SFR-2285: Fix has part item build

NYPL · Oct 25, 2024 · beec0a1 · beec0a1
1 parent d2778ae
commit beec0a1
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 6 deletions.
diff --git a/managers/sfrRecord.py b/managers/sfrRecord.py
@@ -258,8 +258,10 @@ def parseInstance(self, workData, editionData, rec):
         editionData['dcdw_uuids'].append(rec.uuid.hex)
 
     def buildItems(self, editionData, rec, itemContributors):
+        max_part_number = max(int(item.split('|')[0]) for item in rec.has_part)
+
         startPos = len(editionData['items']) - 1
-        editionData['items'].extend([None] * len(rec.has_part))
+        editionData['items'].extend([None] * max_part_number)
 
         for item in rec.has_part:
             no, uri, source, linkType, flags = tuple(item.split('|'))

diff --git a/processes/cluster.py b/processes/cluster.py
@@ -28,9 +28,9 @@ def __init__(self, *args):
 
         self.createRedisClient()
 
-        self.createElasticConnection()
-        self.createElasticSearchIngestPipeline()
-        self.createElasticSearchIndex()
+        # self.createElasticConnection()
+        # self.createElasticSearchIngestPipeline()
+        # self.createElasticSearchIndex()
 
     def runProcess(self):
         try:
@@ -55,6 +55,7 @@ def cluster_records(self, full=False, start_datetime=None):
                 .filter(Record.cluster_status == False)
                 .filter(Record.source != 'oclcClassify')
                 .filter(Record.source != 'oclcCatalog')
+                .filter(Record.uuid == '2ddb63df-e4f5-479a-ad95-c03702c577b2')
         )
 
         if not full:
@@ -83,7 +84,7 @@ def cluster_records(self, full=False, start_datetime=None):
                 raise e
 
             if len(works_to_index) >= self.CLUSTER_BATCH_SIZE:
-                self.update_elastic_search(works_to_index, work_ids_to_delete)
+                #  self.update_elastic_search(works_to_index, work_ids_to_delete)
                 logger.info(f'Clustered {len(works_to_index)} works')
                 works_to_index = []
 
@@ -93,7 +94,7 @@ def cluster_records(self, full=False, start_datetime=None):
                 self.session.commit()
 
         logger.info(f'Clustered {len(works_to_index)} works')
-        self.update_elastic_search(works_to_index, work_ids_to_delete)
+        # self.update_elastic_search(works_to_index, work_ids_to_delete)
         self.delete_stale_works(work_ids_to_delete)
 
         self.session.commit()