From 5eded442b7c7141b890aec17ef9e6e373697e335 Mon Sep 17 00:00:00 2001
From: JestDotty <jestdottydev@gmail.com>
Date: Sun, 23 Mar 2025 21:39:12 -0400
Subject: [PATCH] sync. rayon and build options, README
---
jest_rust/.gitignore | 2 +
jest_rust/Cargo.lock | 54 ++++++++++++++++++++++++
jest_rust/Cargo.toml | 6 +++
jest_rust/README.md | 71 +++++++++++++++----------------
jest_rust/src/main.rs | 97 ++++++++++++++++++++++++-------------------
5 files changed, 152 insertions(+), 78 deletions(-)
create mode 100644 jest_rust/.gitignore
diff --git a/jest_rust/.gitignore b/jest_rust/.gitignore
new file mode 100644
index 0000000..4fffb2f
--- /dev/null
+++ b/jest_rust/.gitignore
@@ -0,0 +1,2 @@
+/target
+/Cargo.lock
diff --git a/jest_rust/Cargo.lock b/jest_rust/Cargo.lock
index b23345f..e8971c0 100644
--- a/jest_rust/Cargo.lock
+++ b/jest_rust/Cargo.lock
@@ -2,6 +2,60 @@
# It is not intended for manual editing.
version = 4
+[[package]]
+name = "crossbeam-deque"
+version = "0.8.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "9dd111b7b7f7d55b72c0a6ae361660ee5853c9af73f70c3c2ef6858b950e2e51"
+dependencies = [
+ "crossbeam-epoch",
+ "crossbeam-utils",
+]
+
+[[package]]
+name = "crossbeam-epoch"
+version = "0.9.18"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5b82ac4a3c2ca9c3460964f020e1402edd5753411d7737aa39c3714ad1b5420e"
+dependencies = [
+ "crossbeam-utils",
+]
+
+[[package]]
+name = "crossbeam-utils"
+version = "0.8.21"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d0a5c400df2834b80a4c3327b3aad3a4c4cd4de0629063962b03235697506a28"
+
+[[package]]
+name = "either"
+version = "1.15.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "48c757948c5ede0e46177b7add2e67155f70e33c07fea8284df6576da70b3719"
+
[[package]]
name = "jisspam"
version = "0.1.0"
+dependencies = [
+ "rayon",
+]
+
+[[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",
+]
diff --git a/jest_rust/Cargo.toml b/jest_rust/Cargo.toml
index 75c1343..6df2ee3 100644
--- a/jest_rust/Cargo.toml
+++ b/jest_rust/Cargo.toml
@@ -4,3 +4,9 @@ version = "0.1.0"
edition = "2024"
[dependencies]
+rayon = "1.10.0"
+
+[profile.release]
+lto = "thin" # Full Link-Time Optimization for maximum runtime speed
+debug = false # Disables debug symbols to streamline the binary
+panic = "abort"
diff --git a/jest_rust/README.md b/jest_rust/README.md
index 2170adc..03feba5 100644
--- a/jest_rust/README.md
+++ b/jest_rust/README.md
@@ -1,39 +1,5 @@
-`cd jestdotty_rust/jisspam && cargo run --release && cp target/release/jisspam ../../`
-
for https://retoor.molodetz.nl/retoor/isspam
-some older benchmarks to know what to beat, or something:
-```
-Time C: 11.447573184967041
-Time Rust: 1.2248871326446533
-Time CPP: 2.1745784282684326
-Time Borded CPP: 1.4606633186340332
-Time Retoor Python: 38.008224964141846
-
-Time C: 10.476306915283203
-Time Rust: 1.1816489696502686
-Time CPP: 2.030345916748047
-Time Borded CPP: 0.6507000923156738
-
-Time Rust: 1.1833229064941406
-Time C: 10.77005124092102
-Time CPP: 2.075010061264038
-Time Borded CPP: 0.8050553798675537
-Time Retoor Python: 39.06818628311157
-
-Time Rust: 1.187262773513794
-Time C: 10.271284818649292
-Time CPP: 2.0337636470794678
-Time Borded CPP: 0.7784948348999023
-Time Retoor Python: 37.15883994102478
-
-Time Rust: 1.239715337753296
-Time C: 11.51186990737915
-Time CPP: 2.085871934890747
-Time Borded CPP: 0.6888203620910645
-Time Retoor Python: 35.5970196723938
-```
-
https://snek.molodetz.nl/terminal.html ubuntu running thing instructions:
```
mkdir /project
@@ -50,4 +16,39 @@ rustup default nightly
make
make benchmark
python3 bench.py
-```
\ No newline at end of file
+```
+
+clone: `git clone https://gitlab.com/jestdotty-group/draft/jisspam.git jest_rust`
+
+edit make: `vi makefile` and add build:
+```
+build_jest:
+ @echo "compiling jest_rust project"
+ cd jest_rust && cargo build --release && cp target/release/jisspam ..
