Files
shopdb-flask/plugins/backups/api/routes.py
cproudlock 6c975a107c
Some checks failed
CI / backend (push) Failing after 8s
CI / naming (push) Successful in 2s
CI / frontend (push) Successful in 10s
CI / migrations-mysql (push) Failing after 7s
backups: record that a config was checked, not only that it changed
The stale-backup card could not be built as designed, and the reason is more
important than the card. Dedup means an unchanged configuration writes no
revision, so collectedat moves only on a CHANGE. A machine stable for six
months has a six-month-old newest revision and is perfectly healthy. Keying a
staleness card on revision age would have flagged most of the fleet - exactly
the noise that makes a board worth ignoring.

Underneath that: ShopDB could not distinguish those cases at all. On a no-op
the server returned "unchanged" and wrote nothing, so "we checked yesterday and
it matched" was discarded. That fact is the one thing a backup system must be
able to prove, and the only record of it was a line in a log file on the PC.

lastseenat records the check rather than the change. Touched on every matching
post including the no-op; set on creation, since a new revision has by
definition just been seen; backfilled from collectedat or createdat so existing
rows start from the last moment the config can be PROVEN current, rather than
from now - claiming a check that never happened would be worse than silence.

The card keys on it, one row per CHAIN rather than per asset: a machine with
two part markers can have one still reporting while the other stopped, and a
per-asset view would report the machine as fine. It stays deliberately silent
about assets never backed up, because whether one SHOULD be is a question only
the manifest can answer, and guessing would list a hundred healthy machines.

The rule lives in services/staleness.py rather than the route, so it is
testable without an auth layer in the way - the same split retention.py uses.

Threshold is backups_staledays, default 3, and 0 disables the card.
2026-08-11 13:52:07 -04:00

