.ic^dZddlZddlZddlmZddlmZddlm Z ddl m Z ddl mZddlmZddlmZddlmZejeZGd d e jZd ZGd d e jZGdde jZGdde jZGdde jZdS)) PdfDocument PdfFormEnv PdfXObject PdfBookmarkPdfDestN)Path) PDFIUM_INFO) PdfiumError)PdfPage) PdfObject) PdfAttachmentc8eZdZdZd'fd ZdZdZfdZedZ e d Z d Z d Z d Zd ZedZd(dZdZdZdZd)dZejfdZdZdZdZd*dZdZdZdZ dZ!dZ"d(dZ#d Z$d+d!Z%d"Z&d#Z'd$Z( d,d&Z)xZ*S)-ra Document helper class. Parameters: input_data (str | pathlib.Path | bytes | ctypes.Array | typing.BinaryIO | FPDF_DOCUMENT): The input PDF given as file path, bytes, ctypes array, byte stream, or raw PDFium document handle. A byte stream is defined as an object that implements ``seek() tell() read() readinto()``. password (str | None): A password to unlock the PDF, if encrypted. Otherwise, None or an empty string may be passed. If a password is given but the PDF is not encrypted, it will be ignored (as of PDFium 5418). autoclose (bool): Whether byte stream input should be automatically closed on finalization. Raises: PdfiumError: Raised if the document failed to load. The exception is annotated with the reason reported by PDFium (via message and :attr:`~.PdfiumError.err_code`). FileNotFoundError: Raised if an invalid or non-existent file path was given. Hint: * Documents may be used in a ``with``-block, closing the document on context manager exit. This is recommended when *input_data* is a file path, to safely and immediately release the bound file handle. * :func:`len` may be called to get a document's number of pages. * Pages may be loaded using list index access. * Looping over a document will yield its pages from beginning to end. * The ``del`` keyword and list index access may be used to delete pages. Attributes: raw (FPDF_DOCUMENT): The underlying PDFium document handle. formenv (PdfFormEnv | None): Form env, if the document has forms and :meth:`.init_forms` was called. NFct|trt|}t|trI|}|st |||_||_||_ g|_ g|_ d|_ t|jtjr |j|_nIt!|j|j|j \|_}}|xj |z c_ |xj |z c_ t#t&j|j |j dSN) isinstancestrr expanduserresolveis_fileFileNotFoundError_input _password _autoclose _data_holder _data_closerformenvpdfium_c FPDF_DOCUMENTraw _open_pdfsuper__init__r _close_impl)selfinputpassword autocloseto_holdto_close __class__s W/var/www/html/analyses/venv/lib/python3.11/site-packages/pypdfium2/_helpers/document.pyr"zPdfDocument.__init__6s0 eS ! ! KKE eT " " /$$&&..00E==?? /'... !# dk8#9 : : *{DHH*3DKQUQ`*a*a 'DHgx    (      )   0$2CTEVWWWWWc|Srr$s r+ __enter__zPdfDocument.__enter__Ss r,c.|dSr)close)r$_s r+__exit__zPdfDocument.__exit__Vs r,c t|jtr"tt |j}nt|jt r&dt t|jd}nYt|jtj r&dt t|jd}nt|j}t ddd|dS)Nzz*>AAAGG  X%; < < (B3r$++?+?BBBGG4;''G''""$$SbS);;;;;;r,cdSrr.r/s r+parentzPdfDocument.parentfstr,ctj||D]}t||D]}|||dSr)rFPDF_CloseDocumentr;r2clear)r data_holder data_closerdatas r+r#zPdfDocument._close_implksw#C(((  D tHHHH  D JJLLLLr,c*tj|Sr)rFPDF_GetPageCountr/s r+__len__zPdfDocument.__len__vs)$///r,c#\Ktt|D] }||V dSr)rangelenr$is r+__iter__zPdfDocument.