V0.96 Strip newline characters from 'chem_comp.*' data item values

HISTORY.txt

@@ -86,3 +86,5 @@
  29-Oct-2024  - V0.94 Add patch for ATC data processing to handle stringified arrays;
                       Update CI/CD (to use python 3.10)
  15-Jul-2025  - V0.95 Update base ChEMBL version to 35
+  4-Nov-2025  - V0.96 Strip newline characters from 'chem_comp.*' data item values;
+                      Switch to 'pyproject.toml' file and hatch build system, and update pipelines to Python 3.13

README.md

@@ -17,15 +17,10 @@ git clone --recurse-submodules https://github.com/rcsb/py-rcsb_utils_chemref.git
 
 ```
 
-Optionally, run test suite (Python versions 2.7, 3.6, and 3.8) using
-[setuptools](https://setuptools.readthedocs.io/en/latest/) or
+Optionally, run test suite (Python versions > 3.9) using
 [tox](http://tox.readthedocs.io/en/latest/example/platform.html):
 
 ```bash
-python setup.py test
-
-or simply run
-
 tox
 ```
 

azure-pipelines.yml

@@ -25,14 +25,18 @@ schedules:
 
 jobs:
   - template: azure-template-tox-job.yml
-    parameters: { tox: "format_pep8", python: "3.10", os: "linux" }
+    parameters: { tox: "format_pep8", python: "3.13", os: "linux" }
   - template: azure-template-tox-job.yml
-    parameters: { tox: "lint_pylint", python: "3.10", os: "linux" }
+    parameters: { tox: "lint_pylint", python: "3.13", os: "linux" }
   - template: azure-template-tox-job.yml
-    parameters: { tox: "test_coverage", python: "3.10", os: "linux" }
+    parameters: { tox: "test_coverage", python: "3.13", os: "linux" }
     #
   - template: azure-template-tox-job.yml
-    parameters: { tox: "py310", python: "3.10", os: "linux" }
+    parameters: { tox: "py313", python: "3.13", os: "linux" }
+  #
+  - template: azure-template-tox-job.yml
+    parameters: { tox: "py313", python: "3.13", os: "macos" }
+  #
   - template: azure-template-publish-job.yml
-    parameters: { tox: "py310", python: "3.10", os: "linux" }
+    parameters: { tox: "py313", python: "3.13", os: "linux" }
   #

azure-template-publish-job.yml

@@ -15,9 +15,9 @@ jobs:
 - job: ${{ format('publish_{0}_{1}', parameters.tox, parameters.os) }}
   pool:
     ${{ if eq(parameters.os, 'macos') }}:
-      vmImage: 'macOS-13'
+      vmImage: 'macOS-15'
     ${{ if eq(parameters.os, 'linux') }}:
-      vmImage: 'ubuntu-22.04'
+      vmImage: 'ubuntu-latest'
   dependsOn:
   - ${{ format('build_test_{0}_{1}', parameters.tox, parameters.os) }}
   condition: and(succeeded(), ne(variables['Build.Reason'], 'PullRequest'), eq(variables['Build.SourceBranch'], 'refs/heads/master'))
@@ -41,7 +41,7 @@ jobs:
     - script: ls -lR $(Pipeline.Workspace)/${{ format('sw_{0}_{1}', parameters.tox, parameters.os) }}
       displayName: "Listing of downloaded artifacts"
     #
-    - script: python -m pip install --upgrade pip twine setuptools wheel
+    - script: python -m pip install --upgrade pip twine wheel hatch
       displayName: 'Install packaging tools'
     #
     - task: DownloadSecureFile@1

azure-template-tox-job.yml

@@ -18,9 +18,9 @@ jobs:
     timeoutInMinutes: 0
     pool:
       ${{ if eq(parameters.os, 'macos') }}:
-        vmImage: "macOS-13"
+        vmImage: "macOS-15"
       ${{ if eq(parameters.os, 'linux') }}:
-        vmImage: "ubuntu-22.04"
+        vmImage: "ubuntu-latest"
 
     variables:
       - group: py-shared-variables
@@ -36,12 +36,13 @@ jobs:
       #
       - checkout: self
         submodules: true
+        fetchDepth: 1
       #
       - ${{ if startsWith(parameters.os, 'macos') }}:
           - bash: |
               set -e
               ls -la /Applications/Xcode*
-              sudo xcode-select --switch /Applications/Xcode_14.2.app/Contents/Developer
+              sudo xcode-select --switch /Applications/Xcode_16.app/Contents/Developer
