opendata-rfb 1.0.0__tar.gz

opendata_rfb-1.0.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 guilhermegor
+
+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.

opendata_rfb-1.0.0/PKG-INFO

@@ -0,0 +1,263 @@
+Metadata-Version: 2.4
+Name: opendata-rfb
+Version: 1.0.0
+Summary: Typed pandas readers for the Receita Federal do Brasil (RFB) CNPJ open data
+License: MIT
+License-File: LICENSE
+Keywords: filings-rfb,python,library
+Author: guilhermegor
+Requires-Python: >=3.10,<4.0
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Classifier: Programming Language :: Python :: 3.15
+Classifier: Topic :: Software Development :: Libraries
+Provides-Extra: parquet
+Requires-Dist: beartype (>=0.22)
+Requires-Dist: defusedxml (>=0.7)
+Requires-Dist: numpy (>=1.22)
+Requires-Dist: openpyxl (>=3.1.0)
+Requires-Dist: pandas (>=2.1.0)
+Requires-Dist: pyarrow (>=15.0) ; extra == "parquet"
+Project-URL: Bug Reports, https://github.com/guilhermegor/filings-rfb/issues
+Project-URL: Documentation, https://guilhermegor.github.io/filings-rfb/
+Project-URL: Homepage, https://guilhermegor.github.io/filings-rfb/
+Project-URL: Repository, https://github.com/guilhermegor/filings-rfb
+Project-URL: Source, https://github.com/guilhermegor/filings-rfb
+Description-Content-Type: text/markdown
+
+<!-- readme-archetype: library -->
+# filings-rfb
+
+<p align="center"><img src="https://raw.githubusercontent.com/guilhermegor/filings-rfb/main/assets/logo.png" width="200" alt="Receita Federal emblem"></p>
+
+[![Project Status: Active](https://www.repostatus.org/badges/latest/active.svg)](https://www.repostatus.org/#active)
+![Python Version](https://img.shields.io/badge/python-3.10%2B-blue.svg)
+[![PyPI Version](https://img.shields.io/pypi/v/filings-rfb)](https://pypi.org/project/filings-rfb/)
+[![Docs](https://img.shields.io/badge/docs-mkdocs-blue)](https://guilhermegor.github.io/filings-rfb/)
+[![Linting](https://img.shields.io/badge/linting-ruff_%7C_codespell-blue)](https://github.com/astral-sh/ruff)
+[![Type-checked: mypy](https://img.shields.io/badge/type--checked-mypy-blue)](https://mypy-lang.org/)
+![Test Coverage](https://raw.githubusercontent.com/guilhermegor/filings-rfb/main/coverage.svg)
+![License](https://img.shields.io/badge/license-MIT-green.svg)
+![Open Issues](https://img.shields.io/github/issues/guilhermegor/filings-rfb)
+![Contributions Welcome](https://img.shields.io/badge/contributions-welcome-darkgreen.svg)
+
+<!-- slug: overview -->
+## Overview
+
+`filings-rfb` reads the Receita Federal do Brasil (RFB) **CNPJ open data** (the company registry)
+into typed pandas DataFrames. It covers every dataset the RFB publishes:
+
+| Dataset | Reader | Content |
+|---------|--------|---------|
+| Empresas | `read_companies` | Legal entities (basic CNPJ, name, legal nature, share capital) |
+| Estabelecimentos | `read_establishments` | Establishments, with the full 14-character CNPJ and its validity |
+| Socios | `read_partners` | Partners and representatives (CPFs stay masked) |
+| Simples | `read_simples` | Simples Nacional and MEI options |
+| Cnaes, Motivos, Municipios, Naturezas, Paises, Qualificacoes | `read_lookup` | Code lookup tables |
+
+**Data source and cadence.** The data comes from the RFB's public share
+(`arquivos.receitafederal.gov.br`), which publishes one folder per reference month (`YYYY-MM`),
+refreshed monthly. A reader takes the month as its argument; a month the share does not publish
+raises an error rather than falling back to another one.
+
+⚠️ **Size.** The archives are large and are never held in memory: each reader streams every ZIP
+to disk and yields typed chunks. `Estabelecimentos` is the heaviest (ten parts, up to 2.3 GB
+each compressed) and `Simples.zip` inflates to ~3.2 GB. Plan for disk space and a long first
+run; pass `path_workdir=` to keep the ZIPs so a rerun resumes instead of downloading again.
