Extend RDKit::MolStandardize with a validation and standardization Pi…

…peline (rdkit#7582) * Extend RDKit::MolStandardize with a validation and standardization Pipeline * suggested changes * apply clang-format * apply yapf * MolStandardize::FeaturesValidation optionally disallow dative bonds * add allowDativeBondType to MolStandardize::PipelineOptions * apply clang-format * make the API of other validation classes more consistent with MolStandardize::FeaturesValidation * apply clang-format * PipelineStage to enum class remove virtual functions from Pipeline class be explicit about enums * light refactoring to avoid what I think is an unnecessary call to `parse` * a bit of modernization * make the pipeline configurable * make parse and serialize configurable too * switch to storing pipeline stages using uints * add a simple test for providing a pipeline * update pointer alignment for clang-format * test modifying the parser and serializer * update swig requirement * changes in response to review * changes in response to review * rename PipelineResult's *MolBlock members to *MolData * upgrade swig to 4.2 in the CI environments * add a few missing export directives --------- Co-authored-by: greg landrum <[email protected]>
DavidACosgrove · Jul 30, 2024 · 3f7caf0 · 3f7caf0
1 parent 138bdc8
commit 3f7caf0
Show file tree

Hide file tree

Showing 20 changed files with 6,503 additions and 212 deletions.
diff --git a/.azure-pipelines/linux_build_java.yml b/.azure-pipelines/linux_build_java.yml
@@ -9,7 +9,7 @@ steps:
     conda create --name rdkit_build -c conda-forge cmake \
         libboost=$(boost_version) \
         libboost-devel=$(boost_version) \
-        swig=4.1
+        swig=4.2
   displayName: Setup build environment
 - bash: |
     source ${CONDA}/etc/profile.d/conda.sh

diff --git a/.azure-pipelines/mac_build_java.yml b/.azure-pipelines/mac_build_java.yml
@@ -21,7 +21,7 @@ steps:
         libcxx=$(compiler_version) cmake=3.26 \
         libboost=$(boost_version) \
         libboost-devel=$(boost_version) \
-        cairo eigen swig=4.1
+        cairo eigen swig=4.2
     conda activate rdkit_build
   displayName: Setup build environment
 - bash: |

diff --git a/.azure-pipelines/vs_build_swig.yml b/.azure-pipelines/vs_build_swig.yml
@@ -15,7 +15,7 @@ steps:
         cmake=3.26 ^
         libboost=$(boost_version) ^
         libboost-devel=$(boost_version) ^
-        cairo eigen swig=4.1
+        cairo eigen swig=4.2
     call activate rdkit_build
   displayName: Install dependencies
 - script: |

diff --git a/.clang-format b/.clang-format
@@ -23,7 +23,7 @@ BinPackArguments: true
 ColumnLimit:     80
 ConstructorInitializerAllOnOneLineOrOnePerLine: true
 ConstructorInitializerIndentWidth: 4
-DerivePointerAlignment: true
+DerivePointerAlignment: false
 ExperimentalAutoDetectBinPacking: false
 IndentCaseLabels: true
 IndentWrappedFunctionNames: false
@@ -40,7 +40,7 @@ PenaltyBreakString: 1000
 PenaltyBreakFirstLessLess: 120
 PenaltyExcessCharacter: 1000000
 PenaltyReturnTypeOnItsOwnLine: 200
-PointerAlignment: Left
+PointerAlignment: Right
 SpacesBeforeTrailingComments: 2
 Cpp11BracedListStyle: true
 Standard:        Cpp11

diff --git a/Code/GraphMol/MolStandardize/CMakeLists.txt b/Code/GraphMol/MolStandardize/CMakeLists.txt
@@ -1,55 +1,61 @@
-
 rdkit_library(MolStandardize
-              MolStandardize.cpp
-	      Metal.cpp
-	      Normalize.cpp
-	      Validate.cpp
-	      Charge.cpp
-	      Tautomer.cpp
-	      Fragment.cpp
-        FragmentCatalog/FragmentCatalogEntry.cpp
-        FragmentCatalog/FragmentCatalogParams.cpp
-        FragmentCatalog/FragmentCatalogUtils.cpp
-        AcidBaseCatalog/AcidBaseCatalogEntry.cpp
-        AcidBaseCatalog/AcidBaseCatalogParams.cpp
-        AcidBaseCatalog/AcidBaseCatalogUtils.cpp
-        TransformCatalog/TransformCatalogEntry.cpp
-        TransformCatalog/TransformCatalogParams.cpp
-        TransformCatalog/TransformCatalogUtils.cpp
-        TautomerCatalog/TautomerCatalogEntry.cpp
-        TautomerCatalog/TautomerCatalogParams.cpp
-        TautomerCatalog/TautomerCatalogUtils.cpp
-	      LINK_LIBRARIES ChemReactions ChemTransforms SmilesParse SubstructMatch Descriptors GraphMol )
+    Pipeline.cpp
+    MolStandardize.cpp
+    Metal.cpp
+    Normalize.cpp
+    Validate.cpp
+    Charge.cpp
+    Tautomer.cpp
+    Fragment.cpp
+    FragmentCatalog/FragmentCatalogEntry.cpp
+    FragmentCatalog/FragmentCatalogParams.cpp
+    FragmentCatalog/FragmentCatalogUtils.cpp
+    AcidBaseCatalog/AcidBaseCatalogEntry.cpp
+    AcidBaseCatalog/AcidBaseCatalogParams.cpp
+    AcidBaseCatalog/AcidBaseCatalogUtils.cpp
+    TransformCatalog/TransformCatalogEntry.cpp
+    TransformCatalog/TransformCatalogParams.cpp
+    TransformCatalog/TransformCatalogUtils.cpp
+    TautomerCatalog/TautomerCatalogEntry.cpp
+    TautomerCatalog/TautomerCatalogParams.cpp
+    TautomerCatalog/TautomerCatalogUtils.cpp
+        LINK_LIBRARIES ChemReactions ChemTransforms SmilesParse SubstructMatch Descriptors GraphMol )
 target_compile_definitions(MolStandardize PRIVATE RDKIT_MOLSTANDARDIZE_BUILD)
 
