Files
OCRmyPDF/src/ocrmypdf/_exec/pngquant.py
T
James R. Barlow 84f5fe9ee0 Separate probing from execution in _exec and subprocess modules
Split ocrmypdf.subprocess/__init__.py into three private submodules by
concern (_run, _version, _check) and reduce __init__ to re-exports.
Introduce ocrmypdf._exec._probe.ToolProbe to centralize the version()/
available() pattern each tool module was reimplementing, so the "is this
tool installed and suitable?" question is cleanly distinct from the
pure, picklable functions that do the work.

Also replace the ghostscript module-import log.addFilter() side effect
with an idempotent _ensure_log_filter_installed() called at the top of
each work function, so the DuplicateFilter is present in subprocess
workers without relying on import-time ordering.

Public API of ocrmypdf.subprocess is unchanged.
2026-04-24 13:33:34 -07:00

43 lines
1.3 KiB
Python

# SPDX-FileCopyrightText: 2022 James R. Barlow
# SPDX-License-Identifier: MPL-2.0
"""Interface to pngquant executable."""
from __future__ import annotations
from pathlib import Path
from subprocess import PIPE
from ocrmypdf._exec._probe import ToolProbe
from ocrmypdf.subprocess import run
PROBE = ToolProbe(program='pngquant', version_regex=r'(\d+(\.\d+)*).*')
version = PROBE.version
available = PROBE.available
def quantize(input_file: Path, output_file: Path, quality_min: int, quality_max: int):
"""Quantize a PNG image using pngquant.
Args:
input_file: Input PNG image
output_file: Output PNG image
quality_min: Minimum quality to use
quality_max: Maximum quality to use
"""
with open(input_file, 'rb') as input_stream:
args = [
'pngquant',
'--force',
'--skip-if-larger',
'--quality',
f'{quality_min}-{quality_max}',
'--', # pngquant: stop processing arguments
'-', # pngquant: stream input and output
]
result = run(args, stdin=input_stream, stdout=PIPE, stderr=PIPE, check=False)
if result.returncode == 0:
# input_file could be the same as output_file, so we defer the write
output_file.write_bytes(result.stdout)