From 672debb68ad649756735adef64071327f38cbb8c Mon Sep 17 00:00:00 2001
From: Frederick Muriuki Muriithi
Date: Mon, 19 May 2025 10:45:11 -0500
Subject: Fetch next available PublishXRef.DataId value for the phenotypes.

---
 scripts/load_phenotypes_to_db.py | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

(limited to 'scripts')

diff --git a/scripts/load_phenotypes_to_db.py b/scripts/load_phenotypes_to_db.py
index fdf711b..e6623fe 100644
--- a/scripts/load_phenotypes_to_db.py
+++ b/scripts/load_phenotypes_to_db.py
@@ -74,6 +74,14 @@ def save_phenotypes(
          if idx != 0))
 
 
+def __fetch_next_dataid__(conn: mysqldb.Connection) -> int:
+    """Fetch the next available DataId value from the database."""
+    with conn.cursor(cursorclass=DictCursor) as cursor:
+        cursor.execute(
+            "SELECT MAX(DataId) AS CurrentMaxDataId FROM PublishXRef")
+        return int(cursor.fetchone()) + 1
+
+
 def save_phenotypes_data(conn: mysqldb.Connection, dataidmap, samples, datafiles):
     """Read the `datafiles` and save the data in the database."""
     pass
@@ -107,13 +115,12 @@ def load_data(conn, job):
     logger.info("Saving basic phenotype data.")
 
     _phenos = save_phenotypes(cursor, _control_data)
-    _next_data_id = fetch_next_dataid(...)
     dataidmap = {
         row["phenotype_id"]: {
             "phenotype_id": row["phenotype_id"],
-            "data_id": _nextid
+            "data_id": dataid
         }
-        for _nextid, row in enumerate(_phenos, start=_next_data_id)
+        for dataid, row in enumerate(_phenos, start=__fetch_next_dataid__(conn))
     }
     # 2. Save any new publications (in multi-file bundle):
     #     -> return publication IDS
-- 
cgit v1.2.3