crawlberg

# This file is auto-generated by alef — DO NOT EDIT.
# alef:hash:75130b11765cbed0a1ea2b5bcffe59620c4045cee1c7cece391c5e3fa47b10e0
# To regenerate: alef generate
# To verify freshness: alef verify --exit-code
defmodule Crawlberg.ContentConfig do
  @moduledoc """
  Content extraction and conversion configuration.

  Controls how HTML is converted to the output format. Uses
  html-to-markdown-rs as the conversion engine for all formats
  (markdown, plain text, djot).
  """

  @typedoc "Content extraction and conversion configuration."
  @type t :: %__MODULE__{
  output_format: String.t() | nil,
  preprocessing_preset: String.t() | nil,
  remove_navigation: boolean(),
  remove_forms: boolean(),
  strip_tags: [String.t()],
  preserve_tags: [String.t()],
  exclude_selectors: [String.t()],
  skip_images: boolean(),
  max_depth: non_neg_integer() | nil,
  wrap: boolean(),
  wrap_width: non_neg_integer(),
  include_document_structure: boolean()
  }

  defstruct output_format: "markdown",
  preprocessing_preset: "standard",
  remove_navigation: true,
  remove_forms: true,
  strip_tags: [],
  preserve_tags: [],
  exclude_selectors: [],
  skip_images: false,
  max_depth: nil,
  wrap: false,
  wrap_width: 80,
  include_document_structure: true

  defimpl Jason.Encoder do
    @doc false
    def encode(value, opts) do
      value
      |> Map.from_struct()
    |> Enum.reject(fn {_k, v} -> v == nil end)
      |> Enum.into(%{})
      |> Jason.Encoder.encode(opts)
    end
  end
end