rcsb.exdb 1.27__tar.gz → 1.29__tar.gz

{rcsb_exdb-1.27 → rcsb_exdb-1.29}/HISTORY.txt

@@ -108,4 +108,6 @@
                   Update CI/CD to python 3.10
 10-Dec-2024 V1.26 Update PolymerEntityExtractor to sort extracted sequence data;
                   Update Azure pipelines to run on latest macOS and ubuntu version
-23-Jan-2025 V1.27 Update TreeNodeListWorker to index 'id' field
+23-Jan-2025 V1.27 Update TreeNodeListWorker to index 'id' field
+11-Feb-2025 V1.28 Move ExDB CLI code (workflow, exec, and tests) and Dockerfile to rcsb.workflow to avoid circular imports
+ 8-Apr-2025 V1.29 Add more logging to PubChemIndexCacheProvider and increase default numProc

{rcsb_exdb-1.27/rcsb.exdb.egg-info → rcsb_exdb-1.29}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: rcsb.exdb
-Version: 1.27
+Version: 1.29
 Summary: RCSB Python ExDB data extraction and loading workflows
 Home-page: https://github.com/rcsb/py-rcsb_exdb
 Author: John Westbrook
@@ -16,25 +16,20 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: OpenEye-toolkits>=2024.1.1
 Requires-Dist: numpy
 Requires-Dist: jsonschema>=2.6.0
 Requires-Dist: rcsb.utils.io>=1.48
-Requires-Dist: rcsb.db>=1.725
-Requires-Dist: rcsb.utils.chem>=0.79
+Requires-Dist: rcsb.db>=1.800
+Requires-Dist: rcsb.utils.chem>=0.81
 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>=0.82
-Requires-Dist: rcsb.utils.seqalign>=0.31
 Requires-Dist: rcsb.utils.targets>=0.82
 Requires-Dist: rcsb.utils.struct>=0.47
 Requires-Dist: rcsb.utils.taxonomy>=0.43
 Requires-Dist: rcsb.utils.dictionary>=1.27
-Requires-Dist: rcsb.workflow>=0.46
-Requires-Dist: statistics; python_version < "3.0"
 Provides-Extra: dev
 Requires-Dist: check-manifest; extra == "dev"
 Provides-Extra: test
@@ -46,6 +41,7 @@ Dynamic: description
 Dynamic: description-content-type
 Dynamic: home-page
 Dynamic: license
+Dynamic: license-file
 Dynamic: provides-extra
 Dynamic: requires-dist
 Dynamic: summary
@@ -115,57 +111,3 @@ install this system.   Once HomeBrew is installed, you can further install the
 [MongoDB](https://docs.mongodb.com/manual/tutorial/install-mongodb-on-os-x/) packages which
 are required to support the ExDB tools.  HomeBrew also provides a variety of options for
 managing a [Python virtual environments](https://gist.github.com/Geoyi/f55ed54d24cc9ff1c14bd95fac21c042).
-
-### Command Line Interfaces
-
-A convenience CLI `exdb_exec_cli` is provided for performing update and loading operations.
-
-```bash
-exdb_exec_cli --help
-
-usage: exdb_exec_cli [-h] [--data_set_id DATA_SET_ID] [--full] [--etl_chemref]
-                     [--etl_tree_node_lists] [--config_path CONFIG_PATH]
-                     [--config_name CONFIG_NAME] [--db_type DB_TYPE]
-                     [--read_back_check] [--num_proc NUM_PROC]
-                     [--chunk_size CHUNK_SIZE]
-                     [--document_limit DOCUMENT_LIMIT] [--debug] [--mock]
-                     [--cache_path CACHE_PATH] [--rebuild_cache]
-
-optional arguments:
-  -h, --help            show this help message and exit
-  --data_set_id DATA_SET_ID
-                        Data set identifier (default= 2019_14 for current
-                        week)
-  --full                Fresh full load in a new tables/collections (Default)
-  --etl_chemref         ETL integrated chemical reference data
-  --etl_tree_node_lists
-                        ETL tree node lists
-  --config_path CONFIG_PATH
-                        Path to configuration options file
-  --config_name CONFIG_NAME
-                        Configuration section name
-  --db_type DB_TYPE     Database server type (default=mongo)
-  --read_back_check     Perform read back check on all documents
-  --num_proc NUM_PROC   Number of processes to execute (default=2)
-  --chunk_size CHUNK_SIZE
-                        Number of files loaded per process
-  --document_limit DOCUMENT_LIMIT
-                        Load document limit for testing
-  --debug               Turn on verbose logging
-  --mock                Use MOCK repository configuration for testing
-  --cache_path CACHE_PATH
-                        Top cache path for external and local resource files
-  --rebuild_cache       Rebuild cached files from remote resources
-________________________________________________________________________________
-
-```
-
-For example, to construct and load tree nodes list data collections, the following
-command may be used:
-
-```bash
-exdb_exec_cli --mock --full --etl_tree_node_lists --rebuild_cache \
-              --cache_path ./CACHE  \
-              --config_path ./rcsb/mock-data/config/dbload-setup-example.yml \
-              --config_name site_info_configuration >& LOGTREE \
-```