+
+<!-- slug: documentation -->
+## Documentation
+
+The full documentation is published at <https://guilhermegor.github.io/filings-rfb/>:
+
+- [Usage](https://guilhermegor.github.io/filings-rfb/latest/usage/): install, readers, basics
+- [Examples](https://guilhermegor.github.io/filings-rfb/latest/examples/): task-oriented recipes
+- [API Reference](https://guilhermegor.github.io/filings-rfb/latest/api/): every public function
+- [FAQ](https://guilhermegor.github.io/filings-rfb/latest/faq/): common questions and troubleshooting
+- [Changelog](https://guilhermegor.github.io/filings-rfb/latest/changelog/): release history
+
+To serve it locally: `bash bin/poe_exec.sh docs_serve` (runs the project venv's `poe`, no activation needed).
+
+<!-- slug: getting-started -->
+## Getting Started
+
+Python 3.10+ is the only prerequisite.
+
+<!-- slug: install -->
+### Install
+
+```bash
+pip install filings-rfb
+pip install 'filings-rfb[parquet]'   # optional: Parquet export (pulls in pyarrow)
+```
+
+Or with Poetry:
+
+```bash
+poetry add filings-rfb
+```
+
+To work on the library itself, see [CONTRIBUTING.md](CONTRIBUTING.md).
+
+<!-- slug: usage -->
+### Usage
+
+Every dataset reader (`read_companies`, `read_establishments`, `read_partners`,
+`read_simples`) takes a reference month (`YYYY-MM`) and yields chunks of `int_chunk_rows` rows
+(default 500,000), so memory stays flat. `read_lookup` is the exception: it takes
+`str_table, path_zip, str_url, str_etag` and returns a single DataFrame, since each lookup table
+is small. Every row carries provenance columns (`url`,
+`updated_at`, `source_key`, `package_version`, `ingestion_run_id`, `content_hash`,
+`source_etag`).
+
+**Empresas.** `capital_social` is an exact `Decimal`, never a float.
+
+```python
+from filings_rfb import read_companies
+
+for df_chunk in read_companies("2026-10"):
+    ...
+```
+
+**Estabelecimentos.** Adds the full `cnpj_completo` and its validity flag `cnpj_valido`
+(alphanumeric-aware).
+
+```python
+from filings_rfb import read_establishments
+
+for df_chunk in read_establishments("2026-10"):
+    ...
+```
+
+**Socios.** Masked CPFs (`***240659**`) are kept verbatim, never unmasked; `***000000**` as
+representative document becomes null.
+
+```python
+from filings_rfb import read_partners
+
+for df_chunk in read_partners("2026-10"):
+    ...
+```
+
+**Simples.** Booleans and real dates, with the RFB's `00000000` read as null.
+
+```python
+from filings_rfb import read_simples
+
+for df_chunk in read_simples("2026-10"):
+    ...
+```
+
+**Lookups.** `read_lookup` reads one downloaded lookup ZIP (one of `CNPJ_LOOKUP_NAMES`).
+
+```python
+from pathlib import Path
+
+from filings_rfb import read_lookup
+from filings_rfb._internal.utils.stream_downloader import download_file_streaming
+from filings_rfb.ingestion.cnpj._share import file_url, latest_reference_month
+
+str_url = file_url(latest_reference_month(), "Cnaes.zip")
+path_zip, str_etag = download_file_streaming(str_url, Path("data/raw/Cnaes.zip"))
+df_cnaes = read_lookup("Cnaes", path_zip, str_url, str_etag)
+```
+
+**Parquet.** `export_companies_parquet("2026-10", path)` writes `Empresas` to one Parquet file
+for lazy querying (DuckDB, Polars `scan_parquet`); it needs the `parquet` extra.
+
+⚠️ Do not read these files with Polars directly: it silently misparses the `.zip` and corrupts
+latin-1 text.