363 lines
13 KiB
Python

"""Backups API.
Read + download only. Revisions are created exclusively through the ADR-006
collector endpoint (POST /api/collector/backups), so there is deliberately no
create route here: a hand-posted "backup" that never came off a machine would
poison the history this feature exists to provide.
Downloads differ by storage backend. 'shopdb' kinds re-render from the stored
projection, which is what lets one revision produce either .reg dialect. 'share'
kinds are not streamed - ShopDB returns the UNC path for the tech to open,
because requiring the app server to mount the SFLD share would turn a
permissions slip into an unexplained empty download.
"""
from datetime import timezone
from zoneinfo import ZoneInfo
from flask import Blueprint, current_app, request, Response
from flask_jwt_extended import jwt_required
from shopdb.api import (
db, Asset,
success_response, error_response, ErrorCodes,
require_permission,
)
from ..models import BackupRevision
from ..models.backup import _utciso
from ..services.registry import REGISTRY, getkind
from ..services.retention import samesource
backups_bp = Blueprint('backups', __name__)
_DEFAULTTZ = 'America/New_York'
def _sitezone():
"""Site-configured IANA zone (settings key site_timezone).
Same lookup the notifications plugin uses. A stored timestamp is UTC, so
anything rendered server-side has to be converted or it shows the wrong
wall clock for the site - four hours out at West Jefferson.
"""
from shopdb.api import Setting
row = Setting.query.filter_by(key='site_timezone').first()
name = row.value if row and row.value else _DEFAULTTZ
try:
return ZoneInfo(name)
except Exception:
return ZoneInfo(_DEFAULTTZ)
def _label(revision):
"""Panel list title: kind-agnostic, readable at a glance.
Rendered in the SITE zone, not UTC: this string is baked server-side and
the client cannot correct it afterwards.
"""
when = revision.collectedat or revision.createdat
if not when:
return 'unknown time'
local = when.replace(tzinfo=timezone.utc).astimezone(_sitezone())
stamp = local.strftime('%Y-%m-%d %H:%M')
if revision.sourcefilename:
return '{} - {}'.format(stamp, revision.sourcefilename)
return stamp
def _summary(revision, islatest=False):
data = revision.to_dict()
data['label'] = _label(revision)
data['islatest'] = islatest
kind = getkind(revision.backupkind)
data['formats'] = kind.formats() if kind else []
return data
@backups_bp.route('/kinds', methods=['GET'])
@jwt_required()
@require_permission('backups.view')
def list_kinds():
"""Registered backup kinds, for UI that needs to enumerate them."""
return success_response([
{
'key': kind.key,
'displayname': kind.displayname,
'storagebackend': kind.storagebackend,
'assettypes': list(kind.assettypes),
'formats': kind.formats(),
}
for kind in REGISTRY.values()
])
@backups_bp.route('/asset/<int:assetid>', methods=['GET'])
@jwt_required()
@require_permission('backups.view')
def asset_revisions(assetid):
"""Revision history for one asset, newest first.
This is the asset-panel endpoint. Optional ?kind= narrows to a single kind,
which is how each per-kind panel scopes itself.
"""
asset = db.session.get(Asset, assetid)
if asset is None:
return error_response(ErrorCodes.NOT_FOUND, 'Asset not found', http_code=404)
query = db.session.query(BackupRevision).filter(
BackupRevision.assetid == assetid)
kindkey = (request.args.get('kind') or '').strip().lower()
if kindkey:
if getkind(kindkey) is None:
return error_response(ErrorCodes.VALIDATION_ERROR,
'Unknown kind: {}'.format(kindkey))
query = query.filter(BackupRevision.backupkind == kindkey)
revisions = query.order_by(BackupRevision.backuprevisionid.desc()).all()
# "Latest" is per kind, not per asset, so an unfiltered listing still marks
# the current revision of each kind correctly.
seen = set()
out = []
for revision in revisions:
islatest = revision.backupkind not in seen
seen.add(revision.backupkind)
out.append(_summary(revision, islatest=islatest))
return success_response(out)
@backups_bp.route('/asset/<int:assetid>/info', methods=['GET'])
@jwt_required()
@require_permission('backups.view')
def asset_info(assetid):
"""A kind's 'at a glance' card, built from its LATEST revision.
Generic across kinds: the requested kind owns both the panel declaration
and the payload (see BackupKind.infopanel / buildinfo), so a successor to
NTLARS/DNC gets its own card without a new endpoint.
Empty when the machine has no revision of that kind yet, which the generic
renderer turns into the panel's empty text.
"""
kindkey = (request.args.get('kind') or 'ntlars').strip().lower()
kind = getkind(kindkey)
if kind is None:
return error_response(ErrorCodes.VALIDATION_ERROR,
'Unknown kind: {}'.format(kindkey))
revision = (db.session.query(BackupRevision)
.filter(BackupRevision.assetid == assetid,
BackupRevision.backupkind == kindkey)
.order_by(BackupRevision.backuprevisionid.desc())
.first())
if revision is None:
return success_response({'fields': [], 'sectioncount': 0})
data = kind.buildinfo(
revision.payload, assetid,
partmarkertypes=current_app.config.get('BACKUPS_PARTMARKER_TYPES'))
data['backuprevisionid'] = revision.backuprevisionid
data['collectedat'] = _utciso(revision.collectedat)
return success_response(data)
@backups_bp.route('/revisions/<int:backuprevisionid>', methods=['GET'])
@jwt_required()
@require_permission('backups.view')
def get_revision(backuprevisionid):
"""One revision, including its parsed payload where there is one."""
revision = db.session.get(BackupRevision, backuprevisionid)
if revision is None:
return error_response(ErrorCodes.NOT_FOUND, 'Revision not found',
http_code=404)
data = revision.to_dict(includepayload=True)
data['label'] = _label(revision)
kind = getkind(revision.backupkind)
data['formats'] = kind.formats() if kind else []
data['displayname'] = kind.displayname if kind else revision.backupkind
return success_response(data)
