Merge pull request #13 from jaspersiebring/regex_fix

Regex fix (named and optional groups)

.github/workflows/main.yml

@@ -19,29 +19,32 @@ jobs:
         id: setup-python
         uses: actions/setup-python@v4
         with:
-          python-version: 3.8
+          python-version: 3.9
           cache: poetry
 
       - name: Install dependencies
         run: |
           sudo apt update
           sudo apt install -y \
+            libgstreamer-plugins-base1.0-0 \
             dpkg-dev \
             build-essential \
+            libjpeg-dev \
+            libtiff-dev \
+            libsdl1.2-dev \
+            libnotify-dev \
             freeglut3-dev \
+            libsm-dev \
+            libgtk-3-dev \
+            libwebkit2gtk-4.0-dev \
+            libxtst-dev \
             libgl1-mesa-dev \
             libglu1-mesa-dev \
             libgstreamer-plugins-base1.0-dev \
-            libgtk-3-dev \
-            libjpeg-dev \
             libnotify-dev \
             libpng-dev \
             libsdl2-dev \
-            libsm-dev \
             libunwind-dev \
-            libtiff-dev \
-            libwebkit2gtk-4.0-dev \
-            libxtst-dev \
             libgtk2.0-dev
         if: matrix.os == 'ubuntu-latest'
       - name: Installing Poetry environment
@@ -58,17 +61,17 @@ jobs:
       - name: Running mypy
         id: mypy
         run: poetry run mypy libretro_finder/ config/ tests/
-      - name: Running pylint
-        id: pylint
-        run: poetry run pylint libretro_finder/ config/ tests/ --fail-under=8
+      - name: Running ruff
+        id: ruff
+        run: poetry run ruff check libretro_finder/ config/ tests/
       - name: Checking code coverage
         id: coverage
         run: poetry run pytest --cov=config --cov=libretro_finder --cov-fail-under=75
 
       - name: Build source and .whl archives with Poetry
         id: build
         run: poetry build
-        if: steps.pytest.outcome == 'success' && steps.mypy.outcome == 'success' && steps.pylint.outcome == 'success' && steps.coverage.outcome == 'success' && github.event_name == 'push'
+        if: steps.pytest.outcome == 'success' && steps.mypy.outcome == 'success' && steps.ruff.outcome == 'success' && steps.coverage.outcome == 'success' && github.event_name == 'push'
 
       - name: Authorize GitHub Actions to publish on PYPI
         run: poetry config pypi-token.pypi ${{ secrets.PYPI_API_TOKEN }}

Dockerfile

@@ -0,0 +1,38 @@
+FROM python:3.9.18-bookworm
+
+# wxPython dependencies
+RUN apt-get update && apt install -y \
+    libgstreamer-plugins-base1.0-0 \
+    dpkg-dev \
+    build-essential \
+    libjpeg-dev \
+    libtiff-dev \
+    libsdl1.2-dev \
+    libnotify-dev \
+    freeglut3-dev \
+    libsm-dev \
+    libgtk-3-dev \
+    libwebkit2gtk-4.0-dev \
+    libxtst-dev \
+    libgl1-mesa-dev \
+    libglu1-mesa-dev \
+    libgstreamer-plugins-base1.0-dev \
+    libnotify-dev \
+    libpng-dev \
+    libsdl2-dev \
+    libunwind-dev \
+    libgtk2.0-dev
+
+# Copying libretro_finder, installing poetry and adding it to PATH
+WORKDIR /app
+COPY . /app
+ENV POETRY_HOME=/opt/poetry
+RUN python3 -m venv $POETRY_HOME && $POETRY_HOME/bin/pip install poetry
+ENV PATH="/opt/poetry/bin:${PATH}"
+
+# Installing libretro_finder's deps
+RUN poetry config installer.max-workers 10
+RUN poetry install
+
+# Default start
+CMD ["/bin/bash"]

config/__init__.py

@@ -19,33 +19,25 @@
     print("Done.")
 
 # Parsing Libretro's system.dat and formatting as pandas dataframe
-index = 0  # pylint: disable=invalid-name
-
 system_series = []
 with open(FILE_PATH, "r", encoding="utf-8") as file:
     for line in file:
         line = line.strip()
         if line.startswith("comment"):
             current_system = line.split('"')[1]
-        elif line.startswith("rom"):
-            match = re.search(
-                r"name (\S+)(?: size (\S+))?(?: crc (\S+))?(?: md5 (\S+))?(?: sha1 (\S+))?",
-                line,
-            )
-            if match:
-                data = {
-                    "system": current_system,
-                    "name": match.group(1).replace('"', "").replace("'", ""),
-                    "size": match.group(2) if match.group(2) else None,
-                    "crc": match.group(3) if match.group(3) else None,
-                    "md5": match.group(4) if match.group(4) else None,
-                    "sha1": match.group(5) if match.group(5) else None,
-                }
-                system_series.append(pd.DataFrame(data, index=[index]))
-                index += 1
+            continue
+
+        regex_string = r'\brom.+name\s+(?P<name>"[^"]+"|\S+)(?:(?:(?:\s+size\s+(?P<size>\S+))|(?:\s+crc\s+(?P<crc>\S+))|(?:\s+md5\s+(?P<md5>\S+))|(?:\s+sha1\s+(?P<sha1>\S+)))(?=\s|$))*'
+        match = re.search(regex_string, line)
+
+        if match:
+            data = match.groupdict()
+            data["system"] = current_system
+            data["name"] = data["name"].replace('"', "")
+            system_series.append(data)
 
 # join dfs and drop features without checksums
-SYSTEMS = pd.concat(system_series)
+SYSTEMS = pd.DataFrame(system_series)
 SYSTEMS = SYSTEMS[~SYSTEMS["md5"].isnull()].reset_index(drop=True)
 
 # path to retroarch/system (if found)

environment.yml

@@ -2,5 +2,5 @@ name: bscraper
 channels:
   - conda-forge
 dependencies:
-  - python=3.8
-  - poetry>=1.5
+  - python=3.9
+  - poetry