j5jn1 dZddlmZddlZddlmZddlmZddlm Z m Z m Z ddl m Z ddlmZdd lmZmZmZmZmZdd lmZdd lmZdd lmZmZGd de ZGdde ZGdde ZGdde Z GddZ!GddZ"dZ#dZ$dddddddddZ%d$dZ&d%d Z'd!Z(eejRf d&d"Z*d'd#Z+y)(z"PDF content stream interpretation.) annotationsN) defaultdict)Mapping)hypotinfisclose) NamedTuple)warn)MatrixNameObjectPdfInlineImageparse_content_stream)InputFileError) Resolution) UNIT_SQUAREInkc:eZdZUdZded<ded<ded<ded <y ) XobjectSettingsz%Info about an XObject found in a PDF.strname/tuple[float, float, float, float, float, float] shorthandint stack_depthrfill_inkN__name__ __module__ __qualname____doc____annotations__U/var/www/html/qr/venv/lib/python3.12/site-packages/ocrmypdf/pdfinfo/_contentstream.pyrrs/ I>>Mr$rc:eZdZUdZded<ded<ded<ded <y ) InlineSettingsz*Info about an inline image found in a PDF.riimagerrrrrrNrr#r$r%r'r's4 >>Mr$r'cDeZdZUdZded<ded<ded<ded<d ed <y ) ContentsInfoz*Info about various objects found in a PDF.zlist[XobjectSettings]xobject_settingszlist[InlineSettings] inline_imagesbool found_vector found_textz#Mapping[str, list[XobjectSettings]] name_indexNrr#r$r%r*r*'s#4++''33r$r*c0eZdZUdZded<ded<ded<y) TextboxInfoz%Info about a text box found in a PDF.z!tuple[float, float, float, float]bboxr- is_visible is_corruptNrr#r$r%r2r21s/ ++r$r2ceZdZdZy) VectorMarkerzCSentinel indicating vector drawing operations were found on a page.Nrrr r!r#r$r%r7r79sMr$r7ceZdZdZy) TextMarkerzASentinel indicating text drawing operations were found on a page.Nr8r#r$r%r:r:=sKr$r:cjtt|}t|td}t d|DS)z?Check if the shorthand represents a unit square transformation.F)strictc3>K|]\}}t||dyw)MbP?)rel_tolN)r).0abs r% z"_is_unit_square..Es @tq!wq!T**@s)mapfloatziprall)rvaluespairwises r%_is_unit_squarerJAs-  "F6;u5H @x@ @@r$r>grayrgbcmyk) /DeviceGrayz/CalGrayz/G /DeviceRGBz/CalRGBz/RGB /DeviceCMYKz/CMYKcVt}|dk(r6t|dk(r(|d|krtjStjS|dk(rvt|dk(rh|\}}}t ||||krtjSt ||z |kr!t ||z |krtjStjS|dk(rYt|dk(rK|\}}}} ||kr/||kr*||kr%| |krtjStjStjStjS)zClassify a device-color fill into mono/gray/color. ``space`` is one of 'gray', 'rgb', 'cmyk'. Any other value is treated conservatively as color, since we cannot prove it is achromatic. rKrrLrM) _INK_EPSILONlenrmonorKmaxabscolor) spacecompsepsrgrBcmyks r%_ink_from_componentsrdYs C 3u:? 8s?sxx88 ~#e*/1a q!Q<3 88O q1u: QUs!288Oyy 3u:? 1a 8SQ#X Cx388 5SXX 5yy 99r$cj |Dcgc] }t|c}Scc}w#ttf$rYywxYw)aConvert color operands to floats, or None if any is non-numeric. Color operators in a malformed content stream may carry the wrong number of operands or a non-numeric operand (e.g. a Name). Returning None lets the caller keep the prior fill state instead of raising. N)rE TypeError ValueError)operandsos r%_operand_floatsrjqs6"*+Qa+++ z "s   22c#K|D]:\}}t|}tjd|r|D]}g|f 5||f<yw)z8Convert runs of qQ's in the stack into single graphobjs.zQ*q+$N)rrematch) graphobjsrhoperatorchars r%_normalize_stackrq~sW''(x= 88Hh '  !4j  !X& & 'sAAc~g}t|}|}d}g}g}td} d} d} tdj} tdj} tdj}tdj}dj | | z|z|z}t t t||D]1\}}|\}}|d k(rK|j|||ft|d kDs4t|d kDrtd |td \|dk(r |j\}}}w|dk(r t||z}|dk(rt!|x}st#d|}d}|dk(rt!