Refactor cli into basic high level api
This commit is contained in:
James R. Barlow
@@ -44,3 +44,4 @@ from . import hocrtransform
|
||||
from . import leptonica
|
||||
from . import pdfa
|
||||
from . import pdfinfo
|
||||
from .api import ocrmypdf
|
||||
|
||||
+15
-499
@@ -1,5 +1,5 @@
|
||||
#!/usr/bin/env python3
|
||||
# © 2015-17 James R. Barlow: github.com/jbarlow83
|
||||
# © 2015-19 James R. Barlow: github.com/jbarlow83
|
||||
#
|
||||
# This file is part of OCRmyPDF.
|
||||
#
|
||||
@@ -16,513 +16,29 @@
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with OCRmyPDF. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
import argparse
|
||||
import logging
|
||||
import os
|
||||
import sys
|
||||
|
||||
from tqdm import tqdm
|
||||
|
||||
from . import PROGRAM_NAME, VERSION
|
||||
from .exceptions import ExitCode
|
||||
from ._sync import run_pipeline
|
||||
from .cli import parser
|
||||
from .api import configure_logging, run as api_run
|
||||
from ._validation import check_closed_streams
|
||||
|
||||
# -------------
|
||||
# Parser
|
||||
|
||||
|
||||
def numeric(basetype, min_=None, max_=None):
|
||||
"""Validator for numeric params"""
|
||||
min_ = basetype(min_) if min_ is not None else None
|
||||
max_ = basetype(max_) if max_ is not None else None
|
||||
|
||||
def _numeric(string):
|
||||
value = basetype(string)
|
||||
if (min_ is not None and value < min_) or (max_ is not None and value > max_):
|
||||
msg = "%r not in valid range %r" % (string, (min_, max_))
|
||||
raise argparse.ArgumentTypeError(msg)
|
||||
return value
|
||||
|
||||
_numeric.__name__ = basetype.__name__
|
||||
return _numeric
|
||||
|
||||
|
||||
parser = argparse.ArgumentParser(
|
||||
prog=PROGRAM_NAME,
|
||||
fromfile_prefix_chars='@',
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||||
description="""\
|
||||
Generates a searchable PDF or PDF/A from a regular PDF.
|
||||
|
||||
OCRmyPDF rasterizes each page of the input PDF, optionally corrects page
|
||||
rotation and performs image processing, runs the Tesseract OCR engine on the
|
||||
image, and then creates a PDF from the OCR information.
|
||||
""",
|
||||
epilog="""\
|
||||
OCRmyPDF attempts to keep the output file at about the same size. If a file
|
||||
contains losslessly compressed images, and output file will be losslessly
|
||||
compressed as well.
|
||||
|
||||
PDF is a page description file that attempts to preserve a layout exactly.
|
||||
A PDF can contain vector objects (such as text or lines) and raster objects
|
||||
(images). A page might have multiple images. OCRmyPDF is prepared to deal
|
||||
with the wide variety of PDFs that exist in the wild.
|
||||
|
||||
When a PDF page contains text, OCRmyPDF assumes that the page has already
|
||||
been OCRed or is a "born digital" page that should not be OCRed. The default
|
||||
behavior is to exit in this case without producing a file. You can use the
|
||||
option --skip-text to ignore pages with text, or --force-ocr to rasterize
|
||||
all objects on the page and produce an image-only PDF as output.
|
||||
|
||||
ocrmypdf --skip-text file_with_some_text_pages.pdf output.pdf
|
||||
|
||||
ocrmypdf --force-ocr word_document.pdf output.pdf
|
||||
|
||||
If you are concerned about long-term archiving of PDFs, use the default option
|
||||
--output-type pdfa which converts the PDF to a standardized PDF/A-2b. This
|
||||
converts images to sRGB colorspace, removes some features from the PDF such
|
||||
as Javascript or forms. If you want to minimize the number of changes made to
|
||||
your PDF, use --output-type pdf.
|
||||
|
||||
If OCRmyPDF is given an image file as input, it will attempt to convert the
|
||||
image to a PDF before processing. For more control over the conversion of
|
||||
images to PDF, use the Python package img2pdf or other image to PDF software.
|
||||
|
||||
For example, this command uses img2pdf to convert all .png files beginning
|
||||
with the 'page' prefix to a PDF, fitting each image on A4-sized paper, and
|
||||
sending the result to OCRmyPDF through a pipe. img2pdf is a dependency of
|
||||
ocrmypdf so it is already installed.
