a cfyW@sUdZdZdZddlZddlZddlZddlZddlZddlm Z ddl m Z m Z ddl m Z mZddlmZdd lmZmZmZmZmZmZmZmZmZmZejdd d krdd lmZn dd lmZd dlm Z m!Z!m"Z"eee#e#e#fee#e#e#fee#e#e#ffZ$ee%d<ee#e#e#e#e#e#fZ&ee%d<eeZ'ee(e'fZ)ee(ee dddZ*e(e(e(dddZ+die'ee,e-dddZ.e'e-dddZ/e'e0dddZ1e-e0dd d!Z2e'ddd"d#Z3e'ee-e-d$d%d&Z4e'e,e-d'd(d)Z5e'e-dd*d+Z6e$e$e$d,d-d.Z7e'ddd/d0Z8iZ9eee(e-fe-fe%d1<ee(e-fe-d2d3d4Z:ee(d5d6d7Z;ee(e,d5d8d9Z>e=Z?d?e?d@Z@e,e,e,e,dAdBdCZAdje(e,ddEdFdGZBe(ddHdIdJZCe(e(e(ddKdLdMZDe(e(e(ddKdNdOZEe(e(ddPdQdRZFe(e(ddPdSdTZGe(e(ddUdVdWZHe(e(ddUdXdYZIdke(ee(efee(e(fe0dd[d\d]ZJe,e(d^d_d`ZKGdadbdbZLe GdcddddZMe GdedfdfeMZNejOGdgdhdhZPdS)lz"Utility functions for PDF library.zMathieu Fenniakzbiziqe@mathieu.fenniak.netN) dataclass)datetimetimezone)DEFAULT_BUFFER_SIZEBytesIO)SEEK_CUR) IOAnyDictListOptionalPatternTupleUnioncastoverload) ) TypeAlias)STREAM_TRUNCATED_PREMATURELYDeprecationErrorPdfStreamErrorTransformationMatrixTypeCompressedTransformationMatrix)textreturnc Cs|}|durdS|dr$d|}|dr6|d7}|dddddd }t|d|d }|dkr|t|d kr|d 7}d D]L}zt||}WntyYqYq0|dr|jt j d}|Sqtd|dS)NrzD:)ZzZ0000r+r'-Z00)zD:%YzD:%Y%mzD:%Y%m%dz D:%Y%m%d%Hz D:%Y%m%d%H%MzD:%Y%m%d%H%M%SzD:%Y%m%d%H%M%S%zz+0000)tzinfozCan not convert date: ) isdigitendswithreplacemaxfindlenrstrptime ValueErrorrutc)rZorgtextifdr2I/home/httpd/docs/test/DocsMgr/lib/python3.9/site-packages/pypdf/_utils.pyparse_iso8824_dateMs(       r4)header1header2rcCsfd}g}||vr |||||vr8|||t|dkrZtd|d|d|t|S)N)z%PDF-1.3z%PDF-1.4z%PDF-1.5z%PDF-1.6z%PDF-1.7z%PDF-2.0rzneither z nor z are proper headers)appendindexr+r-r))r5r6versionsZpdf_header_indicesr2r2r3_get_max_pdf_version_headerms r:)streammaxcharsrcCs8d}|d}|s4|sq4||7}t||krq4q|S)a; Read non-whitespace characters and return them. Stops upon encountering whitespace or when maxchars is reached. Args: stream: The data stream from which was read. maxchars: The maximum number of bytes returned; by default unlimited. Returns: The data which was read. r)readisspacer+)r;r<txttokr2r2r3read_until_whitespaces    rB)r;rcCs"|d}|tvr|d}q |S)z Find and read the next non-whitespace character (ignores whitespace). Args: stream: The data stream from which was read. Returns: The data which was read. r)r> WHITESPACESr;rAr2r2r3read_non_whitespaces  rEcCs0td}d}|tvr(|d}|d7}q |dkS)a Similar to read_non_whitespace, but return a boolean if more than one whitespace character was read. Args: stream: The data stream from which was read. Returns: True if more than one whitespace was skipped, otherwise return False. rr)rCr>)r;rAZcntr2r2r3skip_over_whitespaces   rF)valuercCs4tt|D]"}|||d}|tvr dSq dS)z Check if the given value consists of whitespace characters only. Args: value: The bytes to check. Returns: True if the value only has whitespace characters, otherwise return False. rFT)ranger+rC)rGr8currentr2r2r3check_if_whitespace_onlys rJcCs6|d}|dd|dkr2|dvr2|d}qdS)Nr%)  )r>seekrDr2r2r3skip_over_comments   rP)r;regexrcCspd}|d}|s|S|||}|durb||t|t|d||d|}ql||7}q|S)z Read until the regular expression pattern matched (ignore the match). Treats EOF on the underlying stream as the end of the token to be matched. Args: regex: re.Pattern Returns: The read bytes. r=Nr)r>searchrOstartr+)r;rQnamerAmr2r2r3read_until_regexs    rW)r;to_readrcCs>||krtd|| t||}|| t|S)a Given a stream at position X, read a block of size to_read ending at position X. This changes the stream's position to the beginning of where the block was read. Args: stream: to_read: Returns: The data which was read. z!Could not read malformed PDF file)tellrrOrr>)r;rXr>r2r2r3read_block_backwardss   rZcCsg}d}|dkrtttt|}|dkr4qt||}t|d}|sx|dkrl||dvrl|d8}qN|dkrxd}|r|||dd|dkr||dvr|d8}qn |||dkr||dt qqd |dddS) a Given a byte stream with current position X, return the previous line. All characters between the first CR/LF byte found before X (or, the start of the file, if no such byte is found) and position X After this call, the stream will be positioned one byte after the first non-CRLF character found beyond the first CR/LF byte before X, or, if no such byte is found, at the beginning of the stream. Args: stream: StreamType: Returns: The data which was read. Frrs TNr=rK) rYrrminrrZr+r7rOrjoin)r;Z line_contentZ found_crlfrXblockidxr2r2r3read_previous_lines.      r_)abrcstfdd|DS)Nc3s(|] tfddtDVqdS)c3s&|]}tddt|DVqdS)css"|]\}}t|t|VqdSN)float).0r/jr2r2r3 Br=z6matrix_multiply....N)sumzip)rdcolrowr2r3rfBr=z,matrix_multiply...N)tuplerh)rdrarjr3rfAsz"matrix_multiply..)rl)r`rar2rmr3matrix_multiply>s rncCsxd}|| dtdd:}||||d|||Wdn1s\0Y|| ddS)z5Create text file showing current location in context.irzpypdf_pdfLocation.txtwbsHEREN)rOopenwriter>)r;ZradiusZ output_fhr2r2r3 mark_locationGs  .rrB_CACHE)srcCst|tr|St}||vr"||Sz$|d}t|dkrB|||<|WStyz|d}t|dkrr|||<|YS0dS)Nlatin-1rzutf-8) isinstancebytesrsencoder+ Exception)rtbcrr2r2r3b_Vs      r|)rarcCs t|tr|dSt|SdS)Nru)rvrwdecodestrrmr2r2r3str_hs  rcCsdSrbr2rmr2r2r3ord_osrcCsdSrbr2rmr2r2r3rtscCsdSrbr2rmr2r2r3ryscCst|trt|S|Srb)rvr~ordrmr2r2r3r~s ) rMrN r=[])leftupup_leftrcCsX|||}t||}t||}t||}||krD||krD|S||krP|S|SdSrb)abs)rrrpZ dist_leftZdist_upZ dist_up_leftr2r2r3paeth_predictors    rr)msg stacklevelrcCstj|t|ddS)N)r)warningswarnDeprecationWarning)rrr2r2r3 deprecatesr)rrcCs t|dSrb)r)rr2r2r3 deprecationsr)old_namenew_name removed_inrcCs t|d|d|dddS)zIRaise an exception that a feature will be removed, but has a replacement., is deprecated and will be removed in pypdf . Use instead.Nrrrrr2r2r3deprecate_with_replacementsrcCst|d|d|ddS)zMRaise an exception that a feature was already removed, but has a replacement.( is deprecated and was removed in pypdf rrNrrr2r2r3deprecation_with_replacementsr)rUrrcCst|d|dddS)zFRaise an exception that a feature will be removed without replacement.r.rNrrUrr2r2r3deprecate_no_replacementsrcCst|d|ddS)zJRaise an exception that a feature was already removed without replacement.rrNrrr2r2r3deprecation_no_replacementsr)rsrcrcCst||dS)z Use this instead of logger.error directly. That allows people to overwrite it more easily. See the docs on when to use which: https://pypdf.readthedocs.io/en/latest/user/suppress-warnings.html N)logging getLoggererrorrrr2r2r3 logger_errors rcCst||dS)a Use this instead of logger.warning directly. That allows people to overwrite it more easily. ## Exception, warnings.warn, logger_warning - Exceptions should be used if the user should write code that deals with an error case, e.g. the PDF being completely broken. - warnings.warn should be used if the user needs to fix their code, e.g. DeprecationWarnings - logger_warning should be used if the user needs to know that an issue was handled by pypdf, e.g. a non-compliant PDF being read in a way that pypdf could apply a robustness fix to still read it. This applies mainly to strict=False mode. N)rrwarningrr2r2r3logger_warningsrF) func_namekwargsaliasesfailrc Cs|D]~\}}||vr|r0t|d|d||vr^t|d|d|d|d|d ||||<tj|d|dtdqd S) z Helper function to deprecate arguments. Args: func_name: Name of the function to be deprecated kwargs: aliases: fail: z# is deprecated as an argument. Use z insteadz received both z and z as an argument. z is deprecated. Use r)messagecategoryN)itemsr TypeErrorpoprrr)rrrrZold_termZnew_termr2r2r3 rename_kwargss& r)rwrcCsV|dkr|dS|dkr*|dddS|dkrB|dddS|dddSdS) Niz Bytei@Bz.1fz kBiʚ;z MBz GBr2)rwr2r2r3_human_readable_bytess rc@s2eZdZdZd ddZd edddZdd ZdS) classpropertyz Decorator that converts a method with a single cls argument into a property that can be accessed directly from the class. NcCs ||_dSrbfgetselfmethodr2r2r3__init__&szclassproperty.__init__rcCs ||Srbr)rinstanceclsr2r2r3__get__)szclassproperty.__get__cCs ||_|Srbrrr2r2r3getter,szclassproperty.getter)N)N)__name__ __module__ __qualname____doc__rr rrr2r2r2r3r s rc@sfeZdZUddlmZeed<eed<dZe e ed<dZ e eed<edd d Z edd d Z dS) FilerIndirectObjectrUdataNimageindirect_referencercCs&|jjd|jdtt|jdS)Nz(name=z, data: )) __class__rrUrr+rrr2r2r3__str__:sz File.__str__cCs"|dddt|jdS)NrKz, hash: r)rhashrrr2r2r3__repr__=sz File.__repr__)rrrgenericrr~__annotations__rwrr r rrrr2r2r2r3r1s  rc@sLeZdZUddlmZdZeeed<dZ eeed<eeddddZ dS) ImageFilerrNrr) new_imagerrc Ks<ddlm}ddlm}ddlm}ddlm}m}|j durFt dt |j j d s\t d t ||jspt d t}|j|d fi|||} | jdjdj dusJ| jdjdj |j j j|j jd<|j t||j _ |t||j \} } } | dusJ|jd|jd | |_| |_| |_dS)a Replace the Image with a new PIL image. Args: new_image (PIL.Image.Image): The new PIL image to replace the existing image. **kwargs: Additional keyword arguments to pass to `Image.Image.save()`. Raises: TypeError: If the image is inline or in a PdfReader. TypeError: If the image does not belong to a PdfWriter. TypeError: If `new_image` is not a PIL Image. Note: This method replaces the existing image with a new image. It is not allowed for inline images or images within a PdfReader. The `kwargs` parameter allows passing additional parameters to `Image.Image.save()`, such as quality. r)Imager) PdfReader)_xobj_to_image)DictionaryObject PdfObjectNzCan not update an inline imageZ_id_translatedz4Can not update an image not belonging to a PdfWriterznew_image shall be a PIL ImageZPDFr)ZPILr_readerrfiltersrrrrrrhasattrZpdfrvrsaveZpagesZimagesZ get_object_objectsZidnumrrUrfindrr) rrrrrrrrrareader extensionZ byte_streamimgr2r2r3r(Hs6       zImageFile.replace) rrrrrrr r rrr(r2r2r2r3rAs  rc@sbeZdZedZeddddZeee e efdddZ e e dd d Zee dd d ZdS) Versionz ^(\d+)(.*)$N) version_strrcCs||_|||_dSrb)r_parse_version components)rrr2r2r3rszVersion.__init__cCsn|d}g}|D]V}tj|}|s6|d|fq|d}|d}|durVd}|t||fq|S)Nrrrr)splitrCOMPONENT_PATTERNmatchr7groupint)rrrZparsed_components componentrZinteger_prefixsuffixr2r2r3rs    zVersion._parse_version)otherrcCst|tsdS|j|jkS)NF)rvrr)rrr2r2r3__eq__s zVersion.__eq__cCst|tstdt|tt|jt|j}t|D]X}|j|\}}|j|\}}||krhdS||krvdS||krdS||kr:dSq:t|jt|jkS)Nz#Version cannot be compared against TF)rvrr-typer[r+rrH)rrZmin_lenr/Z self_valueZ self_suffixZ other_valueZ other_suffixr2r2r3__lt__s  zVersion.__lt__)rrrrecompilerr~rr rrrobjectboolrr rr2r2r2r3r}s  r)N)r)F)Qr __author____author_email__ functoolsrrsysr dataclassesrrriorrosrtypingrr r r r r rrrr version_inforZtyping_extensionserrorsrrrrcrrrZ StreamTyper~Z StrByteTyper4r:rrwrBrErrFrJrPrWrZr_rnrrrsr|rrrCr\ZWHITESPACES_AS_BYTESZWHITESPACES_AS_REGEXPrrrrrrrrrrrrrrtotal_orderingrr2r2r2r3s  0  &    :  "    !-;