rcsb.exdb 1.2__tar.gz → 1.22__tar.gz

{rcsb_exdb-1.2 → rcsb_exdb-1.22}/HISTORY.txt

@@ -100,3 +100,5 @@
  6-May-2024 V1.1  Update ExDbExec CLI and ExDbWorkflow to support CLI usage from weekly-update workflow;
                   Update unit tests and setuptools config
  9-May-2024 V1.2  Adjust provider type exclusion input to accept a list of types
+13-May-2024 V1.21 Update requirements; fix linting
+17-Jul-2024 V1.22 Adjust LigandNeighborMappingExtractor

{rcsb_exdb-1.2/rcsb.exdb.egg-info → rcsb_exdb-1.22}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rcsb.exdb
-Version: 1.2
+Version: 1.22
 Summary: RCSB Python ExDB data extraction and loading workflows
 Home-page: https://github.com/rcsb/py-rcsb_exdb
 Author: John Westbrook
@@ -18,18 +18,18 @@ License-File: LICENSE
 Requires-Dist: OpenEye-toolkits>=2020.2.2
 Requires-Dist: numpy
 Requires-Dist: jsonschema>=2.6.0
-Requires-Dist: rcsb.utils.io>=1.28
-Requires-Dist: rcsb.db>=1.720
-Requires-Dist: rcsb.utils.chemref>=0.79
-Requires-Dist: rcsb.utils.chem>=0.75
-Requires-Dist: rcsb.utils.citation>=0.16
-Requires-Dist: rcsb.utils.config>=0.35
-Requires-Dist: rcsb.utils.ec>=0.22
-Requires-Dist: rcsb.utils.go>=0.17
-Requires-Dist: rcsb.utils.seq>=0.63
-Requires-Dist: rcsb.utils.struct>=0.37
-Requires-Dist: rcsb.utils.taxonomy>=0.39
-Requires-Dist: rcsb.utils.dictionary>=1.23
+Requires-Dist: rcsb.utils.io>=1.46
+Requires-Dist: rcsb.db>=1.721
+Requires-Dist: rcsb.utils.chem>=0.79
+Requires-Dist: rcsb.utils.chemref>=0.91
+Requires-Dist: rcsb.utils.citation>=0.22
+Requires-Dist: rcsb.utils.config>=0.40
+Requires-Dist: rcsb.utils.ec>=0.25
+Requires-Dist: rcsb.utils.go>=0.18
+Requires-Dist: rcsb.utils.seq>=0.79
+Requires-Dist: rcsb.utils.struct>=0.47
+Requires-Dist: rcsb.utils.taxonomy>=0.43
+Requires-Dist: rcsb.utils.dictionary>=1.24
 Requires-Dist: rcsb.workflow>=0.42
 Requires-Dist: statistics; python_version < "3.0"
 Provides-Extra: dev

{rcsb_exdb-1.2 → rcsb_exdb-1.22}/rcsb/exdb/chemref/ChemRefEtlWorker.py

@@ -65,6 +65,7 @@ class ChemRefEtlWorker(object):
             self.__statusList = []
             desp = DataExchangeStatus()
             statusStartTimestamp = desp.setStartTime()
+            addValues = {}
             #
             if extResource == "DrugBank":
                 databaseName = "drugbank_core"
@@ -85,10 +86,10 @@ class ChemRefEtlWorker(object):
                 indexL = sD.getDocumentIndex(collectionName, "primary")
                 logger.info("Database %r collection %r index attributes %r", databaseName, collectionName, indexL)
                 #
-                collectionVersion = sD.getCollectionVersion(collectionName)
-                addValues = {"_schema_version": collectionVersion}
-                #
-                addValues = {}
+                # For some reason, 'addValues' was being overwritten with an empty dict (https://github.com/rcsb/py-rcsb_exdb/commit/26bd79e9a2fffc97c034b4116dece9248d1c1f39)
+                # Will need to review this -- do we want to add the schema version values or not? (Also, see similar logic in UniProtCoreEtlWorker.py)
+                # collectionVersion = sD.getCollectionVersion(collectionName)
+                # addValues = {"_schema_version": collectionVersion}
             #
             dl = DocumentLoader(
                 self.__cfgOb,

{rcsb_exdb-1.2 → rcsb_exdb-1.22}/rcsb/exdb/chemref/PubChemIndexCacheProvider.py

@@ -64,6 +64,8 @@ class PubChemUpdateWorker(object):
             (list): list of ChemicalIdentifier() objects corresponding to the input chemical component.
         """
         chemIdList = []
+        idType = None
+        descr = None
         if ccId in self.__lookupD:
             for sD in self.__lookupD[ccId]:
                 if "inchi-key" in sD:

{rcsb_exdb-1.2 → rcsb_exdb-1.22}/rcsb/exdb/cli/__init__.py

@@ -2,4 +2,4 @@ __docformat__ = "google en"
 __author__ = "John Westbrook"
 __email__ = "john.westbrook@rcsb.org"
 __license__ = "Apache 2.0"
-__version__ = "1.2"
+__version__ = "1.22"

{rcsb_exdb-1.2 → rcsb_exdb-1.22}/rcsb/exdb/seq/LigandNeighborMappingExtractor.py

@@ -5,6 +5,7 @@
 # Utilities to extract ligand neighbor mapping details from the exchange collections.
 #
 # Updates:
+#  17-Jul-2024 dwp Stop fetching and including rcsb_ligand_neighbors.ligand_is_bound, since no longer populating that field
 #
 ##
 __docformat__ = "google en"
@@ -58,7 +59,6 @@ class LigandNeighborMappingExtractor(object):
                     "rcsb_polymer_entity_instance_container_identifiers.entity_id",
                     "rcsb_polymer_entity_instance_container_identifiers.asym_id",
                     "rcsb_ligand_neighbors.ligand_comp_id",
-                    "rcsb_ligand_neighbors.ligand_is_bound",
                 ],
             )
             eCount = obEx.getCount()
@@ -71,8 +71,8 @@ class LigandNeighborMappingExtractor(object):
                     entityId = peiD["rcsb_polymer_entity_instance_container_identifiers"]["entity_id"]
                     ky = entryId + "_" + entityId
                     for lnD in peiD["rcsb_ligand_neighbors"] if "rcsb_ligand_neighbors" in peiD else []:
-                        if "ligand_comp_id" in lnD and "ligand_is_bound" in lnD:
-                            rD.setdefault(ky, set()).add((lnD["ligand_comp_id"], lnD["ligand_is_bound"]))
+                        if "ligand_comp_id" in lnD:
+                            rD.setdefault(ky, set()).add(lnD["ligand_comp_id"])
                         else:
                             logger.warning("%s %s missing details lnD %r", entryId, entityId, lnD)
                 except Exception as e:

{rcsb_exdb-1.2 → rcsb_exdb-1.22}/rcsb/exdb/seq/LigandNeighborMappingProvider.py

@@ -56,7 +56,7 @@ class LigandNeighborMappingProvider(StashableBase):
             list: [chem_comp_id, ... ]
         """
         try:
-            return list(set([t[0] for t in self.__mapD["mapping"][rcsbEntityId.upper()]]))
+            return list(set([t for t in self.__mapD["mapping"][rcsbEntityId.upper()]]))
         except Exception:
             return []
 

{rcsb_exdb-1.2 → rcsb_exdb-1.22}/rcsb/exdb/seq/UniProtCoreEtlWorker.py

@@ -95,6 +95,7 @@ class UniProtCoreEtlWorker(object):
             #
             dList = indexL = []
             databaseName = collectionName = collectionVersion = None
+            addValues = {}
             #
             if extResource == "UniProt":
                 databaseName = "uniprot_core"
@@ -114,7 +115,6 @@ class UniProtCoreEtlWorker(object):
                 collectionVersion = cDL[0]["VERSION"]
                 indexL = self.__docHelper.getDocumentIndexAttributes(collectionName, "primary")
                 logger.info("Database %r collection %r version %r index attributes %r", databaseName, collectionName, collectionVersion, indexL)
-                addValues = {}
             else:
                 logger.error("Unsupported external resource %r", extResource)
             #

{rcsb_exdb-1.2 → rcsb_exdb-1.22}/rcsb/exdb/tests/testLigandNeighborMappingProvider.py

@@ -69,7 +69,9 @@ class LigandNeighborMappingProviderTests(unittest.TestCase):
             ok = crmP.testCache(minCount=2)
             self.assertTrue(ok)
             nL = crmP.getLigandNeighbors("3VFJ_2")
+            logger.info("ligand neighbor list nL %r", nL)
             self.assertGreaterEqual(len(nL), 4)
+            self.assertGreater(len(nL[0]), 1)
             #
         except Exception as e:
             logger.exception("Failing with %s", str(e))