{rcsb_exdb-1.27 → rcsb_exdb-1.29}/README.md

@@ -63,57 +63,3 @@ install this system.   Once HomeBrew is installed, you can further install the
 [MongoDB](https://docs.mongodb.com/manual/tutorial/install-mongodb-on-os-x/) packages which
 are required to support the ExDB tools.  HomeBrew also provides a variety of options for
 managing a [Python virtual environments](https://gist.github.com/Geoyi/f55ed54d24cc9ff1c14bd95fac21c042).
-
-### Command Line Interfaces
-
-A convenience CLI `exdb_exec_cli` is provided for performing update and loading operations.
-
-```bash
-exdb_exec_cli --help
-
-usage: exdb_exec_cli [-h] [--data_set_id DATA_SET_ID] [--full] [--etl_chemref]
-                     [--etl_tree_node_lists] [--config_path CONFIG_PATH]
-                     [--config_name CONFIG_NAME] [--db_type DB_TYPE]
-                     [--read_back_check] [--num_proc NUM_PROC]
-                     [--chunk_size CHUNK_SIZE]
-                     [--document_limit DOCUMENT_LIMIT] [--debug] [--mock]
-                     [--cache_path CACHE_PATH] [--rebuild_cache]
-
-optional arguments:
-  -h, --help            show this help message and exit
-  --data_set_id DATA_SET_ID
-                        Data set identifier (default= 2019_14 for current
-                        week)
-  --full                Fresh full load in a new tables/collections (Default)
-  --etl_chemref         ETL integrated chemical reference data
-  --etl_tree_node_lists
-                        ETL tree node lists
-  --config_path CONFIG_PATH
-                        Path to configuration options file
-  --config_name CONFIG_NAME
-                        Configuration section name
-  --db_type DB_TYPE     Database server type (default=mongo)
-  --read_back_check     Perform read back check on all documents
-  --num_proc NUM_PROC   Number of processes to execute (default=2)
-  --chunk_size CHUNK_SIZE
-                        Number of files loaded per process
-  --document_limit DOCUMENT_LIMIT
-                        Load document limit for testing
-  --debug               Turn on verbose logging
-  --mock                Use MOCK repository configuration for testing
-  --cache_path CACHE_PATH
-                        Top cache path for external and local resource files
-  --rebuild_cache       Rebuild cached files from remote resources
-________________________________________________________________________________
-
-```
-
-For example, to construct and load tree nodes list data collections, the following
-command may be used:
-
-```bash
-exdb_exec_cli --mock --full --etl_tree_node_lists --rebuild_cache \
-              --cache_path ./CACHE  \
-              --config_path ./rcsb/mock-data/config/dbload-setup-example.yml \
-              --config_name site_info_configuration >& LOGTREE \
-```