|
||||
|
||||
img2pdf --pagesize A4 page*.png | ocrmypdf - myfile.pdf
|
||||
|
||||
Online documentation is located at:
|
||||
https://ocrmypdf.readthedocs.io/en/latest/introduction.html
|
||||
|
||||
""",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
'input_file',
|
||||
metavar="input_pdf_or_image",
|
||||
help="PDF file containing the images to be OCRed (or '-' to read from "
|
||||
"standard input)",
|
||||
)
|
||||
parser.add_argument(
|
||||
'output_file',
|
||||
metavar="output_pdf",
|
||||
help="Output searchable PDF file (or '-' to write to standard output). "
|
||||
"Existing files will be ovewritten. If same as input file, the "
|
||||
"input file will be updated only if processing is successful.",
|
||||
)
|
||||
parser.add_argument(
|
||||
'-l',
|
||||
'--language',
|
||||
action='append',
|
||||
help="Language(s) of the file to be OCRed (see tesseract --list-langs for "
|
||||
"all language packs installed in your system). Use -l eng+deu for "
|
||||
"multiple languages.",
|
||||
)
|
||||
parser.add_argument(
|
||||
'--image-dpi',
|
||||
metavar='DPI',
|
||||
type=int,
|
||||
help="For input image instead of PDF, use this DPI instead of file's.",
|
||||
)
|
||||
parser.add_argument(
|
||||
'--output-type',
|
||||
choices=['pdfa', 'pdf', 'pdfa-1', 'pdfa-2', 'pdfa-3'],
|
||||
default='pdfa',
|
||||
help="Choose output type. 'pdfa' creates a PDF/A-2b compliant file for "
|
||||
"long term archiving (default, recommended) but may not suitable "
|
||||
"for users who want their file altered as little as possible. 'pdfa' "
|
||||
"also has problems with full Unicode text. 'pdf' attempts to "
|
||||
"preserve file contents as much as possible. 'pdf-a1' creates a "
|
||||
"PDF/A1-b file. 'pdf-a2' is equivalent to 'pdfa'. 'pdf-a3' creates a "
|
||||
"PDF/A3-b file.",
|
||||
)
|
||||
|
||||
# Use null string '\0' as sentinel to indicate the user supplied no argument,
|
||||
# since that is the only invalid character for filepaths on all platforms
|
||||
# bool('\0') is True in Python
|
||||
parser.add_argument(
|
||||
'--sidecar',
|
||||
nargs='?',
|
||||
const='\0',
|
||||
default=None,
|
||||
metavar='FILE',
|
||||
help="Generate sidecar text files that contain the same text recognized "
|
||||
"by Tesseract. This may be useful for building a OCR text database. "
|
||||
"If FILE is omitted, the sidecar file be named {output_file}.txt "
|
||||
"If FILE is set to '-', the sidecar is written to stdout (a "
|
||||
"convenient way to preview OCR quality). The output file and sidecar "
|
||||
"may not both use stdout at the same time.",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
'--version',
|
||||
action='version',
|
||||
version=VERSION,
|
||||
help="Print program version and exit",
|
||||
)
|
||||
|
||||
jobcontrol = parser.add_argument_group("Job control options")
|
||||
jobcontrol.add_argument(
|
||||
'-j',
|
||||
'--jobs',
|
||||
metavar='N',
|
||||
type=numeric(int, 0, 256),
|
||||
help="Use up to N CPU cores simultaneously (default: use all).",
|
||||
)
|
||||
jobcontrol.add_argument(
|
||||
'-q', '--quiet', action='store_true', help="Suppress INFO messages"
|
||||
)
|
||||
jobcontrol.add_argument(
|
||||
'-v',
|
||||
'--verbose',
|
||||
type=int,
|
||||
default=0,
|
||||
nargs='?',
|
||||
help="Print more verbose messages for each additional verbose level. Use "
|
||||
"`-v 1` typically for much more detailed logging. Higher numbers "
|
||||
"are probably only useful in debugging.",
|
||||
)
|
||||
|
||||
metadata = parser.add_argument_group(
|
||||
"Metadata options",
|
||||
"Set output PDF/A metadata (default: copy input document's metadata)",
|
||||
)
|
||||
metadata.add_argument(
|
||||
'--title', type=str, help="Set document title (place multiple words in quotes)"
|
||||
)
|
||||
metadata.add_argument('--author', type=str, help="Set document author")
|
||||
metadata.add_argument('--subject', type=str, help="Set document subject description")
|
||||
metadata.add_argument('--keywords', type=str, help="Set document keywords")
|
||||
|
||||
preprocessing = parser.add_argument_group(
|
||||
"Image preprocessing options",
|
||||
"Options to improve the quality of the final PDF and OCR",
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'-r',
|
||||
'--rotate-pages',
|
||||
action='store_true',
|
||||
help="Automatically rotate pages based on detected text orientation",
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'--remove-background',
|
||||
action='store_true',
|
||||
help="Attempt to remove background from gray or color pages, setting it "
|
||||
"to white ",
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'-d', '--deskew', action='store_true', help="Deskew each page before performing OCR"
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'-c',
|
||||
'--clean',
|
||||
action='store_true',
|
||||
help="Clean pages from scanning artifacts before performing OCR, and send "
|
||||
"the cleaned page to OCR, but do not include the cleaned page in "
|
||||
"the output",
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'-i',
|
||||
'--clean-final',
|
||||
action='store_true',
|
||||
help="Clean page as above, and incorporate the cleaned image in the final "
|
||||
"PDF. Might remove desired content.",
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'--unpaper-args',
|
||||
type=str,
|
||||
default=None,
|
||||
help="A quoted string of arguments to pass to unpaper. Requires --clean. "
|
||||
"Example: --unpaper-args '--layout double'.",