+
+<!-- slug: project-structure -->
+## Project Structure
+
+```text
+filings-rfb/
+├── .github/              workflows, CODEOWNERS, PR template
+├── assets/               logo
+├── bin/                  gate scripts and helpers
+├── docs/                 published documentation (mkdocs)
+├── src/filings_rfb/
+│   ├── __init__.py       the public API (__all__)
+│   ├── ingestion/cnpj/   one reader per RFB dataset
+│   └── _internal/        private: contracts, utils, ports
+├── tests/
+│   ├── unit/
+│   └── integration/
+├── pyproject.toml
+└── poe_tasks.toml        task runner entry points
+```
+
+<!-- slug: development -->
+## Development
+
+```bash
+git clone https://github.com/guilhermegor/filings-rfb.git
+cd filings-rfb
+bash bin/venv.sh                           # bootstrap: Poetry venv and all deps (poe included)
+bash bin/precommit.sh                      # install the git hooks
+bash bin/poe_exec.sh unit_tests            # unit suite
+bash bin/poe_exec.sh integration_tests     # integration suite
+bash bin/poe_exec.sh lint                  # ruff, codespell and the structure gates
+bash bin/poe_exec.sh docs_serve            # serve the docs locally
+```
+
+<!-- slug: public-api -->
+## Public API
+
+The public surface is whatever the package `__init__.py` lists in `__all__`; everything
+under `_internal/` is private.
+
+- `read_companies(str_month, int_chunk_rows=500_000, path_workdir=None)`: `Empresas` chunks.
+- `read_establishments(...)`: `Estabelecimentos` chunks, same signature.
+- `read_partners(...)`: `Socios` chunks, same signature.
+- `read_simples(...)`: `Simples` chunks, same signature.
+- `export_companies_parquet(str_month, path_dest, int_chunk_rows=500_000, path_workdir=None)`:
+  `Empresas` to one Parquet file (needs the `parquet` extra).
+- `read_lookup(str_table, path_zip, str_url, str_etag)`: one of the six lookup tables
+  (`CNPJ_LOOKUP_NAMES`) as a typed DataFrame.
+- `CNPJ_LOOKUP_NAMES`, `__version__`.
+
+<!-- slug: publishing -->
+## Publishing
+
+Releases go out from the release workflows under `.github/workflows/` through PyPI trusted
+publishing (OIDC); the git tag is the version.
+
+<!-- slug: contributing -->
+## Contributing
+
+See [CONTRIBUTING.md](CONTRIBUTING.md) for the branch, commit and review rules.
+
+<!-- slug: license -->
+## License
+
+This project is licensed under MIT; see [LICENSE](LICENSE).
+
+<!-- slug: authors -->
+## Authors
+
+- guilhermegor — [GitHub](https://github.com/guilhermegor) | [LinkedIn](https://www.linkedin.com/in/guilhermegor)
+
+<!-- slug: useful-links -->
+## Useful Links
+
+- [Documentation](https://guilhermegor.github.io/filings-rfb/)
+- [PyPI](https://pypi.org/project/filings-rfb/)
+- [GitHub Repository](https://github.com/guilhermegor/filings-rfb)
+- [Issue Tracker](https://github.com/guilhermegor/filings-rfb/issues)
+
+---
+
+<sub>Generated from the lib-minimal template via [BlueprintX](https://github.com/guilhermegor/blueprintx).
+Unofficial, community library. Not affiliated with or endorsed by the Receita Federal do Brasil;
+the emblem is theirs.</sub>
+

opendata_rfb-1.0.0/README.md

@@ -0,0 +1,227 @@
+<!-- readme-archetype: library -->
+# filings-rfb
+
+<p align="center"><img src="https://raw.githubusercontent.com/guilhermegor/filings-rfb/main/assets/logo.png" width="200" alt="Receita Federal emblem"></p>
+
+[![Project Status: Active](https://www.repostatus.org/badges/latest/active.svg)](https://www.repostatus.org/#active)
+![Python Version](https://img.shields.io/badge/python-3.10%2B-blue.svg)
+[![PyPI Version](https://img.shields.io/pypi/v/filings-rfb)](https://pypi.org/project/filings-rfb/)
+[![Docs](https://img.shields.io/badge/docs-mkdocs-blue)](https://guilhermegor.github.io/filings-rfb/)
+[![Linting](https://img.shields.io/badge/linting-ruff_%7C_codespell-blue)](https://github.com/astral-sh/ruff)
+[![Type-checked: mypy](https://img.shields.io/badge/type--checked-mypy-blue)](https://mypy-lang.org/)
+![Test Coverage](https://raw.githubusercontent.com/guilhermegor/filings-rfb/main/coverage.svg)
+![License](https://img.shields.io/badge/license-MIT-green.svg)
+![Open Issues](https://img.shields.io/github/issues/guilhermegor/filings-rfb)
+![Contributions Welcome](https://img.shields.io/badge/contributions-welcome-darkgreen.svg)
+
+<!-- slug: overview -->
+## Overview
+
+`filings-rfb` reads the Receita Federal do Brasil (RFB) **CNPJ open data** (the company registry)
+into typed pandas DataFrames. It covers every dataset the RFB publishes:
+
+| Dataset | Reader | Content |
+|---------|--------|---------|
+| Empresas | `read_companies` | Legal entities (basic CNPJ, name, legal nature, share capital) |
+| Estabelecimentos | `read_establishments` | Establishments, with the full 14-character CNPJ and its validity |
+| Socios | `read_partners` | Partners and representatives (CPFs stay masked) |
+| Simples | `read_simples` | Simples Nacional and MEI options |
+| Cnaes, Motivos, Municipios, Naturezas, Paises, Qualificacoes | `read_lookup` | Code lookup tables |
+
+**Data source and cadence.** The data comes from the RFB's public share
+(`arquivos.receitafederal.gov.br`), which publishes one folder per reference month (`YYYY-MM`),
+refreshed monthly. A reader takes the month as its argument; a month the share does not publish
+raises an error rather than falling back to another one.
