Merge pull request #5 from RECETOX/feat/pypi-stats

Feat/pypi stats

Author: hechth

.config

@@ -0,0 +1,3 @@
+[DEFAULT]
+REPO_FILE_PATH=repository_list.tsv
+DEBUG=False

.editorconfig

@@ -0,0 +1,24 @@
+# http://editorconfig.org
+
+root = true
+
+[*]
+indent_style = space
+indent_size = 4
+trim_trailing_whitespace = true
+insert_final_newline = true
+charset = utf-8
+end_of_line = lf
+
+[*.bat]
+indent_style = tab
+end_of_line = crlf
+
+[LICENSE]
+insert_final_newline = false
+
+[Makefile]
+indent_style = tab
+
+[*.{yml, yaml}]
+indent_size = 2

.github/workflows/actions.yml

@@ -0,0 +1,34 @@
+name: specdatri reporting
+on:
+  schedule:
+    - cron: 0 0 * * 1 # At 00:00 on Monday
+jobs:
+  build:
+    runs-on: ubuntu-22.04
+    steps:
+      - name: checkout repo content
+        uses: actions/checkout@v4
+      - name: setup python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+      - name: install python packages
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+      - name: execute py script
+        env:
+          github_token: '${{ secrets.github_token }}'
+          pepy_x_api_key: '${{ secrets.pepy_x_api_key }}'
+        run: python main.py
+      - name: commit files
+        run: |
+          git config --local user.email "action@github.com"
+          git config --local user.name "GitHub Action"
+          git add -A
+          git diff-index --quiet HEAD || (git commit -a -m "updated files" --allow-empty)
+      - name: push changes
+        uses: ad-m/github-push-action@v0.8.0
+        with:
+          github_token: '${{ secrets.github_token }}'
+          branch: main

.github/workflows/codeql-analysis.yml

@@ -0,0 +1,25 @@
+name: "Code Scanning with CodeQL"
+
+on:
+  push:
+    branches: [ main ]
+  pull_request:
+    branches: [ main ]
+  schedule:
+    - cron: '40 17 * * 3'
+
+jobs:
+  analyze:
+    name: Analyze
+    runs-on: ubuntu-22.04
+    permissions:
+      security-events: write
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v4
+    - name: Initialize
+      uses: github/codeql-action/init@v3
+      with:
+        languages: python
+    - name: Perform CodeQL Analysis
+      uses: github/codeql-action/analyze@v3

.pre-commit-config.yaml

@@ -0,0 +1,35 @@
+exclude: '.*\.tsv$'
+default_stages: [pre-commit]
+
+default_language_version:
+  python: python3.12
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-json
+      - id: check-toml
+      - id: check-xml
+      - id: check-yaml
+      - id: debug-statements
+      - id: check-builtin-literals
+      - id: check-case-conflict
+      - id: check-docstring-first
+      - id: detect-private-key
+
+  # Run the Ruff linter.
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.8.3
+    hooks:
+      # Linter
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
+
+# sets up .pre-commit-ci.yaml to ensure pre-commit dependencies stay up to date
+ci:
+  autoupdate_schedule: weekly
+  skip: []
+  submodules: false

README.md

@@ -1,2 +1,44 @@
 # specdatri_reporting
 The code base includes a collection of scripts and GitHub Actions designed to gather various metrics on RECETOX's impact.
+
+## Local development
+
+### Project setup
+It is assumed you can clone and change directories into the development repo.
+Create a virtualenv or conda environment (whatever your poison).
+
+Once in the repos directory, activate your env then run the following command to install the needed python libraries.
+
+> pip install -r .\requirements\local.txt
+
+### Simulating Github Actions
+
+You need [act](https://nektosact.com/) to test your code in development mode.
+Install act for your chosen OS.
+At your terminal, run (This simulates a GitHub action on your local device):
+
+> act --secret-file .env schedule
+
+### Things to note
+
+1: Do not push local development changes from `tmp` folder and `reports` folder. In fact do not edit them at all !!!
+
+2: When testing with `act` do not use a token that has the permission to make push requests else your test data will mess with "production" data.
+
+3: When testing with `act` know that the push may fail due to the fact that you can't directly push to main.
+
+4: Always, I repeat always devlop on another branch not main and never push directly to main.
+
+5: You need tokens to test the code locally, place said tokens in `example.env` and change the filename to `.env`
+
+### Running tests:
+
+#### Running with unittest
+> python -m unittest discover -s tests
+
+#### Running with coverage
+> coverage run -m unittest discover -s tests
+
+> coverage report -m
+
+> coverage html

example.env

@@ -0,0 +1,2 @@
+github_token="your_github_token"
+pepy_x_api_key="your_pepy_x_api_key"

main.py

@@ -0,0 +1,72 @@
+import pandas as pd
+from pandas import DataFrame
+
+from src.github import process_github_repositories
+from src.pypi import process_pypi_repositories
+from src.utils import get_config_var, get_env_var, log_function, setup_logger
+
+logger = setup_logger()
+
+
+@log_function(logger)
+def load_repositories(
+    file_path: str,
+) -> DataFrame:
+    """
+    Reads a list of repositories from a TSV file and returns it as a DataFrame.
+
+    :param file_path: Path to the TSV file containing the list of repositories.
+    :return: DataFrame containing the list of repositories.
+    """
+    return pd.read_csv(file_path, sep="\t")
+
+
+@log_function(logger)
+def process_repositories(
+    repositories_df: DataFrame,
+    github_token: str,
+    pepy_x_api_key: str,
+):
+    """
+    Args:
+        repositories_df (DataFrame): DataFrame containing the list of repositories.
+        github_token (str): GitHub token to access the GitHub API.
+    Returns:
+        None
+    """
+    for _, row in repositories_df.iterrows():
+        source = row["source"].lower()
+        repository = row["repository"]
+        action = row["action"]
+        project = row["project"]
+        package = row["package"]
+        if source == "github":
+            owner, repo = repository.split("/")
+            process_github_repositories(
+                owner, repo, github_token, action, project, package
+            )
+        elif source == "pypi":
+            process_pypi_repositories(
+                package, pepy_x_api_key, action, project
+            )
+        else:
+            logger.error(f"Unknown source: {source}")
+
+
+@log_function(logger)
+def main():
+    repo_file_path = get_config_var("DEFAULT", "REPO_FILE_PATH")
+    if repo_file_path:
+        logger.info("REPO_FILE_PATH found in .config file")
+        repositories_df = load_repositories(repo_file_path)
+        github_token = get_env_var("github_token")
+        pepy_x_api_key = get_env_var("pepy_x_api_key")
+        process_repositories(repositories_df, github_token, pepy_x_api_key)
+        logger.debug(f"Repositories DataFrame: \n{repositories_df}")
+    else:
+        logger.error("REPO_FILE_PATH not found in .config file")
+        print("REPO_FILE_PATH not found in .config file")
+
+
+if __name__ == "__main__":
+    main()

reports/.gitkeep

@@ -0,0 +1 @@
+-r requirements/base.txt