               which g++
               c++ --version
             displayName: "setup Xcode"
@@ -58,11 +59,15 @@ jobs:
             displayName: "Check bison"
       # ----------------------------------------------
       - ${{ if startsWith(parameters.os, 'linux') }}:
+          - script: lsb_release -a
+            displayName: "Ubuntu kernal version"
           - script: which apt
             displayName: "Installing OS dependencies"
           - script: apt-cache policy | grep http | awk '{print $2 $3}' | sort -u
             displayName: "Checking for repos"
           #
+          - script: sudo apt-get update
+            displayName: "update apt"
           - script: sudo apt-get install flex
             displayName: "Install flex"
           - script: sudo apt-get install bison
@@ -123,37 +128,36 @@ jobs:
       - script: python -m pip install --upgrade pip tox
         displayName: "Install tools"
         #
-      - script: pip install -r requirements.txt
+      - script: pip install .[tests]
         displayName: "Install dependencies"
       #
+      # - task: DownloadSecureFile@1
+      #   name: oelicense
+      #   displayName: 'Download OE license file'
+      #   inputs:
+      #     secureFile: 'oe_license.txt'
+      #
       - ${{ if startsWith(parameters.tox, 'py') }}:
           - script: |
               export CONFIG_SUPPORT_TOKEN_ENV=$(VAR_CONFIG_SUPPORT_TOKEN_ENV)
               ${{ format('python -m tox -e {0}', parameters.tox) }}
             displayName: "Running tox task"
-      - ? ${{ if and(not(startsWith(parameters.tox, 'py')), startsWith(parameters.python, '3.10')) }}
-        : - script: |
-              export CONFIG_SUPPORT_TOKEN_ENV=$(VAR_CONFIG_SUPPORT_TOKEN_ENV)
-              ${{ format('python -m tox -e {0}-py310', parameters.tox) }}
-            displayName: "Running tox task"
-      - ? ${{ if and(not(startsWith(parameters.tox, 'py')), startsWith(parameters.python, '3.9')) }}
+      - ? ${{ if and(not(startsWith(parameters.tox, 'py')), startsWith(parameters.python, '3.13')) }}
         : - script: |
               export CONFIG_SUPPORT_TOKEN_ENV=$(VAR_CONFIG_SUPPORT_TOKEN_ENV)
-              ${{ format('python -m tox -e {0}-py39', parameters.tox) }}
+              ${{ format('python -m tox -e {0}-py313', parameters.tox) }}
             displayName: "Running tox task"
       #
       #  Build artifacts if this is a test target (i.e. labeled as py##)
       #
       - ${{ if startsWith(parameters.tox, 'py') }}:
-          - script: pip install --upgrade pip twine setuptools wheel
+          - script: pip install --upgrade pip build twine hatch
             displayName: "Acquire build tools"
-          - script: python setup.py  sdist --dist-dir "$(System.DefaultWorkingDirectory)/dist"
-            displayName: "Build source dist"
-          - script: python setup.py  bdist_wheel --dist-dir "$(System.DefaultWorkingDirectory)/dist"
-            displayName: "Build wheel"
-          #
-          - script: python setup.py  sdist --dist-dir "$(System.DefaultWorkingDirectory)/udist"
-            displayName: "Build source dist"
+          - script: python -m build --sdist --wheel --outdir "$(System.DefaultWorkingDirectory)/dist"
+            displayName: "Build source and wheel distributions"
+          - script: python -m build --sdist --outdir "$(System.DefaultWorkingDirectory)/udist"
+            displayName: "Build source distribution to udist"
+
           #
           # Check the install artifacts
           - script: ls -lR "$(System.DefaultWorkingDirectory)/dist" "$(System.DefaultWorkingDirectory)/udist"

pyproject.toml

@@ -0,0 +1,78 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "rcsb.utils.chemref"
+description = "RCSB Python Chemical Reference Data Utility Classes"
