o j0@sldZddlZddlmZddlmZmZddlmZmZGdddZ Gd d d e eZ Gd d d e Z dS) z9A group of instances, e.g. Blocks, Lines, Spans, Shapes. N)Element)IText TextDirection)solve_rects_intersection graph_bfsc@seZdZdZddefddZddZdd Zd d Ze d d Z e ddZ ddZ defddZ ddefddZddZddZdS)BaseCollectionz1Base collection representing a list of instances.N instancescCs||_g|_||p gdS)z)Init collection from a list of instances.N)_parent _instancesextend)selfr parentr[/var/www/html/Deteccion_Ine/venv/lib/python3.10/site-packages/pdf2docx/common/Collection.py__init__szBaseCollection.__init__cCs4z|j|}W|Styd|d}t|w)NzCollection index z out of range.)r IndexError)r idxr msgrrr __getitem__s  zBaseCollection.__getitem__cCdd|jDS)Ncss|]}|VqdSNr.0instancerrr sz*BaseCollection.__iter__..r r rrr__iter__zBaseCollection.__iter__cCs t|jSr)lenr rrrr__len__ zBaseCollection.__len__cCs|jSr)r rrrrr!szBaseCollection.parentcCs2t}|jD]}||jO}qtdd|DS)zbbox of combined collection.cSsg|]}t|dqS)r)round)rxrrr +z'BaseCollection.bbox..)fitzRectr bbox)r rectrrrrr)%s  zBaseCollection.bboxcCs|sdS|j|dSr)r append)r rrrrr+.szBaseCollection.appendcCs |sdS|D]}||qdSr)r+)r r rrrrr 3szBaseCollection.extendcCsg|_||pg|S)zReset instances list. Args: instances (list, optional): reset to target instances. Defaults to None. Returns: BaseCollection: self )r r )r r rrrreset8s zBaseCollection.resetcCr)z Store attributes in json format.cSsg|]}|qSr)storerrrrr%Hsz(BaseCollection.store..rrrrrr-FszBaseCollection.storecOst)z)Construct Collection from a list of dict.)NotImplementedError)r argskwargsrrrrestoreKszBaseCollection.restore)NNr)__name__ __module__ __qualname____doc__listrrrr!propertyrr)r+r r,r-r1rrrrr s    rc@seZdZdZeddZddZdedefdd Zdd ede de fddZ dd ede de fddZ dde de fddZ ddZ ddZddZdS) CollectionzACollection of instance focusing on grouping and sorting elements.cCs2tdd|jD}t|dkrt|dStjS)z@Get text direction. All instances must have same text direction.css|]}|jVqdSrtext_directionrrrrrVsz,Collection.text_direction..rr)setr r r6rZMIX)r resrrrr:SszCollection.text_directioncstj}ddt|D}tjD]$\}}t|d|D]}||j|r6||||||qqt|}fdd|D}|S)aGroup instances according to user defined criterion. Args: fun (function): with 2 arguments representing 2 instances (Element) and return bool. Returns: list: a list of grouped ``Collection`` instances. Examples 1:: # group instances intersected with each other fun = lambda a,b: a.bbox & b.bbox Examples 2:: # group instances aligned horizontally fun = lambda a,b: a.horizontally_aligned_with(b) .. note:: It's equal to a GRAPH searching problem, build adjacent list, and then search graph to find all connected components. cSg|]}tqSrr;rirrrr%uz$Collection.group..rc$g|]}fdd|DqS)cg|]}j|qSrrr?rrrr%r&z/Collection.group... __class__rgrouprrrr%$)r r range enumerateaddr)r funnum index_groupsr@rjgroupsrrrrGZs zCollection.groupdxdyc stj}ddt|D}gd}}| | ||f}jD]'}ddt|j|D} ||| | df||d| | df|d7}q|jddd t|d||t|} fd d| D} | S) aiCollect connected instances into same group. Args: dx (float): x-tolerances to define connectivity dy (float): y-tolerances to define connectivity Returns: list: a list of grouped ``Collection`` instances. .. note:: * It's equal to a GRAPH traversing problem, which the critical point in building the adjacent list, especially a large number of vertex (paths). * Checking intersections between paths is actually a Rectangle-Intersection problem, studied already in many literatures. cSr=rr>)r_rrrr%rAz4Collection.group_by_connectivity..rcSsg|]\}}||qSrr)rabrrrr%srcSs|dS)Nr)itemrrrsz2Collection.group_by_connectivity..keycrB)crCrrr?rrrr%r&z?Collection.group_by_connectivity...rDrFrrrr%rH) r r rIzipr)r+sortrr) r rQrRrMrNZi_rect_xr@Zd_rectr*ZpointsrPrrrgroup_by_connectivitys    z Collection.group_by_connectivityTFfactorsortedr:cFfdd}||}|r!r|jrdnd|jfddd|S)z.Group elements into columns based on