The Computer Language
24.09 Benchmarks Game

regex-redux F# .NET #6 program

source code

// The Computer Language Benchmarks Game
// https://salsa.debian.org/benchmarksgame-team/benchmarksgame/
//
// regex-dna program contributed by David Grenier
// converted from regex-dna program
// parallelization by Peter Kese
// order variants by execution time by Anthony Lloyd

open System.Text.RegularExpressions

let inline regex s = Regex(s, RegexOptions.Compiled)
let input = stdin.ReadToEnd()
let text = (regex ">.*\n|\n").Replace (input, "")

let inline regexCount pattern = async {
    let rec loop c (m:Match) =
        if not m.Success then c
        else loop (c+1) (m.NextMatch())
    let c = loop 0 ((regex pattern).Match text)
    return pattern + " " + string c
}

let replaceTask = async {
    let l =
        [
            "tHa[Nt]", "<4>"
            "aND|caN|Ha[DS]|WaS", "<3>"
            "a[NSt]|BY", "<2>"
            "<[^>]*>", "|"
            "\\|[^|][^|]*\\|", "-"
        ]
        |> List.fold (fun s (pattern, replace) ->
            (regex pattern).Replace (s, replace)) text
        |> String.length |> string
    return "\n" + string input.Length + "\n" + string text.Length + "\n" + l
}

let results =
    [
        replaceTask
        regexCount "[cgt]gggtaaa|tttaccc[acg]"
        regexCount "a[act]ggtaaa|tttacc[agt]t"
        regexCount "agggt[cgt]aa|tt[acg]accct"
        regexCount "aggg[acg]aaa|ttt[cgt]ccct"
        regexCount "ag[act]gtaaa|tttac[agt]ct"
        regexCount "agg[act]taaa|ttta[agt]cct"
        regexCount "agggtaaa|tttaccct"
        regexCount "agggtaa[cgt]|[acg]ttaccct"
        regexCount "agggta[cgt]a|t[acg]taccct"
    ]
    |> Async.Parallel
    |> Async.RunSynchronously

stdout.WriteLine results.[7]
stdout.WriteLine results.[1]
stdout.WriteLine results.[2]
stdout.WriteLine results.[5]
stdout.WriteLine results.[6]
stdout.WriteLine results.[4]
stdout.WriteLine results.[3]
stdout.WriteLine results.[9]
stdout.WriteLine results.[8]
stdout.WriteLine results.[0]
    

notes, command-line, and program output

NOTES:
64-bit Ubuntu quad core
.NET SDK 8.0.301
Host Version: 8.0.6
Commit: 3b8b000a0e
<ServerGarbageCollection>true
F# 8.0

<OutputType>Exe
<TargetFramework>net8.0
<ImplicitUsings>enable
<Nullable>enable
<AllowUnsafeBlocks>true
<ServerGarbageCollection>true
<ConcurrentGarbageCollection>true
<PublishAot>false


 Tue, 04 Jun 2024 05:07:50 GMT

MAKE:
cp regexredux.fsharpcore-6.fsharpcore Program.fs
cp Include/fsharpcore/program.fsproj .
mkdir obj
cp Include/fsharpcore/project.assets.json ./obj
~/dotnet/dotnet build -c Release --use-current-runtime  	
  Determining projects to restore...
/home/dunham/all-benchmarksgame/benchmarksgame_i53330/regexredux/tmp/program.fsproj : warning NU1900: Error occurred while getting package vulnerability data: Unable to load the service index for source https://api.nuget.org/v3/index.json.
  Restored /home/dunham/all-benchmarksgame/benchmarksgame_i53330/regexredux/tmp/program.fsproj (in 6.06 sec).
/home/dunham/all-benchmarksgame/benchmarksgame_i53330/regexredux/tmp/program.fsproj : warning NU1900: Error occurred while getting package vulnerability data: Unable to load the service index for source https://api.nuget.org/v3/index.json.
  program -> /home/dunham/all-benchmarksgame/benchmarksgame_i53330/regexredux/tmp/bin/Release/net8.0/linux-x64/program.dll

Build succeeded.

/home/dunham/all-benchmarksgame/benchmarksgame_i53330/regexredux/tmp/program.fsproj : warning NU1900: Error occurred while getting package vulnerability data: Unable to load the service index for source https://api.nuget.org/v3/index.json.
/home/dunham/all-benchmarksgame/benchmarksgame_i53330/regexredux/tmp/program.fsproj : warning NU1900: Error occurred while getting package vulnerability data: Unable to load the service index for source https://api.nuget.org/v3/index.json.
    2 Warning(s)
    0 Error(s)

Time Elapsed 00:00:14.44

16.75s to complete and log all make actions

COMMAND LINE:
 ./bin/Release/net8.0/linux-x64/program 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