The Computer Language
24.04 Benchmarks Game

regex-redux Rust #2 program

source code

// The Computer Language Benchmarks Game
// https://salsa.debian.org/benchmarksgame-team/benchmarksgame/
//
// regex-dna program contributed by the Rust Project Developers
// contributed by BurntSushi
// contributed by TeXitoi
// converted from regex-dna program

extern crate regex;

use std::io::{self, Read};
use std::sync::Arc;
use std::thread;

macro_rules! regex { ($re:expr) => { ::regex::bytes::Regex::new($re).unwrap() } }

fn main() {
    let mut seq = Vec::with_capacity(51 * (1 << 20));
    io::stdin().read_to_end(&mut seq).unwrap();
    let ilen = seq.len();

    seq = regex!(">[^\n]*\n|\n").replace_all(&seq, &b""[..]).into_owned();
    let clen = seq.len();
    let seq_arc = Arc::new(seq.clone());

    let variants = vec![
        regex!("agggtaaa|tttaccct"),
        regex!("[cgt]gggtaaa|tttaccc[acg]"),
        regex!("a[act]ggtaaa|tttacc[agt]t"),
        regex!("ag[act]gtaaa|tttac[agt]ct"),
        regex!("agg[act]taaa|ttta[agt]cct"),
        regex!("aggg[acg]aaa|ttt[cgt]ccct"),
        regex!("agggt[cgt]aa|tt[acg]accct"),
        regex!("agggta[cgt]a|t[acg]taccct"),
        regex!("agggtaa[cgt]|[acg]ttaccct"),
    ];
    let mut counts = vec![];
    for variant in variants {
        let seq = seq_arc.clone();
        let restr = variant.to_string();
        let future = thread::spawn(move || variant.find_iter(&seq).count());
        counts.push((restr, future));
    }

    let substs = vec![
        (regex!("tHa[Nt]"), &b"<4>"[..]),
        (regex!("aND|caN|Ha[DS]|WaS"), &b"<3>"[..]),
        (regex!("a[NSt]|BY"), &b"<2>"[..]),
        (regex!("<[^>]*>"), &b"|"[..]),
        (regex!("\\|[^|][^|]*\\|"), &b"-"[..]),
    ];
    let mut seq = seq;
    for (re, replacement) in substs.into_iter() {
        seq = re.replace_all(&seq, replacement).into_owned();
    }

    for (variant, count) in counts {
        println!("{} {}", variant, count.join().unwrap());
    }
    println!("\n{}\n{}\n{}", ilen, clen, seq.len());
}
    

notes, command-line, and program output

NOTES:
64-bit Ubuntu quad core
1.76.0
(07dca489a
2024-02-04)
LLVM version: 17.0.6


 Fri, 12 Apr 2024 21:09:08 GMT

MAKE:
/opt/src/rust-1.76.0/bin/rustc -C opt-level=3 -C target-cpu=ivybridge -C codegen-units=1 -L /opt/src/rust-libs --extern crossbeam_utils=/opt/src/rust-libs/libcrossbeam_utils-01a3ee6d41b413b9.rlib regexredux.rs -o regexredux.rust-2.rust_run

9.51s to complete and log all make actions

COMMAND LINE:
 ./regexredux.rust-2.rust_run 0 < regexredux-input5000000.txt

PROGRAM OUTPUT:
agggtaaa|tttaccct 356
[cgt]gggtaaa|tttaccc[acg] 1250
a[act]ggtaaa|tttacc[agt]t 4252
ag[act]gtaaa|tttac[agt]ct 2894
agg[act]taaa|ttta[agt]cct 5435
aggg[acg]aaa|ttt[cgt]ccct 1537
agggt[cgt]aa|tt[acg]accct 1431
agggta[cgt]a|t[acg]taccct 1608
agggtaa[cgt]|[acg]ttaccct 2178

50833411
50000000
27388361