TAiiU4@SrSSKJr SSKrSSKrSSKrSSKrSSKJr SSK J r J r SSK J r SSKJr SSKJr SS KJr SS KJr SSKrSS KJr SS KJr SS KJrJr SSKJr SSK J!r! SSK"J#r# SSK$J%r%J&r& SSK'J(r( \\)-\*-r+\\+-r,\RZ"5r."SS\ 5r/SSSS.S"Sjjr0S#Sjr1S$Sjr2SSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSS.3S%Sjjr3SSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSSS.&S&Sjjr4SSSSSSSSSSSSSS. S'S jjr5/S!Qr6g)(a"Python API for OCRmyPDF. This module provides the main Python API for OCRmyPDF, allowing you to perform OCR operations programmatically without using the command line interface. Main Functions: ocr(): The primary function for OCR processing. Takes an input PDF or image file and produces an OCR'd PDF with searchable text. configure_logging(): Set up logging to match the command line interface behavior, with support for progress bars and colored output. Experimental Functions: _pdf_to_hocr(): Extract text from PDF pages and save as hOCR files for manual editing before final PDF generation. _hocr_to_ocr_pdf(): Convert hOCR files back to a searchable PDF after manual text corrections. The API maintains thread safety through internal locking since OCRmyPDF uses global state for plugins. Only one OCR operation can run per Python process at a time. For parallel processing, use multiple Python processes. Example: import ocrmypdf # Configure logging (optional) ocrmypdf.configure_logging(ocrmypdf.Verbosity.default) # Perform OCR ocrmypdf.ocr('input.pdf', 'output.pdf', language='eng') For detailed parameter documentation, see the ocr() function docstring and the equivalent command line parameters in the OCRmyPDF documentation. ) annotationsN) Namespace)IterableSequence)IntEnum)IOBase)Path)BinaryIO)warn)PageNumberFilter)run_hocr_to_ocr_pdf_pipeline) run_pipelinerun_pipeline_cli)run_hocr_pipeline)get_plugin_manager) check_options)ArgumentParser get_parser)is_iterable_notstrc(\rSrSrSrSrSrSrSrSr g) VerbosityJz&Verbosity level for configure_logging.rN) __name__ __module__ __qualname____firstlineno____doc__quietdefaultdebug debug_all__static_attributes__rH/var/www/html/land-ocr/venv/lib/python3.13/site-packages/ocrmypdf/api.pyrrJs0 EG EIr'rTF)progress_bar_friendlymanage_root_loggerplugin_managercU(aSOSn[R"U5nUR[R5 SnU(a!U(aURR 5nU(d"[R "[RS9nUS:a UR[R5 OEUS:a UR[R5 OUR[R5 UR[55 US:aSnOS nSnU(d[R"US 9nURU5 URU5 US::aj[R"S 5n U R[R5 [R"S 5n U R[R5 U(a[R "S 5 U$)aSet up logging. Before calling :func:`ocrmypdf.ocr()`, you can use this function to configure logging if you want ocrmypdf's output to look like the ocrmypdf command line interface. It will register log handlers, log filters, and formatters, configure color logging to standard error, and adjust the log levels of third party libraries. Details of this are fine-tuned and subject to change. The ``verbosity`` argument is equivalent to the argument ``--verbose`` and applies those settings. If you have a wrapper script for ocrmypdf and you want it to be very similar to ocrmypdf, use this function; if you are using ocrmypdf as part of an application that manages its own logging, you probably do not want this function. If this function is not called, ocrmypdf will not configure logging, and it is up to the caller of ``ocrmypdf.ocr()`` to set up logging as it wishes using the Python standard library's logging module. If this function is called, the caller may of course make further adjustments to logging. Regardless of whether this function is called, ocrmypdf will