TAix%SrSSKJr SSKrSSKrSSKrSSKrSSKJr SSK J r J r J r J r JrJr SSKJrJr SSKJr SSKJrJr SS KJr SS KJrJrJr SS KJr SS K J!r! SS K"J#r# SSK$J%r% SSK&J'r'J(r( SSK)J*r*J+r+J,r,J-r-J.r.J/r/J0r0J1r1J2r2J3r3J4r4 SSK5J6r6J7r7 SSK8J9r9 SSK:J;r;Jr>J?r?J@r@ SSKAJBrBJCrCJDrDJErE \R"5rG"SS\5rH"SS\5rI\J\K\K\K\K4rL\HR\HR\HR\HR\HR\HR\HR\HR\HR\HR\HR\HR\HR\HR\HRS.rVS\WS'\IR\IR\IR\IR\IR\IR\IR\IR\IR\IR\IRS. raS\WS'\HRS \HRS!\HRS"\HRS!\HRS 0rbS#\WS$'S%rcS&rd"S'S(\#5re"S)S*\#5rf"S+S,\#5rg"S-S.\#5rh"S/S05ri"S1S25rjS3rk\c4SLS4jjrlSMS5jrm"S6S75rnSNS8jroSOS9jrpSPS:jrqSQS;jrrSS<.SRS=jjrsSSS>jrtSTS?jruSqvSUS@jrw\SVSAj5rxSWSCjrySXSYSDjjrz"SESF\#5r{"SGSB5r|\7"5r}"SHSI5r~SJr\SK:Xa\"5 gg)Zz/Extract information about the content of a PDF.) annotationsN) defaultdict)Callable ContainerIterableIteratorMappingSequence)contextmanager nullcontext)Decimal)Enumauto)partial)hypotinfisclose)PathLike)Path) NamedTuple)warn)LTPage LTTextBox) DictionaryMatrixNameObjectPagePdfPdfImagePdfInlineImageStreamUnsupportedImageTypeErrorparse_content_stream)ExecutorSerialExecutor) ProgressBar)EncryptedPdfErrorInputFileError) Resolutionavailable_cpu_countpikepdf_enable_mmap)LTStateAwareChar PdfMinerStateget_page_analysisget_text_boxesc\rSrSrSr\"5r\"5r\"5r\"5r \"5r \"5r \"5r \"5r \"5r\"5rSrg) Colorspace6z1Description of common image colorspaces in a PDF.N)__name__ __module__ __qualname____firstlineno____doc__rgrayrgbcmyklabiccindexsepdevnpatternjpeg2000__static_attributes__r4Q/var/www/html/land-ocr/venv/lib/python3.13/site-packages/ocrmypdf/pdfinfo/info.pyr2r26sM; 6D &C 6D &C &C FE &C 6DfGvHrEr2c\rSrSrSr\"5r\"5r\"5r\"5r \"5r \"5r \"5r \"5r \"5rSrg)EncodingFz/Description of common image encodings in a PDF.r4N)r5r6r7r8r9rccittjpegrCjbig2asciihexascii85lzwflate runlengthrDr4rErFrHrHFsF9 FE 6DvH FEvHfG &C FEIrErH)z /DeviceGrayz/CalGrayz /DeviceRGBz/CalRGBz /DeviceCMYKz/Labz /ICCBasedz/Indexedz /Separationz/DeviceNz/Patternz/Gz/RGBz/CMYKz/Izdict[str, Colorspace]FRIENDLY_COLORSPACE) z/CCITTFaxDecodez /DCTDecodez /JPXDecodez /JBIG2Decodez/CCFz/DCTz/AHxz/A85z/LZWz/Flz/RLzdict[str, Encoding]FRIENDLY_ENCODINGzdict[Colorspace, int] FRIENDLY_COMP)?rYrXrYrYcf[[U5n[U[5n[ SU55$)Nc3:# UHup[XSS9v M g7f)gMbP?)rel_tolN)r).0abs rF "_is_unit_square..s@xtqwqT*xs)mapfloatzip UNIT_SQUAREall) shorthandvaluespairwises rF_is_unit_squarerjs+  "F6;'H @x@ @@rEc8\rSrSr%SrS\S'S\S'S\S'S rg ) XobjectSettingsz%Info about an XObject found in a PDF.strname/tuple[float, float, float, float, float, float]rgint stack_depthr4Nr5r6r7r8r9__annotations__rDr4rErFrlrls/ I>>rErlc8\rSrSr%SrS\S'S\S'S\S'S rg ) InlineSettingsz*Info about an inline image found in a PDF.r!iimagerprgrqrrr4Nrsr4rErFrvrvs4 >>rErvcL\rSrSr%SrS\S'S\S'S\S'S\S 'S \S 'S rg ) ContentsInfoz*Info about various objects found in a PDF.zlist[XobjectSettings]xobject_settingszlist[InlineSettings] inline_imagesbool found_vector found_textz#Mapping[str, list[XobjectSettings]] name_indexr4Nrsr4rErFrzrzs#4++''33rErzc8\rSrSr%SrS\S'S\S'S\S'Srg ) TextboxInfoz%Info about a text box found in a