Refactor script into python pypi package for easier reuse in pipelines

.gitignore

@@ -0,0 +1,4 @@
+.idea
+.venv
+.env
+dist

README.md

@@ -0,0 +1,22 @@
+# How to use
+This project can be run via:
+
+`poetry run create_report`
+
+provided the appropriate environment variables are set in a `.env` file.
+
+Alternatively, the project can also be built into a package and the package file installed in another machine:
+
+```
+poetry build
+# distribute package file to another machine
+pip install dist/create_report*.whl
+create_report
+```
+
+Another way, is to run directly from git using pipx. This is useful for usage in pipelines:
+
+```
+pipx run --spec git+https://<link to git repo> create_report
+```
+

env.sample

@@ -0,0 +1,31 @@
+REPORTING_SQL_SERVER=127.0.0.1
+REPORTING_SQL_PORT=3306
+REPORTING_SQL_DATABASE=myreportingdatabase
+REPORTING_SQL_USERNAME=
+REPORTING_SQL_PASSWORD=
+REPORTING_SQL_TABLENAME=auldata_lake
+
+AUDIT_MONGO_SERVER=127.0.0.1:27018
+AUDIT_MONGO_REPLICASET=rs4
+AUDIT_MONGO_USERNAME=
+AUDIT_MONGO_PASSWORD=
+AUDIT_MONGO_DATABASE=mydb
+AUDIT_MONGO_COLLECTION=myauditcollection
+
+ARC_MONGO_SERVER_A=127.0.0.1:27017
+ARC_MONGO_REPLICASET_A=rs0
+ARC_MONGO_SERVER_B=127.0.0.1:27017
+ARC_MONGO_REPLICASET_B=rs1
+ARC_MONGO_SERVER_C=127.0.0.1:27017
+ARC_MONGO_REPLICASET_C=rs2
+ARC_MONGO_USERNAME=
+ARC_MONGO_PASSWORD=
+ARC_MONGO_DATABASE=mydb
+ARC_MONGO_COLLECTION=mycollection
+ARC_MONGO_AUTH_MECHANISM=SCRAM-SHA-1
+ARC_MONGO_AUTH_SOURCE=admin
+ARC_MONGO_AUTH_DATABASE=admin
+ARC_MONGO_READ_PREFERENCE=secondary
+
+OFFER_NAME=MYOFFERNAME
+LOG_LEVEL=DEBUG

pyproject.toml

@@ -0,0 +1,53 @@
+[tool.poetry]
+name = "create_report"
+version = "0.1.0"
+description = ""
+authors = ["Kenneth Langga"]
+readme = "README.md"
+packages = [{ include = "create_report", from = "src" }]
+
+[tool.poetry.scripts]
+create_report = "create_report.cli:main"
+
+[tool.poetry.dependencies]
+python = "^3.11"
+pandas = "^2.0.3"
+pymongo = "^4.4.1"
+sqlalchemy = "^2.0.19"
+python-dotenv = "^1.0.0"
+python-dateutil = "^2.8.2"
+pymysql = "^1.1.0"
+
+[tool.poetry.group.dev.dependencies]
+black = "^23.7.0"
+ruff = "^0.0.282"
+
+[tool.poetry.group.test.dependencies]
+pytest = "^7.4.0"
+pytest-env = "^0.8.2"
+pytest-runner = "^6.0.0"
+
+[tool.ruff]
+select = ["ALL"]
+ignore = ["ERA001", "D", "S608"]
+fixable = ["E", "F", "I"]
+
+[tool.pytest.ini_options]
+pythonpath = ["src"]
+testpaths = [
+    "tests",
+]
+env = [
+    "ARC_MONGO_AUTH_MECHANISM=SCRAM-SHA-1",
+    "ARC_MONGO_AUTH_SOURCE=admin",
+    "ARC_MONGO_READ_PREFERENCE=secondary",
+    "REPORTING_SQL_SERVER=127.0.0.1",
+    "REPORTING_SQL_PORT=3306",
+    "REPORTING_SQL_DATABASE=testdb",
+    "REPORTING_SQL_USERNAME=testuser",
+    "REPORTING_SQL_PASSWORD=testpass",
+]
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"