From e6aea8c81e231b5d1f72231bae984da2a3c6d114 Mon Sep 17 00:00:00 2001
From: jal347 <linjason.03@gmail.com>
Date: Thu, 3 Oct 2024 15:23:34 -0700
Subject: [PATCH] test 1-1 no _id

---
 src/hub/dataload/sources/chembl/parser.py | 33 +++++++++++------------
 src/hub/dataload/sources/chembl/upload.py |  6 ++---
 2 files changed, 19 insertions(+), 20 deletions(-)

diff --git a/src/hub/dataload/sources/chembl/parser.py b/src/hub/dataload/sources/chembl/parser.py
index d1e1a51..c4632a2 100644
--- a/src/hub/dataload/sources/chembl/parser.py
+++ b/src/hub/dataload/sources/chembl/parser.py
@@ -18,24 +18,23 @@ def parse_data(data):
         for accession in accessions:
             if UNIPROT_ACCESSION_PATTERN.fullmatch(accession):
                 uniprot_accessions.append(accession)
-        # if uniprot_accessions:
-        #     for uniprot_accession in uniprot_accessions:
-        #         output = {
-        #             "_id": uniprot_accession,
-        #             "chembl": {
-        #                 "chembl_target": item["target_chembl_id"],
-        #                 "uniprot_accession": uniprot_accession,
-        #             },
-        #         }
-        #         yield output
         if uniprot_accessions:
-            output = {
-                "chembl": {
-                    "chembl_target": item["target_chembl_id"],
-                    "uniprot_accession": uniprot_accessions,
-                },
-            }
-            yield output
+            for uniprot_accession in uniprot_accessions:
+                output = {
+                    "chembl": {
+                        "chembl_target": item["target_chembl_id"],
+                        "uniprot_accession": uniprot_accession,
+                    },
+                }
+                yield output
+        # if uniprot_accessions:
+        #     output = {
+        #         "chembl": {
+        #             "chembl_target": item["target_chembl_id"],
+        #             "uniprot_accession": uniprot_accessions,
+        #         },
+        #     }
+        #     yield output
 
 
 def load_data(target_filepaths):
diff --git a/src/hub/dataload/sources/chembl/upload.py b/src/hub/dataload/sources/chembl/upload.py
index 0e0cd6c..ee49579 100644
--- a/src/hub/dataload/sources/chembl/upload.py
+++ b/src/hub/dataload/sources/chembl/upload.py
@@ -44,8 +44,8 @@ class ChemblUploader(uploader.BaseSourceUploader):
 
     keylookup = MyGeneKeyLookup(
         input_types=[
-            ("swissprot", "chembl.uniprot_accessions"),
-            ("trembl", "chembl.uniprot_accessions"),
+            ("swissprot", "chembl.uniprot_accession"),
+            ("trembl", "chembl.uniprot_accession"),
         ],
         skip_on_failure=True,
     )
@@ -65,7 +65,7 @@ def get_mapping(klass):
                         "type": "keyword",
                         "normalizer": "keyword_lowercase_normalizer",
                     },
-                    "uniprot_accessions": {
+                    "uniprot_accession": {
                         "type": "keyword",
                         "normalizer": "keyword_lowercase_normalizer",
                     },