rcsb.exdb 1.29__tar.gz → 1.31__tar.gz

rcsb_exdb-1.31/.gitignore

@@ -0,0 +1,112 @@
+.vscode
+test-output/
+!test-output/.gitkeep
+test-cache-preserve/
+LOGTOX
+CACHE/
+Archive/
+.idea/
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+.hypothesis/
+.pytest_cache/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# pyenv
+.python-version
+
+# celery beat schedule file
+celerybeat-schedule
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/

{rcsb_exdb-1.29 → rcsb_exdb-1.31}/HISTORY.txt

@@ -111,3 +111,5 @@
 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
+ 2-Oct-2025 V1.30 Make use of ExDB configuration file for loading drugbank and tree node list DBs/collections and setting indexed fields
+ 2-Dec-2025 V1.31 Switch to 'pyproject.toml' file and update test pipelines to python 3.12

{rcsb_exdb-1.29/rcsb.exdb.egg-info → rcsb_exdb-1.31}/PKG-INFO

@@ -1,50 +1,43 @@
 Metadata-Version: 2.4
 Name: rcsb.exdb
-Version: 1.29
+Version: 1.31
 Summary: RCSB Python ExDB data extraction and loading workflows
-Home-page: https://github.com/rcsb/py-rcsb_exdb
-Author: John Westbrook
-Author-email: john.westbrook@rcsb.org
-License: Apache 2.0
-Classifier: Development Status :: 3 - Alpha
+Project-URL: Homepage, https://github.com/rcsb/py-rcsb_exdb
+Author-email: John Westbrook <john.westbrook@rcsb.org>
+Maintainer-email: Dennis Piehl <dennis.piehl@rcsb.org>
+License-Expression: Apache-2.0
+License-File: LICENSE
+Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Developers
 Classifier: Natural Language :: English
-Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: numpy
+Classifier: Programming Language :: Python :: 3.12
+Requires-Python: >=3.9
 Requires-Dist: jsonschema>=2.6.0
-Requires-Dist: rcsb.utils.io>=1.48
-Requires-Dist: rcsb.db>=1.800
-Requires-Dist: rcsb.utils.chem>=0.81
-Requires-Dist: rcsb.utils.chemref>=0.91
-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.targets>=0.82
-Requires-Dist: rcsb.utils.struct>=0.47
-Requires-Dist: rcsb.utils.taxonomy>=0.43
-Requires-Dist: rcsb.utils.dictionary>=1.27
-Provides-Extra: dev
-Requires-Dist: check-manifest; extra == "dev"
-Provides-Extra: test
-Requires-Dist: coverage; extra == "test"
-Dynamic: author
-Dynamic: author-email
-Dynamic: classifier
-Dynamic: description
-Dynamic: description-content-type
-Dynamic: home-page
-Dynamic: license
-Dynamic: license-file
-Dynamic: provides-extra
-Dynamic: requires-dist
-Dynamic: summary
+Requires-Dist: numpy
+Requires-Dist: openeye-toolkits>=2024.1.1
+Requires-Dist: rcsb-db>=1.808
+Requires-Dist: rcsb-utils-chem>=0.84
+Requires-Dist: rcsb-utils-chemref>=0.91
+Requires-Dist: rcsb-utils-config>=0.40
+Requires-Dist: rcsb-utils-dictionary>=1.27
+Requires-Dist: rcsb-utils-ec>=0.25
+Requires-Dist: rcsb-utils-go>=0.18
+Requires-Dist: rcsb-utils-io>=1.48
+Requires-Dist: rcsb-utils-seq>=0.82
+Requires-Dist: rcsb-utils-struct>=0.47
+Requires-Dist: rcsb-utils-targets>=0.82
+Requires-Dist: rcsb-utils-taxonomy>=0.43
+Provides-Extra: tests
+Requires-Dist: black>=21.5b1; extra == 'tests'
+Requires-Dist: check-manifest; extra == 'tests'
+Requires-Dist: coverage; extra == 'tests'
+Requires-Dist: flake8; extra == 'tests'
+Requires-Dist: pylint; extra == 'tests'
+Requires-Dist: rcsb-utils-citation>=0.25; extra == 'tests'
+Requires-Dist: tox; extra == 'tests'
+Description-Content-Type: text/markdown
 
 # py-rcsb_exdb
 
@@ -68,14 +61,9 @@ git clone --recurse-submodules https://github.com/rcsb/py-rcsb_exdb.git
 ```
 
 Optionally, run test suite (Python versions 2.7 and 3.7) using
-[setuptools](https://setuptools.readthedocs.io/en/latest/) or
 [tox](http://tox.readthedocs.io/en/latest/example/platform.html):
 