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'--oversample',
|
||||
metavar='DPI',
|
||||
type=numeric(int, 0, 5000),
|
||||
default=0,
|
||||
help="Oversample images to at least the specified DPI, to improve OCR "
|
||||
"results slightly",
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'--remove-vectors',
|
||||
action='store_true',
|
||||
help="EXPERIMENTAL. Mask out any vector objects in the PDF so that they "
|
||||
"will not be included in OCR. This can eliminate false characters.",
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'--mask-barcodes',
|
||||
action='store_true',
|
||||
help="EXPERIMENTAL. Mask out any barcodes that appear in the PDF so they are not "
|
||||
"considered during OCR. Barcodes can introduce false characters into "
|
||||
"OCR.",
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'--threshold',
|
||||
action='store_true',
|
||||
help="EXPERIMENTAL. Threshold image to 1bpp before sending it to Tesseract for OCR. Can "
|
||||
"improve OCR quality compared to Tesseract's thresholder.",
|
||||
)
|
||||
|
||||
ocrsettings = parser.add_argument_group("OCR options", "Control how OCR is applied")
|
||||
ocrsettings.add_argument(
|
||||
'-f',
|
||||
'--force-ocr',
|
||||
action='store_true',
|
||||
help="Rasterize any text or vector objects on each page, apply OCR, and "
|
||||
"save the rastered output (this rewrites the PDF)",
|
||||
)
|
||||
ocrsettings.add_argument(
|
||||
'-s',
|
||||
'--skip-text',
|
||||
action='store_true',
|
||||
help="Skip OCR on any pages that already contain text, but include the "
|
||||
"page in final output; useful for PDFs that contain a mix of "
|
||||
"images, text pages, and/or previously OCRed pages",
|
||||
)
|
||||
ocrsettings.add_argument(
|
||||
'--redo-ocr',
|
||||
action='store_true',
|
||||
help="Attempt to detect and remove the hidden OCR layer from files that "
|
||||
"were previously OCRed with OCRmyPDF or another program. Apply OCR "
|
||||
"to text found in raster images. Existing visible text objects will "
|
||||
"not be changed. If there is no existing OCR, OCR will be added.",
|
||||
)
|
||||
ocrsettings.add_argument(
|
||||
'--skip-big',
|
||||
type=numeric(float, 0, 5000),
|
||||
metavar='MPixels',
|
||||
help="Skip OCR on pages larger than the specified amount of megapixels, "
|
||||
"but include skipped pages in final output",
|
||||
)
|
||||
|
||||
optimizing = parser.add_argument_group(
|
||||
"Optimization options", "Control how the PDF is optimized after OCR"
|
||||
)
|
||||
optimizing.add_argument(
|
||||
'-O',
|
||||
'--optimize',
|
||||
type=int,
|
||||
choices=range(0, 4),
|
||||
default=1,
|
||||
help=(
|
||||
"Control how PDF is optimized after processing:"
|
||||
"0 - do not optimize; "
|
||||
"1 - do safe, lossless optimizations (default); "
|
||||
"2 - do some lossy optimizations; "
|
||||
"3 - do aggressive lossy optimizations (including lossy JBIG2)"
|
||||
),
|
||||
)
|
||||
optimizing.add_argument(
|
||||
'--jpeg-quality',
|
||||
type=numeric(int, 0, 100),
|
||||
default=0,
|
||||
metavar='Q',
|
||||
help=(
|
||||
"Adjust JPEG quality level for JPEG optimization. "
|
||||
"100 is best quality and largest output size; "
|
||||
"1 is lowest quality and smallest output; "
|
||||
"0 uses the default."
|
||||
),
|
||||
)
|
||||
optimizing.add_argument(
|
||||
'--jpg-quality',
|
||||
type=numeric(int, 0, 100),
|
||||
default=0,
|
||||
metavar='Q',
|
||||
dest='jpeg_quality',
|
||||
help=argparse.SUPPRESS, # Alias for --jpeg-quality
|
||||
)
|
||||
optimizing.add_argument(
|
||||
'--png-quality',
|
||||
type=numeric(int, 0, 100),
|
||||
default=0,
|
||||
metavar='Q',
|
||||
help=(
|
||||
"Adjust PNG quality level to use when quantizing PNGs. "
|
||||
"Values have same meaning as with --jpeg-quality"
|
||||
),
|
||||
)
|
||||
optimizing.add_argument(
|
||||
'--jbig2-lossy',
|
||||
action='store_true',
|
||||
help=(
|
||||
"Enable JBIG2 lossy mode (better compression, not suitable for some "
|
||||
"use cases - see documentation)."
|
||||
),
|
||||
)
|
||||
optimizing.add_argument(
|
||||
'--jbig2-page-group-size',
|
||||
type=numeric(int, 1, 10000),
|
||||
default=0,
|
||||
metavar='N',
|
||||
# Adjust number of pages to consider at once for JBIG2 compression
|
||||
help=argparse.SUPPRESS,
|
||||
)
|
||||
|
||||
advanced = parser.add_argument_group(
|
||||
"Advanced", "Advanced options to control Tesseract's OCR behavior"
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--max-image-mpixels',
|
||||
action='store',
|
||||
type=numeric(float, 0),
|
||||
metavar='MPixels',
|
||||
help="Set maximum number of pixels to unpack before treating an image as a "
|
||||
"decompression bomb",
|
||||
default=128.0,
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--tesseract-config',
|
||||
action='append',
|
||||
metavar='CFG',
|
||||
default=[],
|
||||
help="Additional Tesseract configuration files -- see documentation",
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--tesseract-pagesegmode',
|
||||
action='store',
|
||||
type=int,
|
||||
metavar='PSM',
|
||||
choices=range(0, 14),
|
||||
help="Set Tesseract page segmentation mode (see tesseract --help)",
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--tesseract-oem',
|
||||
action='store',
|
||||
type=int,
|
||||
metavar='MODE',
|
||||
choices=range(0, 4),
|
||||
help=(
|
||||
"Set Tesseract 4.0 OCR engine mode: "
|
||||
"0 - original Tesseract only; "
|
||||
"1 - neural nets LSTM only; "
|
||||
"2 - Tesseract + LSTM; "
|
||||
"3 - default."
