# -*- coding: utf-8 -*- # ============================================================================= # Nazev: store_cda_seaweed_v1.1.py # Verze: 1.1 # Datum: 2026-06-19 # Popis: Ulozi podepsane CDA (PDF) z e-mailu asistentek do Mongo # feasibility.investigators do pole cda.* a posune lekare na # KROK "5 - CDA podepsano". PDF se stahuji primo ze SeaweedFS # (seaweed_url z attachments v emaily."vbuzalka@its.jnj.com"), # overuje se SHA256 proti metadatum z Mongo. # Pouziti: python store_cda_seaweed_v1.1.py (dry-run / nahled) # python store_cda_seaweed_v1.1.py --apply (zapise do Mongo) # Zmena: v1.1 - STATUS radek + datum bere z DATE; MAPPING = Leksa Vaclav. # v1.0 -> TRASH. # Pozn.: MAPPING nize = explicitni parovani investigator -> CDA priloha. # Jen stdlib + pymongo. SeaweedFS host 192.168.1.50:8888. # ============================================================================= import sys import base64 import hashlib import urllib.request from datetime import datetime, timezone from pymongo import MongoClient from bson import ObjectId MONGO_URI = "mongodb://192.168.1.76:27017" DBN, COL = "feasibility", "investigators" DATE = "19JUN2026" # (investigator _id, seaweed_url, filename, sha256, size, source_msg_id, label) MAPPING = [ ("6a268cdeb84bf5597759b478", "http://192.168.1.50:8888/mail-attachments/b5/c8/b5c8677c335f77e2b3184aca71628393bf30bd843334edfdecd32b544e91882d", "CZ_CDA PI_MUDr. Stanislav Reif_ICO_fully signed_18Jun2026.pdf", "b5c8677c335f77e2b3184aca71628393bf30bd843334edfdecd32b544e91882d", 476306, "", "Reif Stanislav"), ] def fetch(url): with urllib.request.urlopen(url, timeout=30) as r: return r.read() def main(): apply = "--apply" in sys.argv cli = MongoClient(MONGO_URI) col = cli[DBN][COL] now = datetime.now(timezone.utc).isoformat() ok = 0 for _id, url, fname, sha, size, src, label in MAPPING: oid = ObjectId(_id) doc = col.find_one({"_id": oid}, {"STATUS": 1, "KROK": 1, "cda.stav": 1}) if not doc: print(f" !! {label}: investigator _id={_id} NENALEZEN"); continue try: raw = fetch(url) except Exception as e: print(f" !! {label}: stazeni selhalo: {e}"); continue got = hashlib.sha256(raw).hexdigest() sha_ok = (got == sha) size_ok = (len(raw) == size) head_ok = raw[:5] == b"%PDF-" print(f" [{label}]") print(f" soubor : {fname}") print(f" stazeno : {len(raw)} B (ocek. {size}) {'OK' if size_ok else 'MISMATCH'}") print(f" sha256 : {'OK' if sha_ok else 'MISMATCH! ' + got}") print(f" PDF hdr : {'OK' if head_ok else 'NENI PDF'}") print(f" KROK : {doc.get('KROK')} -> 5 - CDA podepsano") if not (sha_ok and size_ok and head_ok): print(" >> PRESKAKUJI (kontrola selhala)"); continue if not apply: ok += 1; continue b64 = base64.b64encode(raw).decode("ascii") old_status = doc.get("STATUS", "") or "" new_line = (f"{DATE}: podepsane CDA ULOZENO do Mongo (cda.data) — {fname} " f"(z e-mailu asistentky CTA). KROK 5, pripraveno na SIPIQ.") col.update_one({"_id": oid}, {"$set": { "KROK": "5 - CDA podepsano", "STATUS": new_line + "\n" + old_status, "cda.stav": "podepsano", "cda.soubor": fname, "cda.zdroj": "e-mail asistentky (SeaweedFS)", "cda.data_base64": b64, "cda.data_sha256": sha, "cda.data_filename": fname, "cda.data_mime": "application/pdf", "cda.data_size": len(raw), "cda.data_stored_at": now, "cda.data_source_msg": src, }}) ok += 1 print(" >> ULOZENO + KROK 5") print(f"\n{'ZAPSANO' if apply else 'DRY-RUN OK'}: {ok}/{len(MAPPING)}") if not apply: print(">>> Pro zapis spust s --apply") if __name__ == "__main__": main()