U-SQL UDO Zip Extrator

ZipExtrator.cs

using Microsoft.Analytics.Interfaces;
using System.Collections.Generic;
using System.IO;

namespace DocExtraction.Udo
{
    [SqlUserDefinedExtractor(AtomicFileProcessing = true)]
    public class ZipExtractor : IExtractor
    {
        private readonly bool _textMode;

        public ZipExtractor(bool textMode = false)
        {
            _textMode = textMode;
        }

        public override IEnumerable<IRow> Extract(IUnstructuredReader input, IUpdatableRow output)
        {
            var extractor = new ZipExtractorImpl(_textMode);
            using (var ms = new MemoryStream())
            {
                input.BaseStream.CopyTo(ms);
                foreach (var result in extractor.Extract(ms))
                {
                    output.Set(0, result.FileName);
                    output.Set(1, result.Content);
                    output.Set(2, result.Text);
                    yield return output.AsReadOnly();
                }
            }
        }
    }
}

ZipExtratorImpl.cs

using System;
using System.Collections.Generic;
using System.IO;
using System.IO.Compression;

namespace DocExtraction.Udo
{
    public class ZipExtractorImpl
    {
        private bool _textMode;

        public ZipExtractorImpl(bool textMode = false)
        {
            _textMode = textMode;
        }

        public IEnumerable<ZipExtractorResult> Extract(Stream stream)
        {
            using (var package = new ZipArchive(stream, ZipArchiveMode.Read))
            {
                foreach (var entry in package.Entries)
                {
                    if (entry.CompressedLength == 0) continue;
                    using (var entryStream = entry.Open())
                    {
                        yield return new ZipExtractorResult
                        {
                            FileName = entry.FullName,
                            Content = _textMode ? ReadText(entryStream) : ReadBase64(entryStream),
                            Text = _textMode
                        };
                    }
                }
            }
        }

        private string ReadText(Stream input)
        {
            using (var ms = new MemoryStream())
            {
                CopyStream(input, ms);
                ms.Position = 0;
                using (var sr = new StreamReader(ms))
                {
                    return sr.ReadToEnd();
                }
            }
        }

        private static string ReadBase64(Stream input)
        {
            using (var ms = new MemoryStream()) {
                CopyStream(input, ms);
                return Convert.ToBase64String(ms.ToArray());
            }
        }

        private static void CopyStream(Stream source, Stream target)
        {
            const int bufSize = 0x1000;
            byte[] buf = new byte[bufSize];
            int bytesRead = 0;
            while ((bytesRead = source.Read(buf, 0, bufSize)) > 0)
                target.Write(buf, 0, bytesRead);
        }
    }
}

ZipExtratorResult.cs

namespace DocExtraction.Udo
{
    public class ZipExtractorResult
    {
        public string FileName { get; set; }

        public string Content { get; set; }

        public bool Text { get; set; }
    }
}