|
||||
),
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--pdf-renderer',
|
||||
choices=['auto', 'hocr', 'sandwich'],
|
||||
default='auto',
|
||||
help="Choose OCR PDF renderer - the default option is to let OCRmyPDF "
|
||||
"choose. See documentation for discussion.",
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--tesseract-timeout',
|
||||
default=180.0,
|
||||
type=numeric(float, 0),
|
||||
metavar='SECONDS',
|
||||
help='Give up on OCR after the timeout, but copy the preprocessed page '
|
||||
'into the final output',
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--rotate-pages-threshold',
|
||||
default=14.0,
|
||||
type=numeric(float, 0, 1000),
|
||||
metavar='CONFIDENCE',
|
||||
help="Only rotate pages when confidence is above this value (arbitrary "
|
||||
"units reported by tesseract)",
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--pdfa-image-compression',
|
||||
choices=['auto', 'jpeg', 'lossless'],
|
||||
default='auto',
|
||||
help="Specify how to compress images in the output PDF/A. 'auto' lets "
|
||||
"OCRmyPDF decide. 'jpeg' changes all grayscale and color images to "
|
||||
"JPEG compression. 'lossless' uses PNG-style lossless compression "
|
||||
"for all images. Monochrome images are always compressed using a "
|
||||
"lossless codec. Compression settings "
|
||||
"are applied to all pages, including those for which OCR was "
|
||||
"skipped. Not supported for --output-type=pdf ; that setting "
|
||||
"preserves the original compression of all images.",
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--user-words',
|
||||
metavar='FILE',
|
||||
help="Specify the location of the Tesseract user words file. This is a "
|
||||
"list of words Tesseract should consider while performing OCR in "
|
||||
"addition to its standard language dictionaries. This can improve "
|
||||
"OCR quality especially for specialized and technical documents.",
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--user-patterns',
|
||||
metavar='FILE',
|
||||
help="Specify the location of the Tesseract user patterns file.",
|
||||
)
|
||||
|
||||
debugging = parser.add_argument_group(
|
||||
"Debugging", "Arguments to help with troubleshooting and debugging"
|
||||
)
|
||||
debugging.add_argument(
|
||||
'-k',
|
||||
'--keep-temporary-files',
|
||||
action='store_true',
|
||||
help="Keep temporary files (helpful for debugging)",
|
||||
)
|
||||
|
||||
|
||||
class TqdmConsole:
|
||||
"""Wrapper to log messages in a way that is compatible with the progress bar"""
|
||||
|
||||
def __init__(self, file):
|
||||
self.file = file
|
||||
self.py36 = sys.version_info >= (3, 6)
|
||||
|
||||
def write(self, msg):
|
||||
# When no progress bar is active, tqdm.write() routes to print()
|
||||
if self.py36:
|
||||
if msg.strip() != '':
|
||||
tqdm.write(msg.rstrip(), end='\n', file=self.file)
|
||||
else:
|
||||
tqdm.write(msg.rstrip(), end='\n', file=self.file)
|
||||
|
||||
def flush(self):
|
||||
if hasattr(self.file, "flush"):
|
||||
self.file.flush()
|
||||
|
||||
|
||||
def setup_app_logging(options):
|
||||
"""Set up logging"""
|
||||
|
||||
log = logging.getLogger()
|
||||
log.setLevel(logging.INFO)
|
||||
formatter = logging.Formatter('%(levelname)7s - %(message)s')
|
||||
console = logging.StreamHandler(stream=TqdmConsole(sys.stderr))
|
||||
if options.quiet:
|
||||
console.setLevel(logging.ERROR)
|
||||
elif options.verbose >= 2:
|
||||
console.setLevel(logging.DEBUG)
|
||||
log.setLevel(logging.DEBUG)
|
||||
else:
|
||||
console.setLevel(logging.INFO)
|
||||
console.setFormatter(formatter)
|
||||
log.addHandler(console)
|
||||
|
||||
pdfminer_log = logging.getLogger('pdfminer')
|
||||
pdfminer_log.setLevel(logging.ERROR)
|
||||
|
||||
|
||||
def configure_app_environment(options):
|
||||
"""Configure the application environment
|
||||
|
||||
Don't do anything here that a library user would not expect.
|
||||
"""
|
||||
if not check_closed_streams(options):
|
||||
return ExitCode.bad_args
|
||||
if hasattr(os, 'nice'):
|
||||
os.nice(5)
|
||||
from .exceptions import ExitCode
|
||||
|
||||
|
||||
def run(args=None):
|
||||
options = parser.parse_args(args=args)
|
||||
setup_app_logging(options)
|
||||
configure_app_environment(options)
|
||||
result = run_pipeline(options)
|
||||
|
||||
if not check_closed_streams(options):
|
||||
return ExitCode.bad_args
|
||||
|
||||
if os.environ.get('PYTEST_CURRENT_TEST'):
|
||||
os.environ['_OCRMYPDF_TEST_INFILE'] = options.input_file
|
||||
if hasattr(os, 'nice'):
|
||||
os.nice(5)
|
||||
|
||||
configure_logging(options, manage_root_logger=True)
|
||||
result = api_run(options=options)
|
||||
return result
|
||||
|
||||
|
||||
|
||||
@@ -257,8 +257,6 @@ def run_pipeline(options):
|
||||
os.environ.setdefault('OMP_THREAD_LIMIT', '1')
|
||||
|
||||
check_environ(options)
|
||||
if os.environ.get('PYTEST_CURRENT_TEST'):
|
||||
os.environ['_OCRMYPDF_TEST_INFILE'] = options.input_file
|
||||
|
||||
work_folder = mkdtemp(prefix="com.github.ocrmypdf.")
