xSaherElmAiApi/Providers/Extractors/XPlainTextFileContentExtractor.cs

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

namespace xAiApi.Providers.Extractors
{
    /// <summary>
    /// Extracts content from plain text files (txt, md, csv, json, xml) ...
    /// </summary>    
    public class XPlainTextFileContentExtractor : IXPlainTextFileContentExtractor
    {
        /// <summary>
        /// Supported MIME Types ...
        /// </summary>
        private static readonly string[] SupportedMimeTypes =
        [
            "text/plain",
            "text/markdown",
            "text/csv",
            "text/html",
            "text/xml",
            "application/json",
            "application/xml"
        ];

        /// <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
        )
        {
            //
            using var reader = new StreamReader(fileStream);
            return await reader.ReadToEndAsync();
        }

        /// <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;
        }
    }
}