o e+H@sdZddlmZmZddlmZddlmZddlmZddl m Z m Z m Z dd l mZdd l mZm Z dd lmZdd lmZGd ddeZdS)aIText block objects based on PDF raw dict extracted with ``PyMuPDF``. Data structure based on this `link `_:: { # raw dict # -------------------------------- 'type': 0, 'bbox': (x0,y0,x1,y1), 'lines': [ lines ] # introduced dict # -------------------------------- 'before_space': bs, 'after_space': as, 'line_space': ls, 'alignment': 0, 'left_space': 10.0, 'right_space': 0.0, 'tab_stops': [15.4, 35.0] } )PtInches)WD_ALIGN_PARAGRAPH)Lines) ImageSpan)RectType TextAlignment lower_round)Block)rgb_component_from_namer ) constants)docxc seZdZdZd+deffdd ZeddZedd Zed d Z ed d Z eddZ eddZ fddZ ddZfddZddZdedededededef d d!Zd"d#Zd$d%Zd&d'Zd(ededededef d)d*ZZS), TextBlockz Text block.NrawcsL|pi}d|vr |dt|t|d|dg|_|dS)Nbbox)parentlines)popsuper__init__rrestoregetrZset_text_block)selfr __class__GD:\Projects\ConvertPro\env\Lib\site-packages\pdf2docx/text/TextBlock.pyr)s   zTextBlock.__init__cCdd|jD}d|S)zJText content in block. Note image is counted as a placeholder ````.cSg|]}|jqSr)text.0linerrr :z"TextBlock.text..rjoinrZ lines_textrrrr!7 zTextBlock.textcCr)z5Raw text content in block without considering images.cSr r)raw_textr"rrrr%@r&z&TextBlock.raw_text..r'r(r*rrrr,=r+zTextBlock.raw_textcCtdd|jDS)zZIf this block contains only white space or not. If True, this block is safe to be removed.cs|]}|jVqdSN)white_space_onlyr"rrr Fz-TextBlock.white_space_only..)allrrrrrr0CszTextBlock.white_space_onlycCs|jjS)zsAll lines contained in text block must have same text direction. Otherwise, set normal direction. )rtext_directionr4rrrr5HszTextBlock.text_directioncsn|jrdnd|j}t|}|dkrdS|jd|j}fdd}tt||}|||dS)z4Average distance between adjacent two physical rows.rrNrctfdd|DS)Nc3s,|]}t|jd|jVqdS)rN)absrr"idxrrr1[s*z>TextBlock.average_row_gap....maxrowr8rr[z+TextBlock.average_row_gap..)is_horizontal_textrgroup_by_physical_rowslenrsummap)rrowsnum block_heightZf_max_row_heightZsum_row_heightrr8raverage_row_gapOs   zTextBlock.average_row_gapcCst|jS)zCount of physical rows.)rBrrAr4rrr row_count`szTextBlock.row_countcs"t}|d|ji|S)Nr)rstoreupdater)rresrrrrJfs  zTextBlock.storecCs:t|tttfr|D]}|j|q dS|j|dS)zAdd line or lines to TextBlock.N) isinstancerlisttuplerappend)rZ line_or_linesr$rrraddns z TextBlock.addcsbtd}tj||dd|jD]}td}|j||d|jD] }td}|j||dq qdS) ztPlot block/line/span area for debug purpose. Args: page (fitz.Page): pdf page. bluez [3.0 3.0] 0)strokedashesred)rSr')colorN)r rplotrspans)rpagerRr$rUspancrrrrWws  zTextBlock.plotcCsFd}|D]}|tjs|jrq|j|jsq|j|r d}q|S)zParse text format with style represented by rectangles. Args: shapes (Shapes): Shapes representing potential styles applied on blocks. FT)Z equal_to_typer Z HYPERLINKZ is_determinedrZ intersectsrparse_text_format)rZshapesflagshaperrrr\s zTextBlock.parse_text_formatline_separate_thresholdline_break_width_ratioline_break_free_space_ratiolines_left_aligned_thresholdlines_right_aligned_thresholdlines_center_aligned_thresholdc Cs|jrdnd\}} } |||| | f|||||_|jtjkr(tj|_|j||j} | dkr9|jtjkr9d|_ n| dkrG|jtj krGd|_ n| dkrW|jtj krWd|_ d|_ |j |||dS)a Set horizontal spacing based on lines layout and page bbox. * The general spacing is determined by paragraph alignment and indentation. * The detailed spacing of block lines is determined by tab stops. Multiple alignment modes may exist in block (due to improper organized lines from ``PyMuPDF``), e.g. some lines align left, and others right. In this case, **LEFT** alignment is set, and use ``TAB`` to position each line. )rrg?)rgrrN)r@_parse_alignment alignmentr NONELEFTrZparse_tab_stoprI right_spaceRIGHT left_spaceCENTERZparse_line_break) rrr_r`rarbrcrdidx0idx1frIrrrparse_horizontal_spacings.  