根据大小计算文件组

Question

如何简化它？我正在尝试根据Excel文件的大小从目录和子目录中获取Excel文件的数量。我至少有10个不同的分组。

var queryList2Only = from i in di.GetFiles("*.xls", SearchOption.TopDirectoryOnly)
                                 .Where(f => f.Length <= 5120)
                     select i.Length;
if (queryList2Only.Any())
{
    dest.WriteLine("Excel File <= 5 KB");
    dest.WriteLine(queryList2Only.Count());
    dest.WriteLine("");
}
var queryList3Only = from i in di.GetFiles("*.xls", SearchOption.TopDirectoryOnly)
                                 .Where(f => f.Length > 5120 && f.Length <= 10240)
                     select i.Length;
if (queryList3Only.Any())
{
    dest.WriteLine("Excel File > 5 KB and <= 10 KB");
    dest.WriteLine(queryList3Only.Count());
    dest.WriteLine("");

编辑：我需要这个

  <= 5 KB,> 5 KB and <= 10 KB,> 10 KB and <= 20 KB,> 20 KB and <= 100 KB,> 100 KB and <= 1000 KB,> 1000 KB and <=5 MB,> 5 MB and <=10 MB,> 10 MB and <=20 MB,> 20 MB and <=50 MB,> 50 MB and <=100 MB

---

private void button1_Click(object sender, EventArgs e)
        {

            DirectoryInfo Folder = new DirectoryInfo(textBox1.Text);
            var _logFolderPath4 = Path.Combine(textBox1.Text.Trim(), "log");
            if (Folder.Exists)
                if (!Directory.Exists(_logFolderPath4))
                    Directory.CreateDirectory(_logFolderPath4);
            DirectoryInfo di = new DirectoryInfo(@"D:Material");
            bool time = false;
            using (var dest = File.AppendText(Path.Combine(_logFolderPath4, "Excel.txt")))
            {
                    if (!time)
                    {
                        dest.WriteLine("---------------------" + DateTime.Now + "---------------------");
                        dest.WriteLine("");
                        time = true;
                    }
                    CountFiles(dest, di, @"*.txt");
            }
    }

Answer 1

您需要将范围放在集合中，并对其进行枚举。下面是一个应该让你开始的例子-size数组包含步骤，当然你应该选择对你的应用程序有意义的步骤：

int[] sizes = Enumerable.Range(0,10).Select(n => (int)Math.Pow(2,n + 8)).ToArray();
int lower = 0;
foreach(var size in sizes)
{
    var files = di.GetFiles("*.*").Where(f => f.Length >= lower && f.Length < size);
    Console.WriteLine("Between {0} and {1} bytes:", lower,size);
    foreach(var file in files)
        Console.WriteLine("t{0}",file);
    lower = size;
}

