z230

Clario/import_to_mongo.py

@@ -1,14 +1,16 @@
 """
 import_to_mongo.py
-Verze: 1.1
-Datum: 2026-06-01
+Verze: 1.2
+Datum: 2026-06-02
 
 Import Clario CSV do MongoDB (databáze: Clario).
 
-Kolekce: Clario.MayoDiary / Clario.MayoScore  (dle názvu souboru)
+Kolekce: Clario.MayoDiary / Clario.MayoScore / Clario.eCOA_DCRs / Clario.ECG_DCRs
 Filtr:   pouze řádky s Country == "Czech Republic"
-Klíč:    MayoDiary → Subject ID + Form Number
-         MayoScore → Participant ID + Visit
+Klíč:    MayoDiary  → Subject ID + Form Number
+         MayoScore  → Participant ID + Visit
+         eCOA_DCRs  → Data Correction ID
+         ECG_DCRs   → Data Correction ID
 Historie: při změně fields se stará verze uloží do pole history[]
 Po importu přesune zpracované CSV do downloads/Zpracovano/
 
@@ -58,6 +60,16 @@ COLLECTION_CONFIG = {
             "Partial Mayo Response for Clinical Non-Responders",
         ),
     },
+    "eCOA DCRs": {
+        "collection": "Clario.eCOA_DCRs",
+        "subject_col": "Subject ID",
+        "key_cols": ("Data Correction ID",),
+    },
+    "ECG DCRs": {
+        "collection": "Clario.ECG_DCRs",
+        "subject_col": "Subject Number",
+        "key_cols": ("Data Correction ID",),
+    },
 }
 
 DATE_FORMATS = [
@@ -120,7 +132,9 @@ def map_row(row: dict, col_type: str) -> dict:
 
     subject_col = cfg["subject_col"]
     doc["subject"] = {"id": cleaned.get(subject_col, "")}
-    doc["site"] = {"name": cleaned.get("Site", "")}
+    # ECG DCRs používají "Site ID" místo "Site"
+    site_name = cleaned.get("Site") or cleaned.get("Site ID", "")
+    doc["site"] = {"name": site_name}
     doc["country"] = cleaned.get("Country", "")
     doc["study"] = cleaned.get("Protocol", "")
 
@@ -173,7 +187,7 @@ def import_file(csv_path: str, db) -> dict:
         for row in reader:
             cleaned_row = {clean_colname(k): v for k, v in row.items()}
             country = cleaned_row.get("Country", "").strip()
-            if country != COUNTRY_FILTER:
+            if COUNTRY_FILTER not in country:
                 filtered_out += 1
                 continue
 
@@ -221,6 +235,9 @@ def import_file(csv_path: str, db) -> dict:
     collection.create_index([("site.name", ASCENDING)])
     if col_type == "MayoScore":
         collection.create_index([("Site Action", ASCENDING)])
+    if col_type in ("eCOA DCRs", "ECG DCRs"):
+        collection.create_index([("fields.Status", ASCENDING)])
+        collection.create_index([("fields.Type", ASCENDING)])
 
     stats = {
         "collection": col_name,