feat(sheets): refactor google sheets importer with granular entities and interactive preview grid v3.4.3

This commit is contained in:
2026-10-07 22:51:41 -03:00
parent e1c2c6e8c6
commit 22c545e2df
12 changed files with 1001 additions and 195 deletions
+274 -119
View File
@@ -352,21 +352,55 @@ class GoogleSheetsImporter:
except Exception:
return None, None
def inspect_sheet_content(self):
def inspect_sheet_content(self, filter_career=None, filter_subject=None, filter_day=None, filter_days=None, manual_date=None):
"""
Descarga e inspecciona las hojas del Sheet online para extraer:
- Días disponibles con cantidad de filas
- Carreras únicas
- Materias únicas con sus códigos, nombres y carreras
- Grilla de pre-visualización interactiva (preview_rows) según los filtros aplicados
"""
sheets_to_process = self.get_sheets_config()
days_info = []
careers_set = set()
subjects_map = {}
total_rows = 0
preview_rows = []
# Normalizar días seleccionados
allowed_days = None
if filter_days:
if isinstance(filter_days, str):
allowed_days = [normalize_day_name(d) for d in filter_days.split(',') if d.strip()]
elif isinstance(filter_days, (list, set)):
allowed_days = [normalize_day_name(d) for d in filter_days if d]
elif filter_day:
nd = normalize_day_name(filter_day)
if nd and nd.upper() not in ['ALL', 'TODOS', 'TODOS LOS DÍAS', 'TODOS LOS DIAS', '']:
allowed_days = [nd]
# Normalizar fecha manual para fecha inferida base
manual_dt = None
if manual_date:
try:
if isinstance(manual_date, (datetime, date)):
manual_dt = manual_date if isinstance(manual_date, date) else manual_date.date()
elif isinstance(manual_date, str) and manual_date.strip():
manual_dt = datetime.strptime(manual_date.strip(), '%Y-%m-%d').date()
except Exception:
pass
# Referencia de semana base: lunes 5 de octubre de 2026 (semana activa del 2° cuatrimestre)
ref_monday = date(2026, 10, 5)
if manual_dt:
ref_monday = manual_dt - timedelta(days=manual_dt.weekday())
row_counter = 0
for sheet_cfg in sheets_to_process:
day_name = sheet_cfg['name']
norm_day = normalize_day_name(day_name)
day_idx = sheet_cfg.get('day_idx', 0)
try:
csv_data = self.fetch_sheet_csv(sheet_cfg['gid'])
rows = self.parse_sheet_rows(csv_data, day_name)
@@ -374,10 +408,15 @@ class GoogleSheetsImporter:
days_info.append({
'name': day_name,
'gid': sheet_cfg['gid'],
'day_idx': sheet_cfg['day_idx'],
'day_idx': day_idx,
'rows_count': len(rows),
'status': 'OK'
})
# Si este día no está entre los permitidos, no lo agregamos a preview_rows
if allowed_days and norm_day not in allowed_days:
continue
for r in rows:
carreras = parse_careers_list(r.get('carrera', ''))
for c in carreras:
@@ -394,11 +433,67 @@ class GoogleSheetsImporter:
'careers': carreras,
'day': day_name
}
# Evaluar coincidencia de filtros de Carrera y Materia para la pre-visualización
if filter_career:
fc = filter_career.strip().upper()
match_c = any(fc in c.upper() or c.upper() in fc for c in carreras) or (fc in r.get('carrera', '').upper())
if not match_c:
continue
if filter_subject:
fs = filter_subject.strip().upper()
sub_codes = parse_subject_codes(code)
match_s = (fs in code.upper()) or (fs in name.upper()) or any(fs in sc.upper() for sc in sub_codes)
if not match_s:
continue
row_counter += 1
aula_raw = r.get('aula', '').strip()
room_info = self.normalize_room(aula_raw)
is_virtual = bool(room_info and ('VIRTUAL' in room_info.get('code', '').upper() or room_info.get('building') == 'Campus Virtual'))
# Calcular fecha tentativa
target_date = ref_monday + timedelta(days=day_idx)
if manual_dt and norm_day == normalize_day_name(['Lunes', 'Martes', 'Miércoles', 'Jueves', 'Viernes', 'Sábado'][manual_dt.weekday()]):
target_date = manual_dt
# Validaciones
is_valid = True
has_warning = False
warning_msg = None
if not code or not name:
is_valid = False
warning_msg = "Falta código o nombre de asignatura"
