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
{
///
/// Extracts content from plain text files (txt, md, csv, json, xml) ...
///
public class XPlainTextFileContentExtractor : IXPlainTextFileContentExtractor
{
///
/// Supported MIME Types ...
///
private static readonly string[] SupportedMimeTypes =
[
"text/plain",
"text/markdown",
"text/csv",
"text/html",
"text/xml",
"application/json",
"application/xml"
];
///
/// Check if this extractor supports the specified MIME type ...
///
public bool CanExtract(string mimeType)
{
//
return SupportedMimeTypes.Contains(
mimeType?.ToLowerInvariant() ?? string.Empty
);
}
///
/// Extract text content from file stream ...
///
public async Task ExtractAsync(
Stream fileStream,
string mimeType,
CancellationToken cancellationToken = default
)
{
//
using var reader = new StreamReader(fileStream);
return await reader.ReadToEndAsync();
}
///
/// Extract content from stream as Rich Result ...
///
///
///
///
///
///
public async Task 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;
}
}
}