o f@@sdZddlZddlmZmZddlmZddlmZddlm Z ddl m Z ddlmZddlmZddlmZzddlZWn eyIdZYnwGd d d e jZGd d d eZed dZGdddeZddZdddZddZdS)) PdfObjectPdfImageN)c_uintc_float)Path) namedtuple) PdfiumError) PdfMatrix) PdfBitmapcsZeZdZdZfddZdfdd Zedd Zd d Zd d Z ddZ ddZ Z S)ra Page object helper class. When constructing a :class:`.PdfObject`, an instance of a more specific subclass may be returned instead, depending on the object's :attr:`.type` (e. g. :class:`.PdfImage`). Attributes: raw (FPDF_PAGEOBJECT): The underlying PDFium pageobject handle. type (int): The object's type (:data:`FPDF_PAGEOBJ_*`). page (PdfPage): Reference to the page this pageobject belongs to. May be None if it does not belong to a page yet. pdf (PdfDocument): Reference to the document this pageobject belongs to. May be None if the object does not belong to a document yet. This attribute is always set if :attr:`.page` is set. level (int): Nesting level signifying the number of parent Form XObjects, at the time of construction. Zero if the object is not nested in a Form XObject. cs8t|}|tjkrtt}ntt}||_|SN)pdfium_cFPDFPageObj_GetTypeFPDF_PAGEOBJ_IMAGEsuper__new__rrtype)clsrawargskwargsrinstance __class__W/home/ubuntu/webapp/venv/lib/python3.10/site-packages/pypdfium2/_helpers/pageobjects.pyr-s   zPdfObject.__new__Nrcsf||||f\|_|_|_|_|dur&|jdur|j|_n |j|jur&tdtjtj|duddS)Nz;*page* must belong to *pdf* when constructing a pageobject.) needs_free) rpagepdflevel ValueErrorr__init__r FPDFPageObj_Destroy)selfrrrrrrrr 9s   zPdfObject.__init__cCs|jdur|jS|jSr rr)r"rrrparentFszPdfObject.parentcCs`|jdur tdttttf\}}}}t|||||}|s&td|j|j|j|jfS)z Get the position of the object on the page. Returns: A tuple of four :class:`float` coordinates for left, bottom, right, and top. Nz.Must not call get_pos() on a loose pageobject.zFailed to locate pageobject.)r RuntimeErrorrr FPDFPageObj_GetBoundsrvalue)r"lbrtokrrrget_posLs zPdfObject.get_poscCs*t}t||}|stdt|S)z\ Returns: PdfMatrix: The pageobject's current transform matrix. z#Failed to get matrix of pageobject.)r FS_MATRIXFPDFPageObj_GetMatrixrr from_raw)r" fs_matrixr,rrr get_matrix^s   zPdfObject.get_matrixcCst||}|s tddS)zs Parameters: matrix (PdfMatrix): Set this matrix as the pageobject's transform matrix. z#Failed to set matrix of pageobject.N)r FPDFPageObj_SetMatrixr)r"matrixr,rrr set_matrixjs zPdfObject.set_matrixcCstj|g|RdS)z Parameters: matrix (PdfMatrix): Multiply the page object's current transform matrix by this matrix. N)r FPDFPageObj_Transformget)r"r4rrr transformtszPdfObject.transform)NNr) __name__ __module__ __qualname____doc__rr propertyr$r-r2r5r8 __classcell__rrrrrs     rc@sjeZdZdZdZeddZddZddZdd d Z dddZ dddZ dddZ dddZ ddZd S)rzC Image object helper class (specific kind of page object). )ASCIIHexDecode ASCII85DecodeRunLengthDecode FlateDecode LZWDecodecCst|}||d|dS)a Parameters: pdf (PdfDocument): The document to which the new image object shall be added. Returns: PdfImage: Handle to a new, empty image. Note that position and size of the image are defined by its matrix, which defaults to the identity matrix. This means that new images will appear as a tiny square of 1x1 units on the bottom left corner of the page. Use :class:`.PdfMatrix` and :meth:`.set_matrix` to