|
||||
|
||||
|
||||
@@ -0,0 +1,177 @@
|
||||
# © 2019 James R. Barlow: github.com/jbarlow83
|
||||
#
|
||||
# This file is part of OCRmyPDF.
|
||||
#
|
||||
# OCRmyPDF is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
#
|
||||
# OCRmyPDF is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with OCRmyPDF. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
import argparse
|
||||
import logging
|
||||
import sys
|
||||
from pathlib import Path
|
||||
|
||||
from tqdm import tqdm
|
||||
|
||||
from .cli import parser
|
||||
from ._sync import run_pipeline
|
||||
|
||||
|
||||
class TqdmConsole:
|
||||
"""Wrapper to log messages in a way that is compatible with tqdm progress bar"""
|
||||
|
||||
def __init__(self, file):
|
||||
self.file = file
|
||||
self.py36 = sys.version_info >= (3, 6)
|
||||
|
||||
def write(self, msg):
|
||||
# When no progress bar is active, tqdm.write() routes to print()
|
||||
if self.py36:
|
||||
if msg.strip() != '':
|
||||
tqdm.write(msg.rstrip(), end='\n', file=self.file)
|
||||
else:
|
||||
tqdm.write(msg.rstrip(), end='\n', file=self.file)
|
||||
|
||||
def flush(self):
|
||||
if hasattr(self.file, "flush"):
|
||||
self.file.flush()
|
||||
|
||||
|
||||
def configure_logging(options, progress_bar_friendly=True, manage_root_logger=False):
|
||||
"""Set up logging
|
||||
|
||||
Library users may wish to use this function if they want their log output to be
|
||||
similar to ocrmypdf's when run as a command. If not use, 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:
|
||||
options: OCRmyPDF options
|
||||
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
|
||||
"""
|
||||
|
||||
prefix = '' if manage_root_logger else 'ocrmypdf'
|
||||
log = logging.getLogger(prefix)
|
||||
log.setLevel(logging.INFO)
|
||||
|
||||
if progress_bar_friendly:
|
||||
console = logging.StreamHandler(stream=TqdmConsole(sys.stderr))
|
||||
if options.quiet:
|
||||
console.setLevel(logging.ERROR)
|
||||
elif options.verbose >= 2:
|
||||
console.setLevel(logging.DEBUG)
|
||||
else:
|
||||
console.setLevel(logging.INFO)
|
||||
|
||||
formatter = logging.Formatter('%(levelname)7s - %(message)s')
|
||||
|
||||
if options.verbose >= 2:
|
||||
log.setLevel(logging.DEBUG)
|
||||
|
||||
console.setFormatter(formatter)
|
||||
log.addHandler(console)
|
||||
|
||||
pdfminer_log = logging.getLogger('pdfminer')
|
||||
pdfminer_log.setLevel(logging.ERROR)
|
||||
|
||||
|
||||
def create_options(*, input_file, output_file, **kwargs):
|
||||
cmdline = []
|
||||
|
||||
for arg, val in kwargs.items():
|
||||
if val is None:
|
||||
continue
|
||||
cmd_style_arg = arg.replace('_', '-')
|
||||
cmdline.append(f"--{cmd_style_arg}")
|
||||
if isinstance(val, bool):
|
||||
continue
|
||||
if isinstance(val, (int, float)):
|
||||
cmdline.append(str(val))
|
||||
elif isinstance(val, str):
|
||||
cmdline.append(val)
|
||||
elif isinstance(val, Path):
|
||||
cmdline.append(str(val))
|
||||
else:
|
||||
raise TypeError(f"{val} ({type(val)})")
|
||||
|
||||
cmdline.append(str(input_file))
|
||||
cmdline.append(str(output_file))
|
||||
|
||||
try:
|
||||
options = parser.parse_args(cmdline)
|
||||
except argparse.ArgumentError as e:
|
||||
raise ValueError(str(e))
|
||||
return options
|
||||
|
||||
|
||||
def ocrmypdf( # pylint: disable=unused-argument
|
||||
input_file,
|
||||
output_file,
|
||||
*,
|
||||
language=None,
|
||||
image_dpi=None,
|
||||
output_type=None,
|
||||
sidecar=None,
|
||||
jobs=None,
|
||||
quiet=None,
|
||||
verbose=None,
|
||||
title=None,
|
||||
author=None,
|
||||
subject=None,
|
||||
keywords=None,
|
||||
rotate_pages=None,
|
||||
remove_background=None,
|
||||
deskew=None,
|
||||
clean=None,
|
||||
clean_final=None,
|
||||
unpaper_args=None,
|
||||
oversample=None,
|
||||
remove_vectors=None,
|
||||
mask_barcodes=None,
|
||||
threshold=None,
|
||||
force_ocr=None,
|
||||
skip_text=None,
|
||||
redo_ocr=None,
|
||||
skip_big=None,
|
||||
optimize=None,
|
||||
jpg_quality=None,
|
||||
png_quality=None,
|
||||
jbig2_lossy=None,
|
||||
jbig2_page_group_size=None,
|
||||
max_image_mpixels=None,
|
||||
tesseract_config=None,
|
||||
tesseract_pagesegmode=None,
|
||||
tesseract_oem=None,
|
||||
pdf_renderer=None,
|
||||
tesseract_timeout=None,
|
||||
rotate_pages_threshold=None,
|
||||
pdfa_image_compression=None,
|
||||
user_words=None,
|
||||
user_patterns=None,
|
||||
keep_temporary_files=None,
|
||||
):
|
||||
options = create_options(**locals())
|
||||
return run(options)
|
||||
|
||||
|
||||
def run(options):
|
||||
return run_pipeline(options)
|
||||
@@ -0,0 +1,458 @@
|
||||
# © 2015-19 James R. Barlow: github.com/jbarlow83
|
||||
#
|
||||
# This file is part of OCRmyPDF.
|
||||
#
|
||||
# OCRmyPDF is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
#
|
||||
# OCRmyPDF is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU General Public License
|
||||
# along with OCRmyPDF. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
import argparse
|
||||
|
||||
from . import PROGRAM_NAME, VERSION
|
||||
|
||||
|
||||
# -------------
|
||||
# Parser
|
||||
|
||||
|
||||
def numeric(basetype, min_=None, max_=None):
|
||||
"""Validator for numeric params"""
|
||||
min_ = basetype(min_) if min_ is not None else None
|
||||
max_ = basetype(max_) if max_ is not None else None
|
||||
|
||||
def _numeric(string):
|
||||
value = basetype(string)
|
||||
if (min_ is not None and value < min_) or (max_ is not None and value > max_):
|
||||
msg = "%r not in valid range %r" % (string, (min_, max_))
|
||||
raise argparse.ArgumentTypeError(msg)
|
||||
return value
|
||||
|
||||
_numeric.__name__ = basetype.__name__
|
||||
return _numeric
|
||||
|
||||
|
||||
parser = argparse.ArgumentParser(
|
||||
prog=PROGRAM_NAME,
|
||||
fromfile_prefix_chars='@',
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter,
|
||||
description="""\
|
||||
Generates a searchable PDF or PDF/A from a regular PDF.
