使LINQ到一个字典变成一个方法体

本文关键字：一个 方法 字典 LINQ | 更新日期: 2023-09-27 17:49:37

我使用两个几乎相同的(唯一的例外是一个得到.ToDictinct()，而另一个没有)调用。是否有可能将它们变成一个方法，我可以在一个地方调用和更改?

private void Splitter1(string[] file)
{               
    tempDict = file
        .SelectMany(i => File.ReadAllLines(i)
        .SelectMany(line => line.Split(new[] { ' ', ',', '.', '?', '!', '{', '[', '(', '}', ']', ')',
        '<', '>', '-', '=', '/', '"', ';', ':', '+', '_', '*' }, StringSplitOptions.RemoveEmptyEntries))                    
        .AsParallel()
        .Select(word => word.ToLower()) 
        .Where(word => !StopWords.Contains(word))
        .Where(word => !PopulatNetworkWords.Contains(word)) 
        .Where(word => !word.All(char.IsDigit))
        .Distinct())
        .GroupBy(word => word)                    
        .ToDictionary(g => g.Key, g => g.Count());
}
private void Splitter2(string[] file)
{               
    tempDict = file
        .SelectMany(i => File.ReadAllLines(i)
        .SelectMany(line => line.Split(new[] { ' ', ',', '.', '?', '!', '{', '[', '(', '}', ']', ')',
        '<', '>', '-', '=', '/', '"', ';', ':', '+', '_', '*' }, StringSplitOptions.RemoveEmptyEntries)))                    
        .AsParallel()
        .Select(word => word.ToLower()) 
        .Where(word => !StopWords.Contains(word))
        .Where(word => !PopulatNetworkWords.Contains(word)) 
        .Where(word => !word.All(char.IsDigit))
        .GroupBy(word => word)                    
        .ToDictionary(g => g.Key, g => g.Count());
}

使LINQ到一个字典变成一个方法体

由于两者之间的区别在于Distinct()是否被调用，并且由于Distinct()既作用于并返回IEnumerable<T>(或作用于并返回IQueryable<T>)。然后首先创建相应的IEnumerable<T>，然后决定是否用调用Distinct()的结果替换它，然后继续:

private void Splitter(string[] file, bool distinct)
{               
  IEnumerable<string> query = file
    .SelectMany(i => File.ReadAllLines(i)
    .SelectMany(line => line.Split(new[] { ' ', ',', '.', '?', '!', '{', '[', '(', '}', ']', ')',
    '<', '>', '-', '=', '/', '"', ';', ':', '+', '_', '*' }, StringSplitOptions.RemoveEmptyEntries))                    
    .AsParallel()
    .Select(word => word.ToLower()) 
    .Where(word => !StopWords.Contains(word))
    .Where(word => !PopulatNetworkWords.Contains(word)) 
    .Where(word => !word.All(char.IsDigit));
  if(distinct)
    query = query.Distinct());
  return query
    .GroupBy(word => word)                    
    .ToDictionary(g => g.Key, g => g.Count());
}
(顺便说一下，您可能会发现较新的ReadLines比ReadAllLines工作得更好，特别是对于大文件。ReadAllLines立即将所有行读入内存，而不是在使用它们时读取它们，因此它浪费了大量内存并延迟了处理)。

为什么不这样呢:

    private void Splitter1(string[] file, bool useDistinct = false))
    {
        tempDict = file
            .SelectMany(i => File.ReadAllLines(i)
            .SelectMany(line => line.Split(new[] { ' ', ',', '.', '?', '!', '{', '[', '(', '}', ']', ')',
    '<', '>', '-', '=', '/', '"', ';', ':', '+', '_', '*' }, StringSplitOptions.RemoveEmptyEntries))
            .AsParallel()
            .Select(word => word.ToLower())
            .Where(word => !StopWords.Contains(word))
            .Where(word => !PopulatNetworkWords.Contains(word))
            .Where(word => !word.All(char.IsDigit))
            .Select(x => useDistinct ? x.Distinct() : x)
            .GroupBy(word => word)
            .ToDictionary(g => g.Key, g => g.Count());
    }

由于Linq延迟执行，您可以在单独的语句中构建子句。

 private void Splitter1(string[] file, bool distinct)
    {               
         var query = file.SelectMany (i => File.ReadAllLines(i)
                .SelectMany(line => line.Split(new[] { ' ', ',', '.', '?', '!', '{', '[', '(', '}', ']', ')',
                '<', '>', '-', '=', '/', '"', ';', ':', '+', '_', '*' }, StringSplitOptions.RemoveEmptyEntries))                    
                .AsParallel()
                .Select(word => word.ToLower()) 
                .Where(word => !StopWords.Contains(word))
                .Where(word => !PopulatNetworkWords.Contains(word)) 
                .Where(word => !word.All(char.IsDigit)));
        if (distinct) 
        {
            query = query.Distinct();
        }
        query.GroupBy(word => word)                    
              .ToDictionary(g => g.Key, g => g.Count());
    }

我没有测试这段代码，所以你需要调整它。但是，其基本思想是延迟执行允许您根据逻辑更改查询。

相关文章：