PDF.z!tuple[float, float, float, float]bboxr~ is_visible is_corruptr4Nrsr4rErFrrs/ ++rErc\rSrSrSrSrg) VectorMarkerzCSentinel indicating vector drawing operations were found on a page.r4Nr5r6r7r8r9rDr4rErFrrsMrErc\rSrSrSrSrg) TextMarkerzASentinel indicating text drawing operations were found on a page.r4Nrr4rErFrrsKrErc## UHBup[U5n[R"SU5(aUH n/U4v M M=X4v MD g7f)z8Convert runs of qQ's in the stack into single graphobjs.zQ*q+$N)rnrematch) graphobjsoperandsoperatorchars rF_normalize_stackrsK'x= 88Hh ' ' 4j !& & (sA A cB/n[U5n/n/n[S5nSnSn[SR55n [SR55n [SR55n SR X-U -5n [ [ [X 555GH9upUunnUS:XaLURU5 [U5S:a*[U5S :a[S U 35e[S 5 M[M]US :XaUR5nMvUS:Xa[U5U-nMUS:XaSUSn[!UUR"[U5S9nURU5 U[%U5RU5 MUS:Xa7USn['UUR"[U5S9nURU5 GM#UU ;aSnGM.UU ;dGM7SnGM< [)UUUUUS9$![a [S 5 GMdf=f![a [S5ef=f)aInterpret the PDF content stream. The stack represents the state of the PDF graphics stack. We are only interested in the current transformation matrix (CTM) so we only track this object; a full implementation would need to track many other items. The CTM is initialized to the mapping from user space to device space. PDF units are 1/72". In a PDF viewer or printer this matrix is initialized to the transformation to device space. For example if set to (1/72, 0, 0, 1/72, 0, 0) then all units would be calculated in inches. Images are always considered to be (0, 0) -> (1, 1). Before drawing an image there should be a 'cm' that sets up an image coordinate system where drawing from (0, 0) -> (1, 1) will draw on the desired area of the page. PDF units suit our needs so we initialize ctm to the identity matrix. According to the PDF specification, the maximum stack depth is 32. Other viewers tolerate some amount beyond this. We issue a warning if the stack depth exceeds the spec limit and set a hard limit beyond this to bound our memory requirements. If the stack underflows behavior is undefined in the spec, but we just pretend nothing happened and leave the CTM unchanged. c/$Nr4r4rErF%_interpret_contents..sRrEFzS s f F f* B B* b b*z TJ Tj " 'zBI ID EI q Q Do cm q z5PDF graphics stack overflowed hard limit at operator z(PDF graphics stack overflowed spec limitQz5PDF graphics stack underflowed - PDF may be malformedcmzwPDF content stream is corrupt - this PDF is malformed. Use a PDF editor that is capable of visually inspecting the PDF.Dor)rorgrrz INLINE IMAGE)rxrgrrT)r|r}rrr)rrsetsplitjoin enumeraterr$appendlen RuntimeErrorrpop IndexError ValueErrorr)rlrgrnrvrz) contentstreaminitial_shorthandstackctmr|r}rrr vector_opstext_showing_ops image_opsoperator_whitelistngraphobjrr image_namesettingsrxinlines rF_interpret_contentsrsG4 E " #C.0*,MZ(JLJ+1134J?0023(..01I*"?)"KL -mPQ &( s? LL 5zBu:#&OPQsS?@  _ Niik   X&,  !!J&3==c%jH  # #H - s: ' . .x 8  'a[F#CJF   (  #L ) )JWZ )#!  = NLMM N $W sG+H+HHHc^^ ^ Uup#pE n[X#5[XE54m SSjm U U U4Sj[S55upx[Xx5$)aGiven the transformation matrix and image size, find the image DPI. PDFs do not include image resolution information within image data. Instead, the PDF page content stream describes the location where the image will be rasterized, and the effective resolution is the ratio of the pixel size to raster target size. Normally a scanned PDF has the paper size set appropriately but this is not guaranteed. The most common case is a cropped image will change the page size (/CropBox) without altering the page content stream. That means it is not sufficient to assume that the image fills the page, even though that is the most common case. A PDF image may be scaled (always), cropped, translated, rotated in place to an arbitrary angle (rarely) and skewed. Only equal area mappings can be expressed, that is, it is not necessary to consider distortions where the effective DPI varies with position. To determine the image scale, transform an offset axis vector v0 (0, 0), width-axis vector v0 (1, 0), height-axis vector vh (0, 1) with the matrix, which gives the dimensions of the image in PDF units. From there we can compare to actual image dimensions. PDF uses row vector * matrix_transposed unlike the traditional matrix * column vector. The offset, width and height vectors can be combined in a matrix and multiplied by the transform matrix. Then we want to calculated magnitude(width_vector - offset_vector) and magnitude(height_vector - offset_vector) When the above is worked out algebraically, the effect of translation cancels out, and the vector magnitudes become functions of the nonzero transformation matrix indices. The results of the derivation are used in this code. pdfimages -list does calculate the DPI in some way that is not completely naive, but it does not get the DPI of rotated images right, so cannot be used anymore to validate this. Photoshop works, or using Acrobat to rotate the image back to normal. It does not matter if the image is partially cropped, or even out of the /MediaBox. c.US:waX- O[nX2-nU$)Nr)r)drawnpixels inches_per_ptscaledpis rFcalc_get_dpi..calcMs"'1*## rEc3B># UHnT"TUTU5v M g7frr4)r]rr image_drawn image_sizes rFr`_get_dpi..Ss#JADQA77s)R@)rranger*) ctm_shorthandrr^r_cd_dpi_wdpi_hrrs ` @@rF_get_dpirsK\%A!1+uQ{*K KqJLE e ##rEc0\rSrSr%Sr\"S5rS\S'S\S'SS S S S .SS jjrSS jr \ S 5r \ S5r \ SSj5r \ SSj5r\ S5r\ S5r\ S5r\ S5r\ SSj5r\ SSj5r\ SSj5rSrSrg ) ImageInfoiWzInformation about an image found in a PDF. This gathers information from pikepdf and pdfminer.six, and is pickle-able so that it can be passed to a worker process, unlike objects from those libraries. z1.000 int | None_comprn_nameN)ropdfimagerrgc[U5UlX@lUb SUlUnO6Ub([ U[ 5(aSUl[ U5nO [S5eURUl URUl URR[RS5=nb[ U[ [ -5(ar[#UR[R$S5UR5Ul [#UR[R&S5UR5Ul URR[R(S5=nb[ U[ [ -5(ar[#UR[R$S5UR5Ul [#UR[R&S5UR5Ul UR*(aSUlOSUl[/UR05Ul[4RUR6S5Ul[<RUR>=(d S5Ul UR8[DRF:Xa[HRFUl SUl%UR@[HRL:Xa,[ U[ 5(aUROU5Ul%g[ UR@[H5(a$[PRUR@5Ul%URJcLUR8[DRR[DRT4;a[P[HRVUl%ggg![:a SUlGNcf=f![Ba SUl GNMf=f) zInitialize an ImageInfo.Nrxobjectz%Either pdfimage or inline must be setrstencilimager),rnr _shorthand_origin isinstancer"r rwidth_widthheight_heightobjgetrSMaskrmaxWidthHeightMask image_mask_typerqbits_per_component_bpcrSfilters_encrrR colorspace_colorNotImplementedErrorrHrCr2rr> _init_iccrWrJrLr:)selfrorrrgpimsmaskmasks rF__init__ImageInfo.