perform all of its logging under the ``"ocrmypdf"`` logging namespace. In addition, ocrmypdf imports pdfminer, which logs under ``"pdfminer"``. A library user may wish to configure both; note that pdfminer is extremely chatty at the log level ``logging.INFO``. This function does not set up the ``debug.log`` log file that the command line interface does at certain verbosity levels. Applications should configure their own debug logging. Args: verbosity: Verbosity level. progress_bar_friendly: If True (the default), install a custom log handler that is compatible with progress bars and colored output. manage_root_logger: Configure the process's root logger. plugin_manager: The plugin manager, used for obtaining the custom log handler. Returns: The toplevel logger for ocrmypdf (or the root logger, if we are managing it). ocrmypdfN)streamrrrz/%(levelname)7s %(name)s -%(pageno)s %(message)sz%(pageno)s%(message)s)fmtpdfminerPILT)logging getLoggersetLevelDEBUGhookget_logging_console StreamHandlersysstderrERRORINFO addFilterr Formatter setFormatter addHandlercaptureWarnings) verbosityr)r*r+prefixlogconsoler0 formatter pdfminer_logpil_logs r(configure_loggingrJTs^Z&R:F   F #CLLG/ %%99; ''szz:1}' a'& &()A~?%I %%#.  #NN7A~((4 gmm,##E*&% Jr'c /n0nUR5GH[upEUcM X@;aXSU'MURSS5n[U[5(aU(aUR SU35 MZ[ U5(a0UH(nUR SU35 UR U5 M* MUR SU35 [U[ [-5(aUR [U55 M[U[5(aUR U5 GM[U[5(aUR [U55 GMA[USUS[U5S35e X#4$)z)Convert kwargs to command line arguments._-z--z: z ()) itemsreplace isinstanceboolappendrintfloatstrr TypeErrortype) defer_kwargskwargscmdlinedeferredargval cmd_style_argelems r(_kwargs_to_cmdlinerasF"$GHLLN ;   SM  C-  c4 M?34  c " "M?34t$  M?+, c3; ' ' NN3s8 $ S ! ! NN3  T " " NN3s8 $se2cU"T#YKq9: :A#B  r'c [SS1Sk0UD6upE[U[[-5(aUR S5 O%UR [ R "U55 [U[[-5(aUR S5 O%UR [ R "U55 SU;aA[US[[-5(a"UR S5 UR S5 UR5 URU5nUR5Hupx[XgU5 M URS:XaXl URS:XaXl URS:Xa USUl U$) aConstruct an options object from the input/output files and keyword arguments. Args: input_file: Input file path or file object. output_file: Output file path or file object. parser: ArgumentParser object. **kwargs: Keyword arguments. Returns: argparse.Namespace: A Namespace object containing the parsed arguments. Raises: TypeError: If the type of a keyword argument is not supported. rY>parserplugins input_file output_file progress_barzstream://input_filezstream://output_filesidecarz --sidecarzstream://sidecarr)rarQr rrSosfspathenable_api_mode parse_argsrOsetattrrerfrh) rerfrcrZr[r\optionskeywordr^s r(create_optionsrpsE"+W G*h/00,-ryy,-+x&011-.ryy-.Fz&*;X=NOO{#)* (G ( #&)22'44),, + Nr')3language image_dpi output_typerhjobs use_threadstitleauthorsubjectkeywords rotate_pagesremove_backgrounddeskewclean clean_final unpaper_args oversampleremove_vectors force_ocr skip_textredo_ocrskip_bigoptimize jpg_quality png_quality jbig2_lossyjbig2_page_group_sizejbig2_thresholdpagesmax_image_mpixelstesseract_configtesseract_pagesegmode tesseract_oemtesseract_thresholding pdf_renderertesseract_timeouttesseract_non_ocr_timeouttesseract_downsample_above!tesseract_downsample_large_imagesrotate_pages_thresholdpdfa_image_compressioncolor_conversion_strategy user_words user_patterns fast_web_viewcontinue_on_soft_render_errorinvalidate_digital_signaturesrdr+keep_temporary_filesrgc3 PU1(aU2(a [S5eU1(d/n1O+[U1[[-5(aU1/n1O [ U15n1[ 5R 5V6V7s0sHun6n7U6S;dMU6U7_M n8n6n7U8RU55 [5n9[ U2(d [U15n2U2RRU9S9 SU5;a [S5 [S UUU9S.U8D6n:[U:U25 [!U:U2S9sSSS5 $s sn7n6f!,(df  