elif not room_info or not aula_raw or any(x in aula_raw.upper() for x in ['FERIADO', 'SIN ACTIVIDAD', 'CONSULTAR']):
has_warning = True
warning_msg = f"Aula pendiente o sin asignar ({aula_raw or 'Vacía'})"
preview_rows.append({
'id': row_counter,
'dia': norm_day,
'day_idx': day_idx,
'codigo': code,
'asignatura': name,
'aula': aula_raw or (room_info['code'] if room_info else 'Sin Aula'),
'aula_normalizada': room_info['code'] if room_info else 'Sin Aula',
'is_virtual': is_virtual,
'carrera': r.get('carrera', 'General'),
'carreras_list': carreras,
'horario': r.get('horario', ''),
'turno': r.get('turno', 'Mañana'),
'inferred_date': target_date.strftime('%Y-%m-%d'),
'is_valid': is_valid,
'has_warning': has_warning,
'warning_msg': warning_msg
})
except Exception as e:
days_info.append({
'name': day_name,
'gid': sheet_cfg['gid'],
'day_idx': sheet_cfg.get('day_idx', 0),
'day_idx': day_idx,
'rows_count': 0,
'status': 'Error',
'error': str(e)
@@ -406,19 +501,28 @@ class GoogleSheetsImporter:
return {
'total_rows': total_rows,
'matching_rows': len(preview_rows),
'days': days_info,
'careers': sorted(list(careers_set)),
'subjects': sorted(list(subjects_map.values()), key=lambda x: x['code'])
'subjects': sorted(list(subjects_map.values()), key=lambda x: x['code']),
'preview_rows': preview_rows
}
def sync(self, filter_career=None, filter_subject=None, filter_day=None, manual_date=None, single_date_only=False):
def sync(self, filter_career=None, filter_subject=None, filter_day=None, filter_days=None, manual_date=None, single_date_only=False, import_careers=True, import_subjects=True, import_commissions=True, import_classrooms=True, import_reservations=True, selected_rows=None):
"""
Proceso principal de sincronización con soporte de filtros y fechas manuales:
Proceso principal de sincronización con soporte de filtros, entidades granulares y filas seleccionadas:
:param filter_career: Filtrar por carrera específica (ej. 'DATOS (CCC)')
:param filter_subject: Filtrar por código o nombre de materia (ej. 'ASIG00113')
:param filter_day: Filtrar por día específico ('Lunes'..'Sábado' o 'ALL')
:param filter_days: Lista o cadena de días específicos (ej. ['Lunes', 'Martes'])
:param manual_date: Fecha manual específica (YYYY-MM-DD o objeto date)
:param single_date_only: Si es True y hay manual_date, crea reserva solo para esa fecha puntual
:param import_careers: Booleano para importar/crear carreras
:param import_subjects: Booleano para importar/crear asignaturas
:param import_commissions: Booleano para importar/crear comisiones
:param import_classrooms: Booleano para importar/crear aulas
:param import_reservations: Booleano para importar/crear reservas
:param selected_rows: Lista de filas específicas pre-seleccionadas desde la grilla interactiva
"""
dias_esp = ['Lunes', 'Martes', 'Miércoles', 'Jueves', 'Viernes', 'Sábado', 'Domingo']
@@ -430,19 +534,26 @@ class GoogleSheetsImporter:
manual_dt = manual_date if isinstance(manual_date, date) else manual_date.date()
elif isinstance(manual_date, str) and manual_date.strip():
manual_dt = datetime.strptime(manual_date.strip(), '%Y-%m-%d').date()
except Exception as e:
except Exception:
pass
# Normalizar día filtro si fue provisto
norm_filter_day = normalize_day_name(filter_day) if filter_day else None
if norm_filter_day and norm_filter_day.upper() in ['ALL', 'TODOS', 'TODOS LOS DÍAS', 'TODOS LOS DIAS', '']:
norm_filter_day = None
# Normalizar días permitidos
allowed_days = None
if filter_days:
if isinstance(filter_days, str):
allowed_days = [normalize_day_name(d) for d in filter_days.split(',') if d.strip()]
elif isinstance(filter_days, (list, set)):
allowed_days = [normalize_day_name(d) for d in filter_days if d]
elif filter_day:
nd = normalize_day_name(filter_day)
if nd and nd.upper() not in ['ALL', 'TODOS', 'TODOS LOS DÍAS', 'TODOS LOS DIAS', '']:
allowed_days = [nd]
# Si el usuario no especificó filter_day pero ingresó fecha manual puntual, inferir día
if not norm_filter_day and manual_dt and single_date_only:
# Si el usuario no especificó días pero ingresó fecha manual puntual, inferir día
if not allowed_days and manual_dt and single_date_only:
manual_w = manual_dt.weekday()
if manual_w < 6:
norm_filter_day = dias_esp[manual_w]
allowed_days = [dias_esp[manual_w]]
stats = {
'total_rows_processed': 0,
@@ -461,39 +572,56 @@ class GoogleSheetsImporter:
'filters_applied': {
'career': filter_career.strip() if filter_career else None,
'subject': filter_subject.strip() if filter_subject else None,
'day': norm_filter_day or 'Todos los Días',
'days': allowed_days or ['Todos los Días'],
'manual_date': manual_dt.strftime('%Y-%m-%d') if manual_dt else None,
'single_date_only': bool(single_date_only and manual_dt)
'single_date_only': bool(single_date_only and manual_dt),
'entities': {
'careers': bool(import_careers),
'subjects': bool(import_subjects),
'commissions': bool(import_commissions),
'classrooms': bool(import_classrooms),
'reservations': bool(import_reservations)
}
}
}
all_raw_records = []
sheets_to_process = self.get_sheets_config()
# Filtrar pestañas si se especificó un día específico
if norm_filter_day:
sheets_to_process = [s for s in sheets_to_process if normalize_day_name(s['name']) == norm_filter_day]
if selected_rows and isinstance(selected_rows, list) and len(selected_rows) > 0:
# Modo grilla interactiva: se procesan las filas explícitamente seleccionadas por el usuario
for r in selected_rows:
d_name = r.get('dia') or 'Lunes'
d_idx = map_day_to_idx(d_name)
all_raw_records.append((r, d_idx))
if d_name not in stats['by_day']:
stats['by_day'][d_name] = {'rows_count': 0, 'status': 'OK'}
stats['by_day'][d_name]['rows_count'] += 1
else:
# Modo descarga general desde Google Sheets
sheets_to_process = self.get_sheets_config()
if allowed_days:
sheets_to_process = [s for s in sheets_to_process if normalize_day_name(s['name']) in allowed_days]
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, 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:
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)
}
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, 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:
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:
@@ -581,13 +709,15 @@ class GoogleSheetsImporter:
career = careers_cache.get(c_key)
if not career:
career = Career.query.filter(Career.name.ilike(c_name)).first()
if not career:
if not career and import_careers:
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)
if career:
careers_cache[c_key] = career
if career:
career_objs.append(career)
primary_career = career_objs[0] if career_objs else None
@@ -599,23 +729,27 @@ class GoogleSheetsImporter:
classroom = classrooms_cache.get(room_key)
b_entity = buildings_cache.get(room_info['building'].upper())
if not classroom:
classroom = Classroom(
building=room_info['building'],
building_id=b_entity.id if b_entity else None,
floor=room_info['floor'],
capacity=room_info['capacity'],
description=room_info['description'],
is_active=True
)
classroom.code = room_info['code']
db.session.add(classroom)
db.session.flush()
classrooms_cache[room_key] = classroom
stats['classrooms_created'] += 1
if import_classrooms:
classroom = Classroom(
building=room_info['building'],
building_id=b_entity.id if b_entity else None,
floor=room_info['floor'],
capacity=room_info['capacity'],
description=room_info['description'],
is_active=True
)
classroom.code = room_info['code']
db.session.add(classroom)
db.session.flush()
classrooms_cache[room_key] = classroom
stats['classrooms_created'] += 1
else:
classroom = Classroom.query.filter_by(code=room_info['code']).first()
else:
classroom.capacity = max(classroom.capacity, room_info['capacity'])
if not classroom.building_id and b_entity:
classroom.building_id = b_entity.id
if import_classrooms:
classroom.capacity = max(classroom.capacity, room_info['capacity'])
