diff --git a/.vscode/tasks.json b/.vscode/tasks.json index 616c1f4..e092400 100644 --- a/.vscode/tasks.json +++ b/.vscode/tasks.json @@ -108,6 +108,23 @@ "close": false } }, + { + "label": "cargo bench", + "type": "cargo", + "command": "bench", + "group": { + "kind": "test", + "isDefault": false + }, + "problemMatcher": [ + "$rustc" + ], + "presentation": { + "echo": true, + "reveal": "always", + "close": false + } + }, { "label": "cargo fmt", "type": "cargo", @@ -118,7 +135,7 @@ }, "presentation": { "echo": true, - "reveal": "always", + "reveal": "never", "close": false } } diff --git a/Cargo.lock b/Cargo.lock index 8b53b96..585ea04 100644 --- a/Cargo.lock +++ b/Cargo.lock @@ -11,6 +11,12 @@ dependencies = [ "memchr", ] +[[package]] +name = "anes" +version = "0.1.6" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "4b46cbb362ab8752921c97e041f5e366ee6297bd428a31275b9fcf1e380f7299" + [[package]] name = "anstream" version = "0.6.15" @@ -144,12 +150,51 @@ dependencies = [ "serde", ] +[[package]] +name = "bumpalo" +version = "3.16.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "79296716171880943b8470b5f8d03aa55eb2e645a4874bdbb28adb49162e012c" + +[[package]] +name = "cast" +version = "0.3.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "37b2a672a2cb129a2e41c10b1224bb368f9f37a2b16b612598138befd7b37eb5" + [[package]] name = "cfg-if" version = "1.0.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "baf1de4339761588bc0619e3cbc0120ee582ebb74b53b4efbf79117bd2da40fd" +[[package]] +name = "ciborium" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "42e69ffd6f0917f5c029256a24d0161db17cea3997d185db0d35926308770f0e" +dependencies = [ + "ciborium-io", + "ciborium-ll", + "serde", +] + +[[package]] +name = "ciborium-io" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "05afea1e0a06c9be33d539b876f1ce3692f4afea2cb41f740e7743225ed1c757" + +[[package]] +name = "ciborium-ll" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "57663b653d948a338bfb3eeba9bb2fd5fcfaecb9e199e87e1eda4d9e8b240fd9" +dependencies = [ + "ciborium-io", + "half", +] + [[package]] name = "clap" version = "4.5.17" @@ -196,6 +241,42 @@ version = "1.0.2" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "d3fd119d74b830634cea2a0f58bbd0d54540518a14397557951e79340abc28c0" +[[package]] +name = "criterion" +version = "0.5.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f2b12d017a929603d80db1831cd3a24082f8137ce19c69e6447f54f5fc8d692f" +dependencies = [ + "anes", + "cast", + "ciborium", + "clap", + "criterion-plot", + "is-terminal", + "itertools 0.10.5", + "num-traits", + "once_cell", + "oorandom", + "plotters", + "rayon", + "regex", + "serde", + "serde_derive", + "serde_json", + "tinytemplate", + "walkdir", +] + +[[package]] +name = "criterion-plot" +version = "0.5.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6b50826342786a51a89e2da3a28f1c32b06e387201bc2d19791f622c673706b1" +dependencies = [ + "cast", + "itertools 0.10.5", +] + [[package]] name = "crossbeam-deque" version = "0.8.5" @@ -221,6 +302,12 @@ version = "0.8.20" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "22ec99545bb0ed0ea7bb9b8e1e9122ea386ff8a48c0922e43f36d45ab09e0e80" +[[package]] +name = "crunchy" +version = "0.2.2" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "7a81dae078cea95a014a339291cec439d2f232ebe854a9d672b796c6afafa9b7" + [[package]] name = "difflib" version = "0.4.0" @@ -310,6 +397,16 @@ dependencies = [ "walkdir", ] +[[package]] +name = "half" +version = "2.4.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6dd08c532ae367adf81c312a4580bc67f1d0fe8bc9c460520283f4c0ff277888" +dependencies = [ + "cfg-if", + "crunchy", +] + [[package]] name = "hashbrown" version = "0.14.5" @@ -322,6 +419,12 @@ version = "0.5.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "2304e00983f87ffb38b55b444b5e3b60a884b5d30c0fca7d82fe33449bbe55ea" +[[package]] +name = "hermit-abi" +version = "0.4.