__iter__ys<D ##  Aq'MMMM  r,c,||Sr)get_pagerLs r+ __getitem__zPdfDocument.__getitem__}s}}Qr,c0||dSr)del_pagerLs r+ __delitem__zPdfDocument.__delitem__s ar,c>tj}||S)zJ Returns: PdfDocument: A new, empty document. )rFPDF_CreateNewDocument)clsnew_pdfs r+newzPdfDocument.news 133s7||r,c2|}|tjks|jrdS|sbdtjvr?tjd}tjddtj |}ntjd}tj ||}|std|d t||||_| |j|tjtjfvrdtjvrgtj|}|sOtj}t$d t(j|dSdSt$d dSdS) a Initialize a form env, if the document has forms. If already initialized, nothing will be done. See the :attr:`formenv` attribute. Attention: If form rendering is desired, this method shall be called right after document construction, before getting document length or page handles. Parameters: config (FPDF_FORMFILLINFO | None): Custom form config interface to use (optional). NXFA)versionF)r] xfa_disabled m_pJsPlatformz*Initializing form env failed for document .zFPDF_LoadXFA() failed with zinit_forms() called on XFA pdf, but this pdfium binary was compiled without XFA support. Run `PDFIUM_PLATFORM=auto-v8 pip install -v pypdfium2 --no-binary pypdfium2` to get a build with XFA support.) get_formtyper FORMTYPE_NONErr flagsIPDF_JSPLATFORMFPDF_FORMFILLINFOctypespointerFPDFDOC_InitFormFillEnvironmentr r_add_kidFORMTYPE_XFA_FULLFORMTYPE_XFA_FOREGROUND FPDF_LoadXFAFPDF_GetLastErrorloggerwarningpdfium_i XFAErrorToStrget)r$configformtype js_platformrokerrs r+ init_formszPdfDocument.init_formss$$&& x- - - - F ? )))&6qAAA !3AEagaop{a|a|}}}!3A>>>6tVDD TR4RRRSS S!#tV44  dl### 2H4TU U U )))*400d"466CNN#bAWA[A[\_A`A`#b#bcccccdd D V Ur,c*tj|S)z Returns: int: PDFium form type that applies to the document (:attr:`FORMTYPE_*`). :attr:`FORMTYPE_NONE` if the document has no forms. )rFPDF_GetFormTyper/s r+rbzPdfDocument.get_formtypes (...r,c*tj|S)zV Returns: int: Page displaying mode (:attr:`PAGEMODE_*`). )rFPDFDoc_GetPageModer/s r+ get_pagemodezPdfDocument.get_pagemodes +D111r,cDttj|S)zm Returns: bool: Whether the document is tagged (cf. PDF 1.7, 10.7 "Tagged PDF"). )boolrFPDFCatalog_IsTaggedr/s r+ is_taggedzPdfDocument.is_taggeds X2488:::r,rct|ttfrt|dd}}n-t j|dr|d}}nt d|d |t j||f}|tj |ntj g||R}|std |r| dSdS#|r| wwxYw) a Save the document at its current state. Parameters: dest (str | pathlib.Path | io.BytesIO): File path or byte stream the document shall be written to. version (int | None): The PDF version to use, given as an integer (14 for 1.4, 15 for 1.5, ...). If None (the default), PDFium will set a version automatically. flags (int): PDFium saving flags (defaults to 0). wbTwFzCannot save to ''NzFailed to save document.) rrropenrq is_stream ValueError get_bufwriterrFPDF_SaveAsCopyFPDF_SaveWithVersionr r2)r$destr]rdbuffer need_closesaveargsrws r+savezPdfDocument.saves dS$K ( ( 9!%dD!1!14JFF  c * * 9!%uJFF777788 8 h4V<!"