Answer 2

您不一定需要LINQ。虽然Rup的解决方案在这里是LINQ的一个很好的用途，但对你来说，循环使用它会更有效率。

这里有一个更完整的版本，专门为你想做的事情量身定制。

// count it
CountFiles(dest, di, @"*.xls");
public void CountFiles(TextWriter writer, DirectoryInfo directory, string searchPattern)
{
    var counter = new FileGroupCounter
    {
        { 5,    Multiplier.K },
        { 10,   Multiplier.K },
        { 20,   Multiplier.K },
        { 100,  Multiplier.K },
        { 1000, Multiplier.K },
        { 5,    Multiplier.M },
        { 10,   Multiplier.M },
        { 20,   Multiplier.M },
        { 50,   Multiplier.M },
        { 100,  Multiplier.M },
    };
    foreach (var file in directory.EnumerateFiles(searchPattern, SearchOption.AllDirectories))
                         // or use GetFiles() if you're not targeting .NET 4.0
    {
        counter.CountFile(file);
    }
    foreach (var result in counter)
    {
        writer.WriteLine("Excel File " + result);
        writer.WriteLine(result.Count);
        writer.WriteLine();
    }
}
// and the supporting classes
public enum Multiplier : long
{
    K = 1 << 10,
    M = 1 << 20,
    G = 1 << 30,
    T = 1 << 40,
}
public class FileGroupCounter : IEnumerable<FileGroupCounter.Result>
{
    public ReadOnlyCollection<long> Limits { get { return roLimits; } }
    public ReadOnlyCollection<int> Counts { get { return roCounts; } }
    public ReadOnlyCollection<Multiplier> Multipliers { get { return roMultipliers; } }
    public FileGroupCounter()
    {
        limits = new List<long>();
        counts = new List<int>();
        multipliers = new List<Multiplier>();
        roLimits= limits.AsReadOnly();
        roCounts= counts.AsReadOnly();
        roMultipliers= multipliers.AsReadOnly();
    }
    private List<long> limits;
    private List<int> counts;
    private List<Multiplier> multipliers;
    private ReadOnlyCollection<long> roLimits;
    private ReadOnlyCollection<int> roCounts;
    private ReadOnlyCollection<Multiplier> roMultipliers;
    private long CalculateLength(int index)
    {
        return limits[index] * (long)multipliers[index];
    }
    public void Add(long limit, Multiplier multiplier)
    {
        int lastIndex = limits.Count - 1;
        if (lastIndex >= 0 && limit * (long)multiplier <= CalculateLength(lastIndex))
            throw new ArgumentOutOfRangeException("limit, multiplier", "must be added in increasing order");
        limits.Add(limit);
        counts.Add(0);
        multipliers.Add(multiplier);
    }
    public bool CountFile(FileInfo file)
    {
        if (file == null)
            throw new ArgumentNullException("file");
        for (int i = 0; i < limits.Count; i++)
        {
            if (file.Length <= CalculateLength(i))
            {
                counts[i]++;
                return true;
            }
        }
        return false;
    }
    public IEnumerator<Result> GetEnumerator()
    {
        for (int i = 0; i < limits.Count; i++)
        {
            if (counts[i] > 0)
                yield return new Result(this, i);
        }
    }
    System.Collections.IEnumerator System.Collections.IEnumerable.GetEnumerator() { return GetEnumerator(); }
    public class Result
    {
        public long Limit { get { return counter.limits[index]; } }
        public int Count { get { return counter.counts[index]; } }
        public Multiplier Multiplier { get { return counter.multipliers[index]; } }
        internal Result(FileGroupCounter counter, int index)
        {
            this.counter = counter;
            this.index = index;
        }
        private FileGroupCounter counter;
        private int index;
        public override string ToString()
        {
            if (index > 0)
                return String.Format("> {0} {1}B and <= {2} {3}B",
                    counter.limits[index - 1], counter.multipliers[index - 1],
                    counter.limits[index], counter.multipliers[index]);
            else
                return String.Format("<= {0} {1}B",
                    counter.limits[index], counter.multipliers[index]);
        }
    }
}

Answer 3

我认为这里唯一真正的优化是确保只调用di.GetFiles("*.xls", SearchOption.TopDirectoryOnly)一次，因为这实际上会影响文件系统，而不是像大多数LINQ那样延迟执行。当然，文件系统会缓存此操作的结果，但保持在内存中并重用列表的速度再慢不过了。

一旦你进入记忆，Jeff可能是对的——你自己数一下——认为这似乎不太优雅：——）除非你要处理大量的数据，否则这可能不会有多大区别。你只想尽量减少分配/重新分配的数量。有了尽可能多的LINQ我可以塞进

var files = di.GetFiles("*.xls", SearchOption.TopDirectoryOnly);
// map to a list of numbers, 0 = up to 5K, 1 = 5-10, etc.
var sizes = files.Select(f => (f.Length / 5120));
var countsBySize = sizes.GroupBy(s => s)
                        .Select(g => new { Size = g.Key, Count = g.Count() })
                        .OrderBy(s => s.Size);
var results = countBySize.ToList();

其返回5K个存储桶的列表以及每个存储桶中的文件计数。如果你只是想预先决定，那么就不要做最后的ToList。如果你想要每个bucket中的单个文件，你应该按（f.Length/5120）分组，而不是先选择它。