o UTiZ$Z%S)Arah Page helper class. Attributes: raw (FPDF_PAGE): The underlying PDFium page handle. pdf (PdfDocument): Reference to the document this page belongs to. formenv (PdfFormEnv | None): Formenv handle, if the parent pdf had an active formenv at the time of page retrieval. None otherwise. cs(||_||_||_ttj|jdSN)rawpdfformenvsuper__init__r _close_impl)selfr r r  __class__R/var/www/html/RAG/RAG_venv/lib/python3.10/site-packages/pypdfium2/_helpers/page.pyr "szPdfPage.__init__cCs|rt||t|dSr)pdfium_cFORM_OnBeforeClosePageFPDF_ClosePage)r r rrrr)s zPdfPage._close_implcCs|jSr)r rrrrparent0szPdfPage.parentcC t|S)z` Returns: float: Page width (horizontal size), in PDF canvas units. )rFPDF_GetPageWidthFrrrr get_width6 zPdfPage.get_widthcCr)z_ Returns: float: Page height (vertical size), in PDF canvas units. )rFPDF_GetPageHeightFrrrr get_height=rzPdfPage.get_heightcCs||fS)zb Returns: (float, float): Page width and height, in PDF canvas units. )rrrrrrget_sizeDzPdfPage.get_sizecCstjt|S)zO Returns: int: Clockwise page rotation in degrees. )pdfium_iRotationToDegreesrFPDFPage_GetRotationrrrr get_rotationNr zPdfPage.get_rotationcCst|tj|dS)z\ Define the absolute, clockwise page rotation (0, 90, 180, or 270 degrees). N)rFPDFPage_SetRotationr!RotationToConst)rrotationrrr set_rotationUzPdfPage.set_rotationc CsRttttf\}}}}||||||}|s|r|SdS|j|j|j|jfSr)c_floatvalue) rbox_func fallback_func fallback_okleftbottomrighttopokrrr_get_box\s zPdfPage._get_boxTcCs|tjdd|S)a Returns: (float, float, float, float) | None: The page MediaBox in PDF canvas units, consisting of four coordinates (usually x0, y0, x1, y1). If MediaBox is not defined, returns ANSI A (0, 0, 612, 792) if ``fallback_ok=True``, None otherwise. .. admonition:: Known issue Due to quirks in PDFium, all ``get_*box()`` functions except :meth:`.get_bbox` do not inherit from parent nodes in the page tree (as of PDFium 5418). cSdS)N)rridirrrrrpz&PdfPage.get_mediabox..)r4rFPDFPage_GetMediaBoxrr.rrr get_mediaboxes zPdfPage.get_mediaboxcCt|||||dS)zn Set the page's MediaBox by passing four :class:`float` coordinates (usually x0, y0, x1, y1). N)rFPDFPage_SetMediaBoxrlbrtrrr set_mediaboxrr)zPdfPage.set_mediaboxcC|tj|j|S)zc Returns: The page's CropBox (If not defined, falls back to MediaBox). )r4rFPDFPage_GetCropBoxr:r9rrr get_cropboxxzPdfPage.get_cropboxcCr;)z) Set the page's CropBox. N)rFPDFPage_SetCropBoxr=rrr set_cropboxr)zPdfPage.set_cropboxcCrC)zc Returns: The page's BleedBox (If not defined, falls back to CropBox). )r4rFPDFPage_GetBleedBoxrEr9rrr get_bleedboxrFzPdfPage.get_bleedboxcCr;)z* Set the page's BleedBox. N)rFPDFPage_SetBleedBoxr=rrr set_bleedboxr)zPdfPage.set_bleedboxcCrC)zb Returns: The page's TrimBox (If not defined, falls back to CropBox). )r4rFPDFPage_GetTrimBoxrEr9rrr get_trimboxrFzPdfPage.get_trimboxcCr;)z) Set the page's TrimBox. N)rFPDFPage_SetTrimBoxr=rrr set_trimboxr)zPdfPage.set_trimboxcCrC)za Returns: The page's ArtBox (If not defined, falls back to CropBox). )r4rFPDFPage_GetArtBoxrEr9rrr get_artboxrFzPdfPage.get_artboxcCr;)z( Set the page's ArtBox. N)rFPDFPage_SetArtBoxr=rrr set_artboxr)zPdfPage.set_artboxcCs4t}t||}|std|j|j|j|jfS)zz Returns: The bounding box of the page (the intersection between its media box and crop box). z Failed to get page bounding