o j?@sddlZddlZddlZddlZddlZddlZddlZddlZ ddl m Z ddl m Z ddlmZmZmZmZmZmZmZmZddlmZmZmZmZddlmZed ZGd d d e Z dS) N) BaseParser)Table) scale_image scale_pdfsegments_in_bbox text_in_bboxmerge_close_linesget_table_indexcompute_accuracycompute_whitespace)adaptive_threshold find_lines find_contours find_joints)BACKENDScamelotc@seZdZdZdddddddgddddddd d d d fd dZeddZeddZedddZddZ ddZ ddZ difddZ dS)Latticea- Lattice method of parsing looks for lines between text to parse the table. Parameters ---------- table_regions : list, optional (default: None) List of page regions that may contain tables of the form x1,y1,x2,y2 where (x1, y1) -> left-top and (x2, y2) -> right-bottom in PDF coordinate space. table_areas : list, optional (default: None) List of table area strings of the form x1,y1,x2,y2 where (x1, y1) -> left-top and (x2, y2) -> right-bottom in PDF coordinate space. process_background : bool, optional (default: False) Process background lines. line_scale : int, optional (default: 15) Line size scaling factor. The larger the value the smaller the detected lines. Making it very large will lead to text being detected as lines. copy_text : list, optional (default: None) {'h', 'v'} Direction in which text in a spanning cell will be copied over. shift_text : list, optional (default: ['l', 't']) {'l', 'r', 't', 'b'} Direction in which text in a spanning cell will flow. split_text : bool, optional (default: False) Split text that spans across multiple cells. flag_size : bool, optional (default: False) Flag text based on font size. Useful to detect super/subscripts. Adds around flagged text. strip_text : str, optional (default: '') Characters that should be stripped from a string before assigning it to a cell. line_tol : int, optional (default: 2) Tolerance parameter used to merge close vertical and horizontal lines. joint_tol : int, optional (default: 2) Tolerance parameter used to decide whether the detected lines and points lie close to each other. threshold_blocksize : int, optional (default: 15) Size of a pixel neighborhood that is used to calculate a threshold value for the pixel: 3, 5, 7, and so on. For more information, refer `OpenCV's adaptiveThreshold `_. threshold_constant : int, optional (default: -2) Constant subtracted from the mean or weighted mean. Normally, it is positive but may be zero or negative as well. For more information, refer `OpenCV's adaptiveThreshold `_. iterations : int, optional (default: 0) Number of times for erosion/dilation is applied. For more information, refer `OpenCV's dilate `_. resolution : int, optional (default: 300) Resolution used for PDF to PNG conversion. NFltrri, ghostscriptcKsj||_||_||_||_||_||_||_||_| |_| |_ | |_ | |_ | |_ ||_ ||_t||_dSN) table_regions table_areasprocess_background line_scale copy_text shift_text split_text flag_size strip_textline_tol joint_tolthreshold_blocksizethreshold_constant iterations resolutionr _get_backendbackend)selfrrrrr r!r"r#r$r%r&r'r(r)r*r,kwargsr/]/var/www/html/fyndo/pharma/fyndo/venv/lib/python3.10/site-packages/camelot/parsers/lattice.py__init__as zLattice.__init__csjfdd}ttr(tvrtdddkr#tdttS|s3tddS) NcsddtD}d|vS)NcSsg|] }|ddur|qS)__F) startswith).0methodr/r/r0 szDLattice._get_backend..implements_convert..convert)dir)methodsr,r/r0implements_convertsz0Lattice._get_backend..implements_convertzUnknown backend 'z:' specified. Please use either 'poppler' or 'ghostscript'.rz'ghostscript' will be replaced by 'poppler' as the default image conversion backend in v0.12.0. You can try out 'poppler' with backend='poppler'.'z#' must implement a 'convert' method) isinstancestrrkeysNotImplementedErrorwarningswarnDeprecationWarning)r,r;r/r:r0r+s"      zLattice._get_backendcCs2g}|D]\}}}|D]}|dkr-|j||jr-|j||js-|d8}|j||jr!