z"TextBlock.parse_horizontal_spacingcs|jD]}tdd|jDrtj|_dSq|jrdnd}|j|d|j|}|j}ddfd dt fd d|D}||}t |dkrTt |tj}||_dS) alCalculate relative line spacing, e.g. `spacing = 1.02`. Relative line spacing is based on standard single line height, which is font-related. .. note:: The line spacing could be updated automatically when changing the font size, while the layout might be broken in exact spacing mode, e.g. overlapping of lines. css|] }t|tr|VqdSr/)rMrr#rZrrrr1sz8TextBlock.parse_relative_line_spacing..NrrrcSr-)Ncsr.r/) line_heightrrrrrr1r2JTextBlock.parse_relative_line_spacing....)r;rX)r$rrrr>sz7TextBlock.parse_relative_line_spacing..cr6)Nc3|]}|VqdSr/rr"fun_max_line_heightrrr1rtr:r<rvrrr>r?c3rur/r)r#r=)fun_max_row_heightrrr1rx) rrNrXrZDEFULT_LINE_SPACING line_spacer@rrArCrBr;)rr$r9rGrEZstandard_heightrzr)rwryrparse_relative_line_spacings    z%TextBlock.parse_relative_line_spacingcCs|jrdnd}|jdj}||d||}|j|d|j|}|j}|dkr3|||d}n|}||_|j||7_|jdkrU|j|j|7_d|_dSdS)a0Calculate exact line spacing, e.g. `spacing = Pt(12)`. The layout of pdf text block: line-space-line-space-line, excepting space before first line, i.e. space-line-space-line, when creating paragraph in docx. So, an average line height is ``space+line``. Then, the height of first line can be adjusted by updating paragraph before-spacing. .. note:: Compared with the relative spacing mode, it has a more precise layout, but less flexible editing ability, especially changing the font size. rrrN)r@rrrIrz before_space)rr9rZfirst_line_heightrGcountrzrrrparse_exact_line_spacings   z"TextBlock.parse_exact_line_spacingc Cst|}tt|jdd}tt|jdd}t||_t||_|j dkr0tt|j d|_ nt|j d|_ |j }|j dkrD||j 8}t||_t|j|_t|j |_|jtjkrtj|_|jD] }|jt|j |qbt|jtjd}t||_nB|jtjkrtj|_t|tjd}t||_n*|jtjkrtj|_t|tjd}t||_t|jtjd}t||_ntj|_|jD]}| |q|S)aCreate paragraph for a text block. Refer to ``python-docx`` doc for details on text format: * https://python-docx.readthedocs.io/en/latest/user/text.html * https://python-docx.readthedocs.io/en/latest/api/enum/WdAlignParagraph.html#wdparagraphalignment Args: p (Paragraph): ``python-docx`` paragraph instance. .. note:: The left position of paragraph is set by paragraph indent, rather than ``TAB`` stop. rr|rr)!rZreset_paragraph_formatr;roundr}Z after_spacerZ space_beforeZ space_afterZline_space_typerzZ line_spacingrlfirst_line_spaceZ left_indentrjZ right_indentZfirst_line_indentrgr rirZ tab_stopsZ add_tab_stopr rZITPrrkrmJUSTIFYr make_docx) rppfZbefore_spacingZ after_spacingrlposdr$rrrr sB                 zTextBlock.make_docxtext_direction_paramcsL|\t|j|dt||jd}t|ddtdt|d}t|||_||_|j}|D]$tdkrTqKfddt dtD} t | rot j SqKfdd} t|dkr| Sfdd|D} fd d|D} d dt | | D} t|d kr| dd | d d} } tt| t| |k}tt| t| |k}tt| t| k}|r|rt|d krt jn| }n|rt j}n|rt j}n|rt|d krt jnt j}nt j }|t jks|t jkr$|d d j|dd j|_|S)aDetect text alignment mode based on layout of internal lines. It can't decide when only one line, in such case, the alignment mode is determined by externally check. Args: text_direction_param (tuple): ``(x0_index, x1_index, direction_factor)``, e.g. ``(0, 2, 1)`` for horizontal text, while ``(3, 1, -1)`` for vertical text. r@r|cs4g|]}|j|djkqS)rr)r#i)rprnror_r=rrr%s,z.TextBlock._parse_alignment..cs*tkr tjSdkrtjStjS)Ng?)r7r rmrirkr)Wd_centerd_leftrdrrexternal_alignments  z6TextBlock._parse_alignment..external_alignmentcg|] }|djqS)rrr#r)rnrrr%cr)rr)rorrr%rcSsg|] \}}||dqS)rr)r#Zx0x1rrrr%sreNrr)rrr;r7rlrjrrArBrangeanyr rhzipminrrmrirkr)rrrr_rbrcrdZd_rightrEdisrZX0ZX1XZ left_alignedZ right_alignedZcenter_alignedrgr) rrrrprnror_rdr=rrftsN        &&zTextBlock._parse_alignmentr/)__name__ __module__ __qualname____doc__dictrpropertyr!r,r0r5rHrIrJrQrWr\floatrqr{rrrOrf __classcell__rrrrr's\         5&TrN)rZ docx.sharedrrZdocx.enum.textrrZimage.ImageSpanrZ common.sharer r r Z common.Blockr r commonrrrrrrrs