__init__dsY #  #DLC  !j6&B&B$DL8$CDE Eii zz WW[[T2 2E ? %*!455!%))DJJ":DKKH "599T[[!#>"DJ DJ../  )--ckk!n=DI -11#..2FBGDK 99)) )$--DK ;;*.. (ZX-F-F,DJ$++z22*..t{{; zz!diiHNNHNN3S&S*:??; 'T!% DI  # DK s$-'N#-N;#N87N8;OOcjURnUb[ US5(d[RSU35 gUR R S:XagUR R S:Xagg ![a%n[RSUSU35 SnAgSnAff=f![a gf=f) NznAn image with a corrupt or unreadable ICC profile was found. Output PDF may not match the input PDF visually: z. profilezuAn image with an ICC profile but no ICC profile data was found. The output PDF may not match the input PDF visually. GRAYrTCMYKrVrU)r>r#loggerwarninghasattrr xcolor_spaceAttributeError)rrr>es rFrImageInfo._init_iccs ''C ;gc955 NNHHLvO  {{''61))V3')  NNDDE3bP   (  s. A3B%B%3 B"=BB"% B21B2cUR$)z+Name of the image as it appears in the PDF.)rrs rFroImageInfo.namezzrEcUR$)z+Type of image, either 'image' or 'stencil'.)rrs rFtype_ImageInfo.type_r rEcUR$)zWidth of the image in pixels.)rrs rFrImageInfo.width{{rEcUR$)zHeight of the image in pixels.)rrs rFrImageInfo.height||rEcUR$)zBits per component.)rrs rFbpc ImageInfo.bpcsyyrEc8URb UR$S$)zColorspace of the image.?)rrs rFcolorImageInfo.colors#kk5t{{>3>rEc8URb UR$S$)z+Number of components/channels in the image.r)rrs rFcompImageInfo.comps"ZZ3tzz<w>rEcURR=(a; URS:=(a% URS:=(a URS:g$)zWhether the image is renderable. Some PDFs in the wild have invalid images that are not renderable, due to unusual dimensions. Stencil masks are not also not renderable, since they are not drawn, but rather they control how rendering happens. rr)r is_finiterrr rs rF renderableImageInfo.renderablesJ HH   ( a ( q  ( i'  rEcZ[URURUR45$)z^Dots per inch of the image. Calculated based on where and how the image is drawn in the PDF. )rrrrrs rFr ImageInfo.dpis" $++t||)DEErEcUR(dg[URURR- UR URR - -5$)z,Physical area of the image in square inches.rY)r"rcrrxryrs rF printed_areaImageInfo.printed_area s@djj488::-$++ 2JKLLrEcSURSURSURSURSURSUR SUR SURSURS3$)z,Return a string representation of the image.z ) ror rrrrrrrrs rF__repr__ImageInfo.__repr__sm499+R |1TZZL4;;-qzzl!DII;az488*AdhhZq J rE) rrrrrrrrrr)rz Object | NonerzPdfInlineImage | None)rr returnrqr1r~r1r*)r1rc)r5r6r7r8r9r DPI_PRECrtrrpropertyror rrrrrrr"rr)r.rDr4rErFrrWs3wH  J "&(, I< I< & I.>v}}  ;sAAc#h# [RU;agU[Rn[RU;agU[RR5HLup#Ub[RU;aMU[R[R :XdMEUnXB4v MN g7f)aSearch for all XObject-based images in the container. Usually the container is a page, but it could also be a Form XObject that contains images. Filter out the Form XObjects which are dealt with elsewhere. Generate a sequence of tuples (image, xobj container), where container, where xobj is the name of the object and image is the object itself, since the object does not know its own name. N)r ResourcesXObjectitemsSubtypeImage) container resourceskey candidaters rF_image_xobjectsrD!s ~~Y&$..)I ||9$#DLL1779   I =  T\\ "djj 0 H/ ! :s B B2& B2c## [U5Hxup#X1R;aMURUHOnURS:Xa[UR5(aM/[ UR X$RS9v MQ Mz g7f)zFind images stored in the container's /Resources /XObject. Usually the container is a page, but it could also be a Form XObject that contains images. Generates images with their DPI at time of drawing. r)rorrgN)rDrrrrjrgrro)r@r8rxobjdraws rF_find_regular_imagesrH:sr*)4 .. .  ++D1D1$)H)H XX X25sB B c## [RU;agU[Rn[RU;agU[RR5nUHnXEnUb1UR [R 5[R :waM=UnURH3nURU:waMURn [XU S9ShvN M5 M gN 7f)zuFind any images that are in Form XObjects in the container. The container may be a page, or a parent Form XObject. Npdfr@rg) rr;r<as_dictrr>Formr|rorg_process_content_streams) rKr@r8rAxobjsrFrC form_xobjectrrs rF_find_form_xobject_imagesrQSs  ~~Y&$..)I ||9$ dll # + + -EK   dll ;tyy H  $55H}}$ %..M/=  6  sCC,C*C,)rgc#.# UR[R5[R:Xa$[RU;aU=(d [ nOUR[R5[R :XaU[R[R:Xa`U(a [U5O [5nUR[R[55n[U5nXd-nURnOg[X5nUR(a [5v UR(a [5v [!U5ShvN [#X5ShvN [%XU5ShvN gN,NN 7f)aFind all individual instances of images drawn in the container. Usually the container is a page, but it may also be a Form XObject. On a typical page images are stored inline or as regular images in an XObject. Form XObjects may include inline images, XObject images, and recursively, other Form XObjects; and also vector graphic objects. Every instance of an image being drawn somewhere is flattened and treated as a unique image, since if the same image is drawn multiple times on one page it may be drawn at differing resolutions, and our objective is to find the resolution at which the page can be rastered without downsampling. N)rrTyperContentsrer<r>rMrrgrrrrrr9rHrQ)rKr@rgrrform_shorthand form_matrixr8s rFrNrNss(}}TYY499,)1K%4 dii DLL0 dll #tyy 0$-fY&(#t{{FH=^, MM&yDL  nl"<000#I<<<(FFF1<Fs6E F"F#F5F6F F FFFc[U5[U5pCSnXS-SU- U-SU- U-XT-4nSSjnSnUHn U"X5(dMSn U$ U$)z4Smarter text detection that ignores text in margins.g?rTcUSUS:=(a/ USUS:=(a USUS:=(a USUS:$)zCheck if two 4-tuple rects intersect. Where (a,b) are 4-tuple rects (left-0, top-1, right-2, bottom-3) https://stackoverflow.com/questions/306316/determine-if-two-rectangles-overlap-each-other Formula assumes all boxes are in first quadrant. rrrTrUr4)r^r_s rFrects_intersect'_page_has_text..rects_intersectsItad{Jqtad{Jqtad{Jqtad{JrEFT)r^ FloatRectr_r[r1r~)rc) text_blocks page_width page_heightpwph margin_ratio interior_bboxrYhas_textrs rF_page_has_textrds{ : k 2L \ R \ R MKH 4 / /H  O  OrEc## U"U5HrnURSnURSn[U[5(dM8URS:gnUR 5S:Hn[ UR XV5v Mt g7f)zuExtract only limited content from text boxes. We do this to save memory and ensure that our objects are pickleable. rrUu�N)_objsrr- rendermodeget_textrr) miner_pagetextbox_getterbox first_line first_charvisiblecorrupts rFsimplify_textboxesrpsxj)YYq\ %%a( *&677 ''1,%%'83#((G55*sBBc[5 [R"S5RU5 Uc0[R "U5qSn[R"U5 gg)Npdfminerc,[R5 gr) worker_pdfcloser4rErFon_process_close1_pdf_pageinfo_sync_init..on_process_closes    rE) r,logging getLoggersetLevelropenrtatexitregister)rKinfilepdfminer_loglevelrvs rF_pdf_pageinfo_sync_initrsP j!