<=== >    z   s A CCctj||dd}tj|}tj|||||jd|dz S)a Parameters: type (int): The identifier type to retrieve (:attr:`FILEIDTYPE_*`), either permanent or changing. If the file was updated incrementally, the permanent identifier stays the same, while the changing identifier is re-calculated. Returns: bytes: Unique file identifier from the PDF's trailer dictionary. See PDF 1.7, Section 14.4 "File Identifiers". Nrr^)rFPDF_GetFileIdentifierrgcreate_string_bufferr)r$typen_bytesrs r+get_identifierzPdfDocument.get_identifiersV1$dAFF,W55'dFGDDDz*719*%%r,chtj}tj||}|sdS|jS)z Returns: int | None: The PDF version of the document (14 for 1.4, 15 for 1.5, ...), or None if the document is new or its version could not be determined. N)rgc_intrFPDF_GetFileVersionvalue)r$r]rws r+ get_versionzPdfDocument.get_versions6 ,..  )$ 8 8 4}r,c|dzd}tj||dd}tj|}tj|||||jd|dz dS)z Returns: str: Value of the given key in the PDF's metadata dictionary. If the key is not contained, an empty string will be returned. utf-8Nrr^ utf-16-le)encoderFPDF_GetMetaTextrgrrdecode)r$keyenc_keyrrs r+get_metadata_valuezPdfDocument.get_metadata_values{ <''00+D'4CC,W55!$AAAz*719*%,,[999r,)TitleAuthorSubjectKeywordsCreatorProducer CreationDateModDatecnfdjD}|rd|D}|S)z Get the document's metadata as dictionary. Parameters: skip_empty (bool): If True, skip items whose value is an empty string. Returns: dict: PDF metadata. c<i|]}||Sr.)r).0kr$s r+ z1PdfDocument.get_metadata_dict..*s)NNNaAt..q11NNNr,ci|] \}}||| Sr.r.)rrvs r+rz1PdfDocument.get_metadata_dict..,s#???AQ?1???r,) METADATA_KEYSitems)r$ skip_emptymetadatas` r+get_metadata_dictzPdfDocument.get_metadata_dict sMONNN4;MNNN  @??)9)9???Hr,c*tj|S)zY Returns: int: The number of embedded files in the document. )rFPDFDoc_GetAttachmentCountr/s r+count_attachmentszPdfDocument.count_attachments0s 24888r,cvtj||}|std|dt||S)za Returns: PdfAttachment: The attachment at given index (zero-based). z"Failed to get attachment at index ra)rFPDFDoc_GetAttachmentr r )r$indexraw_attachments r+get_attachmentzPdfDocument.get_attachment8sI "7eDD MK5KKKLL L^T222r,c|dzd}tj|tj}tj||}|st d|dt||S)aN Add a new attachment to the document. It may appear at an arbitrary index (as of PDFium 5418). Parameters: name (str): The name the attachment shall have. Usually a file name with extension. Returns: PdfAttachment: Handle to the new, empty attachment. rrz!Failed to create new attachment 'z'.)rrgcastrFPDF_WIDESTRINGFPDFDoc_AddAttachmentr r )r$nameenc_name enc_name_ptrrs r+new_attachmentzPdfDocument.new_attachmentCst6M))+66{8X-EFF !7lKK LJ$JJJKK K^T222r,cZtj||}|std|ddS)a Unlink the attachment at given index (zero-based). It will be hidden from the viewer, but is still present in the file (as of PDFium 5418). Following attachments shift one slot to the left in the array representation used by PDFium's API. Handles to the attachment in question received from :meth:`.get_attachment` must not be accessed anymore after this method has been called. z%Failed to delete attachment at index raN)rFPDFDoc_DeleteAttachmentr )r$rrws r+del_attachmentzPdfDocument.del_attachmentUsE .tU ; ; PNeNNNOO O P Pr,c tj||}|stdt|||j}|jr5tj||j|j|n|||S)a Returns: PdfPage: The page at given index (zero-based). Note: This calls ``FORM_OnAfterLoadPage()`` if the document has an active form env. In that case, note that closing the formenv would implicitly close the page. zFailed to load page.)r FPDF_LoadPager r rFORM_OnAfterLoadPagerj)r$rraw_pagepages r+rPzPdfDocument.get_pagecs)$66 6455 5xt|44 <  )$ = = = L ! !