box.)rFS_RECTFFPDF_GetPageBoundingBoxrr/r0r1r2)rrectr3rrrget_bboxs  zPdfPage.get_bboxcCs.t|}|s tdt||}|||S)zY Returns: PdfTextPage: A new text page handle for this page. zFailed to load text page.)rFPDFText_LoadPagerr_add_kid)r raw_textpagetextpagerrr get_textpages   zPdfPage.get_textpagecCsN|jrtd|jr|j|jurtdt|||||_|j|_dS)a Insert a pageobject into the page. The pageobject must not belong to a page yet. If it belongs to a PDF, the target page must be part of that PDF. Position and form are defined by the object's matrix. If it is the identity matrix, the object will appear as-is on the bottom left corner of the page. Parameters: pageobj (PdfObject): The pageobject to insert. zAThe pageobject you attempted to insert already belongs to a page.zBThe pageobject you attempted to insert belongs to a different PDF.N)page ValueErrorr rFPDFPage_InsertObject_detach_finalizer)rpageobjrrr insert_objs   zPdfPage.insert_objcCs~|j|ur td|jdkr#|jdusJt|j|}d\|_|_n |jdus*Jt||}|s6tdd|_|dS)a# Remove a pageobject from the page. As of PDFium 5692, detached pageobjects may be only re-inserted into existing pages of the same document. If the pageobject is not re-inserted into a page, its ``close()`` method may be called. Note: If the object's :attr:`~.PdfObject.type` is :data:`FPDF_PAGEOBJ_TEXT`, any :class:`.PdfTextPage` handles to the page should be closed before removing the object. Parameters: pageobj (PdfObject): The pageobject to remove. z@The pageobject you attempted to remove is not part of this page.rN)rNzFailed to remove pageobject.) r^r_level containerrFPDFFormObj_RemoveObjectFPDFPage_RemoveObjectr_attach_finalizer)rrbr3rrr remove_objs    zPdfPage.remove_objcCst|}|s tddS)z Generate page content to apply additions, removals or modifications of pageobjects. If page content was changed, this function should be called once before saving the document or re-loading the page. z Failed to generate page content.N)rFPDFPage_GenerateContentr)rr3rrr gen_contents zPdfPage.gen_contentNrc cs|r tj}tj}|}ntj}tj}|}||}|dkr tdt|D];} ||| } | s1tdt| ||j||d} |rB| j |vrE| V| j tj kr_||dkr_|j ||| |ddEdHq$dS)a< Iterate through the pageobjects on this page. Parameters: filter (list[int] | None): An optional list of pageobject types to filter (:attr:`FPDF_PAGEOBJ_*`). Any objects whose type is not contained will be skipped. If None or empty, all objects will be provided, regardless of their type. max_depth (int): Maximum recursion depth to consider when descending into Form XObjects. Yields: :class:`.PdfObject`: A pageobject. rz$Failed to get number of pageobjects.zFailed to get pageobject.)r^r rerd)filter max_depthformrdN) rFPDFFormObj_CountObjectsFPDFFormObj_GetObjectFPDFPage_CountObjectsFPDFPage_GetObjectrrangerr typeFPDF_PAGEOBJ_FORM get_objects) rrnrorprd count_objects get_objectr n_objectsiraw_obj helper_objrrrrx s6   zPdfPage.get_objectscCs0|jstdt||}|tjkrtd|S)a Flatten form fields and annotations into page contents. Attention: * :meth:`~.PdfDocument.init_forms` must have been called on the parent pdf, before the page was retrieved, for this method to work. In other words, :attr:`.PdfPage.formenv` must be non-null. * Flattening may invalidate existing handles to the page, so you'll want to re-initialize these afterwards. Parameters: flag (int): PDFium flattening target (:attr:`FLAT_*`) Returns: