108 lines
3.2 KiB
Python
108 lines
3.2 KiB
Python
"""
|
|
Import všech čekajících reportů z `Incoming/` do MongoDB.
|
|
|
|
Pořadí zpracování per typ + studie: nejstarší soubor podle mtime první
|
|
(důležité pro chronologickou správnost snapshotů).
|
|
|
|
Po úspěšném importu se soubor přesune do `Incoming/Zpracováno/`.
|
|
Při chybě zůstane soubor v `Incoming/`.
|
|
"""
|
|
|
|
import os
|
|
import sys
|
|
import glob
|
|
import shutil
|
|
|
|
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
|
|
from common.mongo_writer import ensure_indexes
|
|
|
|
import import_to_mongo
|
|
import import_notifications_to_mongo
|
|
|
|
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
|
|
INCOMING_DIR = os.path.join(BASE_DIR, "Incoming")
|
|
DONE_DIR = os.path.join(INCOMING_DIR, "Zpracováno")
|
|
|
|
STUDIES = ["77242113UCO3001", "42847922MDD3003"]
|
|
|
|
|
|
def _move_done(path):
|
|
os.makedirs(DONE_DIR, exist_ok=True)
|
|
dst = os.path.join(DONE_DIR, os.path.basename(path))
|
|
# kolize → přepiš (Mongo už má aktuální data, soubor je jen archiv)
|
|
if os.path.exists(dst):
|
|
os.remove(dst)
|
|
shutil.move(path, dst)
|
|
|
|
|
|
def _sorted_by_mtime(paths):
|
|
"""Nejstarší první."""
|
|
return sorted(
|
|
(p for p in paths if not os.path.basename(p).startswith("~$")),
|
|
key=os.path.getmtime,
|
|
)
|
|
|
|
|
|
def import_summaries(study):
|
|
pattern = os.path.join(INCOMING_DIR, f"* {study} Subject Summary Report*.xlsx")
|
|
files = _sorted_by_mtime(glob.glob(pattern))
|
|
if not files:
|
|
print(f" [{study}] summary: nic ke zpracování")
|
|
return
|
|
print(f" [{study}] summary: {len(files)} soubor(ů) (oldest first)")
|
|
for path in files:
|
|
try:
|
|
import_to_mongo.import_subject_summary(study, path)
|
|
_move_done(path)
|
|
except Exception as e:
|
|
print(f" [{study}] CHYBA summary {os.path.basename(path)}: {e}")
|
|
|
|
|
|
def import_details(study):
|
|
pattern = os.path.join(INCOMING_DIR, f"* {study} * Subject Detail.xlsx")
|
|
files = _sorted_by_mtime(glob.glob(pattern))
|
|
if not files:
|
|
print(f" [{study}] detail: nic ke zpracování")
|
|
return
|
|
print(f" [{study}] detail: {len(files)} soubor(ů) (oldest first)")
|
|
for path in files:
|
|
parsed = import_to_mongo.parse_detail_filename(path)
|
|
if not parsed:
|
|
print(f" [{study}] PŘESKAKUJI (nelze parsovat název): {os.path.basename(path)}")
|
|
continue
|
|
_, parsed_study, subject = parsed
|
|
if parsed_study != study:
|
|
continue # patří jiné studii
|
|
try:
|
|
import_to_mongo.import_visits_single_file(study, subject, path)
|
|
_move_done(path)
|
|
except Exception as e:
|
|
print(f" [{study}] CHYBA detail {os.path.basename(path)}: {e}")
|
|
|
|
|
|
def main():
|
|
if not os.path.isdir(INCOMING_DIR):
|
|
print(f"Adresář neexistuje: {INCOMING_DIR}")
|
|
return
|
|
ensure_indexes()
|
|
|
|
print("=" * 60)
|
|
print("Import Subject Summary + Visits")
|
|
print("=" * 60)
|
|
for study in STUDIES:
|
|
import_summaries(study)
|
|
import_details(study)
|
|
|
|
print("\n" + "=" * 60)
|
|
print("Import notifikací")
|
|
print("=" * 60)
|
|
import_notifications_to_mongo.import_from_dir(INCOMING_DIR, DONE_DIR, STUDIES)
|
|
|
|
print("\n" + "=" * 60)
|
|
print(f"Hotovo. Zpracované soubory: {DONE_DIR}")
|
|
print("=" * 60)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|