feat(v3.4.0): support multi-career subjects with subject_careers Many-to-Many and enhance Google Sheets importer for 6 days

This commit is contained in:
2026-10-07 18:04:23 -03:00
parent 14bf7169c2
commit a60a7cdc78
17 changed files with 335 additions and 67 deletions
+1 -1
View File
@@ -6,7 +6,7 @@ from flask_babel import Babel, gettext as _
from config.config import Config
# Initialize extensions
__version__ = "3.3.0"
__version__ = "3.4.0"
db = SQLAlchemy()
migrate = Migrate()
cors = CORS()
+32
View File
@@ -1,6 +1,13 @@
from app import db
from datetime import datetime
# Tabla asociativa Many-to-Many para materias compartidas entre carreras
subject_careers = db.Table(
'subject_careers',
db.Column('subject_id', db.Integer, db.ForeignKey('subjects.id', ondelete='CASCADE'), primary_key=True),
db.Column('career_id', db.Integer, db.ForeignKey('careers.id', ondelete='CASCADE'), primary_key=True)
)
class Subject(db.Model):
__tablename__ = 'subjects'
@@ -18,9 +25,16 @@ class Subject(db.Model):
# Relationships
commissions = db.relationship('Commission', backref='subject', lazy=True, cascade='all, delete-orphan')
careers = db.relationship('Career', secondary=subject_careers, lazy='subquery', backref=db.backref('shared_subjects', lazy=True))
def to_dict(self):
"""Convert subject to dictionary"""
all_careers = []
if self.careers:
all_careers = [{'id': c.id, 'name': c.name, 'code': c.code} for c in self.careers]
elif self.career_obj:
all_careers = [{'id': self.career_obj.id, 'name': self.career_obj.name, 'code': self.career_obj.code}]
return {
'id': self.id,
'code': self.code,
@@ -30,6 +44,7 @@ class Subject(db.Model):
'credits': self.credits,
'career_id': self.career_id,
'career_name': self.career_obj.name if self.career_obj else None,
'careers': all_careers,
'is_active': self.is_active,
'is_short_course': bool(self.is_short_course),
'created_at': self.created_at.isoformat() if self.created_at else None,
@@ -125,10 +140,25 @@ class Commission(db.Model):
def career(self):
return self.subject.career_obj if self.subject else None
@property
def careers(self):
if self.subject and self.subject.careers:
return [{'id': c.id, 'name': c.name, 'code': c.code} for c in self.subject.careers]
elif self.subject and self.subject.career_obj:
return [{'id': self.subject.career_obj.id, 'name': self.subject.career_obj.name, 'code': self.subject.career_obj.code}]
return []
@property
def career_name(self):
return self.subject.career_obj.name if (self.subject and self.subject.career_obj) else 'Carrera General'
@property
def career_names(self):
c_list = self.careers
if c_list:
return ", ".join([c['name'] for c in c_list])
return self.career_name
@property
def career_id(self):
return self.subject.career_id if self.subject else None
@@ -143,6 +173,8 @@ class Commission(db.Model):
'subject_id': self.subject_id,
'career_id': self.career_id,
'career_name': self.career_name,
'career_names': self.career_names,
'careers': self.careers,
'code': self.code,
'semester': self.semester,
'year': self.year,
+61 -3
View File
@@ -112,9 +112,14 @@ def get_subjects():
query = Subject.query
if search:
query = query.filter((Subject.name.ilike(f'%{search}%')) | (Subject.code.ilike(f'%{search}%')) | (Subject.department.ilike(f'%{search}%')))
query = query.filter(
(Subject.name.ilike(f'%{search}%')) |
(Subject.code.ilike(f'%{search}%')) |
(Subject.department.ilike(f'%{search}%')) |
(Subject.careers.any(Career.name.ilike(f'%{search}%')))
)
if career_id:
query = query.filter(Subject.career_id == career_id)
query = query.filter((Subject.career_id == career_id) | (Subject.careers.any(Career.id == career_id)))
