/j-jSMSrSSKJr SSKrSSKrSSKrSSKJr SSK J r SSK J r SSK Jr SSK Jr SSKrSS KJr SS KJr SS KJr SS KJr SS KJr SSKJr SSKJr SSKJr SSKJr SSKJr SSKJr SSKJ r SSK!J"r" SSK!J#r# SSK!J$r$ SSK!J%r% SSK!J&r& \\ \\\S.r'\(\ -\)-\*-\+-\\)-r,S!Sjr-S"Sjr.S#Sjr/"SS 5r0g)$z0Functions to handle all operations on the PDF's.) annotationsN)partial)chain)Path)IO)Any)PDFPasswordIncorrect)PDFTextExtractionNotAllowed)LTChar)LTImage)LTTextLineHorizontal)LTTextLineVertical) TableList)Hybrid)Lattice)MachineLearning)Network)Stream) download_url)get_image_char_and_text_objects)get_page_layout) get_rotation)is_url)latticestreamnetworkhybridmlc[R"SSSS9nURU5 URsSSS5 $!,(df  g=f)uWrite `data` to a NamedTemporaryFile and return its path. Used by ``PDFHandler`` when the caller passes a ``bytes``-like object or a file-like stream rather than a filesystem path — the Lattice flavor's OpenCV image-conversion backend needs a real on-disk file, so the simplest contract is "always spill once, treat as a path from here on, clean up on close()". The file is created with ``delete=False`` and reaped in :meth:`PDFHandler.close`. zcamelot-z.pdfF)prefixsuffixdeleteN)tempfileNamedTemporaryFilewritename)datafs M/home/mande/repo/quber/.venv/lib/python3.13/site-packages/camelot/handlers.py_spill_bytes_to_tempfiler+.s>  $ $&    vv    s > A c[USS5n[USS5n[U5(aU"5OSn[U5(a U"S5 UR 5nUb[U5(a U"U5 [ U[ [[45(d![S[U5R35e[ U5$![[4a Nf=f![[4a Ntf=f)u%Read a binary stream from the start, preserve the caller's cursor. Always reads from position 0 — a PDF mid-stream isn't useful — and seeks back to whatever position the caller had before the call so they can keep using the same handle. Non-seekable streams (sockets, pipes) silently fall through: ``read()`` returns whatever's left, and the seek-back is best-effort. Raises ``TypeError`` when ``read()`` returns text rather than bytes, which catches accidental text-mode opens before the bad data reaches pdfium and produces a clearer error. tellNseekrz9file-like 'filepath' must return bytes from .read(), got ) getattrcallableOSError ValueErrorread isinstancebytes bytearray memoryview TypeErrortype__name__)filepathr-r.posr(s r*_consume_filelike_to_bytesr=?s 8VT *D 8VT *DTNN$&C~~  G ==?D 8D>>  I dUIz: ; ; J''( *   ;$    $   s$C1CCCC.-C.cH[U[[[45(a[ [U55S4$[ US5(a2[ UR5(a[U5n[ U5S4$[U5(a[[U55S4$US4$)u"Normalise read_pdf's polymorphic filepath argument to a real path. Returns ``(path, is_temp)``. ``is_temp`` is True when the returned path points to a tempfile we created (and therefore own — the caller's :meth:`PDFHandler.close` should reap it). Three branches: * ``bytes`` / ``bytearray`` / ``memoryview``: spill to a tempfile. * binary file-like (``.read()`` returning bytes): read once, preserve the caller's cursor, spill to a tempfile. * everything else (path / URL): URL → download to tempfile; path → pass through untouched. Tr3F) r4r5r6r7r+hasattrr0r3r=rrstr)r;r(s r*_resolve_filepathrAbs(UIz:;;'h8$>>x  Xhmm%<%<)(3'-t33 hCM*D00 U?c\rSrSrSrSSSjjr\SSj5rSSSjjr\ SSj5r SSjr SS jr SS jr S rSS jrSSS jjrSSSjjrSrg) PDFHandler}uHandles all operations on the PDF's. Handles all operations