fil/packages/csharp/src/Kreuzberg/FileExtractionConfig.cs

// This file is auto-generated by alef — DO NOT EDIT.
// alef:hash:4e15143f4af1ae8bafbdb1506ef057da924484c66a19483966333558ad437e75
// To regenerate: alef generate
// To verify freshness: alef verify --exit-code
// Issues & docs: https://github.com/kreuzberg-dev/alef
#nullable enable

using System;
using System.Collections.Generic;
using System.Text.Json;
using System.Text.Json.Serialization;

namespace Kreuzberg;

/// <summary>
/// Per-file extraction configuration overrides for batch processing.
///
/// All fields are `Option&lt;T&gt;` — `None` means "use the batch-level default."
/// This type is used with `batch_extract_files` and
/// `batch_extract_bytes` to allow heterogeneous
/// extraction settings within a single batch.
///
/// # Excluded Fields
///
/// The following `ExtractionConfig` fields are batch-level only and
/// cannot be overridden per file:
/// - `max_concurrent_extractions` — controls batch parallelism
/// - `use_cache` — global caching policy
/// - `acceleration` — shared ONNX execution provider
/// - `security_limits` — global archive security policy
/// </summary>
public sealed record FileExtractionConfig
{
    /// <summary>
    /// Override quality post-processing for this file.
    /// </summary>
    [JsonPropertyName("enable_quality_processing")]
    public bool? EnableQualityProcessing { get; init; } = null;

    /// <summary>
    /// Override OCR configuration for this file (null in the Option = use batch default).
    /// </summary>
    [JsonPropertyName("ocr")]
    public OcrConfig? Ocr { get; init; } = null;

    /// <summary>
    /// Override force OCR for this file.
    /// </summary>
    [JsonPropertyName("force_ocr")]
    public bool? ForceOcr { get; init; } = null;

    /// <summary>
    /// Override force OCR pages for this file (1-indexed page numbers).
    /// </summary>
    [JsonPropertyName("force_ocr_pages")]
    public List<uint>? ForceOcrPages { get; init; } = null;

    /// <summary>
    /// Override disable OCR for this file.
    /// </summary>
    [JsonPropertyName("disable_ocr")]
    public bool? DisableOcr { get; init; } = null;

    /// <summary>
    /// Override chunking configuration for this file.
    /// </summary>
    [JsonPropertyName("chunking")]
    public ChunkingConfig? Chunking { get; init; } = null;

    /// <summary>
    /// Override content filtering configuration for this file.
    /// </summary>
    [JsonPropertyName("content_filter")]
    public ContentFilterConfig? ContentFilter { get; init; } = null;

    /// <summary>
    /// Override image extraction configuration for this file.
    /// </summary>
    [JsonPropertyName("images")]
    public ImageExtractionConfig? Images { get; init; } = null;

    /// <summary>
    /// Override PDF options for this file.
    /// </summary>
    [JsonPropertyName("pdf_options")]
    public PdfConfig? PdfOptions { get; init; } = null;

    /// <summary>
    /// Override token reduction for this file.
    /// </summary>
    [JsonPropertyName("token_reduction")]
    public TokenReductionOptions? TokenReduction { get; init; } = null;

    /// <summary>
    /// Override language detection for this file.
    /// </summary>
    [JsonPropertyName("language_detection")]
    public LanguageDetectionConfig? LanguageDetection { get; init; } = null;

    /// <summary>
    /// Override page extraction for this file.
    /// </summary>
    [JsonPropertyName("pages")]
    public PageConfig? Pages { get; init; } = null;

    /// <summary>
    /// Override keyword extraction for this file.
    /// </summary>
    [JsonPropertyName("keywords")]
    public KeywordConfig? Keywords { get; init; } = null;

    /// <summary>
    /// Override post-processor for this file.
    /// </summary>
    [JsonPropertyName("postprocessor")]
    public PostProcessorConfig? Postprocessor { get; init; } = null;

    /// <summary>
    /// Override HTML conversion options for this file.
    /// </summary>
    [JsonPropertyName("html_options")]
    public string? HtmlOptions { get; init; } = null;

    /// <summary>
    /// Override result format for this file.
    /// </summary>
    [JsonPropertyName("result_format")]
    public ResultFormat? ResultFormat { get; init; } = null;

    /// <summary>
    /// Override output content format for this file.
    /// </summary>
    [JsonPropertyName("output_format")]
    public OutputFormat? OutputFormat { get; init; } = null;

    /// <summary>
    /// Override document structure output for this file.
    /// </summary>
    [JsonPropertyName("include_document_structure")]
    public bool? IncludeDocumentStructure { get; init; } = null;

    /// <summary>
    /// Override layout detection for this file.
    /// </summary>
    [JsonPropertyName("layout")]
    public LayoutDetectionConfig? Layout { get; init; } = null;

    /// <summary>
    /// Override per-file extraction timeout in seconds.
    ///
    /// When set, the extraction for this file will be canceled after the
    /// specified duration. A timed-out file produces an error result without
    /// affecting other files in the batch.
    /// </summary>
    [JsonPropertyName("timeout_secs")]
    public ulong? TimeoutSecs { get; init; } = null;

    /// <summary>
    /// Override tree-sitter configuration for this file.
    /// </summary>
    [JsonPropertyName("tree_sitter")]
    public TreeSitterConfig? TreeSitter { get; init; } = null;

    /// <summary>
    /// Override structured extraction configuration for this file.
    ///
    /// When set, enables LLM-based structured extraction with a JSON schema
    /// for this specific file. The extracted content is sent to a VLM/LLM
    /// and the response is parsed according to the provided schema.
    /// </summary>
    [JsonPropertyName("structured_extraction")]
    public StructuredExtractionConfig? StructuredExtraction { get; init; } = null;


    /// <summary>
    /// Parse a <see cref="FileExtractionConfig"/> from a JSON string.
    /// </summary>
    /// <exception cref="KreuzbergException">When the JSON cannot be deserialised.</exception>
    public static FileExtractionConfig FromJson(string json)
    {
        try
        {
            return JsonSerializer.Deserialize<FileExtractionConfig>(json, JsonOptions)
                ?? throw new KreuzbergException($"Failed to parse FileExtractionConfig from JSON: deserializer returned null");
        }
        catch (KreuzbergException)
        {
            throw;
        }
        catch (Exception e)
        {
            throw new KreuzbergException($"Failed to parse FileExtractionConfig from JSON: {e.Message}", e);
        }
    }

    private static readonly JsonSerializerOptions JsonOptions = new()
    {
        DefaultIgnoreCondition = JsonIgnoreCondition.WhenWritingDefault,
        Converters = { new JsonStringEnumConverter(JsonNamingPolicy.SnakeCaseLower) },
    };

    /// <summary>Options for serializing config/input objects to FFI. Strips nulls
    /// (nullable C# fields default to null and would override required Rust fields with
    /// non-deserialisable nulls) but preserves explicit false/0 so caller intent is kept.</summary>
    private static readonly JsonSerializerOptions JsonSerializationOptions = new()
    {
        DefaultIgnoreCondition = JsonIgnoreCondition.WhenWritingNull,
        Converters = { new JsonStringEnumConverter(JsonNamingPolicy.SnakeCaseLower) },
    };
}