Compute data differences in the script.

1 files changed, 28 insertions, 9 deletions

diff --git a/scripts/phenotypes_bulk_edit.py b/scripts/phenotypes_bulk_edit.py
index 0b4fec5..6fc198c 100644
--- a/scripts/phenotypes_bulk_edit.py
+++ b/scripts/phenotypes_bulk_edit.py
@@ -11,9 +11,11 @@ from MySQLdb.cursors import DictCursor
 from gn_libs import jobs, mysqldb, sqlite3
 
 from uploader.phenotypes.models import phenotypes_data_by_ids
+from uploader.phenotypes.misc import phenotypes_data_differences
+from uploader.phenotypes.views import BULK_EDIT_COMMON_FIELDNAMES
+
 import uploader.publications.pubmed as pmed
 from uploader.publications.misc import publications_differences
-from uploader.phenotypes.views import BULK_EDIT_COMMON_FIELDNAMES
 from uploader.publications.models import (
     update_publications, fetch_phenotype_publications)
 
@@ -213,14 +215,31 @@ def run(conn, job):
             for row in _db_publications + _new_publications})
     logger.debug("Publications diff: %s", _pub_diff)
     # 2. Data differences
-    # _db_pheno_data = phenotypes_data_by_ids(conn, tuple({
-    #     "population_id": job["metadata"]["population-id"],
-    #     "phenoid": row[0],
-    #     "xref_id": row[1]
-    # } for row in pheno_xref_ids))
-    # logger.debug("Phenotype Data in Database: %s", _db_pheno_data)
-
-    # data_diff = data_differences(...)
+    _db_pheno_data = phenotypes_data_by_ids(conn, tuple({
+        "population_id": job["metadata"]["population-id"],
+        "phenoid": row[0],
+        "xref_id": row[1]
+    } for row in pheno_xref_ids))
+
+    data_diff = phenotypes_data_differences(
+        ({
+            "phenotype_id": row["phenotype_id"],
+            "xref_id": row["xref_id"],
+            "data": {
+                key:val for key,val in row.items()
+                if key not in BULK_EDIT_COMMON_FIELDNAMES + [
+                        "phenotype_id", "xref_id"]
+            }
+        } for row in file_contents),
+        ({
+            **row,
+            "PhenotypeId": row["Id"],
+            "data": {
+                dataitem["StrainName"]: dataitem
+                for dataitem in row["data"].values()
+            }
+        } for row in _db_pheno_data))
+    logger.debug("Data differences: %s", data_diff)
     ### END: Compute differences
     update_descriptions()
     link_publications()