if active == 'true':
query = query.filter(Subject.is_active == True)
elif active == 'false':
@@ -125,6 +130,12 @@ def get_subjects():
subjects_data = []
for s in subjects:
c_list = [{'id': c.id, 'name': c.name, 'code': c.code} for c in s.careers] if s.careers else []
if not c_list and s.career_obj:
c_list = [{'id': s.career_obj.id, 'name': s.career_obj.name, 'code': s.career_obj.code}]
c_names = ", ".join([c['name'] for c in c_list]) if c_list else (s.career_obj.name if s.career_obj else (s.department or 'General'))
subjects_data.append({
'id': s.id,
'code': s.code,
@@ -132,6 +143,8 @@ def get_subjects():
'career_id': s.career_id,
'career_name': s.career_obj.name if s.career_obj else (s.department or 'General'),
'career_obj': {'id': s.career_obj.id, 'name': s.career_obj.name} if s.career_obj else None,
'careers': c_list,
'career_names': c_names,
'department': s.department or 'General',
'description': getattr(s, 'description', '') or '',
'credits': getattr(s, 'credits', 4),
@@ -190,7 +203,9 @@ def get_commissions():
if subject_id:
query = query.filter(Commission.subject_id == subject_id)
if career_id:
query = query.join(Subject, Commission.subject_id == Subject.id).filter(Subject.career_id == career_id)
query = query.join(Subject, Commission.subject_id == Subject.id).filter(
(Subject.career_id == career_id) | (Subject.careers.any(Career.id == career_id))
)
if shift:
query = query.filter(Commission.shift == shift)
if active == 'true':
@@ -214,6 +229,8 @@ def get_commissions():
continue
career_name = c.career_name if hasattr(c, 'career_name') else 'Carrera General'
career_names = c.career_names if hasattr(c, 'career_names') else career_name
careers_list = c.careers if hasattr(c, 'careers') else []
career_id_val = c.career_id if hasattr(c, 'career_id') else (c.subject.career_id if c.subject else None)
commissions_data.append({
@@ -225,6 +242,8 @@ def get_commissions():
'subject_code': c.subject.code if c.subject else '-',
'career_id': career_id_val,
'career_name': career_name,
'career_names': career_names,
'careers': careers_list,
'semester': getattr(c, 'semester', '1C') or '1C',
'year': getattr(c, 'year', 2026) or 2026,
'academic_term_id': getattr(c, 'academic_term_id', None),
@@ -721,6 +740,25 @@ def create_subject():
description=description,
is_active=bool(is_active)
)
career_ids = data.get('career_ids')
if career_ids:
if isinstance(career_ids, str):
c_id_list = [int(x.strip()) for x in career_ids.split(',') if x.strip().isdigit()]
elif isinstance(career_ids, list):
c_id_list = [int(x) for x in career_ids if str(x).isdigit()]
else:
c_id_list = []
if c_id_list:
c_objs = Career.query.filter(Career.id.in_(c_id_list)).all()
subject.careers = c_objs
if c_objs and not subject.career_id:
subject.career_id = c_objs[0].id
elif career_id:
c_obj = Career.query.get(career_id)
if c_obj:
subject.careers = [c_obj]
db.session.add(subject)
db.session.commit()
@@ -756,6 +794,26 @@ def update_subject(id):
c_id = data['career_id']
subject.career_id = int(c_id) if c_id else None
if 'career_ids' in data:
career_ids = data.get('career_ids')
if isinstance(career_ids, str):
c_id_list = [int(x.strip()) for x in career_ids.split(',') if x.strip().isdigit()]
elif isinstance(career_ids, list):
c_id_list = [int(x) for x in career_ids if str(x).isdigit()]
else:
c_id_list = []
if c_id_list:
c_objs = Career.query.filter(Career.id.in_(c_id_list)).all()
subject.careers = c_objs
if c_objs and not subject.career_id:
subject.career_id = c_objs[0].id
else:
subject.careers = []