**+<= {XXf%   ()rEc## UbUv g[b [v g[R"U5nUv SSS5 g!,(df  g=f7fr)rtrr{) thread_pdfr~rKs rF_pdf_pageinfo_sync_pdfrs;   XXf I  s/A? A A  APageInfoc h[X5n[X`X#XE5sSSS5 $!,(df  g=fr)rr)pagenorr~ check_pagesdetailed_analysis miner_staterKs rF_pdf_pageinfo_syncrs* 3s .?  4 3 3s # 1c p^^^^^ ^S/[UR5-mSU4Sjjn Uc [5n[UR5n [S[T5S--U5n U S:XaSnU(aU S:aSn U(aUOSm UUUU U4Sj[ U 55n U(a U S:XdS5eU S:dS5e[ R SU S 3U(aS OS -S -5 U"UU [U S SU(+S9[[T T[R"S5R5[U U S9 T$)Npagech>U(d [S5eUTUR'UR5 g)NzCould read a page in the PDF)r)rupdate)rpbarpagess rFupdate_pageinfo1_pdf_pageinfo_concurrent..update_pageinfos) !?@ @!dkk rErTrVTc34># UH nUTTTTT4v M g7frr4)r]rrrr~ initial_pdfrs rFr`+_pdf_pageinfo_concurrent..+s&A K.?MszNot multithreadablezGathering info with rthreadprocessz workerszScanning contents)totaldescunitdisablerr) use_threads max_workersprogress_kwargsworker_initializertasktask_arguments task_finished)rrrr')rrr+minrrdebugdictrrrxrylevelr)rKexecutorrrr~progbarrrrrr n_workerscontextsrrs ` ``` @@rF_pdf_pageinfo_concurrentrsG%)6C N#:E )+  NEAE a'5IA~ y1} %#$KuH)9>S>SS SS < LL yk+"8  3    1G  # #     j ) / /   % LrEcH\rSrSr%SrS\S'S\S'S\S'S\S'Srg ) PageResolutionProfileiHz,Information about the resolutions of a page.rc weighted_dpimax_dpiaverage_to_max_dpi_ratio area_ratior4Nrsr4rErFrrHs.6S N2##rErc\rSrSr%SrS\S'S\S'/rS\S'S S!S jjrS!S jr\ S"S j5r \ S#S j5r \ S#S j5r \ S#Sj5r \ S$Sj5r\ S$Sj5r\ S"Sj5r\ S"Sj5r\ S"Sj5r\R&S5r\ S%Sj5r\ S%Sj5r\ S%Sj5r\ S&Sj5rS'S(Sjjr\ S)Sj5r\ S$Sj5r\ S*Sj5rS+SjrSrSrg),ribz9Information about type of contents on each page in a PDF. bool | None _has_text _has_vectorlist[ImageInfo]_imagesNcNX lX0lXPlURXX4XV5 g)zInitialize a PageInfo object.N)_pageno_infile_detailed_analysis_gather_pageinfo)rrKrr~rrrs rFrPageInfo.__init__is*  "3  .? rEcjURUnURR5Vs/sHn[U5PM n nU SU S- n U SU S- n URR5Vs/sHn[ U5PM snUlURR5Vs/sHn[ U5PM snUlURR5Vs/sHn[ U5PM snUl X$;n U (afU(a_URU5n U b[[U [55UlO/UlSUR5n[XU 5UlO/UlSUlUR#[$R&[S55n[)U[5(d [U5nXlX-[S5- UlX-[S5- Ul[1[3UR4SS55UlUSSUSS4nU (aS UlS Ul/Ul[=XUS 9Hyn[)U[>5(a S UlM![)U[@5(a S UlM?[)U[B5(aUR:REU5 Mq[G5e OSUlSUl/UlSUl$UR:(a[KS S 5RMS UR:55nUUl$[1[OURP[ UR,5-55Ul)[1[OURT[ UR.5-55Ul+ggs snfs snfs snfs snf)NrrrUrTc38# UHoRv M g7frr)r]rks rFr`,PageInfo._gather_pageinfo..s:/3hh/rXrRotateFrJTrYc3^# UH#oR(dMURv M% g7fr)r"r)r]rs rFr`rs0'3e7G7G  |s--),rmediaboxas_listr cropboxrc_cropbox _mediaboxtrimbox_trimboxr/listrpr0 _textboxesrdrrrUserUnitr _userunit _width_inches_height_inchesrqgetattrr_rotaterrrNrrrrr_dpir*take_maxroundr' _width_pixelsr(_height_pixels)rrKrr~rrrrrrwidth_pt height_ptcheck_this_page page_analysisbboxesuserunituserunit_shorthandinfors rFrPageInfo._gather_pageinfozs YYv&(, (=(=(?@(?1GAJ(?@A;!,QK(1+- ,0<<+?+?+AB+Aaq+AB ,0MM,A,A,CD,Cq%(,CD+/<<+?+?+AB+Aaq+AB  / 0'99&AM("&&}nE##%:$//:F+FiHDN DO!DN88DMM73<8(G,,x(H!%074=@'2WT]B7488Xq9: &1h1= $D "DNDL03EdL11'+D$j11%)DNi00LL''--// $D !DNDL <<S#&//0'+||0CDI!