$ ' ' ' ' MM$    r,c|t|}tj||||}t||d}|||S)a Insert a new, empty page into the document. Parameters: width (float): Target page width (horizontal size). height (float): Target page height (vertical size). index (int | None): Suggested zero-based index at which the page shall be inserted. If None or larger that the document's current last index, the page will be appended to the end. Returns: PdfPage: The newly created page. N)rKr FPDFPage_Newr rj)r$widthheightrrrs r+new_pagezPdfDocument.new_pagezsR =IIE(ueVDDxt,, d r,c0tj||dS)z Remove the page at given index (zero-based). It is recommended to close any open handles to the page before calling this method. N)rFPDFPage_Delete)r$rs r+rSzPdfDocument.del_pages  u-----r,cF|t|}t|tr+tj|||d|}n>d}d}|r t|}t j|z|}tj|||||}|stddS)a. Import pages from a foreign document. Parameters: pdf (PdfDocument): The document from which to import pages. pages (list[int] | str | None): The pages to include. It may either be a list of zero-based page indices, or a string of one-based page numbers and ranges. If None, all pages will be included. index (int): Zero-based index at which to insert the given pages. If None, they are appended to the end of the document. NasciirzFailed to import pages.) rKrrrFPDF_ImportPagesrrgrFPDF_ImportPagesByIndexr )r$pdfpagesrrw page_countc_pagess r+ import_pageszPdfDocument.import_pagess =IIE eS ! ! Y*4ell76K6KUSSBBJG > ZZ !<*4u=1$WjRWXXB 9788 8 9 9r,ctj}tj|||}|std|j|jfS)z Returns: (float, float): Width and height of the page at given index (zero-based), in PDF canvas units. z!Failed to get page size by index.)rFS_SIZEFFPDF_GetPageSizeByIndexFr rr)r$rsizerws r+ get_page_sizezPdfDocument.get_page_sizesM  ""  .tUD A A CABB B DK((r,ctj||dd}tj|}tj|||||jd|dz dS)z Returns: str: Label of the page at given index (zero-based). (A page label is essentially an alias that may be displayed instead of the page number.) Nrr^r)rFPDF_GetPageLabelrgrrr)r$rrrs r+get_page_labelzPdfDocument.get_page_labelsd ,T5$BB,W55"4@@@z*719*%,,[999r,ctj|||}|std|dt||}|||S)a_ Capture a page as XObject and attach it to a document's resources. Parameters: index (int): Zero-based index of the page. dest_pdf (PdfDocument): Target document to which the XObject shall be added. Returns: PdfXObject: The page as XObject. z Failed to capture page at index z as FPDF_XOBJECT.rr)rFPDF_NewXObjectFromPager rrj)r$rdest_pdf raw_xobjectxobjects r+page_as_xobjectzPdfDocument.page_as_xobjectsd6xuMM  [YYYYZZ Z(;;; gr,c# K|t}tj||}|rtj|j}||vrt ddS||t|||V||dz kr#| |||dz|Ed{Vn3tj||rt d|dtj ||}|dSdS)z Iterate through the bookmarks