elif 'career_id' in data and subject.career_id:
c_obj = Career.query.get(subject.career_id)
if c_obj and c_obj not in subject.careers:
subject.careers = [c_obj]
if 'description' in data:
subject.description = data['description'].strip()
+1 -1
View File
@@ -7,7 +7,7 @@ OPENAPI_SPEC = {
"info": {
"title": "Edu-Space REST API",
"description": "Enterprise Academic & Physical Space Management REST API with JWT Authentication and Role-Based Access Control.",
"version": "3.3.0"
"version": "3.4.0"
},
"servers": [
{
+159 -41
View File
@@ -11,7 +11,42 @@ from app.models.subject import Subject, Commission
from app.models.reservation import Reservation, ReservationStatus
from app.models.user import User
BASE_CSV_URL = 'https://docs.google.com/spreadsheets/d/e/2PACX-1vSc_T_BQjbn3uPelioCgx52UM5Py-qNhJN0TYPd1kmsN5jdb3Q8rAaIvNMF_2ZTzQt6bH--yIWQKrKR/pub?single=true&output=csv'
BASE_CSV_URL = 'https://docs.google.com/spreadsheets/d/e/2PACX-1vSc_T_BQjbn3uPelioCgx52UM5Py-qNhJN0TYPd1kmsN5jdb3Q8rAaIvNMF_2ZTzQt6bH--yIWQKrKR/pub?output=csv'
# Mapeo canónico de carreras de UniCABA para desglosar y normalizar registros compuestos
CANONICAL_CAREERS = {
'DATOS': 'DATOS (CCC)',
'DATOS (CCC)': 'DATOS (CCC)',
'DATOS(CCC)': 'DATOS (CCC)',
'TEC.DIG': 'TEC. DIG. (CCC)',
'TEC. DIG (CCC)': 'TEC. DIG. (CCC)',
'TEC. DIG. (CCC)': 'TEC. DIG. (CCC)',
'TEC DIG': 'TEC. DIG. (CCC)',
'VIDEOJUEGOS': 'VIDEOJUEGOS (CCC)',
'VIDEOJUEGOS (CCC)': 'VIDEOJUEGOS (CCC)',
'PROF PROF': 'PROF PROF (CCC)',
'PROF PROF (CCC)': 'PROF PROF (CCC)',
'CIENCIAS': 'CIENCIAS',
'EF. SALUD': 'EF. SALUD',
'EF. GESTIÓN': 'EF. GESTIÓN',
'EF. GESTION': 'EF. GESTIÓN',
'ETD': 'ETD (CCC)',
'ETD (CCC)': 'ETD (CCC)',
'MONO': 'MONODISCIPLINARES',
'MONODISCIPLINARES': 'MONODISCIPLINARES',
'PUEP': 'PUEP',
'PUEP CCC': 'PUEP CCC',
'INGLÉS': 'INGLÉS',
'INGLES': 'INGLÉS',
'GESTIÓN (CCC)': 'Gestión (CCC)',
'GESTION (CCC)': 'Gestión (CCC)',
'DIPLO. ALFABETIZACIÓN': 'DIPLO. ALFABETIZACIÓN',
'DIPLO. ALFABETIZACION': 'DIPLO. ALFABETIZACIÓN',
'DIPLO. BILINGUE': 'DIPLO. BILINGUE',
'POSG. PRIMARIA': 'POSG. PRIMARIA',
'POSG. INICIAL': 'POSG. INICIAL',
'POSG. INCLUSIVAS': 'POSG. INCLUSIVAS',
}
def map_day_to_idx(day_str):
"""Mapea el nombre del día (o prefijo) a su índice numérico 0..6 (Lunes=0)"""
@@ -25,6 +60,36 @@ def map_day_to_idx(day_str):
if 'dom' in d: return 6
return 0
def parse_careers_list(c_str):
"""Parsea y normaliza cadenas de carreras compuestas separadas por guiones o comas"""
if not c_str:
return ['General']
parts = re.split(r'\s*-\s*|(?<=\))\s*-\s*|\s*,\s*', c_str)
result = []
for p in parts:
clean = p.strip()
if not clean:
continue
upper_clean = clean.upper()
matched = False
for k, v in CANONICAL_CAREERS.items():
if upper_clean == k.upper():
if v not in result:
result.append(v)
matched = True
break
if not matched:
if clean not in result:
result.append(clean)
return result if result else ['General']
def parse_subject_codes(code_str):
"""Parsea códigos de materias que pueden venir combinados con barras (ej: ASIG00113 / ASIG000082)"""
if not code_str:
return []
parts = re.split(r'\s*/\s*|\s*,\s*', code_str)
return [p.strip() for p in parts if p.strip()]
def normalize_sheets_url(url):
"""
Normaliza enlaces de Google Sheets (compartidos, de edición, con /u/1/, #gid=... o /pubhtml)
@@ -38,7 +103,7 @@ def normalize_sheets_url(url):
pub_match = re.search(r'/spreadsheets/(?:u/\d+/)?d/e/([a-zA-Z0-9-_]+)', url)
if pub_match:
doc_id = pub_match.group(1)
return f"https://docs.google.com/spreadsheets/d/e/{doc_id}/pub?single=true&output=csv"
return f"https://docs.google.com/spreadsheets/d/e/{doc_id}/pub?output=csv"