|dkrM|j||jrM|j||jsM|d7}|j||jrA|dkrm|j||jrm|j||jsm|d8}|j||jra|dkr|j||jr|j||js|d7}|j||jrq ||||fq|S)aReduces index of a text object if it lies within a spanning cell. Parameters ---------- table : camelot.core.Table idx : list List of tuples of the form (r_idx, c_idx, text). shift_text : list {'l', 'r', 't', 'b'} Select one or more strings from above and pass them as a list to specify where the text in a spanning cell should flow. Returns ------- indices : list List of tuples of the form (r_idx, c_idx, text) where r_idx and c_idx are new row and column indices for text. rrrrb)cellshspanleftrightvspantopbottomappend)ridxr!indicesr_idxc_idxtextdr/r/r0 _reduce_indexs4zLattice._reduce_indexcCs(|D]}|dkrKtt|jD]:}tt|j|D].}|j||jdkrH|j||jrH|j||jsH|j||dj|j||_qqq|dkrtt|jD]:}tt|j|D].}|j||jdkr|j||jr|j||js|j|d|j|j||_qaqVq|S)aCopies over text in empty spanning cells. Parameters ---------- t : camelot.core.Table copy_text : list, optional (default: None) {'h', 'v'} Select one or more strings from above and pass them as a list to specify the direction in which text should be copied over when a cell spans multiple rows or columns. Returns ------- t : camelot.core.Table hrrv) rangelenrFrRstriprGrHrJrK)rr fijr/r/r0_copy_spanning_texts(    zLattice._copy_spanning_textcsxfdd}t|j|j|j|jd\|_|_|jjd}|jjd}|t|j }|t|j }|j t|}|j t|}|||j f|||f}|j durd} |j durZ||j } t |j| d|j|jd\} } t |j| d|j|jd\} } t| | }t|| | }n%t |jd|j|jd \} } t |jd|j|jd \} } ||j }t|| | }t||_t|| | |\|_|_|_dS) Nc sg}|D]9}|d\}}}}t|}t|}t|}t|}t||||f\}}}}|||t||t||fq|S)N,)splitfloatrrMabs)areas scaled_areasareax1y1x2y2 image_scalersr/r0 scale_areass$z1Lattice._generate_table_bbox..scale_areas)r blocksizecrrvertical)regions directionrr) horizontal)rprr))r imagenamerr'r(image thresholdshaper` pdf_width pdf_heightrrrrr)rrcopydeepcopytable_bbox_unscaledr table_bboxvertical_segmentshorizontal_segments)r-rk image_width image_heightimage_width_scalerimage_height_scalerpdf_width_scalerpdf_height_scaler pdf_scalersro vertical_maskr|horizontal_maskr}contoursr{rbr/rir0_generate_table_bboxsj               zLattice._generate_table_bboxcs*i}t||j|j\}}t||j|d<t||j|d<|djddd|djddd||_t|j |\t t  |d|dg |d |d gt t |jd t t d d |jd fddtdtd Dfddtdtd D||fS)NrqrncSs|j |jfSr)y0x0xr/r/r0Ez4Lattice._generate_columns_and_rows..)keycSs|j|j fSr)rrrr/r/r0rFrrrr)r%T)reversec g|] }||dfqSrr/r4r[)colsr/r0r6R z6Lattice._generate_columns_and_rows..crrr/r)rowsr/r0r6Sr)rr|r}r horizontal_text vertical_textsortt_bboxzipr{listextendr sortedr%rWrX)r- table_idxtkrv_sh_sr/)rrr0_generate_columns_and_rows<s$    z"Lattice._generate_columns_and_rowsc Ks|d}|d}|dus|durtd|jt||}|j|||jd}|}|}g}dD]?} |j | D]7} t || | |j |j |j d\} } | dddkrr|| tj|| |jd } | D] \} }}||j| |_qdq;q4td |gg}|jdurtj||jd }|j}t||_|jj|_t|}d |_||_||_|d |_ t!t"j#$|j%dd|_&g}|'dd|j(D|'dd|j)D||_*|j+|j,f|_-|j.|j/f|_0d|_1|S)NrrzNo segments found on {})r&)rnrq)r"r#r$r)r)r!d)r latticerzpage-rcS g|] }|j|j|j|jfqSr/rrrerfr4rr/r/r0r6rz+Lattice._generate_table..cSrr/rrr/r/r0r6r)2get ValueErrorformatrootnamer set_edgesr& set_borderset_spanrr r"r#r$rMrrTr!rFrRr r r]datapd DataFramedfrur flavoraccuracy whitespaceorderintospathbasenamereplacepagerrr_textrsrz_imager|r} _segments _textedges)r-rrrr.rrtable pos_errorsrprrOerrorrPrQrRrrrrr/r/r0_generate_tableWs`         zLattice._generate_tablec Cs||||stdtj|j|js9|j r*t dtj|jgSt dtj|jgS|j |j|j|g}tt|jddddD] \}}|||\}}} } |j|||| | d} || _|| qV|S) Nz Processing {}z:{} is image-based, camelot only works on text-based pages.zNo tables found on {}cSs|dS)Nrr/rr/r/r0rsz(Lattice.extract_tables..T)rr)rr)_generate_layoutloggerinforrrrrrimagesrArBr,r7filenamerrr enumeraterr{r?rr_bboxrM) r-rsuppress_stdout layout_kwargs_tablesrrrrrrrr/r/r0extract_tabless2   zLattice.extract_tablesr) __name__ __module__ __qualname____doc__r1 staticmethodr+rTr]rrrrr/r/r/r0r%s:= %  ,  J=r)!rsysrxlocaleloggingrAnumpynppandasrbasercorerutilsrrrr r r r r image_processingrrrrbackends.image_conversionr getLoggerrrr/r/r/r0s  (