scan-vid/test.jl

# То же самое, но на julia

using Logging
using Printf
using Dates
using CRC32c
using JSON
using Base.Threads

debuglogger = ConsoleLogger(stderr, Logging.Debug)
global_logger(debuglogger)

# правильный перевод!
function humanbytes(B)
    """Return the given bytes as a human friendly KB, MB, GB, or TB string."""
    B = float(B)
    KB = float(1024)
    MB = float(KB ^ 2) # 1,048,576
    GB = float(KB ^ 3) # 1,073,741,824
    TB = float(KB ^ 4) # 1,099,511,627,776

    if B < KB
        return @sprintf("%.2f Bytes", B)
    elseif KB <= B && B < MB
        return @sprintf("%.2f KB", (B / KB))
    elseif MB <= B && B < GB
        return @sprintf("%.2f MB", (B / MB))
    elseif GB <= B && B < TB
        return @sprintf("%.2f GB", (B / GB))
    elseif TB <= B
        return @sprintf("%.2f TB", (B / KB))
    end
end

function new_name(name)
    matches = Dict(
        "Сек" => r"(.+) Сек.*",
        "Сцен" => r"(.+) Сцен.*",
        "Голые" => r"(.+) Голые.*",
        "Откро" => r"(.+) Откро.*",
        "Посте" => r"(.+) Посте.*",
        "Изнас" => r"(.+) Изнас.*",
        "Инцес" => r"(.+) Инцес.*",
        "Лесб" => r"(.+) Лесб.*",
        "Эро" => r"(.+) Эро.*"
    )
    for (k, v) in matches
        if contains(name, k)
            base, ext = splitext(name)
            new_name = replace(base, v => s"\1")
            # @debug base, new_name
            return string(new_name, ext)
        end
    end
    return name
end

function valid_file(filename)
    valids = [".mp4", ".webm", ".mpeg"]
    _, ext = splitext(filename)
    return ext in valids
end

# file_info function returns information from file
function file_info(filename)
    _, ext = splitext(filename)
    info = stat(filename)
    crc = CRC32c.crc32c(open(filename, "r"))
    m = Dict(
        "filename" => filename,
        "size" => info.size,
        "hsize" => humanbytes(info.size),
        "mtime" => info.mtime,
        "ctime" => info.ctime,
        "htime" => Dates.format(Dates.unix2datetime(info.ctime), "dd.mm.yyyy"),
        "ext" => ext,
        "crc"=> Int(crc),
    )
    return m
end

function file_meta(filename)
    cmd = `ffprobe -v quiet -print_format json -show_format -show_streams "$filename"`
    out = read(cmd, String)
    data = JSON.parse(out)
    # println(data["format"]["duration"])
    return out
end

function check_file(filename)
    # println(filename)
    info = file_info(filename)
    meta = file_meta(filename)  
    # println(info)  
    return meta
end

function parallel_execution()
    nthreads = Threads.nthreads()  # Получаем количество доступных потоков
    println("Running parallel execution: $(nthreads)")
    results = Vector{Int}(undef, nthreads)  # Создаем массив для хранения результатов

    # Создаем и запускаем потоки
    for i in 1:nthreads
        results[i] = Threads.@spawn begin
            # Код, который нужно выполнить параллельно
            return i * 2
        end
    end

    # Получаем результаты из потоков
    for i in 1:nthreads
        println("Результат из потока $i: $(fetch(results[i]))")
    end
end

function main()
    dir = "d:\\vids\\ero"
    @info  "Обработка каталога: $dir"
    
    files = readdir(dir, join=true)
    n = length(files)
    println("всего: $n files")

    @time begin
        @sync begin
            for file in filter(valid_file, files)
                @async begin
                    meta = @spawn check_file(file)
                    println(file)
                end
            end
        end
    end

    # @sync begin
    #     for file in filter(valid_file, files)
    #         @async begin
    #             meta = check_file(file)
    #         end
    #     end
    # end
    
    println("обработано")
end

# -------- основная программа --------------
# parallel_execution()
main()