kh8VdZddlZddlmZddlmZddlmZddlmZGd d eZ y) al Objects representing PDF path (stroke and filling) extracted by ``page.get_drawings()``. This method is new since ``PyMuPDF`` 1.18.0, with both pdf raw path and annotations like Line, Square and Highlight considered. * https://pymupdf.readthedocs.io/en/latest/page.html#Page.get_drawings * https://pymupdf.readthedocs.io/en/latest/faq.html#extracting-drawings N)ImagesExtractor) lazyproperty) Collection)Pathc jeZdZdZdefdZedZedZ dZ dZ dde d e d e d e d e f d Z y)PathszA collection of paths.rawscdd|jj|jjf}|D]:}t|}|jj |s*|j |<|S)z>Initialize paths from raw data get by ``page.get_drawings()``.r)parentwidthheightrbbox intersectsappend)selfr rectrawpaths P/var/www/teggl/fontify/venv/lib/python3.12/site-packages/pdf2docx/shape/Paths.pyrestorez Paths.restoresc1dkk''););< C9D99''-x KK     cntj}|jD]}||jz}|S)N)fitzRect _instancesr)rrinstances rrz Paths.bbox"s.yy{>H)>> rcB|jD]}|jryy)z@It is iso-oriented when all contained segments are iso-oriented.FT)ris_iso_oriented)rrs rr zPaths.is_iso_oriented)s% :H++E :rc|jsy|j}|jD]}|j||jy)zePlot paths for debug purpose. Args: page (fitz.Page): ``PyMuPDF`` page. N)r new_shapeplotcommit)rpagecanvasrs rr#z Paths.plot1s< !OO6DTYYv%66 rcg}|jD].}|js|j|j0|S)zConvert contained paths to ISO strokes or rectangular fills. Returns: list: A list of ``Shape`` raw dicts. )rr extend to_shapes)rshapesrs rr)zPaths.to_shapes>sA OO ,D'' MM$..* + , rmin_svg_gap_dxmin_svg_gap_dymin_wmin_hclip_image_res_ratioc Pg}|jr#|j|j|gfSg}t|jj }|j ||||} dtdtfd} | D cgc] } t} } |jD]P} t| | D]?\\}}}| jj|s%| | |s|j| PRt| | D]\\}}}|jr[|j|j|D]6}|j|jt!j"||8p|j|jt!j"||||fScc} w)aConvert paths to iso-oriented shapes or images. The semantic type of path is either table/text style or vector graphic. This method is to: * detect svg regions -> exist at least one non-iso-oriented path * convert svg to bitmap by clipping page * convert the rest paths to iso-oriented shapes for further table/text style parsing Args: min_svg_gap_dx (float): Merge svg if the horizontal gap is less than this value. min_svg_gap_dy (float): Merge svg if the vertical gap is less than this value. min_w (float): Ignore contours if the bbox width is less than this value. min_h (float): Ignore contours if the bbox height is less than this value. clip_image_res_ratio (float, optional): Resolution ratio of clipped bitmap. Defaults to 3.0. Returns: tuple: (list of shape raw dict, list of image raw dict). rcontourscr|D]2}tj|j|js2yy)NTF)rrcontainsr)rr1rs rcontained_in_inner_contoursz?Paths.to_shapes_and_images..contained_in_inner_contoursns2  D99T?++DII6t Dr)r r(r)rr page_enginedetect_svg_contoursrlistr rziprrrclip_page_to_dictrr)rr+r,r-r.r/ iso_shapesimagesiegroupsr4_ group_pathsrr inner_bboxespathssvg_bboxs rto_shapes_and_imageszPaths.to_shapes_and_imagesLs&      dnn. /r> ! T[[44 5''uU T D  )//1uw/ /OO D/26;/G +$|e99''-6t\JELLY]L^  ,/v{+C [ ' T<%$$!!%//"34 ,cHMM""6"6tyy7JL`"abc  b22499T?DXYZ [6!!'0s;F#N)rDrrg@)__name__ __module__ __qualname____doc__r7rrrpropertyr r#r)floatrCrrr r sx  4    RTY\;"%;"5;"&+;"5:;"SX;"rr ) rHrimage.ImagesExtractorr common.sharercommon.Collectionrrr rKrrrOs) 3'+s"Js"r