{rcsb_exdb-1.27 → rcsb_exdb-1.29}/rcsb/exdb/chemref/PubChemIndexCacheProvider.py

@@ -9,6 +9,7 @@
 # 16-Jul-2020 jdw separate index and reference data management.
 # 23-Jul-2021 jdw Make PubChemIndexCacheProvider a subclass of StashableBase()
 #  2-Mar-2023 aae Return correct status from Single proc
+#  8-Apr-2025 dwp Let MultiProc handle chunking; add more logging to debug slowness on west coast
 #
 ##
 __docformat__ = "google en"
@@ -100,84 +101,82 @@ class PubChemUpdateWorker(object):
            #
         """
         _ = workingDir
-        chunkSize = optionsD.get("chunkSize", 50)
         matchIdOnly = optionsD.get("matchIdOnly", True)
         # Path to store raw request data -
         exportPath = optionsD.get("exportPath", None)
         #
         successList = []
-        retList1 = []
-        retList2 = []
         diagList = []
-        emptyList = []
+        failList = []
+        retList = []
         #
         try:
+            startTime = time.time()
             tU = TimeUtil()
-            ccIdList = dataList
-            numChunks = len(list(self.__chunker(ccIdList, chunkSize)))
-            logger.info("%s search starting for %d reference definitions (in chunks of length %d)", procName, len(ccIdList), chunkSize)
-            for ii, ccIdChunk in enumerate(self.__chunker(ccIdList, chunkSize), 1):
-                logger.info("%s starting chunk for %d of %d", procName, ii, numChunks)
-                # tDL = []
-                tIdxDL = []
-                timeS = tU.getDateTimeObj(tU.getTimestamp())
-                for ccId in ccIdChunk:
-                    # Get various forms from the search index -
-                    chemIdList = self.__genChemIdList(ccId)
-                    tIdxD = {"rcsb_id": ccId, "rcsb_last_update": timeS}
+            ccIdList = dataList  # len(dataList) should be of size chunkSize
+            logger.info("%s search starting for %d reference definitions (matchIdOnly %r exportPath %r)", procName, len(ccIdList), matchIdOnly, exportPath)
+            tIdxDL = []
+            timeS = tU.getDateTimeObj(tU.getTimestamp())
+            for ccId in ccIdList:
+                # Get various forms from the search index -
+                chemIdList = self.__genChemIdList(ccId)
+                tIdxD = {"rcsb_id": ccId, "rcsb_last_update": timeS}
+                #
+                mL = []
+                for chemId in chemIdList:
+                    stA = time.time()
+                    ok, refDL = self.__pcU.assemble(chemId, exportPath=exportPath, matchIdOnly=matchIdOnly)
                     #
-                    mL = []
-                    for chemId in chemIdList:
-                        stA = time.time()
-                        ok, refDL = self.__pcU.assemble(chemId, exportPath=exportPath, matchIdOnly=matchIdOnly)
-                        #
-                        if not ok:
-                            etA = time.time()
-                            logger.debug("Failing %s search source %s for %s (%.4f secs)", chemId.identifierType, chemId.identifierSource, chemId.idCode, etA - stA)
-
-                        #
-                        if ok and refDL:
-                            for tD in refDL:
-                                pcId = tD["cid"]
-                                inchiKey = (
-                                    self.__searchIdxD[chemId.indexName]["inchi-key"]
-                                    if chemId.indexName in self.__searchIdxD and "inchi-key" in self.__searchIdxD[chemId.indexName]
-                                    else None
-                                )
-                                smiles = (
-                                    self.__searchIdxD[chemId.indexName]["smiles"] if chemId.indexName in self.__searchIdxD and "smiles" in self.__searchIdxD[chemId.indexName] else None
-                                )
-                                mL.append(
-                                    {
-                                        "matched_id": pcId,
-                                        "search_id_type": chemId.identifierType,
-                                        "search_id_source": chemId.identifierSource,