{rcsb_exdb-1.2 → rcsb_exdb-1.22}/rcsb/exdb/tests/testObjectExtractor.py

@@ -102,7 +102,7 @@ class ObjectExtractorTests(unittest.TestCase):
         """Test case - extract entries subject to date restriction"""
         try:
             tU = TimeUtil()
-            tS = tU.getTimestamp(useUtc=True, before={"days": 365 * 5})
+            tS = tU.getTimestamp(useUtc=True, before={"days": 365 * 7})
             tD = tU.getDateTimeObj(tS)
             obEx = ObjectExtractor(
                 self.__cfgOb,

{rcsb_exdb-1.2 → rcsb_exdb-1.22}/rcsb/exdb/tests/testReferenceSequenceAnnotationAdapter.py

@@ -60,7 +60,7 @@ class ReferenceSequenceAnnotationAdapterTests(unittest.TestCase):
         endTime = time.time()
         logger.info("Completed %s at %s (%.4f seconds)", self.id(), time.strftime("%Y %m %d %H:%M:%S", time.localtime()), endTime - self.__startTime)
 
-    @unittest.skip("Disable test - no longer using in production, and fails too frequently with 'Bad xml text' when fetching from UniProt")
+    # @unittest.skip("Disable test - no longer using in production, and fails too frequently with 'Bad xml text' when fetching from UniProt")
     def testAnnotationAdapter(self):
         """Test case - create and read cache reference sequences assignments and related data."""
         try:
@@ -71,13 +71,13 @@ class ReferenceSequenceAnnotationAdapterTests(unittest.TestCase):
             rsaP = ReferenceSequenceAnnotationProvider(
                 self.__cfgOb, databaseName, collectionName, polymerType, fetchLimit=self.__fetchLimit, siftsAbbreviated="TEST", cachePath=self.__cachePath, useCache=True
             )
-            ok = rsaP.testCache()
+            ok = rsaP.testCache(minMissing=10)
             self.assertTrue(ok)
             numRef1 = rsaP.getRefDataCount()
             #
             # ---  Reload from cache ---
             rsaP = ReferenceSequenceAnnotationProvider(self.__cfgOb, databaseName, collectionName, polymerType, cachePath=self.__cachePath, useCache=True)
-            ok = rsaP.testCache()
+            ok = rsaP.testCache(minMissing=10)
             self.assertTrue(ok)
             numRef2 = rsaP.getRefDataCount()
             self.assertEqual(numRef1, numRef2)

{rcsb_exdb-1.2 → rcsb_exdb-1.22}/rcsb/exdb/utils/ObjectTransformer.py

@@ -47,6 +47,7 @@ class ObjectTransformer(object):
         docSelectList = docSelectList[:fetchLimit] if fetchLimit else docSelectList
         ok = self.__transform(databaseName, collectionName, docSelectList)
         #
+        okS = True
         if updateId:
             okS = self.__updateStatus(updateId, databaseName, collectionName, ok, statusStartTimestamp)
         return ok and okS

{rcsb_exdb-1.2 → rcsb_exdb-1.22}/rcsb/exdb/utils/ObjectValidator.py

@@ -78,6 +78,7 @@ class ObjectValidator(object):
 
         ok = self.__transform(databaseName, collectionName, docSelectList)
         #
+        okS = True
         if updateId:
             okS = self.__updateStatus(updateId, databaseName, collectionName, ok, statusStartTimestamp)
         return ok and okS

{rcsb_exdb-1.2 → rcsb_exdb-1.22/rcsb.exdb.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rcsb.exdb
-Version: 1.2
+Version: 1.22
 Summary: RCSB Python ExDB data extraction and loading workflows
 Home-page: https://github.com/rcsb/py-rcsb_exdb
 Author: John Westbrook
@@ -18,18 +18,18 @@ License-File: LICENSE
 Requires-Dist: OpenEye-toolkits>=2020.2.2
 Requires-Dist: numpy
 Requires-Dist: jsonschema>=2.6.0
-Requires-Dist: rcsb.utils.io>=1.28
-Requires-Dist: rcsb.db>=1.720
-Requires-Dist: rcsb.utils.chemref>=0.79
-Requires-Dist: rcsb.utils.chem>=0.75
-Requires-Dist: rcsb.utils.citation>=0.16
-Requires-Dist: rcsb.utils.config>=0.35
-Requires-Dist: rcsb.utils.ec>=0.22
-Requires-Dist: rcsb.utils.go>=0.17
-Requires-Dist: rcsb.utils.seq>=0.63
-Requires-Dist: rcsb.utils.struct>=0.37
-Requires-Dist: rcsb.utils.taxonomy>=0.39
-Requires-Dist: rcsb.utils.dictionary>=1.23
+Requires-Dist: rcsb.utils.io>=1.46
+Requires-Dist: rcsb.db>=1.721
+Requires-Dist: rcsb.utils.chem>=0.79
+Requires-Dist: rcsb.utils.chemref>=0.91
+Requires-Dist: rcsb.utils.citation>=0.22
+Requires-Dist: rcsb.utils.config>=0.40
+Requires-Dist: rcsb.utils.ec>=0.25
+Requires-Dist: rcsb.utils.go>=0.18
+Requires-Dist: rcsb.utils.seq>=0.79
+Requires-Dist: rcsb.utils.struct>=0.47
+Requires-Dist: rcsb.utils.taxonomy>=0.43
+Requires-Dist: rcsb.utils.dictionary>=1.24
 Requires-Dist: rcsb.workflow>=0.42
 Requires-Dist: statistics; python_version < "3.0"
 Provides-Extra: dev

