Parse pdfbox versions

pdfbox_version_parsing.py

# 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:]+)'
PB_DATE_FMT = r"%Y-%m-%d %H:%M"

class PdfboxVersion (PypaVersion):
    
    def __init__(self, version, date):
        super().__init__(version)
        self.date = date
        # prioritize date over pre-release tags because pdfbox uses them inconsistently, and pre-releases will not get backports
        # (indices 0, 1 are epoch and release, the rest follows)
        self._key = (*self._key[:2], date, *self._key[2:])
    
    def __repr__(self):
        return f"PdfboxVersion({super().__str__()!r}, {self.date!r})"
    
    def __str__(self):
        return f"{super().__str__():<10} {self.date}"

content = urlopen(PB_RELEASE_URL).read().decode("utf-8")
results = [PdfboxVersion(m.group(1), datetime.strptime(m.group(2), PB_DATE_FMT)) for m in re.finditer(PB_DISTS_RE, content)]
results.sort()

if __name__ == "__main__":
    print(*results, sep="\n")

Another problem: If a backport were made to a minor release series, like so,

a.b.0  2024-07-01
a.c.0  2024-07-02
a.b.1  2024-07-03

then the above would produce the wrong order.

So sorting just by version might be better after all, we'd just need to resolve the v3 RC/alpha situation somehow:

[3.0.0-RC1/]     2021-04-01 21:18
[3.0.0-alpha2/]  2021-09-11 11:54
[3.0.0-alpha3/]  2022-06-17 12:27

Updated the code yet again. This time by inheriting from packaging's Version class and hooking date into the compare key.
While that addresses the above issue, it might be a bit wonky, because technically that's private API...