-                                        "source_index_name": chemId.indexName,
-                                        "source_smiles": smiles,
-                                        "source_inchikey": inchiKey,
-                                    }
-                                )
-                                # tD.update({"rcsb_id": pcId, "rcsb_last_update": timeS})
-                                # tDL.append(tD)
+                    if not ok:
+                        etA = time.time()
+                        logger.debug("Failing %s search source %s for %s (%.4f secs)", chemId.identifierType, chemId.identifierSource, chemId.idCode, etA - stA)
                     #
-                    if mL:
-                        tIdxD["matched_ids"] = mL
-                        successList.append(ccId)
-                    else:
-                        logger.info("No match result for any form of %s", ccId)
-                    #
-                    tIdxDL.append(tIdxD)
-                # --
-                startTimeL = time.time()
-                logger.info("Saving chunk %d (len=%d)", ii, len(ccIdChunk))
-                self.__updateObjectStore(self.__databaseName, self.__matchIndexCollectionName, tIdxDL)
-                endTimeL = time.time()
-                logger.info("Saved chunk %d (len=%d) in %.3f secs", ii, len(ccIdChunk), endTimeL - startTimeL)
+                    if ok and refDL:
+                        for tD in refDL:
+                            pcId = tD["cid"]
+                            inchiKey = (
+                                self.__searchIdxD[chemId.indexName]["inchi-key"]
+                                if chemId.indexName in self.__searchIdxD and "inchi-key" in self.__searchIdxD[chemId.indexName]
+                                else None
+                            )
+                            smiles = (
+                                self.__searchIdxD[chemId.indexName]["smiles"] if chemId.indexName in self.__searchIdxD and "smiles" in self.__searchIdxD[chemId.indexName] else None
+                            )
+                            mL.append(
+                                {
+                                    "matched_id": pcId,
+                                    "search_id_type": chemId.identifierType,
+                                    "search_id_source": chemId.identifierSource,
+                                    "source_index_name": chemId.indexName,
+                                    "source_smiles": smiles,
+                                    "source_inchikey": inchiKey,
+                                }
+                            )
+                #
+                if mL:
+                    tIdxD["matched_ids"] = mL
+                    successList.append(ccId)
+                else:
+                    logger.info("No match result for any form of %s", ccId)
+                #
+                tIdxDL.append(tIdxD)
+            # --
+            failList = sorted(set(dataList) - set(successList))
+            if failList:
+                logger.info("%s returns %d definitions with failures: %r", procName, len(failList), failList)
+            # --
+            endTime = time.time()
+            logger.info("%s completed updateList len %r duration %.3f secs", procName, len(ccIdList), endTime - startTime)
+            startTimeL = time.time()
+            logger.info("Saving dataList (len=%d)", len(ccIdList))
+            self.__updateObjectStore(self.__databaseName, self.__matchIndexCollectionName, tIdxDL)
+            endTimeL = time.time()
+            logger.info("Saved chunk (len=%d) in %.3f secs", len(ccIdList), endTimeL - startTimeL)
         except Exception as e:
             logger.exception("Failing %s for %d data items %s", procName, len(dataList), str(e))
-        logger.info("%s dataList length %d success length %d rst1 %d rst2 %d", procName, len(dataList), len(successList), len(retList1), len(retList2))
+        logger.info("%s dataList length %d success length %d retList %d", procName, len(dataList), len(successList), len(retList))
         #
-        return successList, emptyList, emptyList, diagList
+        return successList, retList, diagList
 
