kh0~dZddlZddlmZddlmZmZddlmZmZGddZ Gd d e eZ Gd d e Z y) z9A group of instances, e.g. Blocks, Lines, Spans, Shapes. N)Element)IText TextDirection)solve_rects_intersection graph_bfsc|eZdZdZddefdZdZdZdZe dZ e d Z d Z defd Z ddefd Zd ZdZy)BaseCollectionz1Base collection representing a list of instances.N instancescJ||_g|_|j|xsgy)z)Init collection from a list of instances.N)_parent _instancesextend)selfr parents V/var/www/teggl/fontify/venv/lib/python3.12/site-packages/pdf2docx/common/Collection.py__init__zBaseCollection.__init__s   IO$cb |j|}|S#t$rd|d}t|wxYw)NzCollection index z out of range.)r IndexError)ridxr msgs r __getitem__zBaseCollection.__getitem__sF ,I    "%cU.9CS/ ! "s.c(d|jDS)Nc3 K|]}|ywN.0instances r z*BaseCollection.__iter__..sIXIs )rrs r__iter__zBaseCollection.__iter__sIIIrc,t|jSr)lenrr"s r__len__zBaseCollection.__len__sc$//22rc|jSr)r r"s rrzBaseCollection.parent!s !\\)rc tj}|jD]}||jz}tj|Dcgc]}t |dc}Scc}w)zbbox of combined collection.r)fitzRectrbboxround)rrectr xs rr+zBaseCollection.bbox%sSyy{ "H HMM !D "yyd3%!*3443sA"c@|sy|jj|yr)rappendrr s rr0zBaseCollection.append.s x(rc:|sy|D]}|j|yr)r0)rr r s rrzBaseCollection.extend3s&!8H4;;x#88rc>g|_|j|xsg|S)zReset instances list. Args: instances (list, optional): reset to target instances. Defaults to None. Returns: BaseCollection: self )rr)rr s rresetzBaseCollection.reset8s  IO$ rc\|jDcgc]}|jc}Scc}w)z Store attributes in json format.)rstorer1s rr6zBaseCollection.storeFs!26//Ch!CCCs)ct)z)Construct Collection from a list of dict.)NotImplementedError)rargskwargss rrestorezBaseCollection.restoreKs!!r)NNr)__name__ __module__ __qualname____doc__listrrr#r&propertyrr+r0rr4r6r;rrrr r si;%% J2 ))55) 9t9 d D "rr ceZdZdZedZdZdedefdZddede d e fd Z ddede d e fd Z dde d e fd Z d Z dZdZy) CollectionzACollection of instance focusing on grouping and sorting elements.ctd|jD}t|dk(rt|dStj S)z@Get text direction. All instances must have same text direction.c34K|]}|jywrtext_directionrs rr!z,Collection.text_direction..VsJh())Jsrr)setrr%r@rMIX)rress rrGzCollection.text_directionSs;J$//JJ"3x{tCy|A 0A0AArc t|j}t|Dcgc] }t}}t |jD]X\}}t|dz|D]A}|||j|s||j |||j |CZt |}|Dcgc].}|j|Dcgc]}|j|c}0}}}|Scc}wcc}wcc}}w)aGroup instances according to user defined criterion. Args: fun (function): with 2 arguments representing 2 instances (Element) and return bool. Returns: list: a list of grouped ``Collection`` instances. Examples 1:: # group instances intersected with each other fun = lambda a,b: a.bbox & b.bbox Examples 2:: # group instances aligned horizontally fun = lambda a,b: a.horizontally_aligned_with(b) .. note:: It's equal to a GRAPH searching problem, build adjacent list, and then search graph to find all connected components. r)r%rrangerH enumerateaddr __class__) rfunnumi index_groupsr jgroupsgroups rrVzCollection.groupZs4$//"',Sz2!2 2$T__5 +KAx1Q3_ +x!34 O''* O''* + +<(SYZ%$..e!D$//!"4!DEZZ 3"EZsC.6C8 C3 C83C8dxdyc jt|j}t|Dcgc] }t}}gd}}| | ||f}|jD]c} t | j |D cgc] \} } | | z } } } |j || | df|j |dz| | df|dz }e|jdt|d|z|t|} | Dcgc].}|j|Dcgc]}|j|c}0} }}| Scc}wcc} } wcc}wcc}}w)aiCollect connected instances into same group. Args: dx (float): x-tolerances to define connectivity dy (float): y-tolerances to define connectivity Returns: list: a list of grouped ``Collection`` instances. .. note:: * It's equal to a GRAPH traversing problem, which the critical point in building the adjacent list, especially a large number of vertex (paths). * Checking intersections between paths is actually a Rectangle-Intersection problem, studied already in many literatures. rrc |dS)Nr)items rz2Collection.group_by_connectivity..s tBxrkey) r%rrLrHzipr+r0sortrrrO)rrWrXrQ_rSi_rect_xrRd_rectr-abpointsrUrVs rgroup_by_connectivityz Collection.group_by_connectivitys1&$//"',Sz2!2 2!!#sB#OO D%(F%;.s!11!FSa1brrc"|jSrr+rVrs rr^z-Collection.group_by_columns..%**S/rr_rVis_vertical_textrbrrjrkrGrPrUrs ` ` @rgroup_by_columnszCollection.group_by_columnssBcC %$*?