rcsb.exdb 1.33__tar.gz → 1.34__tar.gz

{rcsb_exdb-1.33 → rcsb_exdb-1.34}/HISTORY.txt

@@ -115,3 +115,4 @@
  2-Dec-2025 V1.31 Switch to 'pyproject.toml' file and update test pipelines to python 3.12
  8-Dec-2025 V1.32 Correction to pyproject.toml
  6-Jan-2026 V1.33 Updates to TreeNodeListWorker to raise errors upon failures and allow for manual specification of tree lists to load
+ 2-Feb-2026 V1.34 Handle case of missing 'rcsb_entity_source_organism.source_type' in PolymerEntityExtractor

{rcsb_exdb-1.33 → rcsb_exdb-1.34}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: rcsb.exdb
-Version: 1.33
+Version: 1.34
 Summary: RCSB Python ExDB data extraction and loading workflows
 Project-URL: Homepage, https://github.com/rcsb/py-rcsb_exdb
 Author-email: John Westbrook <john.westbrook@rcsb.org>

{rcsb_exdb-1.33 → rcsb_exdb-1.34}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "hatchling.build"
 [project]
 name = "rcsb.exdb"
 description = "RCSB Python ExDB data extraction and loading workflows"
-version = "1.33"
+version = "1.34"
 readme = "README.md"
 authors = [
     { name="John Westbrook", email="john.westbrook@rcsb.org" }

{rcsb_exdb-1.33 → rcsb_exdb-1.34}/rcsb/exdb/seq/PolymerEntityExtractor.py

@@ -9,6 +9,7 @@
 #  9-Jan-2024 dwp Turn off use of uniprot_exdb DB for enriching protein entity details file (data not used)
 # 10-Dec-2024 dwp Sort extracted polymer entity sequence data by entity ID (alphabetically), to ensure consistent
 #                 ordering between coasts (order of sequence data influences results of mmseqs2 sequence searching)
+#  2-Feb-2026 dwp Handle case of missing 'rcsb_entity_source_organism.source_type'
 #
 ##
 __docformat__ = "google en"
@@ -115,7 +116,7 @@ class PolymerEntityExtractor(object):
                             begSeqNum = 1
                             endSeqNum = seqLen
                         srcId = tD["pdbx_src_id"]
-                        srcType = tD["source_type"]
+                        srcType = tD["source_type"] if "source_type" in tD else None
                         taxId = tD["ncbi_taxonomy_id"] if "ncbi_taxonomy_id" in tD else -1
                         if srcName and taxId == -1:
                             missingSrcD.setdefault(srcName, []).append(rId)
@@ -138,7 +139,7 @@ class PolymerEntityExtractor(object):
                     pD = eD["rcsb_polymer_entity"]
                     taxCount = pD["rcsb_source_taxonomy_count"]
                 except Exception:
-                    if srcType == "synthetic":
+                    if srcType is not None and srcType == "synthetic":
                         taxCount = 0
                     else:
                         logger.warning("%s (srcName %r) no source taxonomy count type %r", rId, srcName, srcType)