Walidacja i weryfikacja danych z formularza/issue w pythonie

.github/ISSUE_TEMPLATE/nowa.yaml

@@ -85,6 +85,8 @@ body:
     id: kod_pocztowy
     attributes:
       label: Kod Pocztowy
+      description: Wprowadź kod pocztowy w formacie `00-000`
+      placeholder: 00-000
     validations:
       required: true
   - type: input
@@ -97,5 +99,7 @@ body:
     id: telefon
     attributes:
       label: Telefon kontaktowy dla kuriera
+      description: Wprowadź numer telefonu w formacie `000 000 000`
+      placeholder: 000 000 000
     validations:
-      required: true
+      required: true

.github/scripts/.gitignore

@@ -0,0 +1,168 @@
+# 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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.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/

.github/scripts/consts.py

@@ -0,0 +1,18 @@
+import enum
+
+
+class OrgSchemaIds(enum.StrEnum):
+    name = "nazwa"
+    www = "www"
+    krs = "krs"
+    slug = "nazwa_strony"
+    street = "ulica"
+    postal_code = "kod_pocztowy"
+    city = "miasto"
+    phone_number = "telefon"
+
+NEW_ORG_ISSUE_DEFAULT_TITLE = "[Nowa Organizacja]"
+NEW_ORG_SCHEMA_FILENAME = "nowa.yaml"
+
+
+ORG_SCHEMA_SLUG_FIELD = "adres"

.github/scripts/labels.py

@@ -0,0 +1,19 @@
+import enum
+
+from consts import OrgSchemaIds
+
+
+class Label(enum.StrEnum):
+    INVALID_KRS = "niepoprawny KRS"
+    INVALID_POSTAL_CODE = "niepoprawny kod pocztowy"
+    INVALID_PHONE = "niepoprawny numer telefonu"
+    INVALID_SLUG = "niepoprawna nazwa strony"
+    AUTO_VERIFIED = "zweryfikowana automatycznie"
+
+
+INVALID_FIELD_TO_LABEL = {
+    OrgSchemaIds.krs: Label.INVALID_KRS,
+    OrgSchemaIds.postal_code: Label.INVALID_POSTAL_CODE,
+    OrgSchemaIds.phone_number: Label.INVALID_PHONE,
+    OrgSchemaIds.slug: Label.INVALID_SLUG,
+}

.github/scripts/parsers.py

@@ -0,0 +1,26 @@
+from typing import Any
+
+import yaml
+
+
+class FormDataParser:
+
+    def __init__(self, form_data: dict[str, Any], form_schema_filename: str):
+        self.form_data = form_data
+        self.form_schema_filename = form_schema_filename
+        self.form_schema = self.get_form_schema(form_schema_filename)
+
+    @staticmethod
+    def get_form_schema(template_filename):
+        with open(f"../ISSUE_TEMPLATE/{template_filename}") as f:
+            return yaml.safe_load(f)
+
+    def get_label(self, identifier: str) -> str | None:
+        for field in self.form_schema.get("body", []):
+            if "id" in field and field["id"] == identifier:
+                return field["attributes"]["label"]
+        return None
+
+    def get(self, identifier: str) -> str | None:
+        label = self.get_label(identifier)
+        return self.form_data.get(label, "")