 ```bash
-python setup.py test
-
-or simply run
-
 tox
 ```
 
@@ -83,9 +71,11 @@ Installation is via the program [pip](https://pypi.python.org/pypi/pip).  To run
 from the source tree, the package must be installed in editable mode (i.e. -e):
 
 ```bash
-pip install -r requirements.txt   # OR:   pip install -i https://pypi.anaconda.org/OpenEye/simple OpenEye-toolkits
+pip install -e . --extra-index-url https://pypi.anaconda.org/OpenEye/simple
+
+# or using uv
 
-pip install -e .
+uv pip install -e .
 ```
 
 #### Installing in Ubuntu Linux (tested in 18.04)

{rcsb_exdb-1.29 → rcsb_exdb-1.31}/README.md

@@ -20,14 +20,9 @@ git clone --recurse-submodules https://github.com/rcsb/py-rcsb_exdb.git
 ```
 
 Optionally, run test suite (Python versions 2.7 and 3.7) using
-[setuptools](https://setuptools.readthedocs.io/en/latest/) or
 [tox](http://tox.readthedocs.io/en/latest/example/platform.html):
 
 ```bash
-python setup.py test
-
-or simply run
-
 tox
 ```
 
@@ -35,9 +30,11 @@ Installation is via the program [pip](https://pypi.python.org/pypi/pip).  To run
 from the source tree, the package must be installed in editable mode (i.e. -e):
 
 ```bash
-pip install -r requirements.txt   # OR:   pip install -i https://pypi.anaconda.org/OpenEye/simple OpenEye-toolkits
+pip install -e . --extra-index-url https://pypi.anaconda.org/OpenEye/simple
+
+# or using uv
 
-pip install -e .
+uv pip install -e .
 ```
 
 #### Installing in Ubuntu Linux (tested in 18.04)

rcsb_exdb-1.31/pyproject.toml

@@ -0,0 +1,95 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "rcsb.exdb"
+description = "RCSB Python ExDB data extraction and loading workflows"
+version = "1.31"
+readme = "README.md"
+authors = [
+    { name="John Westbrook", email="john.westbrook@rcsb.org" }
+]
+maintainers = [
+    { name="Dennis Piehl", email="dennis.piehl@rcsb.org" }
+]
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+requires-python = ">=3.9"  # Latest OpenEye (2025.1.1) only supports up to 3.12 (as of Nov. 2025)
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Developers",
+    "Natural Language :: English",
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.12",  # Latest OpenEye (2025.1.1) only supports up to 3.12 (as of Nov. 2025)
+]
+
+dependencies = [
+    # OpenEye is needed here despite it 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 >= 1.808",
+    "rcsb.utils.chem >= 0.84",
+    "rcsb.utils.chemref >= 0.91",
+    "rcsb.utils.config >= 0.40",
+    "rcsb.utils.ec >= 0.25",
+    "rcsb.utils.go >= 0.18",
+    "rcsb.utils.seq >= 0.82",
+    "rcsb.utils.targets >= 0.82",
+    "rcsb.utils.struct >= 0.47",
+    "rcsb.utils.taxonomy >= 0.43",
+    "rcsb.utils.dictionary >= 1.27",
+]
+
+[project.optional-dependencies]
+tests = ["tox", "pylint", "black>=21.5b1", "flake8", "coverage", "rcsb.utils.citation>=0.25", "check-manifest"]
+
+[project.urls]
+Homepage = "https://github.com/rcsb/py-rcsb_exdb"
+
+# ----------------  hatch configuration ----------------
+[tool.hatch.build.targets.sdist]
+include = [
+    "/rcsb/**",
+    "/README.md",
+    "/LICENSE",
+    "/HISTORY.txt",
+    "/pyproject.toml",
+]
+exclude = [
+    "/rcsb/mock-*",
+    "/rcsb/exdb/test*/test*-*",
+    "/rcsb/exdb/test*/**.tdd",
+    "/rcsb/exdb/test*/**.txt",
+    "/rcsb/exdb/test*/**.sh",
+]
+
+[tool.hatch.build.targets.wheel]
+packages = ["rcsb"]
+exclude = [
+    "/rcsb/db/test*",
+    "/rcsb/mock-*",
+]
+
+[tool.hatch.envs.default]
+skip-install = true
+dependencies = ["OpenEye-toolkits>=2024.1.1"]
+
+[tool.hatch.envs.default.env-vars]
+PIP_EXTRA_INDEX_URL = "https://pypi.anaconda.org/OpenEye/simple"
+
+# ----------------  test configuration ----------------
+[tool.hatch.envs.hatch-test]
+dependencies = ["tox"]
+
+[tool.hatch.envs.hatch-test.scripts]
+run = ["tox"]
+
+# ----------------  UV configuration ----------------
+[tool.uv]
+extra-index-url = ["https://pypi.anaconda.org/OpenEye/simple"]
+managed = false  # This prevents uv from automatically creating venvs within individual packages when running 'uv run ...' from within the package directory

