})
});
}

#[bench]
fn parse_no_tokens(b: &mut test::Bencher) {
let parser = typos::tokens::Parser::new();
b.iter(|| {
data::NO_TOKENS
.as_bytes()
.lines()
.enumerate()
.for_each(|(_idx, l)| {
parser.parse_bytes(l).last();
()
})
});
}

#[bench]
fn parse_single_token(b: &mut test::Bencher) {
let parser = typos::tokens::Parser::new();
b.iter(|| {
data::SINGLE_TOKEN
.as_bytes()
.lines()
.enumerate()
.for_each(|(_idx, l)| {
parser.parse_bytes(l).last();
()
})
});
}

#[bench]
fn parse_sherlock(b: &mut test::Bencher) {
let parser = typos::tokens::Parser::new();
b.iter(|| {
data::SHERLOCK
.as_bytes()
.lines()
.enumerate()
.for_each(|(_idx, l)| {
parser.parse_bytes(l).last();
()
})
});
}

#[bench]
fn parse_code(b: &mut test::Bencher) {
let parser = typos::tokens::Parser::new();
b.iter(|| {
data::CODE
.as_bytes()
.lines()
.enumerate()
.for_each(|(_idx, l)| {
parser.parse_bytes(l).last();
()
})
});
}

#[bench]
fn parse_corpus(b: &mut test::Bencher) {
let parser = typos::tokens::Parser::new();
b.iter(|| {
data::CORPUS
.as_bytes()
.lines()
.enumerate()
.for_each(|(_idx, l)| {
parser.parse_bytes(l).last();
()
})
});
}

#[bench]
fn split_empty(b: &mut test::Bencher) {
let parser = typos::tokens::Parser::new();
b.iter(|| {
data::EMPTY
.as_bytes()
.lines()
.enumerate()
.for_each(|(_idx, l)| {
parser.parse_bytes(l).for_each(|l| {
l.split().last();
()
})
})
});
}

#[bench]
fn split_no_tokens(b: &mut test::Bencher) {
let parser = typos::tokens::Parser::new();
b.iter(|| {
data::NO_TOKENS
.as_bytes()
.lines()
.enumerate()
.for_each(|(_idx, l)| {
parser.parse_bytes(l).for_each(|l| {
l.split().last();
()
})
})
});
}

#[bench]
fn split_single_token(b: &mut test::Bencher) {
let parser = typos::tokens::Parser::new();
b.iter(|| {
data::SINGLE_TOKEN
.as_bytes()
.lines()
.enumerate()
.for_each(|(_idx, l)| {
parser.parse_bytes(l).for_each(|l| {
l.split().last();
()
})
})
});
}

#[bench]
fn split_sherlock(b: &mut test::Bencher) {
let parser = typos::tokens::Parser::new();
b.iter(|| {
data::SHERLOCK
.as_bytes()
.lines()
.enumerate()
.for_each(|(_idx, l)| {
parser.parse_bytes(l).for_each(|l| {
l.split().last();
()
})
})
});
}

#[bench]
fn split_code(b: &mut test::Bencher) {
let parser = typos::tokens::Parser::new();
b.iter(|| {
data::CODE
.as_bytes()
.lines()
.enumerate()
.for_each(|(_idx, l)| {
parser.parse_bytes(l).for_each(|l| {
l.split().last();
()
})
})
});
}

#[bench]
fn split_corpus(b: &mut test::Bencher) {
let parser = typos::tokens::Parser::new();
b.iter(|| {
data::CORPUS
.as_bytes()
.lines()
.enumerate()
.for_each(|(_idx, l)| {
parser.parse_bytes(l).for_each(|l| {
l.split().last();
()
})
})
});
}

0 comments on commit a1a8ba2

Please sign in to comment.