如何使用 C# 从 CSV 文件中删除标题和整列？

Question

我正在将 JSON 文件转换为 CSV。转换完成后，我需要检查没有任何行的值的列。如果是这种情况，则应将整个列与标题一起删除。

在上面的示例中，“Retiring Period”列在其任何行中都没有任何值。因此，更新后的 CSV 应如下所示。

这是使用 C# 的预期和需要完成的。对此的任何帮助都将非常重要。

Answer 1

通用解决方案可能类似于

class Program {
    static void Main (string[] args) {
        GenerateNonEmptyCSV ("data.json", "data", "output.csv");
    }

    public static void GenerateNonEmptyCSV (string inputJsonFilePath_, string arrayName_, string outputFilePath_) {
        //Read data from json file
        DataSet dataSet;
        using (TextReader tr = new StreamReader (inputJsonFilePath_)) {
            dataSet = JsonConvert.DeserializeObject<DataSet> (tr.ReadToEnd ());
        }
        DataTable dataTable = dataSet.Tables[arrayName_];

        //Get Valid column index into a hashset
        var validColumns = new HashSet<int> ();
        foreach (DataRow row in dataTable.Rows) {
            if (validColumns.Count == dataTable.Columns.Count) { break; } //All columns are valid, no need to loop through rows anymore
            for (int columnIndex = 0; columnIndex < dataTable.Columns.Count; columnIndex++) {
                if (validColumns.Contains (columnIndex)) { continue; }
                if (!string.IsNullOrWhiteSpace (row?.ItemArray[columnIndex]?.ToString ())) { validColumns.Add (columnIndex); }
            }
        }

        //output valid columns into csv file
        using (TextWriter tw = new StreamWriter (outputFilePath_)) {
            string[] columnData = new string[validColumns.Count];
            int index = 0;
            foreach (int columnIndex in validColumns) {
                columnData[index++] = dataTable.Columns[columnIndex].ColumnName;
            }
            tw.WriteLine (string.Join (",", columnData)); //Write column header

            foreach (DataRow row in dataTable.Rows) {
                string[] rowData = new string[validColumns.Count];
                index = 0;
                foreach (int columnIndex in validColumns) {
                    rowData[index++] = row?.ItemArray[columnIndex]?.ToString ();
                }
                tw.WriteLine (string.Join (",", rowData));
            }
        }
    }
}

使用的样本数据

{
"data": [
    {
        "EmployeeId": "1",
        "EmployeeName": "Name1",
        "RetiringPeriod": "",
        "Salary":"80k"
    },
    {
        "EmployeeId": "2",
        "EmployeeName": "Name2",
        "RetiringPeriod": "",
        "Salary":"60k"
    }
  ]
}

Answer 2

假设您知道如何从集合移到 .CSV 文件并返回，并且您有一个包含您的数据（包括空的 Retirement）的员工集合，您可以生成一个EmployeesWithoutRetirements 集合并将其保存为 .CSV。

void Main()
{
    var employeeWithoutRetirements = (List<EmployeeWithoutRetirement>) Employees
        .Select(x => new EmployeeWithoutRetirement {
            EmployeeID = x.EmployeeID,
            EmployeeName = x.EmployeeName, 
            Salary = x.Salary });
    }
class EmployeeWithoutRetirement
{
    public int EmployeeID  {get;set;}
    public string EmployeeName {get;set;}
    public decimal Salary { get; set; }
}