xSaherElmAiApi/Providers/Extractors/XExcelFileContentExtractor.cs

using System;
using System.IO;
using System.Data;
using System.Linq;
using System.Text;
using ExcelDataReader;
using System.Threading;
using xAiModels.Models;
using System.Threading.Tasks;
using xAiApi.Interfaces.Extractors;

namespace xAiApi.Providers.Extractors
{
    public class XExcelFileContentExtractor : IXExcelFileContentExtractor
    {
        /// <summary>
        /// Supported MIME Types ...
        /// </summary>
        private static readonly string[] SupportedMimeTypes =
        [
            "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet", // .xlsx
            "application/vnd.ms-excel" // .xls        
        ];

        /// <summary>
        /// Check if this extractor supports the specified MIME type ...
        /// </summary>
        public bool CanExtract(string mimeType)
        {
            //
            return SupportedMimeTypes.Contains(
                mimeType?.ToLowerInvariant() ?? string.Empty
            );
        }

        /// <summary>
        /// Extract text content from file stream ...
        /// </summary>
        public async Task<string> ExtractAsync(
            Stream fileStream,
            string mimeType,
            CancellationToken cancellationToken = default
        )
        {
            //
            Encoding.RegisterProvider(CodePagesEncodingProvider.Instance);

            //
            using var memoryStream = new MemoryStream();
            await fileStream.CopyToAsync(memoryStream, cancellationToken);
            memoryStream.Position = 0;

            //
            var stringBuilder = new StringBuilder();

            //
            using (var reader = ExcelReaderFactory.CreateReader(memoryStream))
            {
                //
                var result = reader.AsDataSet();
                foreach (DataTable table in result.Tables)
                {
                    //
                    stringBuilder.AppendLine($"--- Sheet: {table.TableName} ---");

                    //
                    var headers = new string[table.Columns.Count];
                    for (int i = 0; i < table.Columns.Count; i++)
                    {
                        headers[i] = table.Columns[i].ColumnName;
                    }
                    stringBuilder.AppendLine(string.Join(" | ", headers));
                    stringBuilder.AppendLine(new string('-', 50));

                    //
                    foreach (DataRow row in table.Rows)
                    {
                        //
                        var rowValues = new string[row.ItemArray.Length];
                        for (int i = 0; i < row.ItemArray.Length; i++)
                        {
                            rowValues[i] = row.ItemArray[i]?.ToString()?.Trim() ?? string.Empty;
                        }
                        stringBuilder.AppendLine(string.Join(" | ", rowValues));
                    }
                    stringBuilder.AppendLine();
                }
            }

            //
            return stringBuilder.ToString();
        }

        /// <summary>
        /// Extract content from stream as Rich Result ...
        /// </summary>
        /// <param name="fileStream"></param>
        /// <param name="fileName"></param>
        /// <param name="mimeType"></param>
        /// <param name="cancellationToken"></param>
        /// <returns></returns>
        public async Task<XFileExtractionResult> ExtractRichAsync(
            Stream fileStream,
            string fileName,
            string mimeType,
            CancellationToken cancellationToken = default
        )
        {
            //
            var content = await ExtractAsync(
                mimeType: mimeType, 
                fileStream: fileStream, 
                cancellationToken: cancellationToken
            );

            //
            var result = new XFileExtractionResult
            {
                Text = content,
                FileName = fileName,
                MimeType = mimeType
            };

            //
            return result;
        }
    }
}