     def __updateObjectStore(self, databaseName, collectionName, objDL):
         updateDL = []
@@ -196,10 +195,6 @@ class PubChemUpdateWorker(object):
         ok = obUpd.createCollection(databaseName, collectionName, indexAttributeNames=indexAttributeNames, checkExists=True, bsonSchema=None)
         return ok
 
-    def __chunker(self, iList, chunkSize):
-        chunkSize = max(1, chunkSize)
-        return (iList[i: i + chunkSize] for i in range(0, len(iList), chunkSize))
-
 
 class PubChemIndexCacheProvider(StashableBase):
     """Utilities to manage chemical component/BIRD to PubChem compound identifier mapping data."""
@@ -515,7 +510,7 @@ class PubChemIndexCacheProvider(StashableBase):
         Returns:
             (bool, list): status flag, list of unmatched identifiers
         """
-        chunkSize = 50
+        chunkSize = 10
         exportPath = kwargs.get("exportPath", None)
         logger.info("Length starting list is %d", len(idList))
         optD = {"chunkSize": chunkSize, "exportPath": exportPath, "matchIdOnly": True}
@@ -524,14 +519,20 @@ class PubChemIndexCacheProvider(StashableBase):
             mpu = MultiProcUtil(verbose=True)
             mpu.setOptions(optD)
             mpu.set(workerObj=rWorker, workerMethod="updateList")
-            ok, failList, resultList, _ = mpu.runMulti(dataList=idList, numProc=numProc, numResults=2, chunkSize=chunkSize)
-            logger.info("Multi-proc %r failures %r result lengths %r %r", ok, len(failList), len(resultList[0]), len(resultList[1]))
+            ok, failList, resultList, _ = mpu.runMulti(dataList=idList, numProc=numProc, numResults=1, chunkSize=chunkSize)
+            logger.info("Multi-proc %r failures %r result lengths %r", ok, len(failList), len(resultList[0]))
         else:
-            successList, _, _, _ = rWorker.updateList(idList, "SingleProc", optD, self.__dirPath)
+            successList, _, _ = rWorker.updateList(idList, "SingleProc", optD, self.__dirPath)
             failList = list(set(idList) - set(successList))
             ok = len(failList) == 0
             logger.info("Single-proc status %r failures %r", ok, len(failList))
         #
+        if len(failList) > 0:
+            if len(failList) <= 100:
+                logger.info("failList: %r", failList)
+            else:
+                logger.info("failList[:100]: %r", failList[:100])
+        #
         return ok, failList
 
     def __reloadDump(self, objD, databaseName, collectionName, indexAttributeNames=None):

{rcsb_exdb-1.27 → rcsb_exdb-1.29}/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__ = "1.27"
+__version__ = "1.29"

{rcsb_exdb-1.27 → rcsb_exdb-1.29}/rcsb/exdb/wf/PubChemEtlWorkflow.py

@@ -165,7 +165,7 @@ class PubChemEtlWorkflow(object):
             birdUrlTarget = kwargs.get("birdUrlTarget", None)
             ccFileNamePrefix = kwargs.get("ccFileNamePrefix", "cc-full")
             numProcChemComp = kwargs.get("numProcChemComp", 8)
-            numProc = kwargs.get("numProc", 2)
+            numProc = kwargs.get("numProc", 4)
             rebuildChemIndices = kwargs.get("rebuildChemIndices", True)
             exportPath = kwargs.get("exportPath", None)
             useStash = kwargs.get("useStash", True)
@@ -209,7 +209,7 @@ class PubChemEtlWorkflow(object):
         try:
             ok1 = ok2 = ok3 = ok4 = ok5 = ok6 = False
             #  --
-            numProc = kwargs.get("numProc", 2)
+            numProc = kwargs.get("numProc", 4)
             useStash = kwargs.get("useStash", True)
             useGit = kwargs.get("useGit", False)
             #

