如何配置 CsvHelper 以跳过 MissingFieldFound 行

How to configure CsvHelper to skip MissingFieldFound rows

public interface ICsvProductReaderConfigurationFactory
{
    Configuration Build();
}

public class CsvProductReaderConfigurationFactory : ICsvProductReaderConfigurationFactory
{
    private readonly ClassMap<ProductDto> classMap;

    public CsvProductReaderConfigurationFactory(IProductDtoClassMapProvider classMapProvider)
    {
        classMap = classMapProvider.Get();
    }

    public Configuration Build()
    {
        var config = new Configuration
        {
            Delimiter = "\t",
            HasHeaderRecord = true,
            IgnoreQuotes = true,
            MissingFieldFound = (rows, fieldIndex, readingContext) =>
                Log.Warn($"Missing Field Found at line {readingContext.Row}\r\n" +
                         $"Field at index {fieldIndex} does not exist\r\n" +
                         $"Raw record: {readingContext.RawRecord}"),
            BadDataFound = context => 
                Log.Warn($"Bad data found at row {context.Row}\r\n" +
                         $"Raw data: {context.RawRecord}")
        };

        config.RegisterClassMap(classMap);
        return config;
    }
}


public interface ICvsProductReader
{
    IEnumerable<ProductDto> GetAll(string filePath);
}

public class CvsProductReader : ICvsProductReader
{
    private readonly ICsvProductReaderConfigurationFactory csvProductReaderConfigurationFactory;

    public CvsProductReader(ICsvProductReaderConfigurationFactory csvProductReaderConfigurationFactory)
    {
        this.csvProductReaderConfigurationFactory = csvProductReaderConfigurationFactory;
    }

    public IEnumerable<ProductDto> GetAll(string filePath)
    {
        var csvReaderConfiguration = csvProductReaderConfigurationFactory.Build();

        using (var streamReader = new StreamReader(filePath))
        using (var csvReader = new CsvReader(streamReader, csvReaderConfiguration))
        {
            return csvReader.GetRecords<ProductDto>().ToArray();
        }
    }
}

MissingFieldFound 属性 在找到缺失字段时调用,但不会影响结果。

我想知道是否可以将 CsvHelper 配置为跳过缺少字段的行。

你这样做没有错,这是一个显示完整示例的 mcve

var good = new List<Test>();
var bad = new List<string>();

using (var stream = new MemoryStream())
using (var writer = new StreamWriter(stream))
using (var reader = new StreamReader(stream))
using (var csv = new CsvReader(reader))
{
    writer.WriteLine("FirstName,LastName");
    writer.WriteLine("\"Jon\"hn\"\",\"Doe\"");
    writer.WriteLine("\"JaneDoe\"");
    writer.WriteLine("\"Jane\",\"Doe\"");
    writer.Flush();
    stream.Position = 0;

    var isRecordBad = false;

    csv.Configuration.BadDataFound = context =>
    {
        isRecordBad = true;
        bad.Add(context.RawRecord);
    };

    csv.Configuration.MissingFieldFound = (headerNames, index, context) =>
    {
        isRecordBad = true;
        bad.Add(context.RawRecord);
    };

    while (csv.Read())
    {
        var record = csv.GetRecord<Test>();
        if (!isRecordBad)
        {
            good.Add(record);
        }

        isRecordBad = false;
    }
}

good.Dump();
bad.Dump();

另一种跳过 MissingFieldFound 行的方法是使用 ShouldSkipRecord 并将 header 记录长度与行记录长度进行比较。

// Load header record if you haven't already (CsvDataReader loads it automatically).
csv.Read();
csv.ReadHeader();

// Then do this.
var expectedRecordLength = csv.Context.HeaderRecord.Length;
csv.Configuration.ShouldSkipRecord = rowRecord => rowRecord.Length != expectedRecordLength;

如果您不控制阅读代码(例如,将 CsvDataReaderSqlBulkCopy 结合使用时),这将特别有用。

使用我拥有的新版 csvhelper (24.0.1),下面的代码将用于设置 MissingFieldFound

Dim textReader As TextReader = File.OpenText(filename)

Dim config = New CsvHelper.Configuration.CsvConfiguration(System.Globalization.CultureInfo.InvariantCulture)

        config.Delimiter = ","
        config.MissingFieldFound = Nothing
        config.TrimOptions = True
        config.HeaderValidated = Nothing

Dim csv = New CsvReader(textReader, config)

您还可以使用属性配置缺失的字段

[可选]

Public 字符串字段 {get;设置;}

[忽略]

public int 归档 {get;设置;}