Aug 27 - Add MySQL optimize and security check

This commit is contained in:
2026-08-27 17:36:28 -04:00
parent ba10ec42e0
commit b7bc0f0335
16 changed files with 1524 additions and 58 deletions
+2 -2
View File
@@ -267,8 +267,8 @@ def list_inspections():
if user.role not in _ALLOWED_ROLES:
return api_error('Access denied', 403)
limit = min(int(request.args.get('limit', 50)), 200)
offset = max(int(request.args.get('offset', 0)), 0)
limit = min(request.args.get('limit', 50, type=int) or 50, 200)
offset = max(request.args.get('offset', 0, type=int) or 0, 0)
query = Inspection.query
+2 -2
View File
@@ -149,8 +149,8 @@ def list_issues():
if user.role not in _ALLOWED_ROLES:
return api_error('Access denied', 403)
limit = min(int(request.args.get('limit', 100)), 200)
offset = max(int(request.args.get('offset', 0)), 0)
limit = min(request.args.get('limit', 100, type=int) or 100, 200)
offset = max(request.args.get('offset', 0, type=int) or 0, 0)
query = Issue.query
+1 -1
View File
@@ -73,7 +73,7 @@ def list_notifications():
"""
user = g.api_user
since = _parse_since(request.args.get('since'))
limit = min(int(request.args.get('limit', 50)), 50)
limit = min(request.args.get('limit', 50, type=int) or 50, 50)
def _run_orm():
q = Notification.query.filter_by(user_id=user.id, is_read=False)
+2 -2
View File
@@ -103,8 +103,8 @@ def list_scheduled():
if user.role not in _ALLOWED_ROLES:
return api_error('Access denied', 403)
limit = min(int(request.args.get('limit', 100)), 200)
offset = max(int(request.args.get('offset', 0)), 0)
limit = min(request.args.get('limit', 100, type=int) or 100, 200)
offset = max(request.args.get('offset', 0, type=int) or 0, 0)
query = ScheduledInspection.query.filter(ScheduledInspection.active.is_(True))
+8 -1
View File
@@ -111,7 +111,14 @@ def dashboard_stats():
)
)
open_issues_all = open_q.all()
# Counts and buckets only — never a hydrated Issue. For an admin this is
# every open issue in the system, fetched on every iPad dashboard refresh;
# the full entity would drag the description TEXT and the JSON photo
# columns along with it. A Row exposes the same attribute names, so
# sla_status() below works unchanged.
open_issues_all = open_q.with_entities(
Issue.id, Issue.severity, Issue.status, Issue.reported_at
).all()
open_issues = len(open_issues_all)
# ── Severity breakdown (derived from the same open_issues_all list) ───
+14 -4
View File
@@ -17,6 +17,16 @@ bp = Blueprint('dashboard', __name__)
logger = logging.getLogger(__name__)
# Columns the dashboard actually reads off an issue row. The cards below need
# counts and buckets, never a hydrated Issue — loading the full entity pulls the
# description TEXT and three JSON photo columns for every open issue in scope,
# on every dashboard load, and registers each one in the identity map.
# A Row exposes the same attribute names, so _handler_split() and sla_status()
# work against these unchanged.
_ISSUE_CARD_COLS = (Issue.id, Issue.severity, Issue.status,
Issue.reported_at, Issue.handler_type)
def _handler_split(issues):
"""Count a list of Issues by handler_type (phase35). Rows default to
'internal' when unset. Returns a dict keyed internal/facility/vendor."""
@@ -102,7 +112,7 @@ def index():
))
# Single query — derive count from the list to avoid hitting the DB twice
open_issues_all = open_issues_q.all()
open_issues_all = open_issues_q.with_entities(*_ISSUE_CARD_COLS).all()
open_issues = len(open_issues_all)
severity_breakdown = {
'critical': sum(1 for i in open_issues_all if i.severity == 'critical'),
@@ -224,7 +234,7 @@ def index():
elif is_customer and not customer_facility_ids:
all_open_issues = []
else:
all_open_issues = sla_q.all()
all_open_issues = sla_q.with_entities(*_ISSUE_CARD_COLS).all()
sla_breached = sum(1 for i in all_open_issues if sla_status(i) == 'breached')
sla_at_risk = sum(1 for i in all_open_issues if sla_status(i) == 'at_risk')
@@ -250,7 +260,7 @@ def index():
Issue.facility_id.in_(customer_facility_ids),
_AreaT.facility_id.in_(customer_facility_ids),
))
opened_today_all = opened_today_q.all()
opened_today_all = opened_today_q.with_entities(*_ISSUE_CARD_COLS).all()
issues_opened_today = len(opened_today_all)
opened_today_handler = _handler_split(opened_today_all)
@@ -331,7 +341,7 @@ def index():
))
elif is_customer:
unassigned_q = unassigned_q.filter(False) # not relevant for customers
unassigned_all = unassigned_q.all()
unassigned_all = unassigned_q.with_entities(*_ISSUE_CARD_COLS).all()
unassigned_open = len(unassigned_all)
unassigned_handler = _handler_split(unassigned_all)
+4 -2
View File
@@ -253,7 +253,8 @@ def index():
q = q.filter(Inspection.status == status_filter)
if contract_filter.isdigit():
_contract_fids = [
f.id for f in Facility.query.filter_by(project_id=int(contract_filter)).all()
fid for (fid,) in db.session.query(Facility.id)