if not classroom.building_id and b_entity:
classroom.building_id = b_entity.id
# 3. Upsert Subject (Soporte Many-to-Many con múltiples carreras y subcódigos)
subject_key = codigo.upper()
@@ -638,76 +772,84 @@ class GoogleSheetsImporter:
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=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()
stats['subjects_created'] += 1
if import_subjects:
subject = Subject(
code=codigo,
name=asignatura,
career_id=primary_career.id if primary_career else None,
department=department_str,
credits=4,
is_active=True
)
if career_objs:
subject.careers = career_objs
db.session.add(subject)
db.session.flush()
stats['subjects_created'] += 1
else:
if subject.name != asignatura:
subject.name = asignatura
stats['subjects_updated'] += 1
# 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
if import_subjects:
if subject.name != asignatura:
subject.name = asignatura
stats['subjects_updated'] += 1
# 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
# Registrar en caché con código completo y con subcódigos individuales si existe
if subject:
subjects_cache[subject_key] = subject
for sc in sub_codes:
subjects_cache[sc.upper()] = subject
# 4. Upsert Commission
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,
code=comm_code,
semester='2026-2',
year=2026
).first()
if not commission:
commission = Commission(
commission = None
if subject:
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,
code=comm_code,
semester='2026-2',
year=2026,
teacher_id=default_user_id,
max_students=classroom.capacity if classroom else 35,
current_students=0,
schedule=f"{dia} {horario_raw}",
shift=turno,
active=True
)
db.session.add(commission)
db.session.flush()
stats['commissions_created'] += 1
else:
commission.schedule = f"{dia} {horario_raw}"
commission.shift = turno
if classroom:
commission.max_students = max(commission.max_students or 0, classroom.capacity)
year=2026
).first()
if not commission:
if import_commissions:
commission = Commission(
subject_id=subject.id,
code=comm_code,
semester='2026-2',
year=2026,
teacher_id=default_user_id,
max_students=classroom.capacity if classroom else 35,
current_students=0,
schedule=f"{dia} {horario_raw}",
shift=turno,
active=True
)
db.session.add(commission)
db.session.flush()
stats['commissions_created'] += 1
else:
if import_commissions:
commission.schedule = f"{dia} {horario_raw}"
commission.shift = turno
if classroom:
commission.max_students = max(commission.max_students or 0, classroom.capacity)
# 5. Generar Reservas de Calendario
t_start, t_end = self.parse_time_range(horario_raw)
effective_day_idx = day_idx if day_idx is not None else (manual_dt.weekday() if manual_dt else 0)
if classroom and t_start and t_end:
if import_reservations and classroom and subject and commission and t_start and t_end:
is_room_virtual = bool(classroom.is_virtual or 'VIRTUAL' in (classroom.code or '').upper())
v_link = None
@@ -718,9 +860,22 @@ class GoogleSheetsImporter:
if not commission.virtual_link:
commission.virtual_link = v_link
# Determinar fechas a generar: puntual o 16 semanas
# Determinar fechas a generar: específica de la fila (datepicker), puntual o 16 semanas
dates_to_generate = []
if single_date_only and manual_dt:
row_specific_date = None
raw_row_date = rec.get('date') or rec.get('inferred_date')
if raw_row_date:
try:
if isinstance(raw_row_date, (datetime, date)):
row_specific_date = raw_row_date if isinstance(raw_row_date, date) else raw_row_date.date()
elif isinstance(raw_row_date, str) and raw_row_date.strip():
row_specific_date = datetime.strptime(raw_row_date.strip(), '%Y-%m-%d').date()
except Exception:
pass
if row_specific_date:
dates_to_generate = [row_specific_date]
elif single_date_only and manual_dt:
dates_to_generate = [manual_dt]
else:
dates_to_generate = [base_monday + timedelta(days=effective_day_idx, weeks=w) for w in range(weeks_to_generate)]