File: //usr/lib/python3/dist-packages/ocrmypdf/__pycache__/api.cpython-38.pyc
U
��Z^�# � - @ s� d dl Z d dlZd dlZd dlmZ d dlmZ d dlmZ d dl m
Z
m Z d dl m Z ddl
mZ dd lmZ dd
lmZ G d d � d �ZG d
d� de�Zddd�Zdd� Zdddddddddddddddddddddddddddddddddddddddddddd�+ejeje e eejeeeeeeeeeeeeeeeeeeeeeeeeeee e eeeeejejeeee
eef d�*dd�Z dS )� N)�suppress)�IntEnum)�Path)�Dict�List)�tqdm� )� run_pipeline)�
check_options)�parserc @ s( e Zd ZdZdd� Zdd� Zdd� ZdS ) � TqdmConsolean Wrapper to log messages in a way that is compatible with tqdm progress bar
This routes log messages through tqdm so that it can print them above the
progress bar, and then refresh the progress bar, rather than overwriting
it which looks messy.
For some reason Python 3.6 prints extra empty messages from time to time,
so we suppress those.
c C s || _ tjdd� dk| _d S )Nr � )� � )�file�sys� version_info�py36)�selfr � r �./usr/lib/python3/dist-packages/ocrmypdf/api.py�__init__, s zTqdmConsole.__init__c C sD | j r*|�� dkr@tj|�� d| jd� ntj|�� d| jd� d S )N� �
)�endr )r �stripr �write�rstripr )r �msgr r r r 0 s zTqdmConsole.writec C s" t t�� | j�� W 5 Q R X d S )N)r �AttributeErrorr �flush)r r r r r 8 s
zTqdmConsole.flushN)�__name__�
__module__� __qualname__�__doc__r r r r r r r r ! s
r c @ s e Zd ZdZdZdZdZdZdS )� Verbosityz&Verbosity level for configure_logging.���r r r
N)r! r" r# r$ �quiet�default�debugZ debug_allr r r r r% = s
r% TFc C s� |rdnd}t �|�}|�t j� |r:t jttj�d�}nt jtjd�}| dk r^|�t j� n"| dkrt|�t j� n |�t j � t �
d�}| dkr�t �
d�}|� |� |� |� | dkr�t �d �}|�t j� t �d
�}|�t j � |r�t �
d � |S ) a9 Set up logging.
Library users may wish to use this function if they want their log output to be
similar to ocrmypdf command line interface. If not used, the external application
should configure logging on its own.
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``.
Library users may perform additional configuration afterwards.
Args:
verbosity (Verbosity): Verbosity level.
progress_bar_friendly (bool): Install the TqdmConsole log handler, which is
compatible with the tqdm progress bar; without this log messages will
overwrite the progress bar
manage_root_logger (bool): Configure the process's root logger, to ensure
all log output is sent through
Returns:
The toplevel logger for ocrmypdf (or the root logger, if we are managing it).
r Zocrmypdf)�streamr r z %(levelname)7s - %(message)sr
z'%(name)s - %(levelname)7s - %(message)sZpdfminerZPILT)�loggingZ getLoggerZsetLevel�DEBUGZ
StreamHandlerr r �stderrZERROR�INFOZ FormatterZ setFormatterZ
addHandlerZcaptureWarnings) � verbosityZprogress_bar_friendlyZmanage_root_logger�prefix�logZconsoleZ formatterZ pdfminer_logZpil_logr r r �configure_loggingF s0
r2 c
K sV g }g }|� � D ]�\}}|d kr"q|dkr:|�||f� q|�dd�}t|t�rf|r|�d|� �� q|�d|� �� t|ttf�r�|�t|�� qt|t�r�|�|� qt|t�r�|�t|�� qt |� d|� dt
|�� d���q|�t| �� |�t|�� dt _ t �
|�}|D ]\} }t|| |� �qtj�d ��rR|j�rRt�| �|jd
< |S ) N> � progress_bar�
tesseract_env�_�-z--z: z (�)TZPYTEST_CURRENT_TESTZ_OCRMYPDF_TEST_INFILE)�items�append�replace�
isinstance�bool�int�float�strr � TypeError�typer Zapi_mode�
parse_args�setattr�os�environ�getr4 �fspath)
�
input_file� output_file�kwargsZcmdlineZdeferred�arg�valZ
cmd_style_arg�options�keywordr r r �create_options� s<
rO )+�language� image_dpi� output_type�sidecar�jobs� use_threads�title�author�subject�keywords� rotate_pages�remove_background�deskew�clean� clean_final� unpaper_args�
oversample�remove_vectors� threshold� force_ocr� skip_text�redo_ocr�skip_big�optimize� jpg_quality� png_quality� jbig2_lossy�jbig2_page_group_size�pages�max_image_mpixels�tesseract_config�tesseract_pagesegmode�
tesseract_oem� pdf_renderer�tesseract_timeout�rotate_pages_threshold�pdfa_image_compression�
user_words�
user_patterns�
fast_web_view�keep_temporary_filesr3 r4 )*rH rI rP rQ rS rT rU rV rW rX rY rZ r[ r\ r] r^ r_ r` ra rb rc rd re rf rg rh ri rj rk rl rm rn ro rp rr rs ru rv rw rx r3 r4 c + . C s t f t� �}-t|-� t|-dd�S )a� Run OCRmyPDF on one PDF or image.
For most arguments, see documentation for the equivalent command line parameter.
A few specific arguments are discussed here:
Args:
use_threads (bool): Use worker threads instead of processes. This reduces
performance but may make debugging easier since it is easier to set
breakpoints.
tesseract_env (dict): Override environment variables for Tesseract
Raises:
ocrmypdf.PdfMergeFailedError: If the input PDF is malformed, preventing merging
with the OCR layer.
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`
T)Zapi)rO �localsr
r ).rH rI rP rQ rR rS rT rU rV rW rX rY rZ r[ r\ r] r^ r_ r` ra rb rc rd re rf rg rh ri rj rk rl rm rn ro rp rq rr rs rt ru rv rw rx r3 r4 rM r r r �ocr� s R rz )TF) r+ rD r �
contextlibr �enumr �pathlibr �typingr r r Z_syncr Z _validationr
Zclir r r% r2 rO �PathLiker? r= r< r> rz r r r r �<module> s�
=4�
