Merge pull request #694 from KnowledgeCaptureAndDiscovery/dev

Fix issues about poetry deployment. Update Docker image

.github/workflows/pypi-publish.yml

@@ -1,31 +1,34 @@
-# This workflows will upload a Python Package using Twine when a release is created
+# This workflows will upload a Python Package using poetry when a release is created
 # For more information see: https://help.github.com/en/actions/language-and-framework-guides/using-python-with-github-actions#publishing-to-package-registries
 
-name: Publish SOMEF package to PyPi
+name: Publish SOMEF package to PyPI
 
 on:
   release:
     types: [created]
 
 jobs:
   deploy:
-
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v2
-    - name: Set up Python
-      uses: actions/setup-python@v2
-      with:
-        python-version: '3.x'
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install setuptools wheel twine
-    - name: Build and publish
-      env:
-        TWINE_USERNAME: ${{ secrets.PYPI_USERNAME }}
-        TWINE_PASSWORD: ${{ secrets.PYPI_PASSWORD }}
-      run: |
-        python setup.py sdist bdist_wheel
-        twine upload dist/*
+      - name: Checkout code
+        uses: actions/checkout@v2
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: "3.x"
+      - name: Install Poetry
+        run: curl -sSL https://install.python-poetry.org | python3 -
+      - name: Update version
+        run: python update_version.py
+      - name: Install dependencies
+        run: poetry install
+      - name: Configure Poetry for PyPI
+        run: |
+          poetry config pypi-token.pypi ${{ secrets.PYPI_PASSWORD }}
+
+      - name: Build and publish
+        run: |
+          poetry build
+          poetry publish

Dockerfile

@@ -1,7 +1,19 @@
-from python:3.10
+FROM python:3.10
 
 RUN git clone https://github.com/KnowledgeCaptureAndDiscovery/somef
 
-RUN cd somef && pip install . 
+RUN curl -sSL https://install.python-poetry.org | python3 -
+
+RUN pip install poetry-plugin-shell
+
+WORKDIR "/somef"
+
+RUN poetry install 
+
+RUN poetry run somef configure -a
+
+RUN echo 'source $(poetry env info --path)/bin/activate' >> ~/.bashrc
+
+
+CMD ["bash", "--login"]
 
-RUN somef configure -a

README.md

@@ -124,51 +124,31 @@ Clone this GitHub repository
 git clone https://github.com/KnowledgeCaptureAndDiscovery/somef.git
 ```
 
-For better dependency management, it is necessary to have Poetry installed beforehand. It can be installed as follows:
+We use [Poetry](https://python-poetry.org/) to ensure library compatibility. It can be installed as follows:
 
 ```
 curl -sSL https://install.python-poetry.org | python3 -
 ```
 
 This option is recommended over installing Poetry with pip install.
 
-Now Poetry will handle the installation of SOMEF and all its dependencies configured in the TOML file.
+Now Poetry will handle the installation of SOMEF and all its dependencies configured in the `toml` file.
 
-Test the correct installation of poetry
+To test the correct installation of poetry run:
 
 ```
 poetry --version
 ```
 
-We can first review the list of libraries and dependencies configured as necessary for the operation.
-
-```
-poetry show
-```
-
 Install somef and all their dependencies.
 
 ```
+cd /somef
 poetry install
 ```
 
-With the following instruction, we can see the environments available in the project and which one is currently active.
-
-```
-poetry env list
-```
-
-Now we need to access our virtual environment, to do so you have to install the [poetry plugin shell](https://github.com/python-poetry/poetry-plugin-shell) and run the following possible commands:
+Now we need to access our virtual environment, to do so you have to install the [poetry plugin shell](https://github.com/python-poetry/poetry-plugin-shell) and run the following command:
 
-- If you want to install the `shell` plugin is via the `self add` command of Poetry
-```
-poetry self add poetry-plugin-shell
-```
-- or if you used pipx to install Poetry: 
-```
-pipx inject poetry poetry-plugin-shell
-```
-- otherwise if you used pip install:
 ```
 pip install poetry-plugin-shell
 ```

pyproject.toml

@@ -1,13 +1,13 @@
 [tool.poetry]
 name = "somef"
-version = "0.9.6"
+version = "0.9.7"
 description = "SOftware Metadata Extraction Framework: A tool for automatically extracting relevant software information from readme files."
 authors = ["Daniel Garijo <[email protected]>"]
 packages = [
     { include = "somef", from = "src" }
 ]
 classifiers = [ 
-    "Programming Language :: Python :: 3.9", 
+    "Programming Language :: Python :: 3.10", 
     "Operating System :: OS Independent", 
     "License :: OSI Approved :: MIT License", 
     "Topic :: Software Development :: Libraries :: Python Modules"
@@ -20,7 +20,7 @@ bs4 = "^0.0.1"
 click = "^8.1.7"
 click-option-group = "^0.5.6"
 matplotlib = "^3.8.2"
-nltk = "^3.8.1"
+nltk = "^3.9.0"
 numpy = "^1.26.3"
 pandas = "^2.1.4"
 rdflib = "^7.0.0"
@@ -41,8 +41,6 @@ rdflib-jsonld = "^0.6.2"
 requests = "^2.31.0"
 scikit-learn = "1.3.2"
 
-[tool.poetry.dev-dependencies]
-
 [tool.poetry.scripts]
 somef = "somef.__main__:cli"
 

src/somef/__init__.py

@@ -1,3 +1,3 @@
 # -*- coding: utf-8 -*-
 
-__version__ = "0.9.6"
+__version__ = "0.9.7"

src/somef/test/test_data/repositories/RDFChess/pom.xml

@@ -75,7 +75,7 @@
         <dependency>
             <groupId>org.apache.commons</groupId>
             <artifactId>commons-compress</artifactId>
-            <version>1.21</version>
+            <version>1.26.0</version>
         </dependency>
         <!-- https://mvnrepository.com/artifact/org.jdom/jdom -->
         <!-- https://mvnrepository.com/artifact/jdom/jdom -->

src/somef/utils/constants.py

@@ -86,7 +86,9 @@
 
 # list of those categories to be analyzed with supervised classification.
 # supervised_categories = [CAT_DESCRIPTION, CAT_CITATION, CAT_INSTALLATION, CAT_INVOCATION]
-supervised_categories = [CAT_DESCRIPTION, CAT_INSTALLATION, CAT_INVOCATION]
+# update jan 2025: only description is run, since the installation classifier is a bit noisy.
+# we prioritize returning high precision, since some users get confused otherwise.
+supervised_categories = [CAT_DESCRIPTION]
 
 # list with all categories
 all_categories = [CAT_APPLICATION_DOMAIN, CAT_ACKNOWLEDGEMENT, CAT_CITATION, CAT_CONTRIBUTORS,

update_version.py

@@ -0,0 +1,30 @@
+import re
+
+def get_version(file_path):
+    """get version file __init__.py .
+
+    Args:
+        file_path (str): __init__py.
+
+    Returns:
+        str: version.
+    """
+
+    with open(file_path, 'r') as f:
+        for line in f:
+            if line.startswith('__version__'):
+                return line.split('=')[1].strip().strip('"')
+
+
+def update_version(toml_path, version_file):
+    with open(toml_path, 'r') as f:
+        content = f.read()
+
+    new_version = get_version(version_file)
+    new_content = content.replace("{version-file}", new_version)
+
+    with open(toml_path, 'w') as f:
+        f.write(new_content)
+
+
+update_version("pyproject.toml", "src/somef/__init__.py")