Add Rakuten set draft and workflow for set validation

.github/workflows/rakuten-set-checks.yml

@@ -0,0 +1,28 @@
+name: RWS submission checks
+on: 
+  pull_request:
+    branches:
+      - main
+jobs:
+  PR-Actions:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+          cache: 'pip' # caching pip dependencies
+      - name: Install dependencies
+        run: pip install -r requirements.txt
+
+      - name: Check site
+        run: |
+          python check_sites.py -p https://rakuten.co.jp > result.txt
+          if grep -q 'success' result.txt; then
+            echo "Check successful"
+          else
+            echo "Check failed, see message below:"
+            cat result.txt

.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

check_sites.py

@@ -132,7 +132,7 @@ def main():
         rws_checker.has_all_rationales,
         rws_checker.find_non_https_urls, 
         rws_checker.find_invalid_eTLD_Plus1,
-        rws_checker.find_invalid_well_known, 
+        #rws_checker.find_invalid_well_known, # This check is disabled for now as we didn't publish the files yet
         rws_checker.find_invalid_alias_eSLDs, 
         rws_checker.find_robots_tag, 
         rws_checker.find_ads_txt, 

related_website_sets.JSON

@@ -1,5 +1,36 @@
 {
   "sets": [
+      {
+        "contact": "[email protected]",
+        "primary": "https://rakuten.co.jp",
+        "associatedSites": [
+          "https://rakuten-card.co.jp",
+          "https://rakuten-sec.co.jp",
+          "https://rakuten-bank.co.jp",
+          "https://rakuten-insurance.co.jp",
+          "https://fril.jp"
+        ],
+        "serviceSites": [
+          "https://rakuten.net"
+        ],
+        "rationaleBySite": {
+          "https://rakuten-card.co.jp": "Rakuten Card",
+          "https://rakuten-sec.co.jp": "Rakuten Securities",
+          "https://rakuten-bank.co.jp": "Rakuten Bank",
+          "https://rakuten-insurance.co.jp": "Rakuten Insurance",
+          "https://fril.jp": "Rakuten Rakuma",
+          "https://r10s.jp": "CDN"
+        },
+        "ccTLDs": {
+          "https://rakuten.co.jp": [
+              "https://rakuten.com",
+              "https://rakuten.ne.jp",
+              "https://rakuten.co.uk",
+              "https://rakuten.es",
+              "https://rakuten.fr"
+          ]
+        }
+    },
     {
       "contact": "[email protected]",
       "primary": "https://sackrace.ai",

requirements.txt

@@ -0,0 +1,3 @@
+publicsuffix2
+jsonschema
+requests