kh.dZddlZddlmZddlmZddlmZGddeZGd d eZ Gd d eZ Gd deZ y)a^Objects representing PDF stroke and filling extracted from Path. * Stroke: consider only the horizontal or vertical path segments * Fill : bbox of closed path filling area Hyperlink in ``PyMuPDF`` is represented as uri and its rectangular area (hot-area), while the applied text isn't extracted explicitly. To reuse the process that identifying applied text of text style shape (e.g. underline and highlight), hyperlink is also abstracted to be a ``Shape``. .. note:: The evident difference of hyperlink shape to text style shape is: the ``type`` of hyperlink shape is determined in advance, while text style shape needs to be identified by the position to associated text blocks. Above all, the semantic meaning of shape instance may be: * strike through line of text * under line of text * highlight area of text * table border * cell shading * hyperlink Data structure:: { 'type': int, 'bbox': (x0, y0, x1, y1), 'color': srgb_value, # for Stroke 'start': (x0, y0), 'end': (x1, y1), 'width': float, # for Hyperlink 'uri': str } .. note:: These coordinates are relative to real page CS since they're extracted from ``page.get_drawings()``, which is based on real page CS. So, needn't to multiply Element.ROTATION_MATRIX when initializing from source dict. N)Element)RectType) constantsceZdZdZddeffd ZedZejde fdZedZ de fdZ de fd Z ed Z fd Zd efd ZdZdZxZS)Shapez Shape object.rawc|xsi}|jdd|_t| |jddd|_|jdd|_|j |_y)Ncolorrbbox)rrrrtype)getr super update_bbox_parent_type default_type_potential_typeselfr __class__s P/var/www/teggl/fontify/venv/lib/python3.12/site-packages/pdf2docx/shape/Shape.py__init__zShape.__init__8saiRWWWa(  CGGFF34 WWVR( #00c|jSNrrs rr z Shape.typeGs ::%r rect_typec&|j|_yr)valuerrr s rr z Shape.typeJs 5>__ rc |jdk7S)zz%Shape.default_type..]s-q177-s)sumrrs rrzShape.default_typeZs-H---rctt|}|j|j|jd|S)N)r r )rstoreupdaterr rresrs rr1z Shape.store`s4gmo JJZZ   rblocksc|D]}|jj|jjkr1|jj|jjkDry|j|}||_||j k7syy)aQDetermine semantic type based on the position to text blocks. Note the results might be a combination of raw types, e.g. the semantic type of a stroke can be either text strike, underline or table border. Args: blocks (list): A list of ``Line`` instance, sorted in reading order in advance. N)r y1y0_semantic_typerr)rr5liner s rparse_semantic_typezShape.parse_semantic_typeiss 3Dyy||diill*Hyy||diill*E++D1I#,D $+++U 3rc|jS)z Check semantic type based on the position to a text line. Return all possibilities if can't be determined with this text line. Prerequisite: intersection exists between this shape and line. )r)rr:s rr9zShape._semantic_types    rcD|j|j||ddy)z'Plot rectangle shapes with ``PyMuPDF``.rT)r fillwidthoverlayN) draw_rectr )rpager s rplotz Shape.plots tyyEDQrr)__name__ __module__ __qualname____doc__dictrpropertyr setterrr%r'r)rr1listr;r9rC __classcell__rs@rrr6s 14 1%% [[DXDD   +h+686.. 33,!RrrceZdZdZddeffd ZedZedZedZ edZ edZ ed Z fd Z ed Zd Zfd ZdZxZS)Strokez Horizontal or vertical stroke of a path. The semantic meaning may be table border, or text style line like underline and strike-through. r c:|xsi}tj|jdd|_tj|jdd|_|jj |jj kDs-|jj |jj kDr#|j|jc|_|_t|!||jdd|_ t|)|jy)Nstart)rRendr?rR) fitzPointr_start_endxyrrr?r_to_rectrs rrzStroke.__init__siRjj*!=> JJswwuj9: ;;==499;; &$++--$))++*E%)YY "DK WWWc*  DMMO,rcXt|jd|jdz dkS)NMbP?absrVrWrs r horizontalzStroke.horizontals'!$T[[^DIIaL%@!A$!FFrcXt|jd|jdz dkS)Nrr]r^rs rverticalzStroke.verticals'"4;;q>$))A,#>?DDrc.|jjSr)rVrXrs rx0z Stroke.x0&rc.|jjSr)rWrXrs rx1z Stroke.x1$rc.|jjSr)rVrYrs rr8z Stroke.y0rerc.|jjSr)rWrYrs rr7z Stroke.y1rhrctj|}|jdk(rYtj|dd|_tj|dd|_t ||j|St |||j|jk\rh|j|jzdz }tj|j||_tj|j||_|S|j|jzdz }tj||j|_tj||j|_|S)a!Update stroke bbox (related to real page CS). * Update start/end points if ``rect.area==0``. * Ppdate bbox directly if ``rect.area!=0``. Args: rect (fitz.Rect, tuple): ``(x0, y0, x1, y1)`` like data. Returns: Stroke: self rRrrN@)rTRectget_arearUrVrWrrrZr?heightr8r7rdrg)rrectrYrXrs rrzStroke.update_bboxsyy ==?C **T!AY/DK 48,DI G   0$  G  %zzT[[(WWTWW_c)"jj!4 "jj!4  WWTWW_c)"jjDGG4 "jjDGG4  rctjjtjjztjjzS)zTDefault semantic type for a Stroke shape: table border, underline or strike-through.)rBORDERr" UNDERLINESTRIKErs rrzStroke.default_types4$$x'9'9'?'??(//BWBWWWrc|jd}|jj|s |jS|j}|j }||k7r |jS|r,|jj |jjfn+|jj|jjf\}}|r,|jj |jjfn+|jj|jjf\}}||dz k\r=||dzkr5tjjtjjzStjjS)a7Override. Check semantic type of a Stroke: table border v.s. text style line, e.g. underline and strike-through. It's potentially a text style line when: * the stroke and the text line has same orientation; and * the stroke never exceeds the text line along the main direction rlr\)get_expand_bboxr intersectsrr`is_horizontal_textrdrgr8r7rrtr"rsrr) rr:expanded_shapeh_shapeh_lineline_x0line_x1shape_x0shape_x1s rr9zStroke._semantic_types!--c2yy##N3$$ $//(( f $$ $rsR+Z $#SRGSRl}(U}(@?*5?*D11r