A deterministic PDF extraction engine for .NET.

using Microsoft.Extensions.DependencyInjection;
using Docuoria.Configuration;
using Docuoria.Contracts;
using Docuoria.MatchRules;
using Docuoria.Models;
using Docuoria.Output.Csv;
using Docuoria.Pipeline.Extraction;
using Docuoria.Pipeline.Publish;
using Docuoria.Registration;
using Docuoria.Results;

var services = new ServiceCollection();
services.AddDocuoriaEngine(b => b.AddBuiltInMatchRules().AddCsvOutputGenerator());
var engine = services.BuildServiceProvider().GetRequiredService<IDocuoriaEngine>();

var schema = new RecordDefinition("Invoice", new FieldDefinition[]
{
    new PrimitiveFieldDefinition("vendor", FieldType.String, isRequired: true),
});
var template = TemplateBuilder.Create("quickstart", new DataModel(schema))
    .WithMatchRule<FileNameMatchRule, FileNameMatchRuleConfiguration>(
        new FileNameMatchRuleConfiguration { Pattern = "**/*.pdf", Threshold = 1m })
    .ExtractWith<ExtractionStep, ExtractionStepConfiguration>(new ExtractionStepConfiguration(new IFieldMapping[]
    {
        new FieldMapping("vendor", FieldType.String, MetadataFieldExtractionSource.Standard(MetadataField.Title)),
    }))
    .PublishWith<PublishStep, PublishStepConfiguration>(new PublishStepConfiguration())
    .Build();

await using var pdf = File.OpenRead("invoice.pdf");
var result = await engine.ExecuteTemplateAsync<CsvOutputGenerator, CsvGeneratorOptions>(pdf, template, new CsvGeneratorOptions());
if (result is SucceededResult ok)
    Console.WriteLine(System.Text.Encoding.UTF8.GetString(ok.Output.Payload.Span));

switch (result)
{
    case SucceededResult success:   // success.Output.Payload, success.Output.ContentType
    case FailedResult failure:      // failure.StepIdentifier, failure.ErrorMessage
    case RejectedResult rejection:  // rejection.Reason, rejection.Detail
}