Class DecodeConfig

docling_parse/pdf_parser.py:245–267

How to compute page content (tuning, not selection). Fixed when the document is opened; the C++ page-decoder cache freezes these at first decode, so they cannot vary per page. Entity selection lives on ContentConfig instead.

class DecodeConfig(BaseModel):
    """How to compute page content (tuning, not selection).

    Fixed when the document is opened; the C++ page-decoder cache freezes these
    at first decode, so they cannot vary per page. Entity selection lives on
    ContentConfig instead.
    """

    model_config = ConfigDict(validate_assignment=True)

    do_sanitization: bool = True
    enforce_same_font: bool = True
    horizontal_cell_tolerance: float = 1.0
    word_space_width_factor_for_merge: float = 0.33
    line_space_width_factor_for_merge: float = 1.0
    line_space_width_factor_for_merge_with_space: float = 0.33
    max_num_lines: int = -1
    max_num_bitmaps: int = -1
    min_visible_clip_extent: float = 1e-3
    do_thread_safe: bool = True
    release_native_memory_every_n_pages: int = 0
    keep_glyphs: bool = False
    keep_qpdf_warnings: bool = False


def _compile_decode_config(