adjust size and position. Nr#)r FPDFPageObj_NewImageObj)rrraw_imgrrrnews z PdfImage.newcCs(t}t||j|}|std|S)aB Retrieve image metadata including DPI, bits per pixel, color space, and size. If the image does not belong to a page yet, bits per pixel and color space will be unset (0). Note: * The DPI values signify the resolution of the image on the PDF page, not the DPI metadata embedded in the image file. * Due to issues in PDFium, this function can be slow. If you only need image size, prefer the faster :meth:`.get_size` instead. Returns: FPDF_IMAGEOBJ_METADATA: Image metadata structure zFailed to get image metadata.)r FPDF_IMAGEOBJ_METADATAFPDFImageObj_GetImageMetadatarr)r"metadatar,rrr get_metadatas  zPdfImage.get_metadatacCs4tt}}t|||}|std|j|jfS)z .. versionadded:: 4.8/5731 Returns: (int, int): Image dimensions as a tuple of (width, height). zFailed to get image size.)rr FPDFImageObj_GetImagePixelSizerr')r"whr,rrrget_sizes  zPdfImage.get_sizeNFTc Cst|ttfrt|d}d}nt|dr|}ntd|dt|\}}|r,tj ntj }t |\} } || | ||} | sCt d|rX|D]} t | qG|rV|dSdS|jj|7_|rk|jj|dSdS)a Set a JPEG as the image object's content. Parameters: source (str | pathlib.Path | typing.BinaryIO): Input JPEG, given as file path or readable byte buffer. pages (list[PdfPage] | None): If replacing an image, pass in a list of loaded pages that might contain it, to update their cache. (The same image may be shown multiple times in different transforms across a PDF.) May be None or an empty sequence if the image is not shared. inline (bool): Whether to load the image content into memory. If True, the buffer may be closed after this function call. Otherwise, the buffer needs to remain open until the PDF is closed. autoclose (bool): If the input is a buffer, whether it should be automatically closed once not needed by the PDF anymore. rbTr*zCannot load JPEG from z" - not a file path or byte buffer.z&Failed to load JPEG into image object.N) isinstancestrropenpdfium_i is_bufferr get_bufreaderr FPDFImageObj_LoadJpegFileInlineFPDFImageObj_LoadJpegFile pages_c_arrayridcloser _data_holder _data_closerappend) r"sourcepagesinline autoclosebuffer bufaccessto_holdloaderc_pages page_countr,datarrr load_jpegs,    zPdfImage.load_jpegcCs.t|\}}t||||}|stddS)a Set a bitmap as the image object's content. The pixel data will be flate compressed (as of PDFium 5418). Parameters: bitmap (PdfBitmap): The bitmap to inject into the image object. pages (list[PdfPage] | None): A list of loaded pages that might contain the image object. See :meth:`.load_jpeg`. zFailed to set image to bitmap.N)rSrXr FPDFImageObj_SetBitmapr)r"bitmapr_rfrgr,rrr set_bitmaps  zPdfImage.set_bitmapcCsV|r|jdur tdt|j|j|}nt|}|dur&td|dt|S)a@ Get a bitmap rasterization of the image. Parameters: render (bool): Whether the image should be rendered, thereby applying possible transform matrices and alpha masks. Returns: PdfBitmap: Image bitmap (with a buffer allocated by PDFium). Nz0Cannot get rendered bitmap of loose page object.zFailed to get bitmap of image .) rr%r FPDFImageObj_GetRenderedBitmaprFPDFImageObj_GetBitmaprr r0)r"render raw_bitmaprrr get_bitmaps   zPdfImage.get_bitmapcCs8|rtjntj}||dd}tj|}|||||S)aS Parameters: decode_simple (bool): If True, apply