Merge pull request #836 from alliance-genome/SCRUM-4868

new endpoint to export mod recently sorted out papers

agr_literature_service/api/crud/reference_crud.py

@@ -1145,14 +1145,18 @@ def add_to_corpus(db: Session, mod_abbreviation: str, reference_curie: str):  #
                             detail=f"Error adding {reference_curie} to {mod_abbreviation} corpus: {e}")
 
 
-def get_recently_sorted_references(db: Session, mod_abbreviation, days):
-
-    datestamp = str(date.today()).replace("-", "")
-    metaData = get_meta_data(mod_abbreviation, datestamp)
-
+def get_past_to_present_date_range(num_days_ago: int):
+    current_timestamp = str(date.today()).replace("-", "")
     now = datetime.now().date()
-    start_date = now - timedelta(days=days)
+    start_date = now - timedelta(days=num_days_ago)
     end_date = now + timedelta(days=1)  # to cover timezone issue
+    return current_timestamp, start_date, end_date
+
+
+def get_recently_sorted_references(db: Session, mod_abbreviation, days):
+
+    current_timestamp, start_date, end_date = get_past_to_present_date_range(days)
+    metaData = get_meta_data(mod_abbreviation, current_timestamp)
 
     refColNmList = ", ".join(get_reference_col_names())
 
@@ -1212,3 +1216,42 @@ def get_recently_sorted_references(db: Session, mod_abbreviation, days):
         "metaData": metaData,
         "data": data
     }
+
+
+def get_recently_deleted_references(db: Session, mod_abbreviation, days):
+
+    current_timestamp, start_date, end_date = get_past_to_present_date_range(days)
+    metaData = get_meta_data(mod_abbreviation, current_timestamp)
+
+    sql_query = text(
+        "SELECT cr.curie, u.email, u.id "
+        "FROM cross_reference cr, mod_corpus_association mca, mod m, users u "
+        "WHERE cr.curie_prefix = 'PMID' "
+        "AND cr.reference_id = mca.reference_id "
+        "AND mca.corpus = :corpus "
+        "AND mca.date_updated >= :start_date "
+        "AND mca.date_updated < :end_date "
+        "AND mca.mod_id = m.mod_id "
+        "AND m.abbreviation = :mod_abbreviation "
+        "AND mca.updated_by = u.id"
+    )
+
+    rows = db.execute(sql_query, {
+        "corpus": False,
+        "start_date": start_date,
+        "end_date": end_date,
+        "mod_abbreviation": mod_abbreviation
+    }).fetchall()
+
+    data = []
+    for x in rows:
+        data.append({
+            "pmid": x[0],
+            "updated_by_email": x[1],
+            "updated_by_okta_id": x[2]
+        })
+
+    return {
+        "metaData": metaData,
+        "data": data
+    }

agr_literature_service/api/crud/sort_crud.py

@@ -1,12 +1,12 @@
 import logging
 from sqlalchemy.orm import Session
 from sqlalchemy import text
-from datetime import datetime, timedelta
 
 from agr_literature_service.api.models import ReferenceModel, WorkflowTagModel, CrossReferenceModel,\
     ModCorpusAssociationModel, ModModel, ResourceDescriptorModel, ReferencefileModAssociationModel
 from agr_literature_service.api.schemas import ReferenceSchemaNeedReviewShow, \
     CrossReferenceSchemaShow, ReferencefileSchemaRelated, ReferencefileModSchemaShow
+from agr_literature_service.api.crud.reference_crud import get_past_to_present_date_range
 
 logger = logging.getLogger(__name__)
 
@@ -145,25 +145,30 @@ def get_referencefile_mod(referencefile_id, db: Session):
 
 
 def get_mod_curators(db: Session, mod_abbreviation):
+
+    _, one_month_ago, _ = get_past_to_present_date_range(30)
+
     sql_query_str = """
         SELECT u.id, u.email
         FROM users u
         INNER JOIN mod_corpus_association mca ON mca.updated_by = u.id
         INNER JOIN mod m ON mca.mod_id = m.mod_id
-        WHERE mca.corpus = TRUE
+        WHERE mca.corpus IS NOT NULL
         AND m.abbreviation = :mod_abbreviation
         AND u.email is NOT NULL
+        AND mca.date_updated >= :one_month_ago
     """
     sql_query = text(sql_query_str)
-    result = db.execute(sql_query, {'mod_abbreviation': mod_abbreviation})
+    result = db.execute(sql_query, {
+        'mod_abbreviation': mod_abbreviation,
+        'one_month_ago': one_month_ago
+    })
     return {row[1]: row[0] for row in result}
 
 
 def get_recently_sorted_reference_ids(db: Session, mod_abbreviation, count, curator_okta_id, day):
 
-    now = datetime.now().date()
-    start_date = now - timedelta(days=day)
-    end_date = now + timedelta(days=1)  # to cover timezone issue
+    _, start_date, end_date = get_past_to_present_date_range(day)
 
     sql_query_str = """
         SELECT DISTINCT mcav.reference_id, mcav.date_updated

agr_literature_service/api/routers/reference_router.py

@@ -279,3 +279,13 @@ def get_recently_sorted_references(mod_abbreviation: str,
     references = reference_crud.get_recently_sorted_references(db, mod_abbreviation, days)
 
     return references
+
+
+@router.get('/get_recently_deleted_references/{mod_abbreviation}',
+            status_code=status.HTTP_200_OK)
+def get_recently_deleted_references(mod_abbreviation: str,
+                                    days: int = 7,
+                                    db: Session = db_session):
+    references = reference_crud.get_recently_deleted_references(db, mod_abbreviation, days)
+
+    return references