|
||||
|
||||
OCRmyPDF rasterizes each page of the input PDF, optionally corrects page
|
||||
rotation and performs image processing, runs the Tesseract OCR engine on the
|
||||
image, and then creates a PDF from the OCR information.
|
||||
""",
|
||||
epilog="""\
|
||||
OCRmyPDF attempts to keep the output file at about the same size. If a file
|
||||
contains losslessly compressed images, and output file will be losslessly
|
||||
compressed as well.
|
||||
|
||||
PDF is a page description file that attempts to preserve a layout exactly.
|
||||
A PDF can contain vector objects (such as text or lines) and raster objects
|
||||
(images). A page might have multiple images. OCRmyPDF is prepared to deal
|
||||
with the wide variety of PDFs that exist in the wild.
|
||||
|
||||
When a PDF page contains text, OCRmyPDF assumes that the page has already
|
||||
been OCRed or is a "born digital" page that should not be OCRed. The default
|
||||
behavior is to exit in this case without producing a file. You can use the
|
||||
option --skip-text to ignore pages with text, or --force-ocr to rasterize
|
||||
all objects on the page and produce an image-only PDF as output.
|
||||
|
||||
ocrmypdf --skip-text file_with_some_text_pages.pdf output.pdf
|
||||
|
||||
ocrmypdf --force-ocr word_document.pdf output.pdf
|
||||
|
||||
If you are concerned about long-term archiving of PDFs, use the default option
|
||||
--output-type pdfa which converts the PDF to a standardized PDF/A-2b. This
|
||||
converts images to sRGB colorspace, removes some features from the PDF such
|
||||
as Javascript or forms. If you want to minimize the number of changes made to
|
||||
your PDF, use --output-type pdf.
|
||||
|
||||
If OCRmyPDF is given an image file as input, it will attempt to convert the
|
||||
image to a PDF before processing. For more control over the conversion of
|
||||
images to PDF, use the Python package img2pdf or other image to PDF software.
|
||||
|
||||
For example, this command uses img2pdf to convert all .png files beginning
|
||||
with the 'page' prefix to a PDF, fitting each image on A4-sized paper, and
|
||||
sending the result to OCRmyPDF through a pipe. img2pdf is a dependency of
|
||||
ocrmypdf so it is already installed.
|
||||
|
||||
img2pdf --pagesize A4 page*.png | ocrmypdf - myfile.pdf
|
||||
|
||||
Online documentation is located at:
|
||||
https://ocrmypdf.readthedocs.io/en/latest/introduction.html
|
||||
|
||||
""",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
'input_file',
|
||||
metavar="input_pdf_or_image",
|
||||
help="PDF file containing the images to be OCRed (or '-' to read from "
|
||||
"standard input)",
|
||||
)
|
||||
parser.add_argument(
|
||||
'output_file',
|
||||
metavar="output_pdf",
|
||||
help="Output searchable PDF file (or '-' to write to standard output). "
|
||||
"Existing files will be ovewritten. If same as input file, the "
|
||||
"input file will be updated only if processing is successful.",
|
||||
)
|
||||
parser.add_argument(
|
||||
'-l',
|
||||
'--language',
|
||||
action='append',
|
||||
help="Language(s) of the file to be OCRed (see tesseract --list-langs for "
|
||||
"all language packs installed in your system). Use -l eng+deu for "
|
||||
"multiple languages.",
|
||||
)
|
||||
parser.add_argument(
|
||||
'--image-dpi',
|
||||
metavar='DPI',
|
||||
type=int,
|
||||
help="For input image instead of PDF, use this DPI instead of file's.",
|
||||
)
|
||||
parser.add_argument(
|
||||
'--output-type',
|
||||
choices=['pdfa', 'pdf', 'pdfa-1', 'pdfa-2', 'pdfa-3'],
|
||||
default='pdfa',
|
||||
help="Choose output type. 'pdfa' creates a PDF/A-2b compliant file for "
|
||||
"long term archiving (default, recommended) but may not suitable "
|
||||
"for users who want their file altered as little as possible. 'pdfa' "
|
||||
"also has problems with full Unicode text. 'pdf' attempts to "
|
||||
"preserve file contents as much as possible. 'pdf-a1' creates a "
|
||||
"PDF/A1-b file. 'pdf-a2' is equivalent to 'pdfa'. 'pdf-a3' creates a "
|
||||
"PDF/A3-b file.",
|
||||
)
|
||||
|
||||
# Use null string '\0' as sentinel to indicate the user supplied no argument,
|
||||
# since that is the only invalid character for filepaths on all platforms
|
||||
# bool('\0') is True in Python
|
||||
parser.add_argument(
|
||||
'--sidecar',
|
||||
nargs='?',
|
||||
const='\0',
|
||||
default=None,
|
||||
metavar='FILE',
|
||||
help="Generate sidecar text files that contain the same text recognized "
|
||||
"by Tesseract. This may be useful for building a OCR text database. "
|
||||
"If FILE is omitted, the sidecar file be named {output_file}.txt "
|
||||
"If FILE is set to '-', the sidecar is written to stdout (a "
|
||||
"convenient way to preview OCR quality). The output file and sidecar "
|
||||
"may not both use stdout at the same time.",
|
||||
)
|
||||
|
||||
parser.add_argument(
|
||||
'--version',
|
||||
action='version',
|
||||
version=VERSION,
|
||||
help="Print program version and exit",
|
||||
)
|
||||
|
||||
jobcontrol = parser.add_argument_group("Job control options")
|
||||
jobcontrol.add_argument(
|
||||
'-j',
|
||||
'--jobs',
|
||||
metavar='N',
|
||||
type=numeric(int, 0, 256),
|
||||
help="Use up to N CPU cores simultaneously (default: use all).",
|
||||
)
|
||||
jobcontrol.add_argument(
|
||||
'-q', '--quiet', action='store_true', help="Suppress INFO messages"
|
||||
)
|
||||
jobcontrol.add_argument(
|
||||
'-v',
|
||||
'--verbose',
|
||||
type=int,
|
||||
default=0,
|
||||
