j5jdZddlmZddlZddlZddlmZddlmZ ddl m Z ddl Z ddl m Z mZmZmZmZej$eZdZddd  dd Zdd Zddd Zdd ZddZddZddZddZ ddZy)zAUtilities for PDF/A production and confirmation with Ghostscript.) annotationsN)Iterator)files)Path)Array DictionaryNamePdfStreamzsRGB.icc stream_name stream_datac#@K|du|duk(sJ|rdnd}|r8|Jtj|djd}|d|zd|dk7r d |d |d d |d |jD]\}}d|d|d|rd |d|dddyyw)Nz/streamz/dictT)adobeascii def {Catalog}z [/_objdef z /type z /OBJ pdfmark[z <> /PUT pdfmarkz /PUT pdfmark)base64 a85encodedecodeitems)alias dictionaryr robjtypea85_datakeyvals C/var/www/html/qr/venv/lib/python3.12/site-packages/ocrmypdf/pdfa.py_postscript_objdefr"s 4 [D%8 99 9&iGG&&&##Kt<CCGL Q(**  5' ?? eWC.$$&S3%q %+ab/*-88sBBc #Kdtddt|id|Ed{dtddd dd |d d Ed{dtd ddiEd{y7@7!7 w)Nz%!z {icc_PDFA}z/Nz /ICCProfiler z{OutputIntent_PDFA}z /OutputIntent /GTS_PDFA1())/Type/S/DestOutputProfile/OutputConditionIdentifierrz/OutputIntentsz[ {OutputIntent_PDFA} ])r"str)icc_nameicc_datacolorss r!_make_postscriptr03s J! s6{!  H!$".,-hZq/   H!&(AB#s3"A+A% A+A'A+A) A+'A+)A+c|dk7r tdtdtz j}dj t ||d}t |j|d|S)aCreate a Postscript PDFMARK file for Ghostscript PDF/A conversion. pdfmark is an extension to the Postscript language that describes some PDF features like bookmarks and annotations. It was originally specified Adobe Distiller, for Postscript to PDF conversion. Ghostscript uses pdfmark for PDF to PDF/A conversion as well. To use Ghostscript to create a PDF/A, we need to create a pdfmark file with the necessary metadata. This function takes care of the many version-specific bugs and peculiarities in Ghostscript's handling of pdfmark. The only information we put in specifies that we want the file to be a PDF/A, and we want to Ghostscript to convert objects to the sRGB colorspace if it runs into any object that it decides must be converted. Arguments: target_filename: filename to save icc: ICC identifier such as 'sRGB' References: Adobe PDFMARK Reference: https://opensource.adobe.com/dc-acrobat-sdk-docs/library/pdfmark/ sRGBzOnly supporting sRGB ocrmypdf.data r)encoding)NotImplementedError package_filesSRGB_ICC_PROFILE_NAME read_bytesjoinr0r write_text)target_filenameiccbytes_icc_profile postscripts r!generate_pdfa_psrAKsn0 f}!"899 o&)>>jl+C1BAFGJ $$Z'$B c"tj|5}|j}|jsddddcdddShd}|jj }d|}i}||vr d|d <d |d <||d <ddd|S#1swYSxYw) zDetermines if the file claims to be PDF/A compliant. This only checks if the XMP metadata contains a PDF/A marker. It does not do full PDF/A validation. FpdfzNo PDF/A metadata in XMP)passoutput conformanceN>1a1b2a2b2u3a3b3uzPDF/A-TrEpdfarFrG)pikepdfopen open_metadata pdfa_statuslower)filenamerDpdfmetavalid_part_conformspdfa_status_isorG pdfa_dicts r!file_claims_pdfar[qs h /3##%""9//O"--335/0 +- 1 1 $If "(Ih #. - #/$ %/$ s"B8BBcBtdtz jS)z,Load the sRGB ICC profile from package data.r3)r8r9r:rBr!_load_srgb_icc_profiler^s / *-B B N N PPrBc4ddddd}|j|dS)zExtract PDF/A part and conformance from output_type. Args: output_type: One of 'pdfa', 'pdfa-1', 'pdfa-2', 'pdfa-3' Returns: Tuple of (part, conformance) e.g., ('2', 'B') )2B)1ra)3ra)rPzpdfa-1zpdfa-2zpdfa-3)get) output_typemappings r!_pdfa_part_conformancergs* G ;;{J //rBcb|j5}||d<||d<dddy#1swYyxYw)zAdd PDF/A XMP metadata declaration to a PDF. Args: pdf: An open pikepdf.Pdf object part: PDF/A part number ('1', '2', or '3') conformance: Conformance level ('A', 'B', or 'U') z pdfaid:partzpdfaid:conformanceN)rS)rDpartrGmetas r!add_pdfa_metadatarks<   1"]%0 !"111s %.c,t}t||}d|tj<t tj tdd|d}tj |jvr&tg|jtj <|jj D]D}t|jtjdk(s/tjdy|jj j|y)aLAdd sRGB ICC profile as OutputIntent to PDF catalog. This creates the required PDF/A OutputIntent structure with: - An ICC profile stream containing sRGB profile - An OutputIntent dictionary pointing to that profile - Updates the Catalog's OutputIntents array Args: pdf: An open pikepdf.Pdf object r5r%r2)r(r)r+r*z*sRGB OutputIntent already exists, skippingN)r^r r Nr OutputIntent OutputIntentsRootrr,rdOutputConditionIdentifierlogdebugappend)rDr. icc_stream output_intentintents r!add_srgb_output_intentrxs&'HX&JJtvv""< &,(  M )',Ry##$(((( vzz$889 :f D IIB C  HH!!-0rBct|\}}tj|5}t|t ||||j |dddt jd||S#1swY!xYw)aAttempt to convert a PDF to PDF/A by adding required structures. This function creates a copy of the input PDF and adds: 1. sRGB ICC profile as OutputIntent 2. XMP metadata declaring PDF/A conformance This approach works for PDFs that are already mostly PDF/A compliant but lack the formal declarations. It does NOT perform color conversion, font embedding, or other transformations that Ghostscript does. Args: input_file: Path to input PDF output_file: Path where output PDF should be written output_type: One of 'pdfa', 'pdfa-1', 'pdfa-2', 'pdfa-3' Returns: Path to the output file Raises: pikepdf.PdfError: If the PDF cannot be opened or modified Nz)Speculative PDF/A conversion complete: %s)rgr rRrxrksaverrrs) input_file output_filererirGrDs r!speculative_pdfa_conversionr}sm4/{;D+ * s##t[1   II9;G s *A..A7) rr,rzdict[str, str]r z str | Nonerz bytes | Nonereturn Iterator[str])r-r,r.bytesr/intr~r)r2)r=rr>r,)rVr)r~r)rer,r~ztuple[str, str])rDr rir,rGr,r~None)rDr r~r)r{rr|rrer,r~r)__doc__ __future__rrloggingcollections.abcrimportlib.resourcesrr8pathlibrrQrrr r r getLogger__name__rrr9r"r0rAr[r^rgrkrxr}r]rBr!rsH" $688g!"# $ 9 99 9  9  9:0#L6Q 0$ 1#1L#### #rB