.filter(Facility.project_id == int(contract_filter)).all()
]
q = q.filter(Inspection.facility_id.in_(_contract_fids)) if _contract_fids else q.filter(False)
if facility_filter.isdigit():
@@ -1243,7 +1244,8 @@ def export_list_pdf():
q = q.filter(Inspection.status == status_filter)
if contract_filter.isdigit():
_contract_fids = [
f.id for f in Facility.query.filter_by(project_id=int(contract_filter)).all()
fid for (fid,) in db.session.query(Facility.id)
.filter(Facility.project_id == int(contract_filter)).all()
]
q = q.filter(Inspection.facility_id.in_(_contract_fids)) if _contract_fids else q.filter(False)
if facility_filter.isdigit():
+10 -7
View File
@@ -166,13 +166,14 @@ def export_list_pdf():
date_to_filter = ''
if contract_filter.isdigit():
_contract_fids = [
f.id for f in Facility.query.filter_by(project_id=int(contract_filter)).all()
fid for (fid,) in db.session.query(Facility.id)
.filter(Facility.project_id == int(contract_filter)).all()
]
q = q.filter(db.or_(
Issue.facility_id.in_(_contract_fids),
Area.facility_id.in_(_contract_fids),
)) if _contract_fids else q.filter(False)
if facility_filter:
if facility_filter.isdigit():
fid = int(facility_filter)
q = q.filter(db.or_(Issue.facility_id == fid, Area.facility_id == fid))
if reporter_filter.isdigit():
@@ -201,7 +202,7 @@ def export_list_pdf():
p = db.session.get(Project, int(contract_filter))
if p:
filter_parts.append(f'Contract: {p.name}')
if facility_filter:
if facility_filter.isdigit():
f = db.session.get(Facility, int(facility_filter))
if f:
filter_parts.append(f'Facility: {f.name}')
@@ -303,7 +304,8 @@ def index():
date_to_filter = ''
if contract_filter.isdigit():
_contract_fids = [
f.id for f in Facility.query.filter_by(project_id=int(contract_filter)).all()
fid for (fid,) in db.session.query(Facility.id)
.filter(Facility.project_id == int(contract_filter)).all()
]
q = q.filter(db.or_(
Issue.facility_id.in_(_contract_fids),
@@ -311,7 +313,7 @@ def index():
)) if _contract_fids else q.filter(False)
if reporter_filter.isdigit():
q = q.filter(Issue.reported_by == int(reporter_filter))
if facility_filter:
if facility_filter.isdigit():
fid = int(facility_filter)
q = q.filter(
db.or_(
@@ -338,8 +340,9 @@ def index():
# can render the following badge and inline unfollow button without an
# additional query per row.
followed_ids = {
f.issue_id
for f in IssueFollower.query.filter_by(user_id=current_user.id).all()
iid for (iid,) in
db.session.query(IssueFollower.issue_id)
.filter(IssueFollower.user_id == current_user.id).all()
}
# Facilities for the filter dropdown — scoped for inspectors/customers,
+19 -19
View File
@@ -74,23 +74,29 @@ def index():
if current_user.role in ('admin', 'director', 'project_manager'):
inspector_filter = request.args.get('inspector_id', type=int) or None
# Pre-compute inspection ID sets used by _scope_issue to avoid join conflicts.
inspector_inspection_ids = [] # own inspections (inspector role)
filter_inspection_ids = None # filtered inspector's inspections (admin/dir/PM)
# Scope issues by the relevant inspector's inspections, as a SUBQUERY rather
# than a materialised id list. The previous form pulled every inspection id
# that inspector had ever performed into Python and sent them straight back
# as a literal IN (1, 2, 3, ... N): the round trip is wasted, the statement
# grows without bound with the inspector's history, and a long enough list
# eventually trips max_allowed_packet. A subquery is also still a single
# statement, so the "avoid join conflicts" reason for pre-computing holds.
#
# IN (empty subquery) already matches nothing, so the explicit empty-list
# guards the old code needed are gone rather than merely moved.
inspector_insp_subq = None
if is_inspector:
inspector_inspection_ids = [
row[0] for row in
inspector_insp_subq = (
db.session.query(Inspection.id)
.filter(Inspection.inspector_id == current_user.id)
.all()
]
.scalar_subquery()
)
elif inspector_filter:
filter_inspection_ids = [
row[0] for row in
inspector_insp_subq = (
db.session.query(Inspection.id)
.filter(Inspection.inspector_id == inspector_filter)
.all()
]
.scalar_subquery()
)
def _scope_insp(q):
if is_inspector:
@@ -104,14 +110,8 @@ def index():
return q
def _scope_issue(q):
if is_inspector:
if not inspector_inspection_ids:
return q.filter(False)
return q.filter(Issue.inspection_id.in_(inspector_inspection_ids))
if filter_inspection_ids is not None:
if not filter_inspection_ids:
return q.filter(False)
return q.filter(Issue.inspection_id.in_(filter_inspection_ids))
if inspector_insp_subq is not None:
return q.filter(Issue.inspection_id.in_(inspector_insp_subq))
if customer_facility_ids is not None:
if not customer_facility_ids:
return q.filter(False)
+22 -14
View File
@@ -18,6 +18,7 @@ that no facility-level scoping is required (full access applies).