@backups_bp.route('/revisions/<int:backuprevisionid>/download', methods=['GET'])
@jwt_required()
@require_permission('backups.download')
def download_revision(backuprevisionid):
"""Render a revision back to its native file format.
?format=ntlars (default for NTLARS) omits WOW6432Node - the form the
NTLARS Load... button expects
?format=wow6432node includes WOW6432Node - for `reg import` on 64-bit
"""
revision = db.session.get(BackupRevision, backuprevisionid)
if revision is None:
return error_response(ErrorCodes.NOT_FOUND, 'Revision not found',
http_code=404)
kind = getkind(revision.backupkind)
if kind is None:
return error_response(ErrorCodes.VALIDATION_ERROR,
'Unknown kind: {}'.format(revision.backupkind))
if revision.storagebackend == 'share':
# Not an error: the file exists, ShopDB just is not the one serving it.
return success_response({
'storagebackend': 'share',
'sharepath': revision.sharepath,
'sourcefilename': revision.sourcefilename,
'message': 'This backup lives on the SFLD share. Open the path directly.',
})
formats = kind.formats()
formatid = (request.args.get('format') or '').strip().lower()
if not formatid:
formatid = formats[0]['id'] if formats else ''
if not any(f['id'] == formatid for f in formats):
return error_response(
ErrorCodes.VALIDATION_ERROR,
'Unknown format {!r} for kind {}'.format(formatid, kind.key))
asset = db.session.get(Asset, revision.assetid)
assetnumber = asset.assetnumber if asset else str(revision.assetid)
when = revision.collectedat or revision.createdat
comments = [
'{} backup from ShopDB'.format(kind.displayname),
'Asset: {}'.format(assetnumber),
'Captured: {}'.format(when.strftime('%Y-%m-%d %H:%M:%S') if when else 'unknown'),
'Source PC: {}'.format(revision.sourcehostname or 'unknown'),
'Revision: {} ({})'.format(revision.backuprevisionid,
(revision.contenthash or '')[:12]),
]
try:
raw, ext, mimetype = kind.render(revision.payload, formatid,
comments=comments)
except ValueError as exc:
return error_response(ErrorCodes.VALIDATION_ERROR, str(exc))
# Named for the MACHINE, not the revision or the kind: a tech restoring bay
# 3204 wants 3204.reg, matching how the per-machine backups on the share
# have always been named. sourcefilename is deliberately not reused here -
# a seeded revision carries "3204.reg" already and appending an extension
# to it produced "3204.reg.reg".
filename = '{}{}'.format(assetnumber, ext)
if formatid == 'wow6432node':
# The two dialects must not collide in a downloads folder, and the
# suffix says which one will import correctly outside NTLARS.
filename = '{}-wow6432node{}'.format(assetnumber, ext)
return Response(
raw,
mimetype=mimetype,
headers={'Content-Disposition': 'attachment; filename="{}"'.format(filename)},
)
@backups_bp.route('/revisions/<int:backuprevisionid>/diff', methods=['GET'])
@jwt_required()
@require_permission('backups.view')
def diff_revision(backuprevisionid):
"""Diff two revisions of the same asset+kind.
?against=<id> picks the comparison revision; default is the immediately
preceding one, which answers "what changed" without the user choosing.
"""
revision = db.session.get(BackupRevision, backuprevisionid)
if revision is None:
return error_response(ErrorCodes.NOT_FOUND, 'Revision not found',
http_code=404)
if revision.storagebackend != 'shopdb':
return error_response(
ErrorCodes.VALIDATION_ERROR,
'Kind {} stores opaque files and cannot be diffed'.format(
revision.backupkind))
againstid = request.args.get('against', type=int)
if againstid:
other = db.session.get(BackupRevision, againstid)
else:
# The previous revision FROM THE SAME PC. Several PCs can share a
# machine number, and diffing across them reported one device's COM port
# as a change on another, which is not a change at all.
other = (db.session.query(BackupRevision)
.filter(BackupRevision.assetid == revision.assetid,
BackupRevision.backupkind == revision.backupkind,
samesource(revision.sourcehostname),
BackupRevision.backuprevisionid < revision.backuprevisionid)
.order_by(BackupRevision.backuprevisionid.desc())
.first())
if other is None:
return success_response({
'backuprevisionid': revision.backuprevisionid,
'againstid': None,
'changes': [],
'message': 'No earlier revision to compare against.',
})
changes = _diffprojections(other.payload, revision.payload)
return success_response({
'backuprevisionid': revision.backuprevisionid,
'againstid': other.backuprevisionid,
'changes': changes,
'changecount': len(changes),
})
def _flatten(projection):
"""{(subkey, valuename): (type, data)} from a stored projection."""
flat = {}
for key in (projection or {}).get('keys', []):
path = key.get('path', '')
for name, entry in (key.get('values') or {}).items():
flat[(path, name)] = (entry.get('type'), entry.get('data'))
return flat
def _diffprojections(old, new):
oldflat = _flatten(old)
newflat = _flatten(new)
changes = []
for ref in sorted(set(oldflat) | set(newflat)):
path, name = ref
before = oldflat.get(ref)
after = newflat.get(ref)
if before == after:
continue
if before is None:
change = 'added'
elif after is None:
change = 'removed'
else:
change = 'changed'
changes.append({
'keypath': path,
'valuename': name,
'change': change,
'before': None if before is None else before[1],
'after': None if after is None else after[1],
'beforetype': None if before is None else before[0],
'aftertype': None if after is None else after[0],
})
return changes
@backups_bp.route('/dashboard/stale', methods=['GET'])
@jwt_required()
@require_permission('backups.view')
def dashboard_stale():
"""Chains whose backup has stopped running.
Thin: the rule lives in services/staleness.py, where it is testable without
an auth layer in the way. Keyed on the last CONFIRMED check, never on the
last change - dedup means an unchanged config writes no revision, so a card
keyed on revision age would flag most of a healthy fleet.
"""
from ..services.staleness import stalechains
return success_response(stalechains())