# -*- coding: utf-8 -*-
# =============================================================================
# Nazev:   store_cda_to_mongo_v1.0.py
# Verze:   1.0
# Datum:   2026-06-09
# Popis:   Ulozi binarku dokumentu (napr. CDA PDF) do Mongo k investigatorovi
#          (feasibility.investigators -> pole cda.data_*). Drzi se domluvy:
#          "fyzicky dokument z e-mailu -> do Mongo".
#          Zdroj dat = lokalni soubor (PDF uz extrahovany z .msg).
#          Zapise: cda.data_base64, cda.data_sha256, cda.data_filename,
#                  cda.data_mime, cda.data_size, cda.data_stored_at.
#          Existujici cda.* (stav, datum_*, soubor, zdroj, poznamka) NEMENI.
# Pouziti: python store_cda_to_mongo_v1.0.py            (dry-run / nahled)
#          python store_cda_to_mongo_v1.0.py --apply     (zapise do Mongo)
# =============================================================================

import os
import sys
import base64
import hashlib
from pymongo import MongoClient
from bson import ObjectId

MONGO_URI = os.environ.get("MONGO_URI", "mongodb://192.168.1.76:27017")

# --- Konfigurace konkretniho zapisu ---
INVESTIGATOR_ID = "6a1c4275aa46d8b608065cec"   # Lukac Ludovit
PDF_PATH = r"u:\Dropbox\!!!Days\Downloads Z230\SK_CDA_ PI_doc. MUDr. Ludovít Lukác, Ph.D._fully signed_04Jun2026.pdf"
DATA_FILENAME = "SK_CDA_ PI_doc. MUDr. Ľudovít Lukáč, Ph.D._fully signed_04Jun2026.pdf"
DATA_MIME = "application/pdf"
STORED_AT = "2026-06-09"   # datum ulozeni (date nelze generovat za behu)


def main():
    apply = "--apply" in sys.argv

    if not os.path.exists(PDF_PATH):
        print("!!! Soubor neexistuje:", PDF_PATH)
        return
    with open(PDF_PATH, "rb") as f:
        raw = f.read()
    size = len(raw)
    sha = hashlib.sha256(raw).hexdigest()
    b64 = base64.b64encode(raw).decode("ascii")

    client = MongoClient(MONGO_URI)
    col = client["feasibility"]["investigators"]
    doc = col.find_one({"_id": ObjectId(INVESTIGATOR_ID)},
                        {"prijmeni": 1, "jmeno": 1, "cda": 1})
    if not doc:
        print("!!! Investigator nenalezen:", INVESTIGATOR_ID)
        return

    print("=== NAHLED ZAPISU ===")
    print(f"Investigator: {doc.get('prijmeni')} {doc.get('jmeno')}  (_id {INVESTIGATOR_ID})")
    cda = doc.get("cda", {}) or {}
    print("Stavajici cda.* pole:", ", ".join(sorted(cda.keys())) or "(zadne)")
    print("  - cda.soubor:", cda.get("soubor"))
    print("  - cda.velikost_bytes:", cda.get("velikost_bytes"))
    has_data = "data_base64" in cda
    print("  - cda.data_base64 jiz existuje:", has_data)
    print()
    print("PRIDAM/PREPISI tato pole:")
    print("  cda.data_filename =", DATA_FILENAME)
    print("  cda.data_mime     =", DATA_MIME)
    print("  cda.data_size     =", size, "B")
    print("  cda.data_sha256   =", sha)
    print("  cda.data_stored_at=", STORED_AT)
    print(f"  cda.data_base64   = <base64 {len(b64)} znaku>")
    print()

    if not apply:
        print(">>> DRY-RUN. Pro zapis spust s --apply")
        return

    res = col.update_one(
        {"_id": ObjectId(INVESTIGATOR_ID)},
        {"$set": {
            "cda.data_base64": b64,
            "cda.data_sha256": sha,
            "cda.data_filename": DATA_FILENAME,
            "cda.data_mime": DATA_MIME,
            "cda.data_size": size,
            "cda.data_stored_at": STORED_AT,
        }},
    )
    print(f">>> ZAPSANO: matched={res.matched_count}, modified={res.modified_count}")


if __name__ == "__main__":
    main()