simple filters, resulting in semi-decoded data (see :attr:`.SIMPLE_FILTERS`). Otherwise, the raw data will be returned. Returns: ctypes.Array: The data of the image stream (as :class:`~ctypes.c_ubyte` array). Nr)r FPDFImageObj_GetImageDataDecodedFPDFImageObj_GetImageDataRawctypesc_ubyte)r" decode_simplefuncn_bytesrbrrrget_datas    zPdfImage.get_datacCspg}t|}t|D]*}t||dd}t|}t|||||jd}|r0||jvr0q | |q |S)z Parameters: skip_simple (bool): If True, exclude simple filters. Returns: list[str]: A list of image filters, to be applied in order (from lowest to highest index). Nrzutf-8) r FPDFImageObj_GetImageFilterCountrangeFPDFImageObj_GetImageFilterrucreate_string_bufferr'decodeSIMPLE_FILTERSr])r" skip_simplefilterscountilengthrbfrrr get_filters s     zPdfImage.get_filterscOst|g|Ri|}t|}t|ttfr8t|d|d}||WddS1s1wYdSt|drE||dSt d|d)a Extract the image into an independently usable file or byte buffer. Where possible within PDFium's limited public API, it will be attempted to transfer the image data directly, avoiding an unnecessary layer of decoding and re-encoding. Otherwise, the fully decoded data will be retrieved and (re-)encoded using :mod:`PIL`. As PDFium does not expose all required information, only DCTDecode (JPEG) and JPXDecode (JPEG 2000) images can be extracted directly. For images with complex filters, the bitmap data is used. Otherwise, ``get_data(decode_simple=True)`` is used, which avoids lossy conversion for images whose bit depth or colour format is not supported by PDFium's bitmap implementation. Parameters: dest (str | io.BytesIO): File prefix or byte buffer to which the image shall be written. fb_format (str): The image format to use in case it is necessary to (re-)encode the data. fb_render (bool): Whether the image should be rendered if falling back to bitmap-based extraction. rmwbNrLzCannot extract to '') _extract_smartnextrPrQrrRsendrSrTr)r"destrrextraction_genformatbufrrrextract8s " zPdfImage.extract)NFTr )F)r9r:r;r<r classmethodrFrJrNrirlrrrzrrrrrrr~s   -    r ImageInfoz0format mode metadata all_filters complex_filtersc@s eZdZdS)ImageNotExtractableErrorN)r9r:r;rrrrr]srcCs:|tjkr |dkr dSdS|tjkrdS|tjkrdSdS)N1LRGBCMYK)r FPDF_COLORSPACE_DEVICEGRAYFPDF_COLORSPACE_DEVICERGBFPDF_COLORSPACE_DEVICECMYK) colorspacebpprrr _get_pil_modeas   rFc cszt|\}}Wnty|j|d}Yn#wd}|j}|dkr=|j}tj|j |j |j f|j ddd|j dd}|rL|rC|n|j dkrJdnd }|V}|rX|j ||d n ||dVdSdVdS) N)rprTrwrrrtiffpng)r)_extract_directrrrto_pilrrIPILImage frombuffermodewidthheightrzsavewrite) image_obj fb_format fb_renderrhinfo pil_imagerrIrbrrrrps.      rc Cs|}dd|D}|}t|j|j}t|dkr4|r'|jdd}d}nAtdtj |jdt|d kr`|d}|d krK|jdd}d }n|d krX|jdd}d }ntd|dtd|dt |||||}||fS)NcSsg|] }|tjvr|qSr)rr).0rrrr sz#_extract_direct..rTrrzUnhandled color space z - don't know how to treat data.r DCTDecodejpg JPXDecodejp2zUnhandled complex filter rmz'Cannot handle multiple complex filters ) rrJrrbits_per_pixellenrzrrSColorspaceToStrr7r) r all_filterscomplex_filtersrIrout_data out_formatrrrrrrs*     r)NF) __all__rurrpathlibr collectionsr pypdfium2.rawrr pypdfium2.internalinternalrSpypdfium2._helpers.miscrpypdfium2._helpers.matrixr pypdfium2._helpers.bitmapr PIL.Imager ImportError AutoCloseablerrr Exceptionrrrrrrrrs.         h ]