o eEL@sddlZddlZddlZddlmZddlmZmZddlZddl m Z ddl m Z ddl mZeeeejdgd krCed ejejd d Gd ddZGdddeZGdddeZdS)N) perf_counter)Pool cpu_count)DocumentPage)Pages.)rrz)PyMuPDF>=1.19.0 is required for pdf2docx.z[%(levelname)s] %(message)s)levelformatc @sVeZdZdZd9dedefddZeddZed d Zd d Z ed dZ d:de de de fddZ d:de de de fddZddZddZd9ddZddZdefd d!Zd"efd#d$Zd"efd%d&Zd;d'e d(ed)ed*efd+d,Zdz(Converter.load_pages..F)logginginfo _color_outputrZ needs_passrConversionExceptionrZ authenticatelenrresetrange _page_indexesr0)rr&r'r num page_indexesr3rrrr(us  zConverter.load_pagescKs*t|d|jj|jfi||S)zjStep 2 of converting process: analyze whole document, e.g. page section, header/footer and margin.z[2/4] Analyzing document...)r6r7r8rr,r)rr+rrrr)szConverter.parse_documentc Kst|ddd|jD}t|}t|ddD]G\}}|jd}td|||z |jd i|Wqtya}z |dsM|drMt d ||n t d |d |WYd }~qd }~ww|S)zKStep 3 of converting process: parse pages, e.g. paragraph, image and table.z[3/4] Parsing pages...cSsg|]}|js|qSr)r0r2pagerrrr4sz)Converter.parse_pages..rr&(%d/%d) Page %dr"r#z,Ignore page %d due to parsing page error: %szError when parsing page : Nr) r6r7r8rr: enumerater/r, Exceptionerrorr9)rr+r num_pagesr3rApiderrrr*s   zConverter.parse_pagesc Kst|dttdd|j}|std|p&|jdtd d}t j |r2t |t }t|}t|dd D]H\}}|jsGq?|jd} td ||| z||Wq?ty} z |d ss|d rstd | | n td| d| WYd} ~ q?d} ~ ww||dS)zStep 4 of converting process: create docx file with converted pages. Args: docx_filename (str): docx filename to write to. kwargs (dict, optional): Configuration parameters. z[4/4] Creating pages...cSrr) finalized)rArrrsz%Converter.make_docx..z)No parsed pages. Please parse page first.rz.pdfz.docxrrBrCr"r#z+Ignore page %d due to making page error: %szError when make page rDN)r6r7r8listfilterrr9rr:ospathexistsremoverrErKr/ make_docxrFrGMakedocxExceptionsave) r docx_filenamer+Z parsed_pagesfilenameZ docx_filerHr3rArIrJrrrrSs0   zConverter.make_docxcCs(tj|jt|jdd|jDdS)z"Store parsed pages in dict format.cSsg|] }|jr|qSr)rKstorer@rrrr4sz#Converter.store..)rWpage_cntr )rOrPbasenamerr:rrrrrrXs zConverter.storedatacCs^|js|dd}|jddt|D|dgD]}|dd}|j||qdS) z"Restore pages from parsed results.rYdcSr-r.rr1rrrr4r5z%Converter.restore..r r/N)rgetr;r<restore)rr[r>Zraw_pageidxrrrr_s  zConverter.restorerWcCsLt|ddd}|tj|ddWddS1swYdS)z*Write parsed pages to specified JSON file.wzutf-8)encoding)indentN)openwritejsondumpsrX)rrWfrrr serializes"zConverter.serializecCsBt|d }t|}Wdn1swY||dS)z+Load parsed pages from specified JSON file.rN)rergloadr_)rrWrir[rrr deserializes  zConverter.deserializer3rV debug_pdf layout_filecKsxtj|j\}}|stj|d|}|stj|d}|dt|d|j|fd|gi|| |dS)aParse, create and plot single page for debug purpose. Args: i (int): Page index to convert. docx_filename (str): docx filename to write to. debug_pdf (str): New pdf file storing layout information. Default to add prefix ``debug_``. layout_file (str): New json file storing parsed layout data. Default to ``layout.json``. Zdebug_z layout.jsonT)r"Z debug_docZdebug_filenamer N) rOrPsplitrjoinupdaterrconvertrj)rr3rVrnror+rPrWrrr debug_pages zConverter.debug_pagecKst}td|j|j}|||r|drtd|dr,|j|||fi|n|j|||fi|j |fi|tdt|dS)aConvert specified PDF pages to docx file. Args: docx_filename (str, optional): docx filename to write to. Defaults to