{rcsb_exdb-1.29 → rcsb_exdb-1.31}/rcsb/exdb/chemref/ChemRefEtlWorker.py

@@ -7,6 +7,8 @@
 # Updates:
 #  9-Dec-2018  jdw add validation methods
 #  3-Sep-2019  jdw move to rcsb.exdb.chemref
+#  7-Aug-2025  dwp change target DB and collection from "drugbank_core" to "dw" and "core_drugbank" (as part of transition to DW);
+#                  make use of configuration file for loading drugbank collection and setting indexed fields
 #
 ##
 __docformat__ = "google en"
@@ -66,9 +68,10 @@ class ChemRefEtlWorker(object):
             desp = DataExchangeStatus()
             statusStartTimestamp = desp.setStartTime()
             addValues = {}
+            collectionGroupName = "core_drugbank"
             #
             if extResource == "DrugBank":
-                databaseName = "drugbank_core"
+                databaseNameMongo = self.__schP.getDatabaseMongoName(collectionGroupName=collectionGroupName)
                 configName = self.__cfgOb.getDefaultSectionName()
                 user = self.__cfgOb.get("_DRUGBANK_AUTH_USERNAME", sectionName=configName)
                 pw = self.__cfgOb.get("_DRUGBANK_AUTH_PASSWORD", sectionName=configName)
@@ -81,10 +84,10 @@ class ChemRefEtlWorker(object):
                 #
                 logger.info("Resource %r extracted mapped document length %d", extResource, len(dList))
                 logger.debug("Objects %r", dList[:2])
-                sD, _, collectionList, _ = self.__schP.getSchemaInfo(databaseName)
+                _, _, collectionList, docIndexD = self.__schP.getSchemaInfo(collectionGroupName=collectionGroupName)
                 collectionName = collectionList[0] if collectionList else "unassigned"
-                indexL = sD.getDocumentIndex(collectionName, "primary")
-                logger.info("Database %r collection %r index attributes %r", databaseName, collectionName, indexL)
+                indexDL = docIndexD[collectionName] if collectionName in docIndexD else []
+                logger.info("Database %r collection %r index attributes %r", databaseNameMongo, collectionName, indexDL)
                 #
                 # 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)
@@ -103,8 +106,8 @@ class ChemRefEtlWorker(object):
                 readBackCheck=self.__readBackCheck,
             )
             #
-            ok = dl.load(databaseName, collectionName, loadType=loadType, documentList=dList, indexAttributeList=indexL, keyNames=None, addValues=addValues)
-            self.__updateStatus(updateId, databaseName, collectionName, ok, statusStartTimestamp)
+            ok = dl.load(databaseNameMongo, collectionName, loadType=loadType, documentList=dList, keyNames=None, addValues=addValues, indexDL=indexDL)
+            self.__updateStatus(updateId, databaseNameMongo, collectionName, ok, statusStartTimestamp)
 
             return True
         except Exception as e:

{rcsb_exdb-1.29 → rcsb_exdb-1.31}/rcsb/exdb/chemref/ChemRefExtractor.py

@@ -7,6 +7,7 @@
 # Updates:
 #  7-Jan-2019  jdw moved from ChemRefEtlWorker.
 #  3-Sep-2019  jdw moved again to module rcsb.exdb.chemref
+# 14-Aug-2025  dwp rename bird_chem_comp_core to core_chem_comp
 #
 ##
 __docformat__ = "google en"
@@ -42,8 +43,8 @@ class ChemRefExtractor(object):
         """
         idD = {}
         try:
-            databaseName = "bird_chem_comp_core"
-            collectionName = "bird_chem_comp_core"
+            databaseName = "dw"
+            collectionName = "core_chem_comp"
             selectD = {"rcsb_chem_comp_related.resource_name": referenceResourceName}
             selectionList = ["rcsb_id", "rcsb_chem_comp_related"]
             logger.info("Searching %s %s with selection query %r", databaseName, collectionName, selectD)