$U35559K9K3L+L%M!ND "%eCEEE$:M:M4N,N&O"PD  uA CDBsN!5N&.N+'N0cUR$)zReturn page number (0-based).)rrs rFrPageInfo.pagenorrEc,[UR5$)z6Return True if page has text, False if not or unknown.)r~rrs rFrcPageInfo.has_textsDNN##rEcrUR(d [S5e[SUR55$)z>Return True if page has corrupt text, False if not or unknown.zDid not do detailed analysisc38# UHoRv M g7fr)r)r]tboxs rFr`,PageInfo.has_corrupt_text..s?t??r)rranyrrs rFhas_corrupt_textPageInfo.has_corrupt_texts.&&%&DE E?t???rEc,[UR5$)zReturn True if page has vector graphics, False if not or unknown. Vector graphics are sometimes used to draw fonts, so it may not be obvious on visual inspection whether a page has text or not. )r~rrs rF has_vectorPageInfo.has_vectorsD$$%%rEcUR$)zReturn width of page in inches.)rrs rF width_inchesPageInfo.width_inches!!!rEcUR$)z Return height of page in inches.)rrs rF height_inchesPageInfo.height_inches"""rEc~[[[UR5URR -55$)zReturn width of page in pixels.)rqrrcrrr'rs rF width_pixelsPageInfo.width_pixelss,5t001DHHJJ>?@@rEc~[[[UR5URR -55$)z Return height of page in pixels.)rqrrcrrr(rs rF height_pixelsPageInfo.height_pixelss,5t112TXXZZ?@AArEcUR$)zDReturn rotation of page in degrees. Will only be a multiple of 90. )rrs rFrotationPageInfo.rotations ||rEc2US;aXlg[S5e)N)rZiihiiLiz!rotation must be a cardinal angle)rr)rvalues rFrrs ; ; L@A ArEcUR$)z*Return cropbox of page in PDF coordinates.)rrs rFrPageInfo.cropbox}}rEcUR$)z+Return mediabox of page in PDF coordinates.)rrs rFrPageInfo.mediabox~~rEcUR$)z*Return trimbox of page in PDF coordinates.)rrs rFrPageInfo.trimbox rrEcUR$)zReturn images.)rrs rFimagesPageInfo.imagesrrEc^^^SSjmUR(dTbTb [S5eUR$UUU4SjUR5$)z?Return textareas bounding boxes in PDF coordinates on the page.c^SnUbURU:waSnUbURU:waSnU$)NTF)rr)r want_visible want_corruptresults rF predicate)PageInfo.get_textareas..predicates<F'>>\1"F'>>\1"FMrEz#Incomplete information on textboxesc3^># UH"nT"UTT5(dMURv M$ g7frr)r]rrorrns rFr`)PageInfo.get_textareas..+s"XOSygw7WOs--)rrrrrrr1r~)rr)rrnrors ``@rF get_textareasPageInfo.get_textareassa  ,7 GR   "w':)*OPP?? "XDOOXXrEcLURc [SS5$UR$)z3Return DPI needed to render all images on the page.rY)rr*rs rFr PageInfo.dpi-s% 99 c3' 'yyrEcUR$)zReturn user unit of page.)rrs rFrPageInfo.userunit4r rEc URbgg)z6Return minimum PDF version needed to render this page.z1.6z1.5rrs rF min_versionPageInfo.min_version9s == $rEc/n/nURHZnUR(dMURURR 55 URUR 5 M\ [ U5nUS:XagUVs/sHoUU- PM nn[R"X5n[U5nXx- n URU5n X*U- n [UUU U 5$s snf)a|Return information about the DPIs of the page. This is useful to detect pages with a small proportion of high-resolution content that is forcing us to use a high DPI for the whole page. The ratio is weighted by the area of each image. If images overlap, the overlapped area counts. Vector graphics and text are ignored. Returns None if there is no meaningful DPI for the page. rN) rr"rr to_scalarr)sum statistics harmonic_meanrr?r) r image_dpis image_areasrtotal_drawn_areaareaweightsrrdpi_average_max_ratio arg_max_dpimax_area_ratios rFpage_dpi_profilePageInfo.page_dpi_profileAs  \\E##   eii113 4   u11 2 " {+ q 7BC{t**{C!// D j/ , 6 &&w/ $14DD$   !    