读取CSV文件并展示数据：解决硬编码列索引的适配问题

问题背景 #

我处理CSV文件时遇到了硬编码列索引的问题——当前代码里固定用parts[1]、parts[2]这类索引读取数据，一旦CSV列顺序变动，程序就会出错。我知道可以用循环解决，但卡壳了，求指导。之前的硬编码代码如下：

public override System.Collections.ObjectModel.ObservableCollection ExtractSamples()
{
ObservableCollection samples = new ObservableCollection();
            List<string> lines = this.GetTextLines();

            foreach (string line in lines)
            {
                string[] parts = line.Replace("\"", "").Split(new string[] { "," }, StringSplitOptions.None);
                for (int i = 0; i < parts.Length; i++)
                {
                    parts[i] = parts[i].Trim();
                }

                Sample sample = new Sample(parts[1].Trim()); //for reading sample name Test1, Test2
                samples.Add(sample);

                sample.AddResult(DateTime.Now, "C1", parts[2]); //for adding Sample headers and it's Value like C1, 0.001692
                sample.AddResult(DateTime.Now, "C2", parts[3]);
                sample.AddResult(DateTime.Now, "C3", parts[4]);
            }

        return samples;
    }

解决方案 #

核心思路是先读取CSV的表头行，用字典建立列名和索引的映射关系，之后遍历数据行时通过列名匹配获取对应值，彻底摆脱硬编码索引的限制。优化后的代码如下：

public override System.Collections.ObjectModel.ObservableCollection<Sample> ExtractSamples()
{
    ObservableCollection<Sample> samples = new ObservableCollection<Sample>();
    List<string> lines = this.GetTextLines();
    
    if (lines.Count == 0) return samples;

    // 解析表头，建立列名到索引的映射字典
    string[] headerParts = lines[0].Replace("\"", "").Split(new string[] { "," }, StringSplitOptions.None);
    for (int i = 0; i < headerParts.Length; i++)
    {
        headerParts[i] = headerParts[i].Trim();
    }
    Dictionary<string, int> columnIndexMap = new Dictionary<string, int>();
    for (int i = 0; i < headerParts.Length; i++)
    {
        columnIndexMap[headerParts[i]] = i;
    }

    // 遍历数据行（跳过表头行）
    for (int lineIndex = 1; lineIndex < lines.Count; lineIndex++)
    {
        string line = lines[lineIndex];
        string[] parts = line.Replace("\"", "").Split(new string[] { "," }, StringSplitOptions.None);
        for (int i = 0; i < parts.Length; i++)
        {
            parts[i] = parts[i].Trim();
        }

        // 通过表头映射获取样本名的索引，找不到则跳过该行
        if (!columnIndexMap.TryGetValue("SampleName", out int sampleNameIndex))
        {
            continue;
        }
        Sample sample = new Sample(parts[sampleNameIndex]);
        samples.Add(sample);

        // 用循环批量处理结果列，不用逐个硬编码AddResult
        List<string> resultColumns = new List<string> { "C1", "C2", "C3" };
        foreach (string colName in resultColumns)
        {
            if (columnIndexMap.TryGetValue(colName, out int colIndex) && colIndex < parts.Length)
            {
                sample.AddResult(DateTime.Now, colName, parts[colIndex]);
            }
        }
    }

    return samples;
}

关键优化点 #

• 表头映射字典：不管CSV列顺序怎么变，只要列名不变，就能通过字典找到正确的索引位置
• 循环批量处理列：把需要处理的结果列（C1、C2、C3）放到列表里，用循环遍历添加结果，减少重复代码
• 容错处理：加入TryGetValue判断，避免因列名缺失或索引越界导致程序崩溃

内容的提问来源于stack exchange，提问作者Shalabh Saxena