g=f) aB Run OCRmyPDF on one PDF or image. For most arguments, see documentation for the equivalent command line parameter. This API takes a threading lock, because OCRmyPDF uses global state in particular for the plugin system. The jobs parameter will be used to create a pool of worker threads or processes at different times, subject to change. A Python process can only run one OCRmyPDF task at a time. To run parallelize instances OCRmyPDF, use separate Python processes to scale horizontally. Generally speaking you should set jobs=sqrt(cpu_count) and run sqrt(cpu_count) processes as a starting point. If you have files with a high page count, run fewer processes and more jobs per process. If you have a lot of short files, run more processes and fewer jobs per process. A few specific arguments are discussed here: Args: use_threads: Use worker threads instead of processes. This reduces performance but may make debugging easier since it is easier to set breakpoints. input_file: If a :class:`pathlib.Path`, ``str`` or ``bytes``, this is interpreted as file system path to the input file. If the object appears to be a readable stream (with methods such as ``.read()`` and ``.seek()``), the object will be read in its entirety and saved to a temporary file. If ``input_file`` is ``"-"``, standard input will be read. output_file: If a :class:`pathlib.Path`, ``str`` or ``bytes``, this is interpreted as file system path to the output file. If the object appears to be a writable stream (with methods such as ``.write()`` and ``.seek()``), the output will be written to this stream. If ``output_file`` is ``"-"``, the output will be written to ``sys.stdout`` (provided that standard output does not seem to be a terminal device). When a stream is used as output, whether via a writable object or ``"-"``, some final validation steps are not performed (we do not read back the stream after it is written). Raises: ocrmypdf.MissingDependencyError: If a required dependency program is missing or was not found on PATH. ocrmypdf.UnsupportedImageFormatError: If the input file type was an image that could not be read, or some other file type that is not a PDF. ocrmypdf.DpiError: If the input file is an image, but the resolution of the image is not credible (allowing it to proceed would cause poor OCR). ocrmypdf.OutputFileAccessError: If an attempt to write to the intended output file failed. ocrmypdf.PriorOcrFoundError: If the input PDF seems to have OCR or digital text already, and settings did not tell us to proceed. ocrmypdf.InputFileError: Any other problem with the input file. ocrmypdf.SubprocessOutputError: Any error related to executing a subprocess. ocrmypdf.EncryptedPdfError: If the input PDF is encrypted (password protected). OCRmyPDF does not remove passwords. ocrmypdf.TesseractConfigError: If Tesseract reported its configuration was not valid. Returns: :class:`ocrmypdf.ExitCode` z2plugins= and plugin_manager are mutually exclusive>rZrerfr+rcverbosezDocrmypdf.ocr(verbose=) is ignored. Use ocrmypdf.configure_logging().)rerfrcrnr+Nr) ValueErrorrQrVr listlocalsrOupdater _api_lockrr7 add_optionsr rprr);rerfrqrrrsrhrtrurvrwrxryrzr{r|r}r~rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrdr+rrgrZkvcreate_options_kwargsrcrns; r(ocrr sf>MNN  GS4Z ( ()w- HNN$$DAq M M 1$   ( \F /8N''v'6   W X  !