# 2. Enlace de edición o exportación (/d/<SPREADSHEET_ID>/...)
sheet_id_match = re.search(r'/spreadsheets/(?:u/\d+/)?d/([a-zA-Z0-9-_]+)', url)
@@ -61,8 +126,8 @@ TIME_REGEX = re.compile(r'(\d{1,2})(?::(\d{2}))?\s*(?:a|-|to)\s*(\d{1,2})(?::(\d
class GoogleSheetsImporter:
"""
Service to fetch, parse, and synchronize academic schedules,
classrooms, careers, and subjects from the official UniCABA Google Sheet.
Servicio para descargar, parsear y sincronizar cursadas académicas,
aulas, carreras y asignaturas compartidas desde el Google Sheet oficial de UniCABA.
"""
def __init__(self, base_url=None):
@@ -82,7 +147,7 @@ class GoogleSheetsImporter:
def get_sheets_config(self):
"""
Descubre las pestañas y GIDs dinámicamente desde /pubhtml si está disponible,
o utiliza el fallback SHEETS_CONFIG preconfigurado.
o utiliza el fallback SHEETS_CONFIG preconfigurado para los 6 días de cursada.
"""
pub_match = re.search(r'/spreadsheets/d/e/([a-zA-Z0-9-_]+)', self.base_url)
if pub_match:
@@ -91,12 +156,12 @@ class GoogleSheetsImporter:
try:
req = urllib.request.Request(
pubhtml_url,
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) EduSpace/2.0'}
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) EduSpace/3.4'}
)
with urllib.request.urlopen(req, timeout=12) as resp:
html_content = resp.read().decode('utf-8', errors='replace')
# Extraer pares name y gid de Google Sheets pubhtml
found = re.findall(r'name:\s*["\']([^"\']+)["\'],\s*gid:\s*["\'](\d+)["\']', html_content)
found = re.findall(r'name:\s*["\']([^"\']+)["\'][^}]*?gid:\s*["\'](\d+)["\']', html_content)
if found:
discovered = []
for name, gid in found:
@@ -121,7 +186,7 @@ class GoogleSheetsImporter:
raise ValueError(f"URL scheme not permitted: {url}")
req = urllib.request.Request(
url,
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) EduSpace/2.0'}
headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) EduSpace/3.4'}
)
with urllib.request.urlopen(req, timeout=25) as resp: # nosec B310
return resp.read().decode('utf-8', errors='replace')
@@ -202,7 +267,7 @@ class GoogleSheetsImporter:
def normalize_room(self, aula_raw):
"""
Normalize room string into (building, room_number, floor, capacity)
Normaliza cadena de aula en (building, room_number, floor, capacity)
"""
aula_upper = aula_raw.upper().strip()
if not aula_upper or any(x in aula_upper for x in ['FERIADO', 'SIN ACTIVIDAD', 'CONSULTAR EN BEDELIA']):
@@ -274,10 +339,11 @@ class GoogleSheetsImporter:
def sync(self):
"""
Main synchronization process:
1. Fetches all 6 day sheets.
2. Upserts Careers, Classrooms, Subjects, Commissions.
3. Generates Reservations in the calendar for the semester.
Proceso principal de sincronización:
