using System.Text;
using UglyToad.PdfPig;

namespace Api.Services.Rag;

public interface IPdfTextExtractor
{
    string ExtractText(Stream pdfStream);
}

public sealed class PdfTextExtractor : IPdfTextExtractor
{
    public string ExtractText(Stream pdfStream)
    {
        using var document = PdfDocument.Open(pdfStream);
        var builder = new StringBuilder();

        foreach (var page in document.GetPages())
        {
            builder.AppendLine(page.Text);
            builder.AppendLine();
        }

        return NormalizeWhitespace(builder.ToString());
    }

    private static string NormalizeWhitespace(string value)
    {
        if (string.IsNullOrWhiteSpace(value)) return string.Empty;
        var parts = value.Split((char[]?)null, StringSplitOptions.RemoveEmptyEntries);
        return string.Join(' ', parts).Trim();
    }
}