"""
import logging
from app import db
from app.models.project import CustomerAssignment
from app.models.facility import Facility
@@ -43,30 +44,34 @@ def get_customer_scope(user) -> list[int] | None:
if user.role != 'customer':
return None # no scoping needed for internal staff
assignments = CustomerAssignment.query.filter_by(user_id=user.id).all()
# Select only the two columns needed. The previous .all() built full
# CustomerAssignment ORM objects (and their identity-map entries) purely to
# read two integers off each one; this function runs on nearly every
# request for a customer, sometimes more than once.
assignments = db.session.query(
CustomerAssignment.project_id,
CustomerAssignment.facility_id,
).filter(CustomerAssignment.user_id == user.id).all()
if not assignments:
return []
# Separate direct facility assignments from project-level assignments
direct_facility_ids = {a.facility_id for a in assignments if a.facility_id}
project_ids = {a.project_id for a in assignments if not a.facility_id}
direct_facility_ids = {fac_id for _, fac_id in assignments if fac_id}
project_ids = {proj_id for proj_id, fac_id in assignments if not fac_id}
facility_ids = set(direct_facility_ids)
# Single bulk query for all project-scoped facilities — replaces the
# previous per-assignment Facility.query loop (N+1 pattern).
# previous per-assignment Facility.query loop (N+1 pattern). Only the id
# column is read; nothing here needs a hydrated Facility.
if project_ids:
project_facilities = (
Facility.query
.filter(
facility_ids.update(
fid for (fid,) in db.session.query(Facility.id).filter(
Facility.project_id.in_(project_ids),
Facility.active == True,
)
.all()
).all()
)
for f in project_facilities:
facility_ids.add(f.id)
logger.debug(
'SCOPE | customer_scope | user_id=%s username=%s facility_ids=%s',
@@ -102,16 +107,19 @@ def get_inspector_scope(user) -> list[int] | None:
from app.models.inspector_assignment import InspectorAssignment
# Column-only selects — see the note in get_customer_scope(). This runs on
# every scoped request for both inspector roles.
project_ids = [
a.project_id
for a in InspectorAssignment.query.filter_by(user_id=user.id).all()
pid for (pid,) in
db.session.query(InspectorAssignment.project_id)
.filter(InspectorAssignment.user_id == user.id).all()
]
if not project_ids:
return [] # strict: no assignments = no access
facility_ids = [
f.id for f in Facility.query.filter(
fid for (fid,) in db.session.query(Facility.id).filter(
Facility.project_id.in_(project_ids),
Facility.active == True,
).all()
+31 -4
View File
@@ -110,11 +110,38 @@ def send_sla_alerts():
logger = logging.getLogger(__name__)
# yield_per streams rows in batches of 100 rather than loading all open
# issues into memory at once. At current scale this is a no-op difference,
# but it prevents a memory spike if the issue count grows large.
# Narrow to actual CANDIDATES in SQL rather than reading every open issue
# and deciding in Python. This runs every 30 minutes forever, so the old
# form's cost grew with the whole open-issue backlog even on a quiet night
# where nothing was due. Three filters, each mirroring a `continue` below:
#
# 1. reported_at IS NOT NULL — the column is nullable, and sla_status()
# raises TypeError on a NULL (datetime + timedelta). One such row
# would abort the entire cron run, so exclude it in SQL.
# 2. sla_notified <> 'breached' — the highest level is already sent; the
# loop skips these unconditionally.
# 3. old enough to be at least at-risk for its OWN severity, i.e.
# reported_at <= now - (window * 0.75). A critical issue qualifies
# after 3h, a low one after 90h.
#
# Anything this excludes would have hit a `continue` anyway, so the set of
# notifications sent is unchanged — only the rows read are.
now = now_eastern()
age_clauses = [
db.and_(
Issue.severity == severity,
Issue.reported_at <= now - timedelta(hours=hours * AT_RISK_THRESHOLD),
)
for severity, hours in SLA_HOURS.items()
]
# yield_per streams the survivors in batches rather than materialising them
# all at once.
open_issues = Issue.query.filter(
Issue.status.in_(['open', 'in_progress', 'pending_verification'])
Issue.status.in_(['open', 'in_progress', 'pending_verification']),
Issue.reported_at.isnot(None),
db.or_(Issue.sla_notified.is_(None), Issue.sla_notified != 'breached'),
db.or_(*age_clauses),
).yield_per(100)
total_sent = 0