+```
+append to all script:
+```
+all: build run valgrind build_risspam run_risspam build_cpp build_borded_cpp build_py build_jest
+```
+
+add to bench: `vi bench.py`
+```py
+time_start = time.time()
+subprocess.check_output('./jisspam books/*.txt', shell=True)
+print("Time Jest Rust:", time.time() - time_start)
+```
+
+run: `python3 bench.py`
+output looks something like this:
+```
+***benchmarking***
+Time C: 31.315868377685547
+Time Rust: 41.232205867767334
+Time CPP: 20.1683189868927
+Time Borded CPP: 15.468477964401245
+Time Jest Rust: 54.74523115158081
+Time Retoor Python: 287.63036131858826
+***end benchmark***
+```
+
+add `/jisspam` to `.gitignore` to not commit the executable accidentally
\ No newline at end of file
diff --git a/jest_rust/src/main.rs b/jest_rust/src/main.rs
index 048ad24..ea6b81b 100644
--- a/jest_rust/src/main.rs
+++ b/jest_rust/src/main.rs
@@ -1,3 +1,4 @@
+use rayon::iter::{IntoParallelRefIterator, ParallelIterator};
use std::{env, fmt::Display, fs};
static FORBIDDEN_WORDS: &'static [&'static str] = &[
@@ -39,7 +40,7 @@ static FORBIDDEN_WORDS: &'static [&'static str] = &[
];
#[derive(Debug, Default)]
-struct Stats {
+pub struct Stats {
file_count: u32,
failed_file_count: u32,
@@ -50,6 +51,48 @@ struct Stats {
numeric_count: u32,
forbidden_count: u32,
}
+impl Stats {
+ pub fn process(&mut self, file: &str) {
+ let Ok(text) = fs::read_to_string(&file) else {
+ self.failed_file_count += 1;
+ return;
+ };
+ self.file_count += 1;
+ for sentence in text
+ .split('.')
+ .map(|s| s.trim())
+ .filter(|s| !s.is_empty())
+ {
+ self.sentence_count += 1;
+ for word in sentence
+ .split_whitespace()
+ .map(|s| s.trim())
+ .filter(|s| !s.is_empty())
+ {
+ self.word_count += 1;
+ //get all numbers counted
+ let mut all_capitalized = true;
+ for char in word.chars() {
+ if char.is_numeric() {
+ self.numeric_count += 1;
+ }
+ if !char.is_ascii_uppercase() {
+ all_capitalized = false;
+ }
+ }
+ if all_capitalized {
+ self.capitalized_count += 1;
+ }
+ let lowercase_word = word.to_lowercase();
+ for forbidden_word in FORBIDDEN_WORDS {
+ if lowercase_word.contains(forbidden_word) {
+ self.forbidden_count += 1;
+ }
+ }
+ }
+ }
+ }
+}
impl Display for Stats {
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
writeln!(f, "file count: {}", self.file_count)?;
@@ -83,48 +126,16 @@ impl Display for Stats {
fn main() {
let files = env::args().skip(1);
- let mut stats = Stats::default();
- for file in files {
- let Ok(text) = fs::read_to_string(&file) else {
- stats.failed_file_count += 1;
- continue;
- };
- stats.file_count += 1;
- for sentence in text
- .split('.')
- .map(|s| s.trim())
- .filter(|s| !s.is_empty())
- {
- stats.sentence_count += 1;
- for word in sentence
- .split_whitespace()
- .map(|s| s.trim())
- .filter(|s| !s.is_empty())
- {
- stats.word_count += 1;
- //get all numbers counted
- let mut all_capitalized = true;
- for char in word.chars() {
- if char.is_numeric() {
- stats.numeric_count += 1;
- }
- if !char.is_ascii_uppercase() {
- all_capitalized = false;
- }
- }
- if all_capitalized {
- stats.capitalized_count += 1;
- }
- let lowercase_word = word.to_lowercase();
- for forbidden_word in FORBIDDEN_WORDS {
- if lowercase_word.contains(forbidden_word) {
- stats.forbidden_count += 1;
- }
- }
- }
- }
- }
- println!("{stats}");
+ // let mut stats = Stats::default();
+ // for file in files {
+ // stats.process(&file);
+ // }
+ let files = files.collect::<Vec<_>>();
+ files.par_iter().for_each(|file| {
+ let mut stats = Stats::default();
+ stats.process(&file);
+ println!("{stats}");
+ });
}
#[test]