1. Descarga las 6 hojas de cálculo semanales (Lunes a Sábado).
2. Normaliza carreras individuales y asignaturas compartidas (Many-to-Many).
3. Upserts Aulas, Carreras, Asignaturas, Comisiones.
4. Genera Reservas en el calendario para el semestre académico.
"""
stats = {
'total_rows_processed': 0,
@@ -289,6 +355,7 @@ class GoogleSheetsImporter:
'subjects_updated': 0,
'commissions_created': 0,
'reservations_created': 0,
'by_day': {},
'errors': [],
'sample_records': []
}
@@ -296,12 +363,25 @@ class GoogleSheetsImporter:
all_raw_records = []
sheets_to_process = self.get_sheets_config()
for sheet_cfg in sheets_to_process:
day_name = sheet_cfg['name']
try:
csv_data = self.fetch_sheet_csv(sheet_cfg['gid'])
rows = self.parse_sheet_rows(csv_data, sheet_cfg['name'])
rows = self.parse_sheet_rows(csv_data, day_name)
all_raw_records.extend([(r, sheet_cfg['day_idx']) for r in rows])
stats['by_day'][day_name] = {
'gid': sheet_cfg['gid'],
'rows_count': len(rows),
'status': 'OK'
}
except Exception as e:
stats['errors'].append(f"Error al descargar o procesar la hoja de {sheet_cfg['name']}: {str(e)}")
err_msg = f"Error al descargar o procesar la hoja de {day_name}: {str(e)}"
stats['errors'].append(err_msg)
stats['by_day'][day_name] = {
'gid': sheet_cfg['gid'],
'rows_count': 0,
'status': 'Error',
'error': str(e)
}
stats['total_rows_processed'] = len(all_raw_records)
if not all_raw_records:
@@ -345,29 +425,36 @@ class GoogleSheetsImporter:
subjects_cache = {s.code.strip().upper(): s for s in Subject.query.all()}
# Calculate current semester dates (anchored on academic year 2026)
# Week starting Monday 2026-08-31 to Saturday 2026-09-05
base_monday = date(2026, 8, 31)
weeks_to_generate = 4 # Generate reservations for 4 consecutive weeks
weeks_to_generate = 4 # Generar reservas para 4 semanas consecutivas
for rec, day_idx in all_raw_records:
try:
codigo = rec['codigo']
asignatura = rec['asignatura']
aula_raw = rec['aula']
carrera_name = rec['carrera'].strip()
carrera_raw = rec['carrera'].strip()
horario_raw = rec['horario']
dia = rec['dia']
turno = rec.get('turno', 'Mañana')
# 1. Upsert Career
carrera_key = carrera_name.upper()
career = careers_cache.get(carrera_key)
if not career:
career = Career(name=carrera_name)
db.session.add(career)
db.session.flush()
careers_cache[carrera_key] = career
stats['careers_created'] += 1
# 1. Upsert Careers (Desglosar carreras múltiples normalizadas)
carreras_list = parse_careers_list(carrera_raw)
career_objs = []
for c_name in carreras_list:
c_key = c_name.upper()
career = careers_cache.get(c_key)
if not career:
career = Career.query.filter(Career.name.ilike(c_name)).first()
if not career:
career = Career(name=c_name)
db.session.add(career)
db.session.flush()
stats['careers_created'] += 1
careers_cache[c_key] = career
career_objs.append(career)
primary_career = career_objs[0] if career_objs else None
# 2. Upsert Classroom
room_info = self.normalize_room(aula_raw)
@@ -395,34 +482,63 @@ class GoogleSheetsImporter:
if not classroom.building_id and b_entity:
classroom.building_id = b_entity.id
# 3. Upsert Subject
# 3. Upsert Subject (Soporte Many-to-Many con múltiples carreras y subcódigos)
subject_key = codigo.upper()
sub_codes = parse_subject_codes(codigo)
subject = subjects_cache.get(subject_key)
if not subject:
for sc in sub_codes:
if sc.upper() in subjects_cache:
subject = subjects_cache[sc.upper()]
break
if not subject:
subject = Subject.query.filter_by(code=codigo).first()
if not subject:
for sc in sub_codes:
subj_by_sc = Subject.query.filter_by(code=sc).first()
if subj_by_sc:
subject = subj_by_sc
break