rcsb_exdb-1.22/rcsb.exdb.egg-info/requires.txt

@@ -0,0 +1,25 @@
+OpenEye-toolkits>=2020.2.2
+numpy
+jsonschema>=2.6.0
+rcsb.utils.io>=1.46
+rcsb.db>=1.721
+rcsb.utils.chem>=0.79
+rcsb.utils.chemref>=0.91
+rcsb.utils.citation>=0.22
+rcsb.utils.config>=0.40
+rcsb.utils.ec>=0.25
+rcsb.utils.go>=0.18
+rcsb.utils.seq>=0.79
+rcsb.utils.struct>=0.47
+rcsb.utils.taxonomy>=0.43
+rcsb.utils.dictionary>=1.24
+rcsb.workflow>=0.42
+
+[:python_version < "3.0"]
+statistics
+
+[dev]
+check-manifest
+
+[test]
+coverage

rcsb_exdb-1.22/requirements.txt

@@ -0,0 +1,18 @@
+--extra-index-url https://pypi.anaconda.org/OpenEye/simple
+OpenEye-toolkits >= 2020.2.2
+numpy
+jsonschema >= 2.6.0
+rcsb.utils.io >= 1.46
+rcsb.db >= 1.721
+rcsb.utils.chem >= 0.79
+rcsb.utils.chemref >= 0.91
+rcsb.utils.citation >= 0.22
+rcsb.utils.config >= 0.40
+rcsb.utils.ec >= 0.25
+rcsb.utils.go >= 0.18
+rcsb.utils.seq >= 0.79
+rcsb.utils.struct >= 0.47
+rcsb.utils.taxonomy >= 0.43
+rcsb.utils.dictionary >= 1.24
+rcsb.workflow >= 0.42
+statistics; python_version < "3.0"

rcsb_exdb-1.2/rcsb.exdb.egg-info/requires.txt

@@ -1,25 +0,0 @@
-OpenEye-toolkits>=2020.2.2
-numpy
-jsonschema>=2.6.0
-rcsb.utils.io>=1.28
-rcsb.db>=1.720
-rcsb.utils.chemref>=0.79
-rcsb.utils.chem>=0.75
-rcsb.utils.citation>=0.16
-rcsb.utils.config>=0.35
-rcsb.utils.ec>=0.22
-rcsb.utils.go>=0.17
-rcsb.utils.seq>=0.63
-rcsb.utils.struct>=0.37
-rcsb.utils.taxonomy>=0.39
-rcsb.utils.dictionary>=1.23
-rcsb.workflow>=0.42
-
-[:python_version < "3.0"]
-statistics
-
-[dev]
-check-manifest
-
-[test]
-coverage

rcsb_exdb-1.2/requirements.txt

@@ -1,18 +0,0 @@
---extra-index-url https://pypi.anaconda.org/OpenEye/simple
-OpenEye-toolkits >= 2020.2.2
-numpy
-jsonschema >= 2.6.0
-rcsb.utils.io >= 1.28
-rcsb.db >= 1.720
-rcsb.utils.chemref >= 0.79
-rcsb.utils.chem >= 0.75
-rcsb.utils.citation >= 0.16
-rcsb.utils.config >= 0.35
-rcsb.utils.ec >= 0.22
-rcsb.utils.go >= 0.17
-rcsb.utils.seq >= 0.63
-rcsb.utils.struct >= 0.37
-rcsb.utils.taxonomy >= 0.39
-rcsb.utils.dictionary >= 1.23
-rcsb.workflow >= 0.42
-statistics; python_version < "3.0"