#!/usr/bin/env python3
"""Compute the next monotonic Android versionCode for an application id.

Implements the rule from fdroid-repo-ci#6 -- read that issue (including the
"Superseded" sections, which change the original rule) for the full
reasoning; this is only the arithmetic and the index read.

    candidate  = whole minutes since 2026-01-01T00:00:00Z, of the COMMITTER
                 date of the commit being built
    candidate  = min(candidate, minutes(now) + TOLERANCE)   -- forwards
    published  = highest versionCode already in the index for this app id
    result     = max(candidate, published + 1)              -- backwards

Minutes, not seconds or raw Unix time: versionCode is a signed 32-bit int,
and minutes-since-2026 does not exhaust it for 4,082 years. Granularity is
not what keeps two builds of the same commit from colliding any more --
that is now a concurrency-group-plus-refuse-on-existing problem, handled
elsewhere (see the README) -- so minutes stand purely as a wide, cheap
headroom choice.

The candidate is derived from the COMMIT being built, not the build clock,
so the result is a function of the commit rather than of when a runner
happened to pick the job up: rebuilding the identical commit twice (e.g. a
retry) yields the identical number. That determinism is what makes the two
clamps below necessary, one per direction:

BACKWARDS -- rebase, amend and cherry-pick can all produce a commit that is
older than one already published, and it must not be allowed to re-emit a
number a device has already seen a higher one for. This is why the
COMMITTER date is used and not the author date: author date is preserved
across a rebase, so a rebased branch would keep replaying its original
(now stale) timestamp and defeat this exact clamp. Committer date changes
every time the commit is rewritten, which is what makes "published + 1"
actually catch it.

FORWARDS -- a commit's timestamp is attacker- and typo-controlled (it is
just a field in a commit object anyone with push access can set), and the
version code this produces only ever goes up, so a bad one can never be
walked back down. A commit dated a century in the future would burn decades
of headroom permanently; worse, a value placed just *below* the int32
ceiling would still be accepted by Android, would still publish, and then
NO LATER BUILD COULD EVER EXCEED IT -- the application becomes permanently
un-updatable, recoverable only by shipping a new applicationId and asking
every user to reinstall by hand. Do not remove this clamp to "simplify" the
arithmetic; it is the one guarding against unrecoverable, not merely
annoying, breakage.

TOLERANCE exists only to absorb honest clock skew between the committer's
machine and the runner that builds it -- a few hours is generous for that,
a full day would still be harmless, since its only job is keeping the
number near the present, not pinning it exactly. A future-dated commit is
therefore CLAMPED AND A WARNING IS PRINTED, never rejected outright:
rejecting would block a legitimate build over a few minutes of innocent
skew, and the clamp already removes the actual harm (a permanently reserved
version code range), so there is nothing left for a hard failure to buy.

Reads `packages.<applicationId>.versions.*.manifest.versionCode`, the shape
fdroidserver's own index.py actually writes (`packages` keyed by
applicationId/packageName; `versions` a dict keyed by each APK's sha256, not
a list; the versionCode nested under that version's `manifest`) -- verified
against fdroidserver's source, not assumed from an older v1-shaped example.

An application id absent from the index entirely is not an error: it is the
first-ever publish for a channel, and "published" is then simply nobody, so
the bare (clamped) candidate is correct. An unreadable or unparseable index
IS an error -- guessing a number when the published state is unknown is
exactly how a duplicate or a decrease gets published.

Standard library only, deliberately -- no third-party dependency for a
script that reads a signed index. `urllib.request` handles the http(s)
case; a local path is read directly, which is what makes the offline test
suite possible (fixture index-v2.json files, no server, no network).
"""
import argparse
import datetime
import json
import os
import sys
import urllib.request

EPOCH = datetime.datetime(2026, 1, 1, 0, 0, 0, tzinfo=datetime.timezone.utc)