|x}st#d|}d}|dk(rt!|x}st#d|}d}|dk(r$t$j&}|s t)|d}|dvrht+d|Drt$j,}Ct.j1|}t!|}||t$j,}yt#||}|dk(rW|d}t3||j4t|| }|j|| t)|j||d!k(r:|d}t7||j4t||"}|j|"|| vrd#} *|| vs0d#} 4t9||| | | $S#t$rtdY\wxYw#t$r}td|d}~wwxYw)%aBInterpret the PDF content stream. The stack represents the state of the PDF graphics stack. We track the current transformation matrix (CTM) and the current fill color (so that image masks, which are painted with the fill color, can be classified); a full implementation would need to track many other items. The CTM is initialized to the mapping from user space to device space. PDF units are 1/72". In a PDF viewer or printer this matrix is initialized to the transformation to device space. For example if set to (1/72, 0, 0, 1/72, 0, 0) then all units would be calculated in inches. Images are always considered to be (0, 0) -> (1, 1). Before drawing an image there should be a 'cm' that sets up an image coordinate system where drawing from (0, 0) -> (1, 1) will draw on the desired area of the page. PDF units suit our needs so we initialize ctm to the identity matrix. According to the PDF specification, the maximum stack depth is 32. Other viewers tolerate some amount beyond this. We issue a warning if the stack depth exceeds the spec limit and set a hard limit beyond this to bound our memory requirements. If the stack underflows behavior is undefined in the spec, but we just pretend nothing happened and leave the graphics state unchanged. rNcgSNr#r#r$r%z%_interpret_contents..sRr$FzS s f F f* B B* b b*z TJ Tj " 'zBI ID EI q Q Do cmzg rg k cs sc scn 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.Nr_rKrgrLrOrcrMrPcsr)scscnc3<K|]}t|tywrt) isinstancer )r@ris r%rCz&_interpret_contents..s91:a&9sDo)rrrrz INLINE IMAGE)r(rrrT)r+r,r.r/r0)r rsetsplitjoin enumeraterqrappendrV RuntimeErrorr pop IndexErrorrgrrjrdrrWranyrZ_DEVICE_FILL_SPACEgetrrr'r*) contentstreaminitial_shorthandinitial_fill_inkstackctmr fill_spacer+r,r0r.r/ vector_opstext_showing_ops image_ops color_opsoperator_whitelistngraphobjrhroevalsr[ image_namesettingsr(inlines r%_interpret_contentsrs: E " #CHJ.0*,MZ(JLJ+1134J?0023(..01I&,,./I*/?"?)"Ki"WX -m=OPQM 8&( s? LL#x4 55zBu:#&OPQsS?@ _ N,1IIK)Xz   X&, _&x00t0/=*  &x00t0/t<) _&x00t0/=*  xxH !-  &99999*..z:&x0=DL"yyH3E4@H  !!J&--J! H  # #H - s: ' . .x 8  'a[F#--J! F   (  #L ) )J[M^ )#!  A NLM N $W s*$L?L"LL" L<+ L77L<c |\}}}}}}t||t||f dd fdtdD\}}t||S)azGiven 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. c0|dk7r||z nt}||z}|S)Nr)r)drawnpixels inches_per_ptscaledpis r%calcz_get_dpi..calc@s""'1*#m# r$c3<K|]}||ywrtr#)r@rr image_drawn image_sizes r%rCz_get_dpi..Fs JADQA7Js)gR@)rranger) ctm_shorthandrrArBr`d_dpi_wdpi_hrrs ` @@r%_get_dpir sW\%Aq!Q11+uQ{*K KqJLE5 eU ##r$)r[rr\z list[float]returnr)rzlist[float] | None)rr )rr),r! __future__rrl collectionsrcollections.abcrmathrrrtypingr warningsr pikepdfr r r rrocrmypdf.exceptionsrocrmypdf.helpersrocrmypdf.pdfinfo._typesrrrr'r*r2r7r:rJrUrrdrjrqrWrrr#r$r%rs)" ##$$NN.'4jZ4:4*NNLLA     0 '.9388AAH:$r$