Initial (#1)

* initial

* add TableArch class and add tests

* fix type hint

* fix type hint

* add more methods

* env: fix typo

* remove link_directory_metadata.py

* update README.md

* update

* update

* add get_architecture_table_from_api

* add new scripts

* add more tests

* add verbose param to upload_columns

* add authors

* create_yaml_file strip name and description

.github/workflows/ci.yaml

@@ -0,0 +1,41 @@
+---
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+    branches: [main]
+
+jobs:
+  test:
+    name: main
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Setup poetry
+        run: pipx install poetry
+
+      - name: Setup python
+        uses: actions/setup-python@v4
+        with:
+          cache: poetry
+          architecture: x64
+          python-version: '3.9'
+
+      - name: Poetry check
+        run: poetry check
+
+      - name: Install requirements
+        run: poetry install
+
+      - name: Test
+        run: poetry run pytest
+
+      - name: Ruff check
+        run: poetry run ruff check .
+
+      - name: Ruff format check
+        run: poetry run ruff format --check --diff

.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/

CONTRIBUTING.md

@@ -0,0 +1,51 @@
+# Contribuindo
+
+## Setup
+
+Requisitos:
+
+- [pyenv](https://github.com/pyenv/pyenv): Recomendado
+- [poetry](https://python-poetry.org/)
+
+1. Clone o repositório e entre no diretório clonado
+
+```sh
+git clone https://github.com/basedosdados/databasers-utils
+```
+
+1. Ative a versão 3.9 do Python
+
+```sh
+pyenv shell 3.9
+```
+
+2. Crie a env ou ativa se já existir
+
+```sh
+poetry shell
+```
+
+3. Instale as dependências
+
+```sh
+poetry install --with dev --no-root
+```
+
+## Code Style
+
+Após finalizar as alterações no código execute:
+
+```sh
+poetry run lint
+```
+
+> [!IMPORTANT]
+> O command vai executar o formatador `ruff format .` e o linter `ruff check --fix .`. Algumas regras do linter requer intervenção manual para ser resolvido
+
+## Testes
+
+Para rodar os testes:
+
+```sh
+poetry run pytest
+```

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Base dos Dados
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -1 +1,76 @@
 # databasers-utils
+
+Pacote para uso da equipe de dados na Base dos Dados.
+
+- [CONTRIBUTING.md](./CONTRIBUTING.md)
+
+## Instalação
+
+```sh
+poetry add git+https://github.com/basedosdados/databasers-utils.git
+```
+
+## Setup
+
+### Credenciais
+
+Para fazer o upload de colunas usando a arquitetura você deve configurar suas
+credenciais.
+
+#### Linux/WSL
+
+Adicione no seu `.bashrc` ou `.zshrc`
+
+```sh
+export BD_DJANGO_EMAIL="seuemail@basedosdados.org"
+export BD_DJANGO_PASSWORD="password"
+```
+
+#### Windows
+
+- Em Pesquisar, procure e selecione: Sistema (Painel de Controle)
+- Clique no link Configurações avançadas do sistema.
+- Clique em Variáveis de Ambiente. 
+- Na seção 'Variáveis do Sistema' clique em 'Novo' e insira `BD_DJANGO_EMAIL` como nome da variável e o seu email como valor. Faça o mesmo para `BD_DJANGO_PASSWORD`.
+- Clique em OK. Feche todas as janelas restantes clicando em OK.
+
+### Uso
+
+```python
+from databasers_utils import (
+    TableArchitecture,
+    copy_models_from_dev_to_prod,
+    get_architecture_table_from_api,
+)
+
+arch = TableArchitecture(
+    dataset_id="br_ibge_pib",
+    tables={
+        "uf": "https://docs.google.com/spreadsheets/d/12F5NzhOYlN_bi9flLBEdXDWpa5iVakSP4EKm9UoyWuo/edit?usp=drive_link",
+        "gini": "https://docs.google.com/spreadsheets/d/1K1svie4Gyqe6NnRjBgJbapU5sTsLqXWTQUmTRVIRwQc/edit?usp=drive_link",
+    },
+)
+
+# Retorna um dict[str, pd.DataFrame], cada chave o id da tabela e o dataframe
+# da arquitetura
+arch.tables()
+
+# Cria o yaml file
+arch.create_yaml_file()
+
+# Cria os arquivos sql
+arch.create_sql_files()
+
+# Atualiza o dbt_project.yml
+arch.update_dbt_project()
+
+# Faz o upload das colunas para o DJango
+arch.upload_columns()
+
+# Copia os modelos em dev para prod
+copy_models_from_dev_to_prod(["br_ibge_ppm", "br_ibge_pam"])
+
+# Retorna um DataFrame da arquitetura obtida na API
+# Util para gerar arquitetura quando ela não está no Drive
+get_architecture_table_from_api("br_ms_sinasc", "microdados")
+```