Merge pull request #37 from dcheng2022/master

Merge MOFid 2024

.dockerignore

@@ -0,0 +1,4 @@
+# .dockerignore
+bin/
+openbabel/build
+openbabel/installed

.gitattributes

@@ -5,3 +5,6 @@ openbabel/data/* text eol=lf
 openbabel/data/*.png binary
 Makefile text eol=lf
 *.sh text eol=lf
+
+# Apply spabs filter
+*.py filter=spabs

.github/workflows/main.yml

@@ -0,0 +1,44 @@
+name: run_tests
+on:
+  push:
+    paths:
+      - "**.py"
+      - "Makefile"
+      - "openbabel/**"
+      - "eigen/**"
+      - "src/**"
+  pull_request:
+  workflow_dispatch:
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Setup Python 3.10
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.10"
+      - name: Install colordiff
+        run: |
+          sudo apt-get update
+          sudo apt-get install colordiff 
+      - name: Build Project 
+        run: |
+          mkdir Output
+          make test
+      - name: Run Unit Tests
+        run: make unittest
+      - name: Run Intermediate Tests
+        run : make intermediatetest
+      - name: Archive Mismatch Artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: mismatch
+          path: Mismatch
+          if-no-files-found: ignore
+          retention-days: 1
+      - name: Run Integration Tests
+        run: |
+          python set_paths.py
+          pip install .
+          make pytest

.gitignore

@@ -1,3 +1,8 @@
+Mismatch/
+.venv/
+venv/
+.env/
+env/
 *.pyc
 Data/
 !README.md

Analysis/extract_carbon_mofs.py

@@ -9,18 +9,18 @@
 DEST_DIR = 'Summary/OrigCore/'
 
 if not os.path.isdir(DEST_DIR):
-	print('Moving original CoRE MOF files to a new directory: ' + DEST_DIR)
-	os.mkdir(DEST_DIR)
-	core_files = glob.glob('Summary/core*')
-	for core_output in core_files:
-		shutil.move(core_output, DEST_DIR)
+    print('Moving original CoRE MOF files to a new directory: ' + DEST_DIR)
+    os.mkdir(DEST_DIR)
+    core_files = glob.glob('Summary/core*')
+    for core_output in core_files:
+        shutil.move(core_output, DEST_DIR)
 
 def read_file(data_file):
-	with open(os.path.join('Summary/OrigCore/', data_file), 'r') as f:
-		data_contents = f.readlines()
-		# Let's keep the newlines so we don't have to rewrite them later:
-		#data_contents = [x.strip('\n') for x in data_contents]
-	return data_contents
+    with open(os.path.join('Summary/OrigCore/', data_file), 'r') as f:
+        data_contents = f.readlines()
+        # Let's keep the newlines so we don't have to rewrite them later:
+        #data_contents = [x.strip('\n') for x in data_contents]
+    return data_contents
 
 mofids = read_file('core_mofid.smi')
 #smis = read_file('core.smi')
@@ -37,18 +37,18 @@ def read_file(data_file):
 
 # Map the input to output files line-by-line
 for lineno in range(len(elements)):
-	cif_name = elements[lineno].split()[0]
-	assert cif_name.endswith('.cif') or cif_name.endswith('.CIF')
-	cif_name = cif_name[:-4]
-	# Check that our lines are properly aligned between all of the MOFid code output files
-	assert mofids[lineno].endswith(';' + cif_name + '\n')
-	assert mofkeys[lineno].startswith(cif_name + '.cif\t')
-
-	contains_carbon = re.search(r'[ \t]C ', elements[lineno])
-	if contains_carbon:
-		out_mofids.write(mofids[lineno])
-		out_mofkeys.write(mofkeys[lineno])
-		out_files.write(cif_name + '\n')
+    cif_name = elements[lineno].split()[0]
+    assert cif_name.endswith('.cif') or cif_name.endswith('.CIF')
+    cif_name = cif_name[:-4]
+    # Check that our lines are properly aligned between all of the MOFid code output files
+    assert mofids[lineno].endswith(';' + cif_name + '\n')
+    assert mofkeys[lineno].startswith(cif_name + '.cif\t')
+
+    contains_carbon = re.search(r'[ \t]C ', elements[lineno])
+    if contains_carbon:
+        out_mofids.write(mofids[lineno])
+        out_mofkeys.write(mofkeys[lineno])
+        out_files.write(cif_name + '\n')
 
 out_mofids.close()
 out_mofkeys.close()