nargs='?',
|
||||
help="Print more verbose messages for each additional verbose level. Use "
|
||||
"`-v 1` typically for much more detailed logging. Higher numbers "
|
||||
"are probably only useful in debugging.",
|
||||
)
|
||||
|
||||
metadata = parser.add_argument_group(
|
||||
"Metadata options",
|
||||
"Set output PDF/A metadata (default: copy input document's metadata)",
|
||||
)
|
||||
metadata.add_argument(
|
||||
'--title', type=str, help="Set document title (place multiple words in quotes)"
|
||||
)
|
||||
metadata.add_argument('--author', type=str, help="Set document author")
|
||||
metadata.add_argument('--subject', type=str, help="Set document subject description")
|
||||
metadata.add_argument('--keywords', type=str, help="Set document keywords")
|
||||
|
||||
preprocessing = parser.add_argument_group(
|
||||
"Image preprocessing options",
|
||||
"Options to improve the quality of the final PDF and OCR",
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'-r',
|
||||
'--rotate-pages',
|
||||
action='store_true',
|
||||
help="Automatically rotate pages based on detected text orientation",
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'--remove-background',
|
||||
action='store_true',
|
||||
help="Attempt to remove background from gray or color pages, setting it "
|
||||
"to white ",
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'-d', '--deskew', action='store_true', help="Deskew each page before performing OCR"
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'-c',
|
||||
'--clean',
|
||||
action='store_true',
|
||||
help="Clean pages from scanning artifacts before performing OCR, and send "
|
||||
"the cleaned page to OCR, but do not include the cleaned page in "
|
||||
"the output",
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'-i',
|
||||
'--clean-final',
|
||||
action='store_true',
|
||||
help="Clean page as above, and incorporate the cleaned image in the final "
|
||||
"PDF. Might remove desired content.",
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'--unpaper-args',
|
||||
type=str,
|
||||
default=None,
|
||||
help="A quoted string of arguments to pass to unpaper. Requires --clean. "
|
||||
"Example: --unpaper-args '--layout double'.",
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'--oversample',
|
||||
metavar='DPI',
|
||||
type=numeric(int, 0, 5000),
|
||||
default=0,
|
||||
help="Oversample images to at least the specified DPI, to improve OCR "
|
||||
"results slightly",
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'--remove-vectors',
|
||||
action='store_true',
|
||||
help="EXPERIMENTAL. Mask out any vector objects in the PDF so that they "
|
||||
"will not be included in OCR. This can eliminate false characters.",
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'--mask-barcodes',
|
||||
action='store_true',
|
||||
help="EXPERIMENTAL. Mask out any barcodes that appear in the PDF so they are not "
|
||||
"considered during OCR. Barcodes can introduce false characters into "
|
||||
"OCR.",
|
||||
)
|
||||
preprocessing.add_argument(
|
||||
'--threshold',
|
||||
action='store_true',
|
||||
help="EXPERIMENTAL. Threshold image to 1bpp before sending it to Tesseract for OCR. Can "
|
||||
"improve OCR quality compared to Tesseract's thresholder.",
|
||||
)
|
||||
|
||||
ocrsettings = parser.add_argument_group("OCR options", "Control how OCR is applied")
|
||||
ocrsettings.add_argument(
|
||||
'-f',
|
||||
'--force-ocr',
|
||||
action='store_true',
|
||||
help="Rasterize any text or vector objects on each page, apply OCR, and "
|
||||
"save the rastered output (this rewrites the PDF)",
|
||||
)
|
||||
ocrsettings.add_argument(
|
||||
'-s',
|
||||
'--skip-text',
|
||||
action='store_true',
|
||||
help="Skip OCR on any pages that already contain text, but include the "
|
||||
"page in final output; useful for PDFs that contain a mix of "
|
||||
"images, text pages, and/or previously OCRed pages",
|
||||
)
|
||||
ocrsettings.add_argument(
|
||||
'--redo-ocr',
|
||||
action='store_true',
|
||||
help="Attempt to detect and remove the hidden OCR layer from files that "
|
||||
"were previously OCRed with OCRmyPDF or another program. Apply OCR "
|
||||
"to text found in raster images. Existing visible text objects will "
|
||||
"not be changed. If there is no existing OCR, OCR will be added.",
|
||||
)
|
||||
ocrsettings.add_argument(
|
||||
'--skip-big',
|
||||
type=numeric(float, 0, 5000),
|
||||
metavar='MPixels',
|
||||
help="Skip OCR on pages larger than the specified amount of megapixels, "
|
||||
"but include skipped pages in final output",
|
||||
)
|
||||
|
||||
optimizing = parser.add_argument_group(
|
||||
"Optimization options", "Control how the PDF is optimized after OCR"
|
||||
)
|
||||
optimizing.add_argument(
|
||||
'-O',
|
||||
'--optimize',
|
||||
type=int,
|
||||
choices=range(0, 4),
|
||||
default=1,
|
||||
help=(
|
||||
"Control how PDF is optimized after processing:"
|
||||
"0 - do not optimize; "
|
||||
"1 - do safe, lossless optimizations (default); "
|
||||
"2 - do some lossy optimizations; "
|
||||
"3 - do aggressive lossy optimizations (including lossy JBIG2)"
|
||||
),
|
||||
)
|
||||
optimizing.add_argument(
|
||||
'--jpeg-quality',
|
||||
type=numeric(int, 0, 100),
|
||||
default=0,
|
||||
metavar='Q',
|
||||
help=(
|
||||
"Adjust JPEG quality level for JPEG optimization. "
|
||||
"100 is best quality and largest output size; "
|
||||
"1 is lowest quality and smallest output; "
|
||||
"0 uses the default."