in the document's table of contents (TOC). Parameters: max_depth (int): Maximum recursion depth to consider. Yields: :class:`.PdfBookmark` NzRA circular bookmark reference was detected while traversing the table of contents.) max_depthr?levelseenzMaximum recursion depth z reached (subtree skipped).) setrFPDFBookmark_GetFirstChildrg addressofcontentsrorpaddrget_tocFPDFBookmark_GetNextSibling)r$rr?rrbm_ptraddresss r+rzPdfDocument.get_tocs?" <55D4T6BB H&v77G$sttt!!!fdE22 2 2 2y{""<<)FRWXYRY`d<eeeeeeeeee4T6BB b`)```aaa9$GGF! H H H H Hr,)NFr)Nr)F)NN)rNrN)+__name__ __module__ __qualname____doc__r"r0r4r<propertyr? staticmethodr#rHrNrQrT classmethodrYryrbr~rrrFILEIDTYPE_PERMANENTrrrrrrrrrrPrrSrrrrr __classcell__r*s@r+rrs@XXXXXX: < < < < <X\000   [))))X///222;;;>#+"?&&&&"    : : :qM     999333333$ P P P.0...9999> ) ) ) : : :, 'H'H'H'H'H'H'H'Hr,rcd\}}||dzd}t|tr9tjt |dzd|}nt|t tjfr'tj |t||}|f}nltj |dr2tj |\}}|r|f}tj||}n%tdt!|jdtj|dkrEtj}t)dtj|d | |||fS) N)r.r.rrrzInvalid input type 'rrz!Failed to load document (PDFium: z).)err_code)rrrrFPDF_LoadDocumentrr9rgArrayFPDF_LoadMemDocument64rKrqr get_bufreaderFPDF_LoadCustomDocument TypeErrorrrrGrnr ErrorToStrrs) input_datar&r'r(r)r bufaccessr s r+r r s}GXVO++G44*d## M(#j//&*@)H)H)Q)QS[\\ J 5 6 6 M-j#j//8TT.  J , ,M%3J?? 7  &"~H.y(CCKtJ/?/?/HKKKLLL!#&&**-//ch>Q>U>UV^>_>_cccnvwwww  !!r,cNeZdZdZfdZedZedZxZ S)raM Form environment helper class. Attributes: raw (FPDF_FORMHANDLE): The underlying PDFium form env handle. config (FPDF_FORMFILLINFO): Accompanying form configuration interface, to be kept alive. pdf (PdfDocument): Parent document this form env belongs to. c||_||_||_tt j|j|jdSr)rrrtr!r"rr#)r$rrrtr*s r+r"zPdfFormEnv.__init__7sA  /dhGGGGGr,c|jSrrr/s r+r?zPdfFormEnv.parent= xr,cZtj|t|d|_dSr)rFPDFDOC_ExitFormFillEnvironmentr;r)rrtrs r+r#zPdfFormEnv._close_implAs)0555 6  r,) rrrrr"rr?rr#r r s@r+rr*s}  HHHHH X\r,rc>eZdZdZfdZedZdZxZS)rz XObject helper class. Attributes: raw (FPDF_XOBJECT): The underlying PDFium XObject handle. pdf (PdfDocument): Reference to the document this XObject belongs to. cz||_||_ttjdSr)rrr!r"rFPDF_CloseXObject)r$rrr*s r+r"zPdfXObject.__init__Qs2 344444r,c|jSrrr/s r+r?zPdfXObject.parentVrr,cVtj|}t||jS)a  Returns: PdfObject: An independent pageobject representation of the XObject. If multiple pageobjects are created from an XObject, they share resources. Returned pageobjects remain valid after the XObject is closed. r)rFPDF_NewFormObjectFromXObjectr r)r$ raw_pageobjs r+ as_pageobjectzPdfXObject.as_pageobjectZs)## 1$''(x==3ii(Syr,N)rrrrr"r7rAr.r,r+rrsK)))     r,r) __all__rgloggingpathlibr pypdfium2.rawrrpypdfium2.internalinternalrqpypdfium2.versionr pypdfium2._helpers.miscr pypdfium2._helpers.pager pypdfium2._helpers.pageobjectsr pypdfium2._helpers.attachmentr getLoggerrro AutoCloseablerr rr AutoCastablerrr.r,r+rPs P  %%%%%%))))))//////++++++444444777777  8 $ $xHxHxHxHxH8)xHxHxHv"""4((<88888((888<-/-/-/-/-/8(-/-/-/`!!!!!x$!!!!!r,