int: PDFium flattening status (:attr:`FLATTEN_*`). :attr:`FLATTEN_FAIL` is handled internally. zHpage.flatten() requires previous pdf.init_forms() before page retrieval.z,Failed to flatten annotations / form fields.)r RuntimeErrorrFPDFPage_Flatten FLATTEN_FAILr)rflagrcrrrflatten>s    zPdfPage.flattenrm)rrrrFc st|} t|} |dvr| | } } fdd|D}| |d|d} | |d|d} tdd | | fDrGtd t|fi|\} }}}|d ur^|r^|tjO}|| | | |d }| |dd| | |d |d | | t j |f}||g||R}|d urtj |n,tj dd }t |ddd||}tjg|||R}|tjksJt||r|jrtj|jg|Rt|g|R|_|S)a Rasterize the page to a :class:`.PdfBitmap`. Parameters: scale (float): A factor scaling the number of pixels per PDF canvas unit. This defines the resolution of the image. To convert a DPI value to a scale factor, multiply it by the size of 1 canvas unit in inches (usually 1/72in). [#user_unit]_ rotation (int): Additional rotation in degrees (0, 90, 180, or 270). crop (tuple[float, float, float, float]): Amount in PDF canvas units to cut off from page borders (left, bottom, right, top). Crop is applied after rotation. may_draw_forms (bool): If True, render form fields (provided the document has forms and :meth:`~.PdfDocument.init_forms` was called). bitmap_maker (typing.Callable): Callback function used to create the :class:`.PdfBitmap`. fill_color (tuple[int, int, int, int]): Color the bitmap will be filled with before rendering. This uses RGBA syntax regardless of the pixel format used, with values from 0 to 255. If the fill color is not opaque (i.e. has transparency), ``{BGR,RGB}A`` will be used. grayscale (bool): If True, render in grayscale mode. optimize_mode (None | str): Page rendering optimization mode (None, "lcd", "print"). draw_annots (bool): If True, render page annotations. no_smoothtext (bool): If True, disable text anti-aliasing. Overrides ``optimize_mode="lcd"``. no_smoothimage (bool): If True, disable image anti-aliasing. no_smoothpath (bool): If True, disable path anti-aliasing. force_halftone (bool): If True, always use halftone for image stretching. limit_image_cache (bool): If True, limit image cache size. rev_byteorder (bool): If True, render with reverse byte order, leading to ``RGB{A/x}`` output rather than ``BGR{A/x}``. Other pixel formats are not affected. prefer_bgrx (bool): If True, use 4-byte ``{BGR/RGB}x`` rather than 3-byte ``{BGR/RGB}`` (i.e. add an unused byte). Other pixel formats are not affected. maybe_alpha (bool): If True, use a pixel format with alpha channel (i.e. ``{BGR/RGB}A``) if page content has transparency. This is recommended for performance in these cases, but as page-dependent format selection can be unexpected, it is not enabled by default. force_bitmap_format (int | None): If given, override automatic pixel format selection and enforce use of the given format (one of the :attr:`FPDFBitmap_*` constants). In this case, you should not pass any other format selection options, except potentially *rev_byteorder*. extra_flags (int): Additional PDFium rendering flags. May be combined with bitwise OR (``|`` operator). color_scheme (PdfColorScheme | None): A custom pdfium color scheme. Note that this may flatten different colors into one, so the usability of this is limited. fill_to_stroke (bool): If a *color_scheme* is given, whether to only draw borders around fill areas using the `path_stroke` color, instead of filling with the `path_fill` color. Returns: PdfBitmap: Bitmap of the rendered page. .. admonition:: Format selection This is the format selection hierarchy used by :meth:`.render`, from lowest to highest priority: * default: ``BGR`` * ``prefer_bgrx=True``: ``BGRx`` * ``grayscale=True``: ``L`` * ``maybe_alpha=True``: ``BGRA`` if the page has transparency, else the format selected otherwise * ``fill_color[3] < 255``: ``BGRA`` (background color with transparency) * ``force_bitmap_format=...`` -> any supported by pdfium Additionally, *rev_byteorder* will swap ``BGR{A/x}`` to ``RGB{A/x}`` if applicable. .. [#user_unit] Since PDF 1.6, pages may define an additional user unit factor. In this case, 1 canvas unit is equivalent to ``user_unit * (1/72)`` inches. PDFium does not currently provide an API to get the user unit, so this is not taken into account. )Zicsg|] }t|qSr)mathceil).0cscalerr sz"PdfPage.render..rrmcss|]}|dkVqdS)rmNr)rdrrr sz!PdfPage.render..zCrop exceeds page dimensionsN)format rev_byteorder)versionNeedToPauseNowcSr5)NFr)_rrrr6r7z PdfPage.render..)rrrranyr__parse_renderoptsrFPDF_CONVERT_FILL_TO_STROKE fill_rectr!r&FPDF_RenderPageBitmap IFSDK_PAUSE set_callbackconvert*FPDF_RenderPageBitmapWithColorScheme_StartFPDF_RENDER_DONEFPDF_RenderPage_Closer FPDF_FFLDrawweakrefref _pos_args)rrr'cropmay_draw_forms bitmap_maker color_schemefill_to_strokekwargs src_width src_heightwidthheight cl_formatr fill_colorflagsbitmappos_args render_argspausefpdf_csstatusrrrrenderXs8g         zPdfPage.render)T)NrlNr)&__name__ __module__ __qualname____doc__r staticmethodrpropertyrrrrr$r(r4r:rBrErHrJrLrNrPrRrTrXr]rcrirkrxrFLAT_NORMALDISPLAYrr new_nativer __classcell__rrrrrsL          ! 1rcCs:|ddks |rt|rtjS|rtjS|rtjStjS)Nr)rFPDFPage_HasTransparencyFPDFBitmap_BGRAFPDFBitmap_GrayFPDFBitmap_BGRxFPDFBitmap_BGR)r^r grayscale prefer_bgrx maybe_alpharrr_auto_bitmap_formatsrrrrrFTcCs| dur t|||| | }n| }|tjkrd} |}|r|tjO}|r&|tjO}|r-|tjO}|r4|tjO}|r;|tjO}|rB|tjO}| rI|tj O}| rP|tj O}|rq| }|dkr`|tj O}n|dkrj|tj O}ntd||| ||fS)NFlcdprintzInvalid optimize_mode )rrrFPDF_GRAYSCALE FPDF_ANNOTFPDF_RENDER_NO_SMOOTHTEXTFPDF_RENDER_NO_SMOOTHIMAGEFPDF_RENDER_NO_SMOOTHPATHFPDF_RENDER_FORCEHALFTONEFPDF_RENDER_LIMITEDIMAGECACHEFPDF_REVERSE_BYTE_ORDERlower FPDF_LCD_TEXT FPDF_PRINTINGr_)r^rr optimize_mode draw_annots no_smoothtextno_smoothimage no_smoothpathforce_halftonelimit_image_cacherrrforce_bitmap_format extra_flagsrrrrrrs<            rc@s(eZdZdZddZddZddZdS) rz Rendering color scheme. Each color shall be provided as a list of values for red, green, blue and alpha, ranging from 0 to 255. cCst||||d|_dS)N)path_fill_colorpath_stroke_colortext_fill_colortext_stroke_color)dictcolors)r path_fill path_stroke text_fill text_strokerrrr 1s zPdfColorScheme.__init__cCst|jd|jdS)Nz(**))rvrrrrrr__repr__7szPdfColorScheme.__repr__cCs4t}|jD]\}}t||t||q |S)z\ Returns: The color scheme as :class:`FPDF_COLORSCHEME` object. )rFPDF_COLORSCHEMEritemssetattrr! color_tohex)rrrkeyr+rrrr:szPdfColorScheme.convertN)rrrrr rrrrrrr+s  r)rFNTFFFFFFFFNr)__all__rctypesloggingr pypdfium2.rawr rpypdfium2.internalinternalr!pypdfium2._helpers.miscrpypdfium2._helpers.bitmaprpypdfium2._helpers.textpagerpypdfium2._helpers.pageobjectsrr* getLoggerrlogger AutoCloseablerrrrrrrrsD       S 9