.github/scripts/process.py

@@ -0,0 +1,64 @@
+import json
+import logging
+import os
+
+from github import Auth, Github, Issue
+
+from consts import OrgSchemaIds, NEW_ORG_ISSUE_DEFAULT_TITLE, NEW_ORG_SCHEMA_FILENAME
+from labels import Label
+from parsers import FormDataParser
+from pullers import OrgDataPuller
+from utils import has_label
+from validators import OrgValidator
+
+logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
+logger = logging.getLogger(__file__)
+
+GITHUB_TOKEN = os.getenv("GITHUB_TOKEN")
+GITHUB_REPOSITORY = os.getenv("GITHUB_REPOSITORY")
+
+auth = Auth.Token(GITHUB_TOKEN)
+g = Github(auth=auth)
+repo = g.get_repo(GITHUB_REPOSITORY)
+
+
+def process_new_org_issue(issue: Issue, data: FormDataParser):
+    if has_label(issue, Label.AUTO_VERIFIED):
+        issue.remove_from_labels(Label.AUTO_VERIFIED)
+
+    validator = OrgValidator(data, issue)
+    if not validator.validate():
+        logger.error("Validation failed")
+        return
+
+    if not (org := OrgDataPuller.get_org_by_krs(issue, data.get(OrgSchemaIds.krs))):
+        logger.error("KRS db validation failed")
+        return
+
+    # Update issue title
+    if issue.title == NEW_ORG_ISSUE_DEFAULT_TITLE:
+        logger.info("Updating issue title")
+        issue.edit(title=f"{NEW_ORG_ISSUE_DEFAULT_TITLE} {org.name or data.get(OrgSchemaIds.name)}")
+
+    if not has_label(issue, Label.AUTO_VERIFIED):
+        logger.info("Adding auto-verified label")
+        issue.create_comment(f"@{issue.user.login}, dziękujemy za podanie informacji. "
+                             f"Przyjęliśmy zgłoszenie dodania nowej organizacji. "
+                             f"Wkrótce skontaktujemy się celem weryfikacji zgłoszenia.")
+        issue.add_to_labels(Label.AUTO_VERIFIED)
+
+
+def main():
+    github_form_json = os.getenv("GITHUB_FORM_JSON")
+    github_issue_number = int(os.getenv("GITHUB_ISSUE_NUMBER"))
+
+    issue = repo.get_issue(github_issue_number)
+    data = FormDataParser(
+        json.loads(github_form_json),
+        NEW_ORG_SCHEMA_FILENAME
+    )
+    process_new_org_issue(issue, data)
+
+
+if __name__ == "__main__":
+    main()

.github/scripts/pullers.py

@@ -0,0 +1,43 @@
+import re
+from typing import Optional
+
+import requests
+from github import Issue
+
+from utils import has_label
+from labels import Label
+
+
+class OrgDataPuller:
+
+    def __init__(self, krs: str):
+        self.krs = krs
+        self.data = self.pull_data()
+
+    def pull_data(self) -> dict | None:
+        response = requests.get(f"https://api-krs.ms.gov.pl/api/krs/OdpisAktualny/{self.krs}?rejestr=S&format=json")
+        if response.status_code == 200:
+            return response.json()
+        else:
+            raise requests.HTTPError(f"Failed to fetch data for KRS {self.krs}")
+
+    @property
+    def name(self):
+        return self.data.get("odpis", {}).get("dane", {}).get("dzial1", {}).get("danePodmiotu", {}).get("nazwa")
+
+    @staticmethod
+    def get_org_by_krs(issue: Issue, krs: str) -> Optional["OrgDataPuller"]:
+
+        # Downloading official org data
+        try:
+            org = OrgDataPuller(krs)
+        except requests.HTTPError as e:
+            issue.create_comment(f"Nie udało się pobrać danych o organizacji z KRS. "
+                                 f"Proszę sprawdzić, czy podany numer jest poprawny")
+            issue.add_to_labels(Label.INVALID_KRS)
+            return
+
+        if has_label(issue, Label.INVALID_KRS):
+            issue.remove_from_labels(Label.INVALID_KRS)
+
+        return org

.github/scripts/requirements.txt

@@ -0,0 +1,3 @@
+PyGithub==2.5.0
+PyYAML==6.0.2
+requests==2.32.3

.github/scripts/utils.py

@@ -0,0 +1,5 @@
+from labels import Label
+
+
+def has_label(issue, label: Label):
+    return any([l for l in issue.labels if l.name == label])