like temp directory creation, splitting file into single page PDFs, parsing each PDF and then removing the temp directory. Parameters ---------- filepath : str, Path, bytes, or binary file-like Source PDF. Accepts a filesystem path / URL, or — since #270 — a ``bytes``-like object or any binary stream with a ``.read()`` method (``io.BytesIO``, an open ``"rb"`` file, ``requests`` response ``.raw``, etc). In the in-memory cases the bytes are spilled to a temporary file once and cleaned up when the handler is closed; this keeps the rest of the pipeline (in particular the Lattice OpenCV image-conversion backend) unchanged. pages : str, optional (default: '1') Comma-separated page numbers. Example: '1,3,4' or '1,4-end' or 'all'. password : str, optional (default: None) Password for decryption. debug : bool, optional (default: False) Whether the parser should store debug information during parsing. NcX@l[U5uoPlXPlUcSUlOX0lX lUS:Xa S/UlgSUlg)N1r)debugrA is_temp_filer;password _pages_spec _pages_cache)selfr;pagesrKrIresolveds r*__init__PDFHandler.__init__sO &7&A##$,  DM$M!5:c\qctrBctURc URUR5UlUR$)zResolved 1-based page numbers, sorted and de-duplicated. Lazy: only opens the PDF if the spec is something other than the default ``"1"``. Cached after first access. )rM_resolve_pagesrLrNs r*rOPDFHandler.pagess5    $ $ 3 3D4D4D ED    rBcUS:XaS/$UcE[R"URSURS9nUR X5sSSS5 $UR U[ UR55$!,(df  N3=f)zConvert the ``pages`` spec to a sorted, de-duplicated list of ints. Pass an already-open ``pdf`` to avoid the playa.open() round-trip that would otherwise be needed to read ``len(pdf.pages)``. rHrNpagespacerK)playaopenr;rKrT_expand_pages_speclenrO)rNrOpdfs r*rTPDFHandler._resolve_pagessn C<3J ;DMM$--PTW**56QP&&uc#))n==QPs A77 Bc/nUS:XaURSUS.5 OURS5HtnSU;aEURS5upEUS:XaUO [U5nUR[U5US.5 MNUR[U5[U5S.5 Mv /nUH'nUR[ USUSS-55 M) [ [ U55$)zCExpand a pages spec string (``"all"``, ``"1,3,4"``, ``"1,4-end"``).allrstartend,-rerd)appendsplitintextendrangesortedset) rO page_count page_numbersrabb_intresultps r*r]PDFHandler._expand_pages_specs.0 E>   !J ? @[[%!8773U S:Xa*URURUR S-5 O[ SU 35e[U40UD6up4[U5upVpxUUUUUUU 4$)aGet layout from a page. Parameters ---------- page : playa.Page Page in the document. Returns ------- layout : object dimensions : tuple The dimensions of the pdf page filepath : str The path of the single page PDF - either the original, or a normalized version. clockwiseZ anticlockwisez2rotation should be clockwise or anticlockwise, is )rrrset_initial_ctmrZrotateAssertionError) rNrX layout_kwargslayout dimensionsimagescharshorizontal_text vertical_textrotations r* _get_layoutPDFHandler._get_layout*s>-TC]C8W 9 5  F ;&$$TZZr1AB_,$$TZZr1AB$H S"1!G!G F/7 :F?         rBc Uc0nU=(d 0n[Un U "S SUR0U D6n U(a[U S5(aXl[R "5n U(a!U S:aUcU O[ S[XL55nOSn[R"URURSUS9n U R(d[SUR35eUc:URc!URUR U 5UlURnUVs/sHoS- PM nnU R"UR%['UR(U UUU US95nSSS5 [/[1[2R4"W555$s snf!,(df  N;=f![*an[-S 5UeSnAf[a ef=f) aExtract tables by calling parser.get_tables on all single page PDFs. Parameters ---------- flavor : str (default: 'lattice') The parsing method to use. Lattice is used by default. suppress_stdout : bool (default: False) Suppress logs and warnings. parallel : bool (default: False) Process pages in parallel using all available cpu cores. cpu_count : int, optional (default: None) Maximum number of worker processes to use when ``parallel`` is True. ``None`` (default) uses all available cores. Values are clamped to ``[1, multiprocessing.cpu_count()]``. Ignored when ``parallel`` is False. layout_kwargs : dict, optional (default: {}) A dict of `pdfminer.layout.LAParams `_ kwargs. kwargs : dict See camelot.read_pdf kwargs. Returns ------- tables : camelot.core.TableList List of tables found in PDF. NrI _render_cacherrX)rKrZ max_workersz Text extraction is not allowed: )parserrflavor base_kwargsper_pagezFile has not been decryptedry)PARSERSrIr?rmp cpu_countmaxminr[r\r;rKis_extractabler rMrTrLrOmapr _parse_pager RuntimeErrorrrmr from_iterable)rNrsuppress_stdoutparallelrrrrO render_cachekwargs parser_objrmax_cpusr_xtableses r*parsePDFHandler.parsejsP  M>rV_ 7$**77 GFO<<$0 <<> 1 %-3q#i:R3S I!  %  ))5:4==/J=((0,0,?,?@P@PRU,V) --E(-.1Q.5)--((%&3%$*!)  'B 3 3F ;<==/%:$ E<=1 D*   sI +F,7A+F"F06F&F,F F)%F,)F,, G6 GGc URS-nU=(d 0RU5nU(agURSU5n [U=(d 05n UR5HupU S:wdM XU 'M [U "SSUR 0U D6n OUn UR "U40UD6upnnnnnU RURUUURS-UUUUUS9 U R5nU$)arExtract tables by calling parser.get_tables on a single page PDF. Parameters ---------- page : playa.Page Page to parse parser : Lattice, Stream, Network or Hybrid The default parser to use when no per-page override applies. layout_kwargs : dict, optional (default: {}) A dict of `pdfminer.layout.LAParams `_ kwargs. flavor : str, optional The global flavor; used as the fallback when a per-page override doesn't itself supply ``flavor=``. base_kwargs : dict, optional The global (already-cleaned) parser kwargs. Merged with any per-page override to construct a fresh parser for that page. per_page : dict, optional Page-number-keyed kwargs overrides (already validated upstream). Returns ------- tables : camelot.core.TableList List of tables found in PDF. rrrI)rry) page_idxgetdictitemsrrIrprepare_page_parser;extract_tables)rNrXrrrrrpage_no overrides page_flavormergedkv page_parserrrrrrrrrs r*rPDFHandler._parse_pagesH--!#^((1 #--&9K++,F!)= !1I*"+.JTZZJ6JK K   T 3] 3 TFE?M8 && MM   MMA     ' ' ++- rB)rMrLrIr;rJrK)rHNF)r;FilepathOrBuffer)return list[int])N)rOr@r_z Any | Nonerr)rOr@rorjrr)rrD)rNone)rX playa.Pagerzwtuple[Any, tuple[float, float], list[LTImage], list[LTChar], list[LTTextLineHorizontal], list[LTTextLineVertical], str])rFFNNNNN)rr@rboolrrrz int | Nonerdict[str, Any] | Noner dict[int, dict[str, Any]] | NonerOzlist[int] | Nonerzdict[int, str] | None)rNN)rXrrr@rrrr)r: __module__ __qualname____firstlineno____doc__rQpropertyrOrT staticmethodr]rzrr}rrrr__static_attributes__ryrBr*rDrD}s-8 L"L*!! >##$&6*#X> >  > D % $/359"&.2d>d>d> d>  d> - d>3d> d>,d>V -159>>  > + >3>>rBrD)r(r5rr@)r;z IO[bytes]rr5)r;rrztuple[str | Path, bool])1r __future__rmultiprocessingrrr$ functoolsr itertoolsrpathlibrtypingrrr[playa.exceptionsr r playa.minerr r r rcorerparsersrrrrrutilsrrrrrrr@r5r6r7rr+r=rArDryrBr*rs6"  18,*$2"   :% 1J>EJ" F6QQrB