Dockerfile

@@ -1,26 +1,14 @@
-FROM continuumio/miniconda3
+# MOFid 2024
+FROM python:3.11-bookworm
 
-# set up conda and deps, per .travis.yml
-RUN apt-get update -qq
-RUN mkdir -p /usr/share/man/man1/  # required to prevent default-jre installation from crashing
-RUN apt-get install -qq default-jre
-RUN apt-get install -qq build-essential cmake
+LABEL AUTHOR="[email protected]"
+LABEL version="2024"
 
-RUN conda config --set always_yes yes --set changeps1 no
-RUN conda create -q -n py2 python=2.7
-
-# copy source code from git
 WORKDIR /mofid
 COPY . /mofid
 
-# compile openbabel, C++ analysis code, and Python package
-RUN make init
-RUN python set_paths.py
-RUN pip install .
-# Disabling conda environment for now and keeping with base Python
-#RUN source activate py2
-#RUN pip install .
-#RUN conda deactivate
-
-# then run the code, either interactively or via docker command line
-
+RUN apt-get update -qq \ 
+    && apt-get install -qq default-jre gcc-11 g++-11 cmake \
+    && make init \
+    && python set_paths.py \ 
+    && pip install . \

Makefile

@@ -1,4 +1,7 @@
-.PHONY: all backup test diff ob_changes.patch init eclipse web init-web github-web html one exe btc
+.PHONY: all backup test unittest intermediatetest pytest diff ob_changes.patch init debug eclipse web init-web github-web html one exe btc
+
+mofid-dir := $(shell pwd)
+python-packages-dir := $(shell python -m site | grep -o "/.*/site-packages" | head --lines 1) 
 
 all:
 	@echo "Sample make file for experimentation.  Still needs work.  Only backup implemented"
@@ -17,11 +20,11 @@ bin/tsfm_smiles: src/tsfm_smiles.cpp openbabel/build/lib/cifformat.so
 	cd bin && make tsfm_smiles
 
 exe:
-	cd bin && make
+	cd bin && make -j$$(nproc)
 
 one:
 	cd bin && make; \
-	cd ..; \
+	cd $(mofid-dir); \
 	bin/sbu Resources/TestCIFs/P1-IRMOF-1.cif
 
 btc:
@@ -40,23 +43,58 @@ ob_changes.patch:
 	git diff --no-prefix 7810ca7bb1beef14b2a62cf5bad3a8551b187824 -- openbabel/*.cpp openbabel/*.h ':!openbabel/data/*' ':!openbabel/test/*' > $@
 	# Lists my changes to the main OpenBabel code
 
-test: bin/sbu
-	python tests/check_run_mofid.py
-	python tests/check_mof_composition.py
+test: 
+	cd openbabel; \
+	mkdir build installed; \
+	cd build; \
+	cmake -DCMAKE_C_COMPILER=gcc-11 -DCMAKE_CXX_COMPILER=g++-11 -DCMAKE_INSTALL_PREFIX=../installed -DBUILD_GUI=OFF -DENABLE_TESTS=OFF -DEIGEN3_INCLUDE_DIR=../eigen -DRUN_SWIG=ON -DPYTHON_BINDINGS=ON ..; \
+	make -j$$(nproc) || exit 2; \
+	make install; \
+	cd $(python-packages-dir); \
+	test -f openbabel.pth || echo $(mofid-dir)/openbabel/installed/lib/python*/site-packages > openbabel.pth; \
+	cd $(mofid-dir); \
+	mkdir bin; \
+	cd bin; \
+	cmake -DCMAKE_C_COMPILER=gcc-11 -DCMAKE_CXX_COMPILER=g++-11 -DOpenBabel3_DIR=../openbabel/build -DCMAKE_BUILD_TYPE=Debug -DBUILD_TESTING=ON ../src/; \
+	make -j$$(nproc); \
 