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "fbf6a919d6cf397374f7dfeeea91d974c7c0a7221d0d0f4f20d859d329e53fcc" + [[package]] name = "ignore" version = "0.4.23" @@ -348,12 +451,32 @@ dependencies = [ "hashbrown", ] +[[package]] +name = "is-terminal" +version = "0.4.13" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "261f68e344040fbd0edea105bef17c66edf46f984ddb1115b775ce31be948f4b" +dependencies = [ + "hermit-abi", + "libc", + "windows-sys 0.52.0", +] + [[package]] name = "is_terminal_polyfill" version = "1.70.1" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "7943c866cc5cd64cbc25b2e01621d07fa8eb2a1a23160ee81ce38704e97b8ecf" +[[package]] +name = "itertools" +version = "0.10.5" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b0fd2260e829bddf4cb6ea802289de2f86d6a7a690192fbe91b3f46e0f2c8473" +dependencies = [ + "either", +] + [[package]] name = "itertools" version = "0.11.0" @@ -369,6 +492,15 @@ version = "1.0.11" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "49f1f14873335454500d59611f1cf4a4b0f786f9ac11f4312a78e4cf2566695b" +[[package]] +name = "js-sys" +version = "0.3.72" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "6a88f1bda2bd75b0452a14784937d796722fdebfe50df998aeb3f0b7603019a9" +dependencies = [ + "wasm-bindgen", +] + [[package]] name = "lazy_static" version = "1.5.0" @@ -445,6 +577,12 @@ version = "1.19.0" source = "registry+https://github.com/rust-lang/crates.io-index" checksum = "3fdb12b2476b595f9358c5161aa467c2438859caa136dec86c26fdd2efe17b92" +[[package]] +name = "oorandom" +version = "11.1.4" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b410bbe7e14ab526a0e86877eb47c6996a2bd7746f027ba551028c925390e4e9" + [[package]] name = "parking_lot" version = "0.12.3" @@ -468,6 +606,34 @@ dependencies = [ "windows-targets", ] +[[package]] +name = "plotters" +version = "0.3.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "5aeb6f403d7a4911efb1e33402027fc44f29b5bf6def3effcc22d7bb75f2b747" +dependencies = [ + "num-traits", + "plotters-backend", + "plotters-svg", + "wasm-bindgen", + "web-sys", +] + +[[package]] +name = "plotters-backend" +version = "0.3.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "df42e13c12958a16b3f7f4386b9ab1f3e7933914ecea48da7139435263a4172a" + +[[package]] +name = "plotters-svg" +version = "0.3.7" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "51bae2ac328883f7acdfea3d66a7c35751187f870bc81f94563733a154d7a670" +dependencies = [ + "plotters-backend", +] + [[package]] name = "predicates" version = "3.1.2" @@ -516,6 +682,26 @@ dependencies = [ "proc-macro2", ] +[[package]] +name = "rayon" +version = "1.10.0" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "b418a60154510ca1a002a752ca9714984e21e4241e804d32555251faf8b78ffa" +dependencies = [ + "either", + "rayon-core", +] + +[[package]] +name = "rayon-core" +version = "1.12.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "1465873a3dfdaa8ae7cb14b4383657caab0b3e8a0aa9ae8e04b044854c8dfce2" +dependencies = [ + "crossbeam-deque", + "crossbeam-utils", +] + [[package]] name = "redox_syscall" version = "0.5.3" @@ -594,7 +780,7 @@ dependencies = [ "arc-swap", "base62", "globwalk", - "itertools", + "itertools 0.11.0", "lazy_static", "normpath", "once_cell", @@ -756,6 +942,7 @@ version = "0.1.2" dependencies = [ "assert_cmd", "clap", + "criterion", "predicates", "rust-i18n", "sys-locale", @@ -797,6 +984,16 @@ dependencies = [ "rustc-hash", ] +[[package]] +name = "tinytemplate" +version = "1.2.1" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "be4d6b5f19ff7664e8c98d03e2139cb510db9b0a60b55f8e8709b689d939b6bc" +dependencies = [ + "serde", + "serde_json", +] + [[package]] name = "toml" version = "0.7.8" @@ -873,6 +1070,71 @@ dependencies = [ "winapi-util", ] +[[package]] +name = "wasm-bindgen" +version = "0.2.95" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "128d1e363af62632b8eb57219c8fd7877144af57558fb2ef0368d0087bddeb2e" +dependencies = [ + "cfg-if", + "once_cell", + "wasm-bindgen-macro", +] + +[[package]] +name = "wasm-bindgen-backend" +version = "0.2.95" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "cb6dd4d3ca0ddffd1dd1c9c04f94b868c37ff5fac97c30b97cff2d74fce3a358" +dependencies = [ + "bumpalo", + "log", + "once_cell", + "proc-macro2", + "quote", + "syn", + "wasm-bindgen-shared", +] + +[[package]] +name = "wasm-bindgen-macro" +version = "0.2.95" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "e79384be7f8f5a9dd5d7167216f022090cf1f9ec128e6e6a482a2cb5c5422c56" +dependencies = [ + "quote", + "wasm-bindgen-macro-support", +] + +[[package]] +name = "wasm-bindgen-macro-support" +version = "0.2.95" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "26c6ab57572f7a24a4985830b120de1594465e5d500f24afe89e16b4e833ef68" +dependencies = [ + "proc-macro2", + "quote", + "syn", + "wasm-bindgen-backend", + "wasm-bindgen-shared", +] + +[[package]] +name = "wasm-bindgen-shared" +version = "0.2.95" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "65fc09f10666a9f147042251e0dda9c18f166ff7de300607007e96bdebc1068d" + +[[package]] +name = "web-sys" +version = "0.3.72" +source = "registry+https://github.com/rust-lang/crates.io-index" +checksum = "f6488b90108c040df0fe62fa815cbdee25124641df01814dd7282749234c6112" +dependencies = [ + "js-sys", + "wasm-bindgen", +] + [[package]] name = "winapi-util" version = "0.1.9" diff --git a/Cargo.toml b/Cargo.toml index 2e7b06a..ca3a376 100644 --- a/Cargo.toml +++ b/Cargo.toml @@ -7,6 +7,8 @@ authors = ["guza "] repository = "https://github.com/guuzaa/tc" license = "MIT" readme = "README.md" +exclude = [".github/*", ".vscode/*"] +categories = ["command-line-utilities", "cli-apps", "text-processing"] [dependencies] clap = { version = "4.3", features = ["derive"] } @@ -17,4 +19,9 @@ tiktoken-rs = "0.5.9" [dev-dependencies] assert_cmd = "2.0" predicates = "3.0.0" -tempfile = "3.12.0" \ No newline at end of file +tempfile = "3.12.0" +criterion = "0.5" + +[[bench]] +name = "tc_benches" +harness = false diff --git a/benches/tc_benches.rs b/benches/tc_benches.rs new file mode 100644 index 0000000..36049e4 --- /dev/null +++ b/benches/tc_benches.rs @@ -0,0 +1,73 @@ +use assert_cmd::Command; +use criterion::{criterion_group, criterion_main, Criterion}; +use std::io::Write; +use tempfile::NamedTempFile; + +fn bench_tc_command(c: &mut Criterion) { + let mut group = c.benchmark_group("tc_command"); + + // Benchmark with small input + let small_input = "This is a small input\nfor benchmarking purposes."; + bench_with_input(&mut group, "small_input", small_input); + + // Benchmark with medium input + let medium_input = "This is a medium input\n".repeat(100); + bench_with_input(&mut group, "medium_input", &medium_input); + + // Benchmark with large input + let large_input = "This is a large input\n".repeat(1000); + bench_with_input(&mut group, "large_input", &large_input); + + group.finish(); +} + +fn bench_with_input( + group: &mut criterion::BenchmarkGroup, + name: &str, + input: &str, +) { + let mut temp_file = NamedTempFile::new().unwrap(); + write!(temp_file, "{}", input).unwrap(); + + group.bench_function(name, |b| { + b.iter(|| { + Command::cargo_bin("tc") + .unwrap() + .arg(temp_file.path()) + .assert() + .success(); + }); + }); +} + +fn bench_multiple_files(c: &mut Criterion) { + let mut group = c.benchmark_group("tc_multiple_files"); + let file_contents = "This is a test file\nwith multiple lines\nfor benchmarking purposes.\n안녕하세요, 이것은 한국어 문장입니다.\nこんにちは、これは日本語の文章です。\n"; + + for &num_files in &[1, 10, 50, 500] { + let temp_files: Vec = (0..num_files) + .map(|_| { + let mut file = NamedTempFile::new().unwrap(); + write!(file, "{}", file_contents).unwrap(); + file + }) + .collect(); + + let file_paths: Vec<_> = temp_files + .iter() + .map(|f| f.path().to_str().unwrap()) + .collect(); + + group.bench_function(format!("{}_files", num_files), |b| { + b.iter(|| { + let mut cmd = Command::cargo_bin("tc").unwrap(); + cmd.arg("-l").args(&file_paths).assert().success(); + }); + }); + } + + group.finish(); +} + +criterion_group!(benches, bench_tc_command, bench_multiple_files); +criterion_main!(benches);