+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"
+classifiers = [
+    "Development Status :: 5 - Production/Stable",
+    "Intended Audience :: Developers",
+    "Natural Language :: English",
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.13",
+]
+dependencies = [
+    "mmcif >= 0.69",
+    "rcsb.utils.io >= 1.12",
+    "rcsb.utils.config >= 0.35",
+    "obonet >= 0.2.5",
+    "networkx >= 2.4",
+    "chembl-webresource-client >= 0.10.2",
+]
+dynamic = ["version"]
+
+[project.optional-dependencies]
+tests = ["tox", "pylint", "black>=21.5b1", "flake8", "coverage"]
+
+[project.urls]
+Homepage = "https://github.com/rcsb/py-rcsb_utils_chemref"
+
+# ----------------  hatch configuration ----------------
+[tool.hatch.version]
+path = "rcsb/utils/chemref/__init__.py"
+
+[tool.hatch.build]
+exclude = [
+    "/rcsb/utils/test*/**",
+    "/rcsb/mock-*/**",
+    "test*/**"
+]
+
+[tool.hatch.build.targets.sdist]
+include = [
+    "/rcsb/**",
+    "/README.md",
+    "/LICENSE",
+    "/HISTORY.txt",
+    "/pyproject.toml"
+]
+
+[tool.hatch.build.targets.wheel]
+packages = ["rcsb"]
+
+[tool.hatch.envs.default]
+skip-install = true
+
+# ----------------  test configuration ----------------
+[tool.hatch.envs.hatch-test]
+dependencies = ["tox"]
+
+[tool.hatch.envs.hatch-test.scripts]
+run = ["tox"]
+
+# ----------------  UV configuration ----------------
+# Add this to prevent uv from automatically creating venvs within individual packages when running 'uv run ...' from within the package directory
+[tool.uv]
+managed = false

rcsb/utils/chemref/ChEMBLProvider.py

@@ -216,7 +216,7 @@ def getUniChemData(self, inchiKeyList):
             14: {
                 "name": "fdasrs",
                 "baseUrl": "http://fdasis.nlm.nih.gov/srs/srs.jsp",
-                "entryUrl": "http://fdasis.nlm.nih.gov/srs/ProxyServlet?mergeData=true&objectHandle=DBMaint&APPLICATION_NAME=fdasrs&actionHandle=default&nextPage=jsp/srs/ResultScreen.jsp&TXTSUPERLISTID=",
+                "entryUrl": "http://fdasis.nlm.nih.gov/srs/ProxyServlet?mergeData=true&objectHandle=DBMaint&APPLICATION_NAME=fdasrs&actionHandle=default&nextPage=jsp/srs/ResultScreen.jsp&TXTSUPERLISTID=",  # noqa: E501 line too long
             },
             15: {"name": "surechembl", "baseUrl": "https://www.surechembl.org/search/", "entryUrl": "https://www.surechembl.org/chemical/"},
             21: {"name": "pubchem_tpharma", "baseUrl": "http://www.thomson-pharma.com/", "entryUrl": "http://pubchem.ncbi.nlm.nih.gov/substance/"},

rcsb/utils/chemref/ChemCompProvider.py

@@ -5,6 +5,7 @@
 #
 # Updates:
 #   7-Jun-2023 aae  Include bond count in chem comp data and fix typo
+#   4-Nov-2025 dwp  Strip newline characters from 'chem_comp.*' data item values (primarily for 'chem_comp.name', but should be safe to apply to other data items)
 ##
 """
 Utilities to provide essential data items for chemical component definitions.
@@ -244,7 +245,10 @@ def __buildAbridged(self, cL):
             cObj = dataContainer.getObj("chem_comp")
             ccId = cObj.getValue("id", 0)
             for atName in atNameList:
-                tD[atName] = cObj.getValueOrDefault(atName, 0, defaultValue=None)
+                atVal = cObj.getValueOrDefault(atName, 0, defaultValue=None)
+                if atVal:
+                    atVal = atVal.replace("\n", "")  # strip newline characters
+                tD[atName] = atVal
             tD["formula_weight"] = float(tD["formula_weight"]) if tD["formula_weight"] and "formula_weight" in tD else None
             retD[ccId] = tD
             #

rcsb/utils/chemref/__init__.py

@@ -2,4 +2,4 @@
 __author__ = "John Westbrook"
 __email__ = "john.westbrook@rcsb.org"
 __license__ = "Apache 2.0"
-__version__ = "0.95"
+__version__ = "0.96"