*?!QC KK9K : rcfd}|j|}|r'r|jrdnd|jfd|S)z+Group elements into rows based on the bbox.c,|j|Srn)horizontally_align_withrps rr^z*Collection.group_by_rows..s!33AfUc3drrrc"|jSrrsrts rr^z*Collection.group_by_rows..rurr_rvrxs ` ` @r group_by_rowszCollection.group_by_rowssBeC %$*?*?!QC KK9K : rcd}|j|}|r'|r|jrdnd|jfd|S)zGroup lines into physical rows.c$|j|Sr) in_same_row)rfrgs rr^z3Collection.group_by_physical_rows..s!--*rrrc"|jSrrsrts rr^z3Collection.group_by_physical_rows..rurr_rv)rrkrGrPrUrs @rgroup_by_physical_rowsz!Collection.group_by_physical_rowss?*C %$*?*?!QC KK9K : rc|jr|jjd|S|jjd|S)zSort collection instances in reading order (considering text direction), e.g. for normal reading direction: from top to bottom, from left to right. c|jj|jj|jjfSr)r+y0x0x1es rr^z2Collection.sort_in_reading_order..% 16699affii/Prr_c|jj|jj|jjfSr)r+ry1rrs rr^z2Collection.sort_in_reading_order..rr)is_horizontal_textrrbr"s rsort_in_reading_orderz Collection.sort_in_reading_ordersG  " " OO %P Q  OO %P Q rc|js|jjd|S|jjd|S)zSort collection instances in a physical with text direction considered, e.g. for normal reading direction: from left to right. c|jj|jj|jjfSr)r+rrrrs rr^z/Collection.sort_in_line_order..rrr_c|jj|jj|jjfSr)r+rrrrs rr^z/Collection.sort_in_line_order..rr)rwrrbr"s rsort_in_line_orderzCollection.sort_in_line_ordersG$$ OO %P Q  OO %P Q rcg}|jddD]#}|j|j|%|j|y)akSort instances in reading order, especially for instances in same row. Taking natural reading direction for example: reading order for rows, from left to right for instances in row. In the following example, A comes before B:: +-----------+ +---------+ | | | A | | B | +---------+ +-----------+ Steps: * Sort elements in reading order, i.e. from top to bottom, from left to right. * Group elements in row. * Sort elements in row: from left to right. T)rkrGN)rrrr4)rr rows rsort_in_reading_order_plusz%Collection.sort_in_reading_order_plussP  ..d4.P "C  " " $   S ! " 9rN)gTF)FF)r<r=r>r?rArGrVfloatriboolryr~rrrrrrrrCrCPsK BB &R$u$$N e  RV  5 T t  D t rrCc~eZdZdZdefdZdefdZdedefdZdefdZ dde fd Z d Z dd e jd e fd Zy)ElementCollectionz$Collection of ``Element`` instances.rcT|j|jj|yy)zUpdate parent bbox.N)r union_bboxrrs r _update_bboxzElementCollection._update_bboxs#||# LL # #A &$rc|sy|jj||j||j|j|_yy)zAppend an instance, update parent's bbox accordingly and set the parent of the added instance. Args: e (Element): instance to append. N)rr0rr rrs rr0zElementCollection.append sB & q! !||# QX#rnthc|sy|jj|||j||j|_y)zInsert a Element and update parent's bbox accordingly. Args: nth (int): the position to insert. e (Element): the instance to insert. N)rinsertrr r)rrrs rrzElementCollection.inserts6& sA& !<<rc8|jj|S)zDelete the ``nth`` instance. Args: nth (int): the position to remove. Returns: Collection: the removed instance. )rpop)rrs rrzElementCollection.pop%s""3''rline_separate_thresholdct|s |jryt|dkryt|jdkDry|jrdnd\}}|j dD]U}t dt|D];}t ||j|||dz j|z }||k\s:yWy)z5Whether contained elements are in flow layout or not.FrT)rrZ)rqrrF)rwr%ryrrrLabsr+)rr cell_layoutidx0idx1rrRdiss ris_flow_layoutz ElementCollection.is_flow_layout1st44 t9a< t$$& ' )% $66VF d..d.C @C1c#h' @#a&++d+C!HMM$,??@11% @ @ rcjttfd|j}|j|S)zvFilter instances contained in target bbox. Args: bbox (fitz.Rect): target boundary box. c:j|jSr)containsr+)rr+s rr^z5ElementCollection.contained_in_bbox..MsdmmAFF+r)r@filterrrO)rr+r s ` rcontained_in_bboxz#ElementCollection.contained_in_bboxFs.  +T__>? ~~i((rr+ thresholdcgg}}|jD]}|j|z}|jr|j|0t |j |jj z d}||k\r|j|||j||j ||j |fS)aHSplit instances into two groups: one intersects with ``bbox``, the other not. Args: bbox (fitz.Rect): target rect box. threshold (float): It's intersected when the overlap rate exceeds this threshold. Defaults to 0. Returns: tuple: two group in original class type. rZ)rr+is_emptyr0r,get_arearO)rr+r intersectionsno_intersectionsr intersectionrjs rsplit_with_intersectionz)ElementCollection.split_with_intersectionQs+-b'  6H#==4/L$$ ''1|446x}}7M7M7OOQRSY&!((2$++H5 6~~m,dnn=M.NNNrN)F)gMbP?)r<r=r>r?rrr0intrrrrrr)r*rrrrrrsg.'W' =w =       (c (U*)O499OOrr) r?r)rsharerr algorithmrrr rCrrrrrsF )<A"A"HmmbfO fOr