khh(ndZddlZddlmZddlmZddlmZddlmZdd lm Z dd l m Z Gd d eZ y) zA group of Line objects. N)Line)TextSpan) ImageSpan)ElementCollection) TextAlignment) constantsczeZdZdZedZdefdZedZde de fdZ d e fd Z d Z d e de fd Zde fdZy)LineszCollection of text lines.cvt|sy|jdtfd|jDS)z-Whether all contained lines have same parent.Frc3@K|]}|jywN)same_source_parent).0line first_lines O/var/www/teggl/fontify/venv/lib/python3.12/site-packages/pdf2docx/text/Lines.py z&Lines.unique_parent..sS44**:6Ss)bool _instancesall)selfrs @r unique_parentzLines.unique_parents1Dz%__Q' S4??SSSrawscL|D]}t|}|j| |S)z$Construct lines from raw dicts list.)rappend)rrrawrs rrestorez Lines.restores- C9D KK   rcbg}|jD]}|j|j|S)zGet all ImageSpan instances.)rextend image_spans)rspansrs rr#zLines.image_spans$s3OO +D LL)) * + rline_break_free_space_rationew_paragraph_free_space_ratioc|j}t|}|dk(r|Std|ddD}td|D|z }g}t }t t j} dx} } dx} } |D]}|djjj| } |djd|djdz }| r||z d |z krd } n| r ||z |z |k\rd } | r-|j||j|t }n@| r-|j|t }|j|n|j|| } dx} } |r|j||S) aSplit lines into separate paragraph by checking text. The parent text block consists of lines with similar line spacing, while lines in other paragraph might be counted when the paragraph spacing is relatively small. So, it's necessary to split those lines by checking the text contents. .. note:: Considered only normal reading direction, from left to right, from top to bottom. rc3fK|])}|djd|djdz +yw)rrNbboxrrows rrz1Lines.split_vertically_by_text..>s-C3B QA A.C/1Nc3fK|])}|djd|djdz +yw)rrNr*r,s rrz1Lines.split_vertically_by_text..?s->#A As1v{{1~->r.Fr)rrg?T)group_by_physical_rowslenmaxsumr tupler SENTENCE_END_PUNCtextstripendswithr+r"r)rr%r&rowsnumWHreslinespunc start_of_para end_of_para start_of_sen end_of_senr-ws rsplit_vertically_by_textzLines.split_vertically_by_text-s**,$i 6$; C$qr(C C >> > DY001&++ $)) z 0CR++-66t.os Iq!S& Is cT|jjxs|xr|vSr)encodeisalnum)rMpunc_ex_hyphens ris_end_of_english_wordz6Lines.adjust_last_word..is_end_of_english_wordps'88:%%'FA,E!~2E FrNr)rrrK ) joinstring punctuation enumeraterr$ isinstancercharsrMr9islower) rrGrRirend_span end_charsend_char start_span start_charsnext_start_charrQs @radjust_last_wordzLines.adjust_last_wordis  IF,>,> II G!"!56 "GAtzz"~Hh18 Ih }H1-33A6Jj(3X$**K)!nO& ##C(_->->-F-F-H &hjj16L_M^M^6_ c! 1 "rcd}|jD]}|jtj}|jj |s1|jj |jjkr|Sng}|jD]S}t|tr|j|%|j||j}|j|d}U|jj||S)zParse text format with style represented by rectangle shape. Args: shape (Shape): Potential style shape applied on blocks. Returns: bool: Whether a valid text style. FT)rget_expand_bboxr MAJOR_DISTr+ intersectsy1y0r$rXrrsplitis_horizontal_textr"reset)rshapeflagr expanded_bbox split_spansspanr$s rparse_text_formatzLines.parse_text_formatsOO *D 001E1EFM::((7::==499<</$ #K  dI. 0B0B40H!JJud.E.EFE&&u-D  JJ  [ )) *, rline_break_width_ratioc||j}|jrdnd\}}t|j||j|z }||||z }||z |k} |j } | D]} | D] } d| _ |j tjk(r.| d} t|j|| j|z }n-| d} t|j|| j|z }|j tjk(r|dz}| s ||z |kDsd| _| dD] } d| _ y)aWhether hard break each line. Args: bbox (Rect): bbox of parent layout, e.g. page or cell. line_break_width_ratio (float): user defined threshold, break line if smaller than this value. line_break_free_space_ratio (float): user defined threshold, break line if exceeds this value. Hard line break helps ensure paragraph structure, but pdf-based layout calculation may change in docx due to different rendering mechanism like font, spacing. For instance, when one paragraph row can't accommodate a Line, the hard break leads to an unnecessary empty row. Since we can't 100% ensure a same structure, it's better to focus on the content - add line break only when it's necessary to, e.g. short lines. rrr0rrr)rrN) parentrjabsr+r1 line_break alignmentr RIGHTCENTER)rr+rrr%blockidx0idx1 block_width layout_widthrxr:r?rend_line free_spaces rparse_line_breakzLines.parse_line_breaksH" $77VV d%**T*5::d+;;< DzDJ. !-1GG **, (E 2t 2-"5"55 8 D!1(--2E!EF  9 D!1(--2E!EF -"6"66 a Z 36QQ&'## ((H1Ddo1rline_separate_thresholdc |j jrdnd\ } fd}tt||j}t t d| j _ jsy fd} j }t|jD]\}}|j |z } | |kDr#||j ||z |_ ||jdk(ry|j|j|dzr|j|n j }y) zCalculate tab stops for parent block and whether add TAB stop before each line. Args: line_separate_threshold (float): Don't need a tab stop if the line gap less than this value. rtruchtt|jjz dS)Nr)roundrwr+)rr|r}s rz&Lines.parse_tab_stop..s)5TYYt_UZZ5E%E!FJrc(|tjk\Sr)r MINOR_DIST)poss rrz&Lines.parse_tab_stop..sC1E1E,ErNcXd}|jz}D]}||kr|S|dz }|S)Nrrr*)rr[tr|r} tab_stopss r tab_positionz*Lines.parse_tab_stop..tab_positionsJA 5::d# #C q5%HQ Hrr)r) rvrjsetmaprlistfiltersortrr+rWtab_stop in_same_row) rrr~funall_posrrefr[rdistancer|r}rs @@@rparse_tab_stopzLines.parse_tab_stops  $77VV dJc#t/0 EwOP # jj 1 bGAtyy,H// ,TYYt_ =l3>O O T__R((%%)%5%5dooac6J%K$))D/QVQ[Q[\`QaC brN)__name__ __module__ __qualname____doc__propertyrrr r#floatrFrrbrqrrrLrrr r s# TT4959in9x""d""J!H/2',/2,1/2d(bU(brr ) rrUrrimage.ImageSpanrcommon.Collectionr common.sharer commonr r rLrrrs2'1(|b |br