# Clock skew between the committer's machine and the runner, absorbed
# without complaint. Not tight by design -- see the FORWARDS section of the
# module docstring for why a generous value here is fine: this only has to
# keep a well-formed commit's number near the present, not pin it exactly,
# and everything past it is clamped (and warned about) regardless of size.
TOLERANCE_MINUTES = 6 * 60  # 6 hours


def minutes_since_epoch(dt):
    return int((dt - EPOCH).total_seconds() // 60)


def load_index(source, timeout=30):
    """source is an http(s) URL or a local file path to index-v2.json."""
    if source.startswith("http://") or source.startswith("https://"):
        with urllib.request.urlopen(source, timeout=timeout) as resp:
            data = resp.read()
    else:
        with open(source, "rb") as f:
            data = f.read()
    return json.loads(data)


def highest_published_version_code(index, application_id):
    """The highest versionCode already published for application_id, or None
    if the index has no entry for it at all (a normal state: the first
    publish for this channel)."""
    packages = index.get("packages") or {}
    package = packages.get(application_id)
    if not package:
        return None
    versions = package.get("versions") or {}
    codes = [
        manifest["versionCode"]
        for version in versions.values()
        if isinstance((manifest := (version or {}).get("manifest")), dict)
        and isinstance(manifest.get("versionCode"), int)
    ]
    return max(codes) if codes else None


def clamped_candidate(committer_time, now, tolerance_minutes=TOLERANCE_MINUTES):
    """The forwards clamp: minutes-since-epoch of the commit's committer
    date, capped at minutes-since-epoch of "now" plus TOLERANCE. Warns on
    stderr (never fails) when the cap actually bites, since that is either a
    broken clock or someone probing, and both are worth seeing in the log --
    see the FORWARDS section of the module docstring for why this is a
    clamp-and-warn rather than a rejection."""
    candidate = minutes_since_epoch(committer_time)
    ceiling = minutes_since_epoch(now) + tolerance_minutes
    if candidate > ceiling:
        print(
            f"next_version_code.py: warning: committer date "
            f"{committer_time.isoformat()} is {candidate - ceiling} minute(s) "
            f"beyond now+tolerance; clamping the version code candidate to "
            f"{ceiling} instead of {candidate}",
            file=sys.stderr,
        )
        return ceiling
    return candidate


def next_version_code(source, application_id, committer_time, now=None):
    now = now if now is not None else datetime.datetime.now(datetime.timezone.utc)
    index = load_index(source)
    candidate = clamped_candidate(committer_time, now)
    published = highest_published_version_code(index, application_id)
    if published is None:
        return candidate
    return max(candidate, published + 1)


def _parse_committer_timestamp(value):
    # Unix seconds, exactly what `git log -1 --format=%ct` prints -- the
    # caller already has the commit, so this script takes it as an argument
    # rather than shelling out to git itself (fdroid-repo-ci#6: keeps this
    # script pure and testable).
    try:
        seconds = int(value)
    except ValueError:
        raise argparse.ArgumentTypeError(
            f"expected Unix seconds (e.g. `git log -1 --format=%ct`), got {value!r}"
        )
    return datetime.datetime.fromtimestamp(seconds, tz=datetime.timezone.utc)


def main(argv):
    parser = argparse.ArgumentParser(
        description="Print the next monotonic versionCode for an application id."
    )
    parser.add_argument("index_source", help="index-v2.json URL or local path")
    parser.add_argument("application_id")
    parser.add_argument(
        "committer_timestamp",
        type=_parse_committer_timestamp,
        help="committer date of the commit being built, as Unix seconds "
             "(`git log -1 --format=%%ct`)",
    )
    args = parser.parse_args(argv)

    # Testing seam only, deliberately undocumented in the usage banner: lets
    # the offline suite pin "now" -- the runner's clock, used only for the
    # forwards clamp -- to a fixed, known value instead of whatever minute
    # the test happens to run in. Unset in every real invocation, so
    # production behaviour is untouched.
    now = None
    now_override = os.environ.get("NEXT_VERSION_CODE_NOW")
    if now_override:
        now = datetime.datetime.fromisoformat(now_override)
        if now.tzinfo is None:
            now = now.replace(tzinfo=datetime.timezone.utc)

    try:
        result = next_version_code(
            args.index_source, args.application_id, args.committer_timestamp, now=now
        )
    except (OSError, ValueError) as e:
        # OSError covers both a local file that can't be read and a network
        # failure (urllib.error.URLError is a subclass); ValueError covers
        # malformed JSON. Fail loudly on stderr, print nothing on stdout --
        # a caller doing `versionCode=$(next-version-code.sh ...)` must never
        # capture a number that was actually an error message.
        print(f"next-version-code.py: could not read the index at "
              f"{args.index_source!r}: {e}", file=sys.stderr)
        return 1

    print(result)
    return 0


if __name__ == "__main__":
    sys.exit(main(sys.argv[1:]))