A fast, RFC 4180-conforming CSV reading library for .NET. Written in C#.
| License | CI (AppVeyor) | NuGet | MyGet (pre-release) |
|---|---|---|---|
 |
 |
 |
Documentation is currently being published as GitHub Pages.
Create a subclass of CsvReaderVisitorBase (or one of its own built-in subclasses) with your own logic for processing the individual elements in order. Then, you have some options.
public sealed class MyVisitor : CsvReaderVisitorBase
{
private readonly Decoder _utf8Decoder = Encoding.UTF8.GetDecoder();
private readonly char[] _buffer;
private int _bufferConsumed;
public MyVisitor(int maxFieldLength) =>
_buffer = new char[maxFieldLength];
public override void VisitPartialFieldContents(ReadOnlySpan<byte> chunk) =>
VisitFieldContents(chunk, flush: false);
public override void VisitEndOfField(ReadOnlySpan<byte> chunk) =>
VisitFieldContents(chunk, flush: true);
public override void VisitEndOfRecord() =>
Console.WriteLine("End of fields for this record.");
private void VisitFieldContents(ReadOnlySpan<byte> chunk, bool flush)
{
int charCount = _utf8Decoder.GetCharCount(chunk, flush);
if (charCount _bufferConsumed <= _buffer.Length)
{
_utf8Decoder.GetChars(chunk, new Span<char>(_buffer, _bufferConsumed, charCount), flush);
_bufferConsumed = charCount;
}
else
{
throw new InvalidDataException($"Field is longer than {_buffer.Length} characters.");
}
if (flush)
{
Console.Write("Field: ");
Console.WriteLine(_buffer, 0, _bufferConsumed);
_bufferConsumed = 0;
}
}
}All of the other methods of processing the data are built on top of this, so it gives you the most control:
- Create a new instance of your visitor.
- Create a new instance of
CsvTokenizer. - Call
CsvTokenizer.ProcessNextChunkfor each chunk of the file. - Call
CsvTokenizer.ProcessEndOfStreamafter the last chunk of the file.
Example:
public static void ProcessCsvFile(string csvFilePath)
{
var myVisitor = new MyVisitor(maxFieldLength: 1000);
var tokenizer = new CsvTokenizer();
using (var file = File.OpenRead(csvFilePath))
{
Console.WriteLine($"Started reading '{csvFilePath}'.");
Span<byte> fileReadBuffer = new byte[4096];
while (true)
{
int count = file.Read(fileReadBuffer);
if (count == 0)
{
break;
}
var chunk = fileReadBuffer.Slice(0, count);
tokenizer.ProcessNextChunk(chunk, myVisitor);
}
tokenizer.ProcessEndOfStream(myVisitor);
}
Console.WriteLine($"Finished reading '{csvFilePath}'.");
}- Create a new instance of your visitor.
- Use one of the
CsvSyncInputorCsvAsyncInputmethods to create an input object you can use to describe the data to your visitor.
Examples:
public static void ProcessCsvFile(string csvFilePath)
{
Console.WriteLine($"Started reading '{csvFilePath}'.");
CsvSyncInput.ForMemoryMappedFile(csvFilePath)
.Process(new MyVisitor(maxFieldLength: 1000));
Console.WriteLine($"Finished reading '{csvFilePath}'.");
}
public static void ProcessCsvStream(Stream csvStream)
{
Console.WriteLine($"Started reading CSV file.");
CsvSyncInput.ForStream(csvStream)
.Process(new MyVisitor(maxFieldLength: 1000));
Console.WriteLine($"Finished reading CSV file.");
}
public static async Task ProcessCsvStreamAsync(Stream csvStream)
{
Console.WriteLine($"Started reading CSV file.");
await CsvAsyncInput.ForStream(csvStream)
.ProcessAsync(new MyVisitor(maxFieldLength: 1000));
Console.WriteLine($"Finished reading CSV file.");
}