+unittest:
+	ctest --output-on-failure --test-dir bin/test
+
+intermediatetest:
+	tests/check_intermediate.sh
+
+pytest:
+	python tests/check_run_mofid.py; \
+	python tests/check_mof_composition.py
 
 init:
 	cd openbabel; \
 	mkdir build installed; \
 	cd build; \
-	cmake -DCMAKE_INSTALL_PREFIX=../installed -DBUILD_GUI=OFF -DEIGEN3_INCLUDE_DIR=../eigen ..; \
-	make -j2 || exit 2; \
+	cmake -DCMAKE_C_COMPILER=gcc-11 -DCMAKE_CXX_COMPILER=g++-11 -DCMAKE_INSTALL_PREFIX=../installed -DENABLE_TESTS=OFF -DBUILD_GUI=OFF -DEIGEN3_INCLUDE_DIR=../eigen ..; \
+	make -j$$(nproc) || exit 2; \
+	make install; \
+	cd $(mofid-dir); \
+	mkdir bin; \
+	cd bin; \
+	cmake -DCMAKE_C_COMPILER=gcc-11 -DCMAKE_CXX_COMPILER=g++-11 -DOpenBabel3_DIR=../openbabel/build -DBUILD_TESTING=OFF -DCMAKE_BUILD_TYPE=Release ../src/; \
+	make -j$$(nproc)
+	# Sets up all the cmake details, so that usage is as simple as
+	# `bin/sbu MOF.cif` and re-compilation is as easy as `make exe`
+
+debug:
+	cd openbabel; \
+	mkdir build installed; \
+	cd build; \
+	cmake -DCMAKE_C_COMPILER=gcc-11 -DCMAKE_CXX_COMPILER=g++-11 -DCMAKE_INSTALL_PREFIX=../installed -DBUILD_GUI=OFF -DENABLE_TESTS=OFF -DEIGEN3_INCLUDE_DIR=../eigen ..; \
+	make -j$$(nproc) || exit 2; \
 	make install; \
-	cd ../../; \
+	cd $(mofid-dir); \
 	mkdir bin; \
 	cd bin; \
-	cmake -DOpenBabel2_DIR=../openbabel/build ../src/; \
-	make
+	cmake -DCMAKE_C_COMPILER=gcc-11 -DCMAKE_CXX_COMPILER=g++-11 -DOpenBabel3_DIR=../openbabel/build ../src/ -DCMAKE_BUILD_TYPE=Debug;\
+	make -j$$(nproc)
 	# Sets up all the cmake details, so that usage is as simple as
 	# `bin/sbu MOF.cif` and re-compilation is as easy as `make exe`
 
@@ -91,7 +129,7 @@ init-web:
 	cd ../..; \
 	mkdir embin; \
 	cd embin; \
-	emcmake cmake -DOpenBabel2_DIR=../openbabel/embuild -static ../src/ -DCMAKE_CXX_FLAGS="-O3 --preload-file ../openbabel/data@/ob_datadir/ --preload-file ../src/Web/web_data@/web_data/ --preload-file ../Resources/RCSRnets.arc@/RCSRnets.arc --pre-js ../src/pre_emscripten.js -s TOTAL_MEMORY=128MB -s WASM=1 -s EXTRA_EXPORTED_RUNTIME_METHODS=\"['ccall', 'cwrap', 'UTF8ToString']\""; \
+	emcmake cmake -DOpenBabel3_DIR=../openbabel/embuild -static ../src/ -DCMAKE_CXX_FLAGS="-O3 --preload-file ../openbabel/data@/ob_datadir/ --preload-file ../src/Web/web_data@/web_data/ --preload-file ../Resources/RCSRnets.arc@/RCSRnets.arc --pre-js ../src/pre_emscripten.js -s TOTAL_MEMORY=128MB -s WASM=1 -s EXTRA_EXPORTED_RUNTIME_METHODS=\"['ccall', 'cwrap', 'UTF8ToString']\""; \
 	mkdir kekule; \
 	cd kekule; \
 	unzip ../../Resources/kekule.release.0.7.5.170624.zip; \

