o e[@s:dZddlmZddlmZddlmZGdddZdS)aDDocument 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 prerequite 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. )Line) constants)Shapesc@s|eZdZdZdddZddZddZd d Zd efd d Z de fddZ de fddZ ddZ ddZddZddZdS)Layoutz(Blocks and shapes structure and formats.NcCsDddlm}ddlm}|||d|_t||d|_||d|_dS)a5 Initialize layout. Args: blocks (Blocks): Blocks representing text/table contents. shapes (Shapes): Shapes representing table border, shading and text style like underline, highlight. parent (Page, Column, Cell): The object that this layout belonging to. )Blocksr)TablesConstructor)Z instancesparent)r N)rZtable.TablesConstructorrblocksrshapes _table_parser)selfr r rrrFD:\Projects\ConvertPro\env\Lib\site-packages\pdf2docx/layout/Layout.py__init__&s  zLayout.__init__cOt)zWorking bbox of current Layout.NotImplementedErrorr argskwargsrrr working_bbox6zLayout.working_bboxcOr)z2Whether given element is contained in this layout.rrrrrcontains;rzLayout.containscCs|j|jdS)z#Store parsed layout in dict format.)r r )r storer )r rrrr@sz Layout.storedatacCs,|j|dg|j|dg|S)z#Restore Layout from parsed results.r r )r restoregetr )r rrrrrHszLayout.restorer cCs|D]}||qdS)aAdd 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)r r blockrrr assign_blocksOs zLayout.assign_blocksr cCs(|D]}|j|jr|j|qdS)zuAdd shapes to this cell. Args: shapes (list): a list of Shape instance to add. N)r intersectsbboxr append)r r shaperrr assign_shapes[szLayout.assign_shapescKsT|jsdS|jdi||jdi|tdd|jD] }|jdi|qdS)z]Parse layout. Args: settings (dict): Layout parsing parameters. NcSs|jS)N)Zis_table_block)errruszLayout.parse..r)r _parse_table_parse_paragraphfilterparse)r settingsrrrrr+fs z Layout.parsecCsV|j|tjdr|j|dS|j|j@r't|tr)|j||jdSdSdS)z/Add block (line or table block) to this layout.) thresholdN) rrZ FACTOR_MAJORr r#r" isinstancerr!)r rrrrrys zLayout._assign_blockcKsP|dr|j|d|d|d|dr&|j|d|d|ddSdS)aParse 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)r Zlattice_tablesZ stream_tablesr r,rrrr(szLayout._parse_tablec Ksd|j|d|d|d|j|jj|d|j|d|d|d|d|d|d d S) zmCreate 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_hyphenr/Zline_break_width_ratioZlines_left_aligned_thresholdZlines_right_aligned_thresholdZlines_center_aligned_thresholdN)r Z parse_blockZparse_text_formatr Ztext_style_shapesZ parse_spacingr0rrrr)s"zLayout._parse_paragraph)NN)__name__ __module__ __qualname____doc__rrrrdictrlistr r%r+rr(r)rrrrr#s    rN)r4Z text.LinercommonrZ shape.Shapesrrrrrrs