the bbox.c|j|dSNr`r:)Zvertically_align_withrTrUrerrrYrz-Collection.group_by_columns..rc |jSrr)rGrrrrYr"rZrGis_vertical_textr]r r`rar:rLrPrr`rr:rgroup_by_columns  zCollection.group_by_columnscrb)z+Group elements into rows based on the bbox.crcrd)Zhorizontally_align_withrfrerrrYrz*Collection.group_by_rows..rrcrhrrirjrkrrrYr"rZrlrnrror group_by_rowsrqzCollection.group_by_rowscs@dd}||}|r|r|jrdnd|jfddd|S)zGroup lines into physical rows.cSs ||Sr)Z in_same_rowrfrrrrYr"z3Collection.group_by_physical_rows..rrcrhrrirjrkrrrYr"rZrl)r rar:rLrPrrkrgroup_by_physical_rowss  z!Collection.group_by_physical_rowscCs2|jr|jjddd|S|jjddd|S)zSort collection instances in reading order (considering text direction), e.g. for normal reading direction: from top to bottom, from left to right. cS|jj|jj|jjfSr)r)y0x0x1errrrYr&z2Collection.sort_in_reading_order..rZcSrtr)r)rvy1rurxrrrrYr&)is_horizontal_textr r]rrrrsort_in_reading_order z Collection.sort_in_reading_ordercCs2|js|jjddd|S|jjddd|S)zSort collection instances in a physical with text direction considered, e.g. for normal reading direction: from left to right. cSrtr)r)rvrurwrxrrrrYr&z/Collection.sort_in_line_order..rZcSrtr)r)rzrvrurxrrrrYr&)rmr r]rrrrsort_in_line_orderr}zCollection.sort_in_line_ordercCs8g}|jdddD] }|||q ||dS)akSort instances in reading order, especially for instances in same row. Taking natural reading direction for example: reading order for rows, from left to right for instances in row. In the following example, A comes before B:: +-----------+ +---------+ | | | A | | B | +---------+ +-----------+ Steps: * Sort elements in reading order, i.e. from top to bottom, from left to right. * Group elements in row. * Sort elements in row: from left to right. T)rar:N)rsr~r r,)r r rowrrrsort_in_reading_order_pluss  z%Collection.sort_in_reading_order_plusN)r_TF)FF)r2r3r4r5r7r:rGfloatr^boolrprrrsr|r~rrrrrr8Ps )'  r8c@szeZdZdZdefddZdefddZdedefdd Zdefd d Z dd e fddZ ddZ dde jde fddZdS)ElementCollectionz$Collection of ``Element`` instances.rycCs|jdur |j|dSdS)zUpdate parent bbox.N)r Z union_bboxr ryrrr _update_bboxs zElementCollection._update_bboxcCs8|sdS|j||||jdur|j|_dSdS)zAppend an instance, update parent's bbox accordingly and set the parent of the added instance. Args: e (Element): instance to append. N)r r+rr rrrrrr+ s  zElementCollection.appendnthcCs,|sdS|j|||||j|_dS)zInsert a Element and update parent's bbox accordingly. Args: nth (int): the position to insert. e (Element): the instance to insert. N)r insertrr r)r rryrrrrs  zElementCollection.insertcCs |j|S)zDelete the ``nth`` instance. Args: nth (int): the position to remove. Returns: Collection: the removed instance. )r pop)r rrrrr%s zElementCollection.popFline_separate_thresholdcCs|s|jrdSt|dkrdSt|dkrdS|jrdnd\}}|jddD]&}tdt|D]}t||j|||dj|}||krMdSq1q(dS)z5Whether contained elements are in flow layout or not.FrT)rrV)rgrr9)rmr rpr{rsrIabsr))r rZ cell_layoutZidx0Zidx1rr@disrrris_flow_layout1s $z ElementCollection.is_flow_layoutcs"ttfdd|j}||S)zvFilter instances contained in target bbox. Args: bbox (fitz.Rect): target boundary box. cs |jSr)containsr)rxrirrrYMs z5ElementCollection.contained_in_bbox..)r6filterr rE)r r)r rrircontained_in_bboxFs z#ElementCollection.contained_in_bboxMbP?r) thresholdcCs|gg}}|jD]+}|j|@}|jr||qt||jd}||kr.||q||q||||fS)aHSplit instances into two groups: one intersects with ``bbox``, the other not. Args: bbox (fitz.Rect): target rect box. threshold (float): It's intersected when the overlap rate exceeds this threshold. Defaults to 0. Returns: tuple: two group in original class type. rV)r r)Zis_emptyr+r#Zget_arearE)r r)rZ intersectionsZno_intersectionsr intersectionr`rrrsplit_with_intersectionQs     z)ElementCollection.split_with_intersectionN)F)r)r2r3r4r5rrr+intrrrrrr'r(rrrrrrs   r) r5r'rZsharerr algorithmrrrr8rrrrrs D2