Python/convert_smi_to_tables.py

@@ -13,59 +13,59 @@
 
 
 def dict_to_delim(to_export, filename, delim='\t'):
-	with open(filename, 'w') as f:
-		for key in to_export:
-			if type(to_export[key]) is list:
-				for j in to_export[key]:
-					f.write(key + delim + str(j) + '\n')
-			else:
-				f.write(key + delim + str(to_export[key]) + '\n')
+    with open(filename, 'w') as f:
+        for key in to_export:
+            if type(to_export[key]) is list:
+                for j in to_export[key]:
+                    f.write(key + delim + str(j) + '\n')
+            else:
+                f.write(key + delim + str(to_export[key]) + '\n')
 
 
 class MOFExporter:
-	# Exports a .smi-formatted list of MOFid into separate tables for the various parts
-	def __init__(self):
-		self.tables = dict()
-		self.datatypes = list()  # smiles, topology, catenation, etc.
+    # Exports a .smi-formatted list of MOFid into separate tables for the various parts
+    def __init__(self):
+        self.tables = dict()
+        self.datatypes = list()  # smiles, topology, catenation, etc.
 
-	def parse(self, filename):
-		with open(filename, 'r') as f:
-			for line in f:
-				parsed = parse_mofid(line)
-				name = parsed['name']
-				del parsed['name']
-				parsed['smiles_part'] = parsed['smiles'].split('.')
-				parsed['base_topology'] = parsed['topology'].split(',')[0]
-				parsed['extra_topology'] = ','.join(parsed['topology'].split(',')[1:])  # '' if empty
-				self.tables[name] = copy.deepcopy(parsed)
-				self.datatypes = parsed.keys()
-		return self
+    def parse(self, filename):
+        with open(filename, 'r') as f:
+            for line in f:
+                parsed = parse_mofid(line)
+                name = parsed['name']
+                del parsed['name']
+                parsed['smiles_part'] = parsed['smiles'].split('.')
+                parsed['base_topology'] = parsed['topology'].split(',')[0]
+                parsed['extra_topology'] = ','.join(parsed['topology'].split(',')[1:])  # '' if empty
+                self.tables[name] = copy.deepcopy(parsed)
+                self.datatypes = parsed.keys()
+        return self
 
-	def _tidy_tables(self):
-		tidy_dict = dict()
-		for info in self.datatypes:
-			tidy_dict[info] = dict()
+    def _tidy_tables(self):
+        tidy_dict = dict()
+        for info in self.datatypes:
+            tidy_dict[info] = dict()
 
-		for mof in self.tables:
-			for info in self.datatypes:
-				tidy_dict[info][mof] = self.tables[mof][info]
+        for mof in self.tables:
+            for info in self.datatypes:
+                tidy_dict[info][mof] = self.tables[mof][info]
 
-		return tidy_dict
+        return tidy_dict
 
-	def write(self, folder='.'):
-		if not os.path.isdir(folder):
-			os.mkdir(folder)
+    def write(self, folder='.'):
+        if not os.path.isdir(folder):
+            os.mkdir(folder)
 
-		tidy_output = self._tidy_tables()
-		for key in tidy_output:
-			dict_to_delim(tidy_output[key], folder + '/' + key + '.tsv', delim='\t')
+        tidy_output = self._tidy_tables()
+        for key in tidy_output:
+            dict_to_delim(tidy_output[key], folder + '/' + key + '.tsv', delim='\t')
 
 
 
 if __name__ == '__main__':
-	args = sys.argv[1:]
-	if len(args) != 1:
-		raise SyntaxError('Extract info from a list of MOFid strings.  Only a single .smi filename expected.')
+    args = sys.argv[1:]
+    if len(args) != 1:
+        raise SyntaxError('Extract info from a list of MOFid strings.  Only a single .smi filename expected.')
 
-	input_smi = args[0]
-	MOFExporter().parse(input_smi).write('TableOutput')
+    input_smi = args[0]
+    MOFExporter().parse(input_smi).write('TableOutput')