{rcsb_exdb-1.27 → rcsb_exdb-1.29/rcsb.exdb.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: rcsb.exdb
-Version: 1.27
+Version: 1.29
 Summary: RCSB Python ExDB data extraction and loading workflows
 Home-page: https://github.com/rcsb/py-rcsb_exdb
 Author: John Westbrook
@@ -16,25 +16,20 @@ Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: OpenEye-toolkits>=2024.1.1
 Requires-Dist: numpy
 Requires-Dist: jsonschema>=2.6.0
 Requires-Dist: rcsb.utils.io>=1.48
-Requires-Dist: rcsb.db>=1.725
-Requires-Dist: rcsb.utils.chem>=0.79
+Requires-Dist: rcsb.db>=1.800
+Requires-Dist: rcsb.utils.chem>=0.81
 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>=0.82
-Requires-Dist: rcsb.utils.seqalign>=0.31
 Requires-Dist: rcsb.utils.targets>=0.82
 Requires-Dist: rcsb.utils.struct>=0.47
 Requires-Dist: rcsb.utils.taxonomy>=0.43
 Requires-Dist: rcsb.utils.dictionary>=1.27
-Requires-Dist: rcsb.workflow>=0.46
-Requires-Dist: statistics; python_version < "3.0"
 Provides-Extra: dev
 Requires-Dist: check-manifest; extra == "dev"
 Provides-Extra: test
@@ -46,6 +41,7 @@ Dynamic: description
 Dynamic: description-content-type
 Dynamic: home-page
 Dynamic: license
+Dynamic: license-file
 Dynamic: provides-extra
 Dynamic: requires-dist
 Dynamic: summary
@@ -115,57 +111,3 @@ install this system.   Once HomeBrew is installed, you can further install the
 [MongoDB](https://docs.mongodb.com/manual/tutorial/install-mongodb-on-os-x/) packages which
 are required to support the ExDB tools.  HomeBrew also provides a variety of options for
 managing a [Python virtual environments](https://gist.github.com/Geoyi/f55ed54d24cc9ff1c14bd95fac21c042).
-
-### Command Line Interfaces
-
-A convenience CLI `exdb_exec_cli` is provided for performing update and loading operations.
-
-```bash
-exdb_exec_cli --help
-
-usage: exdb_exec_cli [-h] [--data_set_id DATA_SET_ID] [--full] [--etl_chemref]
-                     [--etl_tree_node_lists] [--config_path CONFIG_PATH]
-                     [--config_name CONFIG_NAME] [--db_type DB_TYPE]
-                     [--read_back_check] [--num_proc NUM_PROC]
-                     [--chunk_size CHUNK_SIZE]
-                     [--document_limit DOCUMENT_LIMIT] [--debug] [--mock]
-                     [--cache_path CACHE_PATH] [--rebuild_cache]
-
-optional arguments:
-  -h, --help            show this help message and exit
-  --data_set_id DATA_SET_ID
-                        Data set identifier (default= 2019_14 for current
-                        week)
-  --full                Fresh full load in a new tables/collections (Default)
-  --etl_chemref         ETL integrated chemical reference data
-  --etl_tree_node_lists
-                        ETL tree node lists
-  --config_path CONFIG_PATH
-                        Path to configuration options file
-  --config_name CONFIG_NAME
-                        Configuration section name
-  --db_type DB_TYPE     Database server type (default=mongo)
-  --read_back_check     Perform read back check on all documents
-  --num_proc NUM_PROC   Number of processes to execute (default=2)
-  --chunk_size CHUNK_SIZE
-                        Number of files loaded per process
-  --document_limit DOCUMENT_LIMIT
-                        Load document limit for testing
-  --debug               Turn on verbose logging
-  --mock                Use MOCK repository configuration for testing
-  --cache_path CACHE_PATH
-                        Top cache path for external and local resource files
-  --rebuild_cache       Rebuild cached files from remote resources
-________________________________________________________________________________
-
-```
-
-For example, to construct and load tree nodes list data collections, the following
-command may be used:
-
-```bash
-exdb_exec_cli --mock --full --etl_tree_node_lists --rebuild_cache \
-              --cache_path ./CACHE  \
-              --config_path ./rcsb/mock-data/config/dbload-setup-example.yml \
-              --config_name site_info_configuration >& LOGTREE \
-```

