39 lines
1.2 KiB
Elixir
39 lines
1.2 KiB
Elixir
|
# 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
|
||
|
|
defmodule Kreuzberg.HierarchyConfig do
|
||
|
|
@moduledoc """
|
||
|
|
Hierarchy extraction configuration for PDF text structure analysis.
|
||
|
|
|
||
|
|
Enables extraction of document hierarchy levels (H1-H6) based on font size
|
||
|
|
clustering and semantic analysis. When enabled, hierarchical blocks are
|
||
|
|
included in page content.
|
||
|
|
"""
|
||
|
|
|
||
|
|
@typedoc "Hierarchy extraction configuration for PDF text structure analysis."
|
||
|
|
@type t :: %__MODULE__{
|
||
|
|
enabled: boolean(),
|
||
|
|
k_clusters: non_neg_integer(),
|
||
|
|
include_bbox: boolean(),
|
||
|
|
ocr_coverage_threshold: float() | nil
|
||
|
|
}
|
||
|
|
|
||
|
|
defstruct enabled: true,
|
||
|
|
k_clusters: 3,
|
||
|
|
include_bbox: true,
|
||
|
|
ocr_coverage_threshold: nil
|
||
|
|
|
||
|
|
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
|