-rdkit_headers(MolStandardize.h
-	      Metal.h
-	      Normalize.h
-	      Validate.h
-	      Charge.h
-	      Tautomer.h
-	      Fragment.h
-	      DEST GraphMol/MolStandardize)
+rdkit_headers(
+    Pipeline.h
+    MolStandardize.h
+    Metal.h
+    Normalize.h
+    Validate.h
+    Charge.h
+    Tautomer.h
+    Fragment.h
+        DEST GraphMol/MolStandardize)
 
-rdkit_headers(FragmentCatalog/FragmentCatalogEntry.h
-        FragmentCatalog/FragmentCatalogParams.h
-        FragmentCatalog/FragmentCatalogUtils.h
-	    DEST GraphMol/MolStandardize/FragmentCatalog)
+rdkit_headers(
+    FragmentCatalog/FragmentCatalogEntry.h
+    FragmentCatalog/FragmentCatalogParams.h
+    FragmentCatalog/FragmentCatalogUtils.h
+        DEST GraphMol/MolStandardize/FragmentCatalog)
 
-rdkit_headers(AcidBaseCatalog/AcidBaseCatalogEntry.h
-        AcidBaseCatalog/AcidBaseCatalogParams.h
-        AcidBaseCatalog/AcidBaseCatalogUtils.h
-	    DEST GraphMol/MolStandardize/AcidBaseCatalog)
+rdkit_headers(
+    AcidBaseCatalog/AcidBaseCatalogEntry.h
+    AcidBaseCatalog/AcidBaseCatalogParams.h
+    AcidBaseCatalog/AcidBaseCatalogUtils.h
+        DEST GraphMol/MolStandardize/AcidBaseCatalog)
 
-rdkit_headers(TransformCatalog/TransformCatalogEntry.h
-        TransformCatalog/TransformCatalogParams.h
-        TransformCatalog/TransformCatalogUtils.h
-	    DEST GraphMol/MolStandardize/TransformCatalog)
+rdkit_headers(
+    TransformCatalog/TransformCatalogEntry.h
+    TransformCatalog/TransformCatalogParams.h
+    TransformCatalog/TransformCatalogUtils.h
+        DEST GraphMol/MolStandardize/TransformCatalog)
 
-rdkit_headers(TautomerCatalog/TautomerCatalogEntry.h
-        TautomerCatalog/TautomerCatalogParams.h
-        TautomerCatalog/TautomerCatalogUtils.h
-	    DEST GraphMol/MolStandardize/TautomerCatalog)
+rdkit_headers(
+    TautomerCatalog/TautomerCatalogEntry.h
+    TautomerCatalog/TautomerCatalogParams.h
+    TautomerCatalog/TautomerCatalogUtils.h
+        DEST GraphMol/MolStandardize/TautomerCatalog)
 
 if(RDK_BUILD_PYTHON_WRAPPERS)
 add_subdirectory(Wrap)
@@ -63,5 +69,6 @@ rdkit_test(molTautomerTest testTautomer.cpp LINK_LIBRARIES MolStandardize )
 rdkit_test(molStandardizeSmallTest test2.cpp LINK_LIBRARIES MolStandardize )
 rdkit_test(molFragmentTest testFragment.cpp LINK_LIBRARIES MolStandardize )
 rdkit_catch_test(molStandardizeCatchTest catch_tests.cpp LINK_LIBRARIES MolStandardize )
+rdkit_catch_test(molStandardizePipelineTest testPipeline.cpp LINK_LIBRARIES MolStandardize)
 
 
diff --git a/Code/GraphMol/MolStandardize/Charge.cpp b/Code/GraphMol/MolStandardize/Charge.cpp
@@ -538,7 +538,7 @@ void Uncharger::unchargeInPlace(RWMol &mol) {
       }
     }
   }
-}  // namespace MolStandardize
+}
 
 }  // namespace MolStandardize
 }  // namespace RDKit