{rcsb_exdb-1.27 → rcsb_exdb-1.29}/rcsb.exdb.egg-info/SOURCES.txt

@@ -9,7 +9,6 @@ rcsb/__init__.py
 rcsb.exdb.egg-info/PKG-INFO
 rcsb.exdb.egg-info/SOURCES.txt
 rcsb.exdb.egg-info/dependency_links.txt
-rcsb.exdb.egg-info/entry_points.txt
 rcsb.exdb.egg-info/not-zip-safe
 rcsb.exdb.egg-info/requires.txt
 rcsb.exdb.egg-info/top_level.txt
@@ -29,7 +28,6 @@ rcsb/exdb/citation/CitationAdapter.py
 rcsb/exdb/citation/CitationExtractor.py
 rcsb/exdb/citation/CitationUtils.py
 rcsb/exdb/citation/__init__.py
-rcsb/exdb/cli/ExDbExec.py
 rcsb/exdb/cli/__init__.py
 rcsb/exdb/entry/EntryInfoProvider.py
 rcsb/exdb/entry/__init__.py
@@ -58,7 +56,6 @@ rcsb/exdb/tests/testCitationExtractor.py
 rcsb/exdb/tests/testCitationUtils.py
 rcsb/exdb/tests/testEntryInfoEtlWorkflow.py
 rcsb/exdb/tests/testEntryInfoProvider.py
-rcsb/exdb/tests/testExDbWorkflow.py
 rcsb/exdb/tests/testGlycanEtlWorkflow.py
 rcsb/exdb/tests/testGlycanProvider.py
 rcsb/exdb/tests/testGlycanUtils.py
@@ -89,7 +86,6 @@ rcsb/exdb/utils/ObjectUpdater.py
 rcsb/exdb/utils/ObjectValidator.py
 rcsb/exdb/utils/__init__.py
 rcsb/exdb/wf/EntryInfoEtlWorkflow.py
-rcsb/exdb/wf/ExDbWorkflow.py
 rcsb/exdb/wf/GlycanEtlWorkflow.py
 rcsb/exdb/wf/PubChemEtlWorkflow.py
 rcsb/exdb/wf/__init__.py

{rcsb_exdb-1.27 → rcsb_exdb-1.29}/rcsb.exdb.egg-info/requires.txt

@@ -1,24 +1,17 @@
-OpenEye-toolkits>=2024.1.1
 numpy
 jsonschema>=2.6.0
 rcsb.utils.io>=1.48
-rcsb.db>=1.725
-rcsb.utils.chem>=0.79
+rcsb.db>=1.800
+rcsb.utils.chem>=0.81
 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>=0.82
-rcsb.utils.seqalign>=0.31
 rcsb.utils.targets>=0.82
 rcsb.utils.struct>=0.47
 rcsb.utils.taxonomy>=0.43
 rcsb.utils.dictionary>=1.27
-rcsb.workflow>=0.46
-
-[:python_version < "3.0"]
-statistics
 
 [dev]
 check-manifest

{rcsb_exdb-1.27 → rcsb_exdb-1.29}/requirements.txt

@@ -1,20 +1,17 @@
 --extra-index-url https://pypi.anaconda.org/OpenEye/simple
-OpenEye-toolkits >= 2024.1.1
+# Above line may be needed despite the OpenEye package not being a direct requirement of this package (it's used by rcsb.utils.chem)
+# OpenEye-toolkits >= 2024.1.1
 numpy
 jsonschema >= 2.6.0
 rcsb.utils.io >= 1.48
-rcsb.db >= 1.725
-rcsb.utils.chem >= 0.79
+rcsb.db >= 1.800
+rcsb.utils.chem >= 0.81
 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 >= 0.82
-rcsb.utils.seqalign >= 0.31
 rcsb.utils.targets >= 0.82
 rcsb.utils.struct >= 0.47
 rcsb.utils.taxonomy >= 0.43
 rcsb.utils.dictionary >= 1.27
-rcsb.workflow >= 0.46
-statistics; python_version < "3.0"

{rcsb_exdb-1.27 → rcsb_exdb-1.29}/setup.py

@@ -47,7 +47,6 @@ setup(
         "Programming Language :: Python :: 3.9",
         "Programming Language :: Python :: 3.10",
     ],
-    entry_points={"console_scripts": ["exdb_exec_cli=rcsb.exdb.cli.ExDbExec:main"]},
     #
     install_requires=packagesRequired[1:],
     packages=find_packages(exclude=["rcsb.mock-data", "rcsb.exdb.tests-anal", "rcsb.exdb.tests-*", "tests.*"]),
@@ -57,7 +56,7 @@ setup(
     },
     #
     test_suite="rcsb.exdb.tests",
-    tests_require=["tox"],
+    tests_require=["tox", "rcsb.utils.citation >= 0.22"],
     #
     # Not configured ...
     extras_require={"dev": ["check-manifest"], "test": ["coverage"]},