None. start (int, optional): First page to process. Defaults to 0, the first page. end (int, optional): Last page to process. Defaults to None, the last page. pages (list, optional): Range of page indexes. Defaults to None. kwargs (dict, optional): Configuration parameters. Defaults to None. Refer to :py:meth:`~pdf2docx.converter.Converter.default_settings` for detail of configuration parameters. .. note:: Change extension from ``pdf`` to ``docx`` if ``docx_file`` is None. .. note:: * ``start`` and ``end`` is counted from zero if ``--zero_based_index=True`` (by default). * Start from the first page if ``start`` is omitted. * End with the last page if ``end`` is omitted. .. note:: ``pages`` has a higher priority than ``start`` and ``end``. ``start`` and ``end`` works only if ``pages`` is omitted. .. note:: Multi-processing works only for continuous pages specified by ``start`` and ``end`` only. zStart to convert %sr$zPMulti-processing works for continuous pages specified by "start" and "end" only.zTerminated in %.2fs.N) rr6r7rr%rrr9_convert_with_multi_processingr,rS)rrVr&r'r r+t0settingsrrrrss  $zConverter.convertcKsV|j}|||j|||fi|g}|jD]}|jr(||jdi|q|S)aExtract table contents from specified PDF pages. Args: start (int, optional): First page to process. Defaults to 0, the first page. end (int, optional): Last page to process. Defaults to None, the last page. pages (list, optional): Range of page indexes. Defaults to None. kwargs (dict, optional): Configuration parameters. Defaults to None. Returns: list: A list of parsed table content. Nr)r%rrr,rrKextendextract_tables)rr&r'r r+rwZtablesrArrrryNs  zConverter.extract_tablesc  sdr tdtntdfddtD}t}|j|dtD]}d|d}tj|sAq0 |t |q0j |fidS) zParse and create pages based on page indexes with multi-processing. Reference: https://pymupdf.readthedocs.io/en/latest/faq.html#multiprocessing rr c s0g|]}|jjd|dfqS)-.json)rrr1cpur'r+prefixrr&rrr4qs z.rrzr{N) minrr<rmap_parse_pages_per_cpurOrPrQrmrRrS) rrVr&r'r+Zvectorspoolr3rWrr|rrugs   z(Converter._convert_with_multi_processingcs|\}}}}}}}}t||} | |pt| j}t||t} t| |} | |} | t|| k} | d|t| |d}t|| | }fddt||D}| jD]}d|_qX|D]}d| j|_q`| j di|j di| || dS) aRender a page range of a document. Args: vector (list): A list containing required parameters. * 0 : segment number for current process * 1 : count of CPUs * 2,3: whole pages range to process * 4 : pdf filename * 5 : password for encrypted pdf * 6 : configuration parameters * 7 : json filename storing parsed results rrcsg|]}|qSrrr1Z all_indexesrrr4z2Converter._parse_pages_per_cpu..TFNr) rr(r:rr<intrr r0r)r*rjr!)Zvectorr`r}srJZ pdf_filenamerr+Z json_filenameZcvrHmnZseg_sizeZseg_fromZseg_tor?rAr3rrrrs,    zConverter._parse_pages_per_cpucCs@|r dd|D}|S|p|}tt|t|}t||}|S)zParsing arguments.cSsg|]}t|qSr)r)r2xrrrr4rz+Converter._page_indexes..)slicerr<)r&r'r Zpdf_lenZindexesrrrrr=s zConverter._page_indexescCs d|dS)Nzzr)msgrrrr8s zConverter._color_outputr)rNN)NNN)NrNN)__name__ __module__ __qualname____doc__rrpropertyrr r!r%rrMr,r(r)r*rSrXdictr_rjrmrtrsryru staticmethodrr=r8rrrrrs:    ( +   / .  rc@ eZdZdS)r9Nrrrrrrrr9r9c@r)rTNrrrrrrTrrT)rOrgr6timermultiprocessingrrrZdocxrZ page.PagerZ page.Pagesr rMrrZ VersionBindrp SystemExit basicConfigINFOrrFr9rTrrrrs*    0