o jK@sZdZddlmZmZddlmZddlmZddlm Z ddl m Z Gdd d e eZ d S) aCDocument layout depends on Blocks and Shapes. **Layout** here refers to the content and position of text, image and table. The target is to convert source blocks and shapes to a *flow layout* that can be re-created as docx elements like paragraph and table. In addition to ``Section`` and ``Column``, ``TableBlock`` is used to maintain the page layout . So, detecting and parsing table block is the principle steps. The prerequisite work is done before this step: 1. Clean up source blocks and shapes in Page level, e.g. convert source blocks to ``Line`` level, because the block structure determined by ``PyMuPDF`` might be not reasonable. #. Parse structure in document level, e.g. page header/footer. #. Parse Section and Column layout in Page level. The page layout parsing idea: 1. Parse table layout in Column level. (a) Detect explicit tables first based on shapes. (#) Then, detect stream tables based on original text blocks and parsed explicit tables. (#) Move table contained blocks (lines or explicit table) to associated cell-layout. #. Parse paragraph in Column level. (a) Detect text blocks by combining related lines. (#) Parse paragraph style, e.g. text format, alignment #. Calculate vertical spacing based on parsed tables and paragraphs. #. Repeat above steps for cell-layout in parsed table level. )ABCabstractmethod)Line) constants)Element)ShapescseZdZdZdfdd ZeeddZfddZd e fd d Z d e fd dZ de fddZ ddZddZddZddZZS)Layoutz(Blocks and shapes structure and formats.Ncs\ddlm}ddlm}|rd|ini}t|||d|_t|d|_||d|_dS)z Initialize layout. Note that layout bbox must be set explicitly, rather than calculated automatically from contained blocks and shapes.)Blocksr)TablesConstructorbbox)parentN) r Ztable.TablesConstructorr super__init__blocksrshapes _table_parser)selfr r r raw __class__W/var/www/html/Deteccion_Ine/venv/lib/python3.10/site-packages/pdf2docx/layout/Layout.pyr&s     zLayout.__init__cCsdS)zWorking bbox of current Layout.Nr)rrrr working_bbox9szLayout.working_bboxcs*t}||j|jd|S)z#Store parsed layout in dict format.)rr)rstoreupdaterr)rresrrrr?s z Layout.storedatacCs>||dd|j|dg|j|dg|S)z#Restore Layout from parsed results.r )rrrrrr)Z update_bboxgetrrestorer)rrrrrr IszLayout.restorercCs|D]}||qdS)zAdd blocks (line or table block) to this layout. Args: blocks (list): a list of text line or table block to add. .. note:: If a text line is partly contained, it must deep into span -> char. N) _assign_block)rrblockrrr assign_blocksQs zLayout.assign_blocksrcCs(|D]}|j|jr|j|qdS)zlAdd shapes to this cell. Args: shapes (list): a list of Shape instance to add. N)r intersectsr rappend)rrshaperrr assign_shapes]szLayout.assign_shapescKsT|jsdS|jdi||jdi|tdd|jD] }|jdi|qdS)z]Parse layout. Args: settings (dict): Layout parsing parameters. NcSs|jSN)Zis_table_block)errrwszLayout.parse..r)r _parse_table_parse_paragraphfilterparse)rsettingsr"rrrr.hs z Layout.parsecCsX|j|tjdr|j|dSt|tr(|j|jr*|j||jdSdSdS)z/Add block (line or table block) to this layout.) thresholdN) containsrZ FACTOR_MAJORrr% isinstancerr r$)rr"rrrr!{s zLayout._assign_blockcKsP|dr|j|d|d|d|dr&|j|d|d|ddSdS)a Parse table layout: * detect explicit tables first based on shapes, * then stream tables based on original text blocks and parsed explicit tables; * move table contained blocks (text block or explicit table) to associated cell layout. Zparse_lattice_tableZconnected_border_toleranceZmin_border_clearanceZmax_border_widthZparse_stream_tableline_separate_thresholdN)rZlattice_tablesZ stream_tablesrr/rrrr+szLayout._parse_tablec Ksd|j|d|d|d|j|jj|d|j|d|d|d|d|d|d d S) zlCreate text block based on lines, and parse text format, e.g. text highlight, paragraph indentation Zmax_line_spacing_ratioZline_break_free_space_ratioZnew_paragraph_free_space_ratioZdelete_end_line_hyphenr3Zline_break_width_ratioZlines_left_aligned_thresholdZlines_right_aligned_thresholdZlines_center_aligned_thresholdN)rZ parse_blockZparse_text_formatrZtext_style_shapesZ parse_spacingr4rrrr,s"zLayout._parse_paragraphr()__name__ __module__ __qualname____doc__rpropertyrrrdictr listr#r'r.r!r+r, __classcell__rrrrr #s      r N) r8abcrrZ text.LinercommonrZcommon.ElementrZ shape.Shapesrr rrrrs