department_str = ", ".join([c.name for c in career_objs]) if career_objs else (primary_career.name if primary_career else 'General')
if not subject:
subject = Subject(
code=codigo,
name=asignatura,
career_id=career.id,
department=career.name,
career_id=primary_career.id if primary_career else None,
department=department_str,
credits=4,
is_active=True
)
subject.careers = career_objs
db.session.add(subject)
db.session.flush()
subjects_cache[subject_key] = subject
stats['subjects_created'] += 1
else:
if subject.name != asignatura:
subject.name = asignatura
stats['subjects_updated'] += 1
subject.career_id = career.id
subject.department = career.name
# Vincular todas las carreras a la asignatura sin duplicados
for c_obj in career_objs:
if c_obj not in subject.careers:
subject.careers.append(c_obj)
if not subject.career_id and primary_career:
subject.career_id = primary_career.id
subject.department = ", ".join([c.name for c in subject.careers]) if subject.careers else department_str
# Registrar en caché con código completo y con subcódigos individuales
subjects_cache[subject_key] = subject
for sc in sub_codes:
subjects_cache[sc.upper()] = subject
# 4. Upsert Commission
# Identify commission subcode e.g. from code suffix or default 'C1'
comm_code = 'C1'
if '-E' in codigo:
comm_code = codigo.split('-')[-1]
elif '-0' in codigo:
comm_code = 'C' + codigo.split('-')[-1]
commission = Commission.query.filter_by(
subject_id=subject.id,
@@ -450,13 +566,14 @@ class GoogleSheetsImporter:
else:
commission.schedule = f"{dia} {horario_raw}"
commission.shift = turno
if classroom:
commission.max_students = max(commission.max_students or 0, classroom.capacity)
# 5. Generate Calendar Reservations
# 5. Generar Reservas de Calendario
t_start, t_end = self.parse_time_range(horario_raw)
if classroom and t_start and t_end and day_idx is not None:
is_room_virtual = bool(classroom.is_virtual or 'VIRTUAL' in (classroom.code or '').upper())
# Generar enlace de videollamada para clases virtuales si no tienen uno asignado
v_link = None
if is_room_virtual:
clean_subj = re.sub(r'[^a-zA-Z0-9]', '', subject.code or 'cls').lower()
@@ -470,7 +587,6 @@ class GoogleSheetsImporter:
dt_start = datetime.combine(class_date, t_start)
dt_end = datetime.combine(class_date, t_end)
# En aulas virtuales la capacidad es infinita y pueden cursar múltiples comisiones en paralelo
if is_room_virtual:
existing_res = Reservation.query.filter_by(
classroom_id=classroom.id,
@@ -485,6 +601,8 @@ class GoogleSheetsImporter:
end_time=dt_end
).first()
c_desc = ", ".join([c.name for c in career_objs]) if career_objs else 'General'
if not existing_res:
res = Reservation(
classroom_id=classroom.id,
@@ -497,22 +615,22 @@ class GoogleSheetsImporter:
expected_attendees=min(classroom.capacity, 30) if not is_room_virtual else 35,
shift=turno,
virtual_link=v_link,
notes=f"Clase semanal {dia} ({turno}) - Carrera: {career.name}"
notes=f"Clase semanal {dia} ({turno}) - Carreras: {c_desc}"
)
db.session.add(res)
stats['reservations_created'] += 1
else:
existing_res.shift = turno
existing_res.notes = f"Clase semanal {dia} ({turno}) - Carrera: {career.name}"
existing_res.notes = f"Clase semanal {dia} ({turno}) - Carreras: {c_desc}"
if is_room_virtual and not existing_res.virtual_link:
existing_res.virtual_link = v_link
if len(stats['sample_records']) < 10:
if len(stats['sample_records']) < 15:
stats['sample_records'].append({
'dia': dia,
'codigo': codigo,
'asignatura': asignatura,
'carrera': career.name,
'carreras': [c.name for c in career_objs],
'aula': classroom.code_display if classroom else aula_raw,
'horario': horario_raw
})