z230

IWRS/Patients/download_subject_details.py

@@ -4,10 +4,11 @@ import glob
 import datetime
 import re
 import json
-import mysql.connector
-
+import sys
 import pandas as pd
-import db_config
+
+sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
+from common.mongo_writer import get_db
 
 # ── CONFIG ──────────────────────────────────────────────────────────────────
 BASE_URL = "https://janssen.4gclinical.com"
@@ -22,8 +23,9 @@ DETAILS_DIR  = os.path.join(BASE_DIR, "IncomingSourceReportsDetails")
 # ────────────────────────────────────────────────────────────────────────────
 
 
-def get_subjects(study):
-    pattern = os.path.join(INCOMING_DIR, f"* {study} Subject Summary Report.xlsx")
+def get_subjects(study, source_dir=None):
+    src = source_dir or INCOMING_DIR
+    pattern = os.path.join(src, f"* {study} Subject Summary Report*.xlsx")
     files = sorted(
         [f for f in glob.glob(pattern) if not os.path.basename(f).startswith("~$")],
         key=os.path.getmtime,
@@ -58,25 +60,22 @@ def strip_html(html):
 
 
 def get_existing_pks(study):
+    """Načte už importované pk notifikací pro studii z Mongo."""
     try:
-        conn = mysql.connector.connect(
-            host=db_config.DB_HOST, port=db_config.DB_PORT,
-            user=db_config.DB_USER, password=db_config.DB_PASSWORD,
-            database=db_config.DB_NAME,
-        )
-        cursor = conn.cursor()
-        cursor.execute("SELECT pk FROM iwrs_notifications WHERE study = %s", (study,))
-        pks = {row[0] for row in cursor.fetchall()}
-        cursor.close()
-        conn.close()
-        return pks
+        db = get_db()
+        return {d["_id"] for d in db.iwrs_notifications.find(
+            {"study": study}, {"_id": 1}
+        )}
     except Exception as e:
-        print(f"  UPOZORNĚNÍ: nelze načíst pk z DB ({e}), stahuji vše")
+        print(f"  UPOZORNĚNÍ: nelze načíst pk z Mongo ({e}), stahuji vše")
         return set()
 
 
-def download_notifications_for_subject(page, study, subject, api_base, existing_pks, out_dir, table1_data):
-    """Stáhne notifikace pro subjekta z již zachycené table_1 response."""
+def download_notifications_for_subject(page, study, subject, api_base, existing_pks, out_dir, table1_data, flat=False):
+    """Stáhne notifikace pro subjekta z již zachycené table_1 response.
+
+    flat=True → název obsahuje study+subject (pro Incoming/ kde leží všechno pohromadě).
+    """
     new_count = 0
     for row in table1_data.get("data", []):
         for notif in (row.get("notification") or []):
@@ -92,9 +91,13 @@ def download_notifications_for_subject(page, study, subject, api_base, existing_
             text        = strip_html(body)
             actual_date = row.get("actual_date_raw", "0000-00-00")
 
-            pdf_filename = os.path.join(out_dir, f"{actual_date}_{safe_label}.pdf")
+            if flat:
+                stem = f"{actual_date}_{study}_{subject}_{safe_label}"
+            else:
+                stem = f"{actual_date}_{safe_label}"
+            pdf_filename = os.path.join(out_dir, f"{stem}.pdf")
             if os.path.exists(pdf_filename):
-                pdf_filename = os.path.join(out_dir, f"{actual_date}_{safe_label}_pk{pk}.pdf")
+                pdf_filename = os.path.join(out_dir, f"{stem}_pk{pk}.pdf")
 
             # Načti JWT čerstvě před každým requestem
             jwt = page.evaluate("localStorage.getItem('JWT.access')")
@@ -126,11 +129,18 @@ def download_notifications_for_subject(page, study, subject, api_base, existing_
     return new_count
 
 
-def run(page, study):
-    out_dir = os.path.join(DETAILS_DIR, study)
+def run(page, study, out_dir=None, subjects_source_dir=None):
+    """
+    out_dir=None → legacy: ukládá do IncomingSourceReportsDetails/{study}/
+    out_dir=cesta → vše ukládá ploše do té cesty (Incoming/).
+    subjects_source_dir=None → čte summary z IncomingSourceReports/ (legacy).
+    """
+    flat = out_dir is not None
+    if out_dir is None:
+        out_dir = os.path.join(DETAILS_DIR, study)
     os.makedirs(out_dir, exist_ok=True)
 
-    subjects = get_subjects(study)
+    subjects = get_subjects(study, subjects_source_dir)
     print(f"  Nalezeno {len(subjects)} subjektů")
     today = datetime.date.today().strftime("%Y-%m-%d")
 
@@ -216,7 +226,7 @@ def run(page, study):
         # Stáhnout notifikace pro tohoto subjekta
         if api_base and table1_data:
             n = download_notifications_for_subject(
-                page, study, subject, api_base, existing_pks, out_dir, table1_data
+                page, study, subject, api_base, existing_pks, out_dir, table1_data, flat=flat
             )
             total_notif += n