menekis/OCRmyPDF
Public Access
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Move optimization options to plugin

Browse Source
This commit is contained in:
James R. Barlow
2022-06-12 02:42:16 -07:00
parent 685a06c93d
commit 61069660a2
5 changed files with 113 additions and 103 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/ocrmypdf/_pipeline.py
+1 -1
View File
@@ -822,7 +822,7 @@ def metadata_fixup(working_file: Path, context: PdfContext):
**get_pdf_save_settings(options.output_type),
linearize=( # Don't linearize if optimize() will be linearizing too
should_linearize(working_file, context)
if options.optimize == 0
if hasattr(options, 'optimize') and options.optimize == 0
else False
),
)
src/ocrmypdf/_validation.py
+1 -33
View File
@@ -194,37 +194,6 @@ def check_options_ocr_behavior(options):
options.pages = _pages_from_ranges(options.pages)
def check_options_optimizing(options):
if options.optimize >= 2:
check_external_program(
program='pngquant',
package='pngquant',
version_checker=pngquant.version,
need_version='2.0.1',
required_for='--optimize {2,3}',
)
if options.optimize >= 2:
# Although we use JBIG2 for optimize=1, don't nag about it unless the
# user is asking for more optimization
check_external_program(
program='jbig2',
package='jbig2enc',
version_checker=jbig2enc.version,
need_version='0.28',
required_for='--optimize {2,3} | --jbig2-lossy',
recommended=True if not options.jbig2_lossy else False,
)
if options.optimize == 0 and any(
[options.jbig2_lossy, options.png_quality, options.jpeg_quality]
):
log.warning(
"The arguments --jbig2-lossy, --png-quality, and --jpeg-quality "
"will be ignored because --optimize=0."
)
def check_options_advanced(options):
if options.pdfa_image_compression != 'auto' and not options.output_type.startswith(
'pdfa'
@@ -262,7 +231,6 @@ def _check_options(options, plugin_manager, ocr_engine_languages):
check_options_sidecar(options)
check_options_preprocessing(options)
check_options_ocr_behavior(options)
check_options_optimizing(options)
check_options_advanced(options)
check_options_pillow(options)
plugin_manager.hook.check_options(options=options)
@@ -356,7 +324,7 @@ def report_output_file_size(
f"The argument --{arg.replace('_', '-')} was issued, causing transcoding."
)
if options.optimize == 0:
if hasattr(options, 'optimize') and options.optimize == 0:
reasons.append("Optimization was disabled.")
else:
image_optimizers = {
src/ocrmypdf/builtin_plugins/optimize.py
+108
View File
@@ -7,12 +7,120 @@
"""Built-in plugin to implement PDF page optimization."""
import argparse
import logging
from pathlib import Path
from ocrmypdf import PdfContext, hookimpl
from ocrmypdf._concurrent import Executor
from ocrmypdf._exec import jbig2enc, pngquant
from ocrmypdf._pipeline import get_pdf_save_settings, should_linearize
from ocrmypdf.cli import numeric
from ocrmypdf.optimize import optimize
from ocrmypdf.subprocess import check_external_program
log = logging.getLogger(__name__)
@hookimpl
def add_options(parser):
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 lossy JPEG and JPEG2000 optimizations; "
"3 - do more aggressive lossy JPEG and JPEG2000 optimizations. "
"To enable lossy JBIG2, see --jbig2-lossy."
),
)
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). Only takes effect if --optimize 1 or "
"higher is also enabled."
),
)
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,
)
@hookimpl
def check_options(options):
if options.optimize >= 2:
check_external_program(
program='pngquant',
package='pngquant',
version_checker=pngquant.version,
need_version='2.0.1',
required_for='--optimize {2,3}',
)
if options.optimize >= 2:
# Although we use JBIG2 for optimize=1, don't nag about it unless the
# user is asking for more optimization
check_external_program(
program='jbig2',
package='jbig2enc',
version_checker=jbig2enc.version,
need_version='0.28',
required_for='--optimize {2,3} | --jbig2-lossy',
recommended=True if not options.jbig2_lossy else False,
)
if options.optimize == 0 and any(
[options.jbig2_lossy, options.png_quality, options.jpeg_quality]
):
log.warning(
"The arguments --jbig2-lossy, --png-quality, and --jpeg-quality "
"will be ignored because --optimize=0."
)
@hookimpl
src/ocrmypdf/cli.py
-66
View File
@@ -352,72 +352,6 @@ Online documentation is located at:
"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 lossy JPEG and JPEG2000 optimizations; "
"3 - do more aggressive lossy JPEG and JPEG2000 optimizations. "
"To enable lossy JBIG2, see --jbig2-lossy."
),
)
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). Only takes effect if --optimize 1 or "
"higher is also enabled."
),
)
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 OCRmyPDF"
)
tests/test_validation.py
+3 -3
View File
@@ -92,9 +92,9 @@ def test_mutex_options():
def test_optimizing(caplog):
vd.check_options_optimizing(
make_opts(optimize=0, jbig2_lossy=True, png_quality=18, jpeg_quality=10)
)
opts = make_opts(optimize=0, jbig2_lossy=True, png_quality=18, jpeg_quality=10)
plugin_manager = get_plugin_manager(opts.plugins)
vd._check_options(opts, plugin_manager, set())
assert 'will be ignored because' in caplog.text