DsC c SURSURSURSURSURSUR S3 $)Return string representation.zAcroFormrFieldsr<XFAr~SigFlagsr=MarkInfoMarked _is_tagged) rr~rrrrrrrK pscript5_moders rFrPdfInfo.__init__s  =1K XXf '))  b ABMMM %f4 ]   ""k6 +&7 +  #%(HHLL1D1De$LD !}}(sxx((,,T[["=>B)-D&XX!2!22)-D&&*388+<+<+@+@PQ+RUV+V&W#" T]]B/33DKKGDO= #" s%B I7H?E(I? I I IcUR$)z9Return list of PageInfo objects, one per page in the PDF.rFrs rFr PdfInfo.pagesrrEc:[SUR55$)z5Return minimum PDF version needed to render this PDF.c3J# UHo(dM URv M g7fr)r!r]rs rFr`&PdfInfo.min_version..sC d#4## s ##)rrrs rFr!PdfInfo.min_versionsC CCCrEc:[SUR55$)z(Return True if any page has a user unit.c3P# UHo(dM URS:gv M g7f)rXNr rWs rFr`'PdfInfo.has_userunit..sGJD$'4==C'Js &&)rrrs rF has_userunitPdfInfo.has_userunitsGDJJGGGrEcUR$)z4Return True if the document catalog has an AcroForm.)r<rs rF has_acroformPdfInfo.has_acroformrrEcUR$)z@Return True if the document annotations has a digital signature.)r=rs rF has_signaturePdfInfo.has_signaturerrEcUR$)zCReturn True if the document catalog indicates this is a Tagged PDF.)rOrs rF is_taggedPdfInfo.is_taggedsrEc|[UR[[-5(d [ S5eUR$)zReturn filename of PDF.zcan't get filename from stream)rrrnrrrs rFfilenamePdfInfo.filenames/$,,d 33%&FG G||rEcUR$)zReturn True if PDF contains XFA forms. XFA forms are not supported by most standard PDF renderers, so we need to detect and suppress them. )r>rs rFneeds_renderingPdfInfo.needs_renderings$$$rEc URU$)z.Return PageInfo object for page number `item`.rS)ritems rF __getitem__PdfInfo.__getitem__s{{4  rEc,[UR5$)zReturn number of pages in PDF.)rrFrs rF__len__PdfInfo.__len__s4;;rEc S[U5S3$)r3zrF) r~rrr~rr~rrrr~rr%)r1Sequence[PageInfo | None]r8r2)r1z str | Path)r1r)r5r6r7r8r9r<rtr=r>DEFAULT_EXECUTORrr5rr!r]r`rcrfrirlrprsr.rDr4rErFr;r;ts/  M4 ND "d" #("& -00 0  0  000dDD HH""## %%! ;rEr;c SSKnSSKJn UR5nURS5 UR 5n[ UR 5nU"U5 URH&nU"U5 URH nU"U5 M M( g)zRun as a script.rN)pprintr~) argparserzArgumentParser add_argument parse_argsr;r~rr)r{rzparserargspdfinforims rFmainrsq  $ $ &F !    Ddkk"G 7O t ++B 2JrE__main__)rrr3)r8rzr1Iterator[ImageInfo])r1zIterator[tuple[Object, str]])r@rr8rzr1r)rKrr@rr8rz)rKrr@rr1z/Iterator[VectorMarker | TextMarker | ImageInfo])r\zIterable[FloatRect]r1r~)rirrjz'Callable[[LTPage], Iterator[LTTextBox]]r1zIterator[TextboxInfo])rKrr~r)r Pdf | Noner~r)rrqrrr~rrr6rr~rr7r1rr5) rr%rrqrr~rr~rr7r1rw)r9 __future__rr|rxrr& collectionsrcollections.abcrrrrr r contextlibr r decimalr enumrr functoolsrmathrrrosrpathlibrtypingrwarningsrpdfminer.layoutrrpikepdfrrrrrrr r!r"r#r$ocrmypdf._concurrentr%r&ocrmypdf._progressbarr'ocrmypdf.exceptionsr(r)ocrmypdf.helpersr*r+r,ocrmypdf.pdfinfo.layoutr-r.r/r0ryrr2rHtuplercr[r:r;r<r=r>r?r@rArBrRrtrJrKrCrLrMrNrOrPrQrSrWrerjrlrvrzrrrrrrrr9rDrHrQrNrdrprtrrrrrrrxr;rr5r4rErFrs 6"  #VV2$$-    :-AQQ       t  %u, - ??..~~?? NN  >>"" // NN __   .*& ~~--##NN NN MM       LL >>    *& OOQNNAOOQNNAa ( $- A jZ4:4*NNLL'BMYx:$z  D "2YY%1YY2B/32G 2G"2G42Gj:66(O66" *"             &    ,$(,BBB BB&BBJJ4L L ^"#v;v;r" zFrE