mara004

# SPDX-FileCopyrightText: 2024 geisserml <[email protected]>
# SPDX-License-Identifier: MPL-2.0
# Note that Poppler is GPL-licensed, so this code is altogether affected by copyleft

import math
from pathlib import Path
import PIL.Image

import cairo
import gi

mara004

# Four lines intentionally left blank




# SPDX-FileCopyrightText: 2025 geisserml <[email protected]>
# SPDX-License-Identifier: MPL-2.0

# Sophisticated parser for a page number mini-language
# Technically, this might be a use case for some parser generator like pyparsing or PLY, but this is a manual implementation based on common string operations.

mara004

# SPDX-FileCopyrightText: 2024 geisserml <[email protected]>
# SPDX-License-Identifier: Apache-2.0 OR BSD-3-Clause

import sys
import argparse

if sys.version_info >= (3, 9):
    from argparse import BooleanOptionalAction

else:

mara004

# Four lines intentionally left blank




# SPDX-FileCopyrightText: 2025 geisserml <[email protected]>
# SPDX-License-Identifier: Apache-2.0 OR BSD-3-Clause

import argparse
from pathlib import Path

mara004

# SPDX-FileCopyrightText: 2023 geisserml <[email protected]>
# SPDX-License-Identifier: CC-BY-4.0 OR Apache-2.0 OR BSD-3-Clause

# Unlike repository files, there is no "raw view" for GH releases, but we can extract the plain markdown content using GH web API
# See also https://stackoverflow.com/q/76995969/15547292

# The following code snippet shows how to get a release title from pdfium-binaries to extract the full version

import re
import json

mara004

# SPDX-FileCopyrightText: 2023 geisserml <[email protected]>
# SPDX-License-Identifier: Apache-2.0 OR BSD-3-Clause OR MPL-2.0

# Safer tar extraction (hopefully) preventing CVE-2007-4559 etc.
# Tries to use the most elegant strategy available in the caller's python version (>= 3.6)

__all__ = ["safer_tar_unpack"]

import sys
if sys.version_info >= (3, 11, 4):  # PEP 706

mara004

# Four lines intentionally left blank




# SPDX-FileCopyrightText: 2025 geisserml <[email protected]>
# SPDX-License-Identifier: Apache-2.0 OR MPL-2.0

# See also https://github.com/extremeheat/JSPyBridge/blob/master/examples/python/pdfjs.py

mara004

# SPDX-FileCopyrightText: 2024 geisserml <[email protected]>
# SPDX-License-Identifier: Apache-2.0

import re
from datetime import datetime
from urllib.request import urlopen
from packaging.version import Version as PypaVersion

PB_RELEASE_URL = "https://archive.apache.org/dist/pdfbox/"
PB_DISTS_RE = r'<a href="([\d\.]+.+?)/">.+</a>\s+([\d\-]+ [\d:]+)'

mara004

# Four lines intentionally left blank




# SPDX-FileCopyrightText: 2025 geisserml <[email protected]>
# SPDX-License-Identifier: Apache-2.0 OR MPL-2.0

# Assuming you have an Apache PDFBox 3 jar in the same directory