|
||||
),
|
||||
)
|
||||
optimizing.add_argument(
|
||||
'--jpg-quality',
|
||||
type=numeric(int, 0, 100),
|
||||
default=0,
|
||||
metavar='Q',
|
||||
dest='jpeg_quality',
|
||||
help=argparse.SUPPRESS, # Alias for --jpeg-quality
|
||||
)
|
||||
optimizing.add_argument(
|
||||
'--png-quality',
|
||||
type=numeric(int, 0, 100),
|
||||
default=0,
|
||||
metavar='Q',
|
||||
help=(
|
||||
"Adjust PNG quality level to use when quantizing PNGs. "
|
||||
"Values have same meaning as with --jpeg-quality"
|
||||
),
|
||||
)
|
||||
optimizing.add_argument(
|
||||
'--jbig2-lossy',
|
||||
action='store_true',
|
||||
help=(
|
||||
"Enable JBIG2 lossy mode (better compression, not suitable for some "
|
||||
"use cases - see documentation)."
|
||||
),
|
||||
)
|
||||
optimizing.add_argument(
|
||||
'--jbig2-page-group-size',
|
||||
type=numeric(int, 1, 10000),
|
||||
default=0,
|
||||
metavar='N',
|
||||
# Adjust number of pages to consider at once for JBIG2 compression
|
||||
help=argparse.SUPPRESS,
|
||||
)
|
||||
|
||||
advanced = parser.add_argument_group(
|
||||
"Advanced", "Advanced options to control Tesseract's OCR behavior"
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--max-image-mpixels',
|
||||
action='store',
|
||||
type=numeric(float, 0),
|
||||
metavar='MPixels',
|
||||
help="Set maximum number of pixels to unpack before treating an image as a "
|
||||
"decompression bomb",
|
||||
default=128.0,
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--tesseract-config',
|
||||
action='append',
|
||||
metavar='CFG',
|
||||
default=[],
|
||||
help="Additional Tesseract configuration files -- see documentation",
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--tesseract-pagesegmode',
|
||||
action='store',
|
||||
type=int,
|
||||
metavar='PSM',
|
||||
choices=range(0, 14),
|
||||
help="Set Tesseract page segmentation mode (see tesseract --help)",
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--tesseract-oem',
|
||||
action='store',
|
||||
type=int,
|
||||
metavar='MODE',
|
||||
choices=range(0, 4),
|
||||
help=(
|
||||
"Set Tesseract 4.0 OCR engine mode: "
|
||||
"0 - original Tesseract only; "
|
||||
"1 - neural nets LSTM only; "
|
||||
"2 - Tesseract + LSTM; "
|
||||
"3 - default."
|
||||
),
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--pdf-renderer',
|
||||
choices=['auto', 'hocr', 'sandwich'],
|
||||
default='auto',
|
||||
help="Choose OCR PDF renderer - the default option is to let OCRmyPDF "
|
||||
"choose. See documentation for discussion.",
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--tesseract-timeout',
|
||||
default=180.0,
|
||||
type=numeric(float, 0),
|
||||
metavar='SECONDS',
|
||||
help='Give up on OCR after the timeout, but copy the preprocessed page '
|
||||
'into the final output',
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--rotate-pages-threshold',
|
||||
default=14.0,
|
||||
type=numeric(float, 0, 1000),
|
||||
metavar='CONFIDENCE',
|
||||
help="Only rotate pages when confidence is above this value (arbitrary "
|
||||
"units reported by tesseract)",
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--pdfa-image-compression',
|
||||
choices=['auto', 'jpeg', 'lossless'],
|
||||
default='auto',
|
||||
help="Specify how to compress images in the output PDF/A. 'auto' lets "
|
||||
"OCRmyPDF decide. 'jpeg' changes all grayscale and color images to "
|
||||
"JPEG compression. 'lossless' uses PNG-style lossless compression "
|
||||
"for all images. Monochrome images are always compressed using a "
|
||||
"lossless codec. Compression settings "
|
||||
"are applied to all pages, including those for which OCR was "
|
||||
"skipped. Not supported for --output-type=pdf ; that setting "
|
||||
"preserves the original compression of all images.",
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--user-words',
|
||||
metavar='FILE',
|
||||
help="Specify the location of the Tesseract user words file. This is a "
|
||||
"list of words Tesseract should consider while performing OCR in "
|
||||
"addition to its standard language dictionaries. This can improve "
|
||||
"OCR quality especially for specialized and technical documents.",
|
||||
)
|
||||
advanced.add_argument(
|
||||
'--user-patterns',
|
||||
metavar='FILE',
|
||||
help="Specify the location of the Tesseract user patterns file.",
|
||||
)
|
||||
|
||||
debugging = parser.add_argument_group(
|
||||
"Debugging", "Arguments to help with troubleshooting and debugging"
|
||||
)
|
||||
debugging.add_argument(
|
||||
'-k',
|
||||
'--keep-temporary-files',
|
||||
action='store_true',
|
||||
help="Keep temporary files (helpful for debugging)",
|
||||
)
|
||||
Reference in New Issue
Block a user