# $   g~.GNK  s* D;D&A!D D%)&rqrrrtrurvrwrxryrzr{r|r}r~rrrrrrrrrrrrrrrrrrrrrrr+rdrc& [5R5V)V*s0sHun)n*U)S;dMU)U*_M n+n)n*U+RU(5 [5n,[ U%(d [ U&5n%U%R RU,S9 [S S1Sk0U+D6un-n.U-R[U55 U-R[U55 U,R5 U,RU-5n/U.R5Hun0n1[U/U0U15 M [U/S5 [U/SU5 [U/U%S9sSSS5 $s sn*n)f!,(df  g=f) aPartially run OCRmyPDF and produces an output folder containing hOCR files. Given a PDF file, this function will run OCRmyPDF up to the point where the PDF is rasterized to images, OCRed, and the hOCR files are produced, all of which are saved to the output folder. This is useful for applications that want to provide an interface for users to edit the text before rendering the final PDF. Use :func:`hocr_to_ocr_pdf` to produce the final PDF. For arguments not explicitly documented here, see documentation for the equivalent command line parameter. This API is **experimental** and subject to change. Args: input_pdf: Input PDF file path. output_folder: Output folder path. **kwargs: Keyword arguments. >rZ input_pdf output_folderrrY>rdrrrfrrNr)rrOrrrrr7rrarSrVrkrlrmdelattrr)2rrrqrrrtrurvrwrxryrzr{r|r}r~rrrrrrrrrrrrrrrrrrrrrrr+rdrrZrrrrcr[r\rnror^s2 r( _pdf_to_hocrrs2FHNN$$DAq < < 1$   ( \F /8N''v'6. B #  s9~&s=)* ##G,$NN,LGS GWc *-'-8 P%   D>D>CE E) rtrurrrrrrrrrr+rdc  [5R5VVs0sHunnUS;dMUU_M nnnURU5 [5n[ U (d [ U5n U R RUS9 [S S1Sk0UD6unnUR[U55 UR[U55 UR5 URU5nUR5Hunn[UUU5 M [US5 [USU5 [UU S9sSSS5 $s snnf!,(df  g=f) aMRun OCRmyPDF on a work folder and produce an output PDF. After running :func:`pdf_to_hocr`, this function will run OCRmyPDF on the work folder to produce an output PDF. This function consolidates any changes made to the hOCR files in the work folder and produces a final PDF. For arguments not explicitly documented here, see documentation for the equivalent command line parameter. This API is **experimental** and subject to change. Args: work_folder: Work folder path, as generated by :func:`pdf_to_hocr`. output_file: Output PDF file path. **kwargs: Keyword arguments. >rZ output_pdf work_folderrrY>rdrfrrerrNr)rrOrrrrr7rrarSrVrkrlrmrr )rrfrtrurrrrrrrrrr+rdrZrrrrcr[r\rnror^s r(_hocr_to_ocr_pdfrs6LHNN$$DAq ; ; 1$   ( \F /8N''v'6. B #  s;'(s;'( ##G,$NN,LGS GWc *-& 4+N %  r) r rrrJrprrrrr)rCrr)rRr*rRr+zpluggy.PluginManager | None)rYzset[str]returnz0tuple[list[str | bytes], dict[str, str | bytes]])rePathOrIOrfrrcrrr)hrerrfrrqIterable[str] | Nonerr int | Noners str | NonerhzPathOrIO | Nonertrru bool | Nonervrrwrrxrryrrzrr{rr|rr}rr~rrrrrrrrrrrrrr float | Nonerrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrros.PathLike | NonerrrrrrrrrdzIterable[Path | str] | Nonerrrgr)Nrr rr rqrrrrrtrrurrvrrwrrxrryrrzrr{rr|rr}rr~rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrdSequence[Path | str] | Nonerr)rr rfr rtrrurrrrrrrrrrrrrrrrrrrrdr)7r! __future__rr3rir: threadingargparsercollections.abcrrenumriorpathlibr typingr warningsr pluggyocrmypdf._loggingr #ocrmypdf._pipelines.hocr_to_ocr_pdfr ocrmypdf._pipelines.ocrrrocrmypdf._pipelines.pdf_to_hocrrocrmypdf._plugin_managerrocrmypdf._validationr ocrmypdf.clirrocrmypdf.helpersrrVbytesStrPathrLockrrrJrarprrr__all__rr'r(rs^"H# . .LB=7.3/ *u  g  NN  #'$26 XX X X 0 Xv''5'T--*2-"?UL@ AULB$CULD+EULF&GULHIULJ'KULLMULN$OULP ,QULR!+SULT(3UULV)WULX'YULZ *[UL\#]UL^&_UL` aULb$/cULd$/eULf)gULj&kULlmULx&* # $%)##!"&!! !&*-1(, $)-&*.2-159+/%)(,1515+/(,S\Q\Q\Q# \Q  \Q  \Q\Q \Q \Q\Q\Q\Q#\Q \Q \Q !\Q"#\Q$%\Q& '\Q()\Q*+\Q,-\Q./\Q0 1\Q2$3\Q4+5\Q6&7\Q89\Q:';\Q<$=\Q> ,?\Q@!+A\QB(3C\QD)E\QF#G\QH&I\QJ$/K\QL$/M\QP)Q\QR&S\QF#""#(,$()-,0"&+/!A A A   A  A  A A A A &A "A 'A  *A  A )!A H r'