+
+⚠️ **Size.** The archives are large and are never held in memory: each reader streams every ZIP
+to disk and yields typed chunks. `Estabelecimentos` is the heaviest (ten parts, up to 2.3 GB
+each compressed) and `Simples.zip` inflates to ~3.2 GB. Plan for disk space and a long first
+run; pass `path_workdir=` to keep the ZIPs so a rerun resumes instead of downloading again.
+
+<!-- slug: documentation -->
+## Documentation
+
+The full documentation is published at <https://guilhermegor.github.io/filings-rfb/>:
+
+- [Usage](https://guilhermegor.github.io/filings-rfb/latest/usage/): install, readers, basics
+- [Examples](https://guilhermegor.github.io/filings-rfb/latest/examples/): task-oriented recipes
+- [API Reference](https://guilhermegor.github.io/filings-rfb/latest/api/): every public function
+- [FAQ](https://guilhermegor.github.io/filings-rfb/latest/faq/): common questions and troubleshooting
+- [Changelog](https://guilhermegor.github.io/filings-rfb/latest/changelog/): release history
+
+To serve it locally: `bash bin/poe_exec.sh docs_serve` (runs the project venv's `poe`, no activation needed).
+
+<!-- slug: getting-started -->
+## Getting Started
+
+Python 3.10+ is the only prerequisite.
+
+<!-- slug: install -->
+### Install
+
+```bash
+pip install filings-rfb
+pip install 'filings-rfb[parquet]'   # optional: Parquet export (pulls in pyarrow)
+```
+
+Or with Poetry:
+
+```bash
+poetry add filings-rfb
+```
+
+To work on the library itself, see [CONTRIBUTING.md](CONTRIBUTING.md).
+
+<!-- slug: usage -->
+### Usage
+
+Every dataset reader (`read_companies`, `read_establishments`, `read_partners`,
+`read_simples`) takes a reference month (`YYYY-MM`) and yields chunks of `int_chunk_rows` rows
+(default 500,000), so memory stays flat. `read_lookup` is the exception: it takes
+`str_table, path_zip, str_url, str_etag` and returns a single DataFrame, since each lookup table
+is small. Every row carries provenance columns (`url`,
+`updated_at`, `source_key`, `package_version`, `ingestion_run_id`, `content_hash`,
+`source_etag`).
+
+**Empresas.** `capital_social` is an exact `Decimal`, never a float.
+
+```python
+from filings_rfb import read_companies
+
+for df_chunk in read_companies("2026-10"):
+    ...
+```
+
+**Estabelecimentos.** Adds the full `cnpj_completo` and its validity flag `cnpj_valido`
+(alphanumeric-aware).
+
+```python
+from filings_rfb import read_establishments
+
+for df_chunk in read_establishments("2026-10"):
+    ...
+```
+
+**Socios.** Masked CPFs (`***240659**`) are kept verbatim, never unmasked; `***000000**` as
+representative document becomes null.
+
+```python
+from filings_rfb import read_partners
+
+for df_chunk in read_partners("2026-10"):
+    ...
+```
+
+**Simples.** Booleans and real dates, with the RFB's `00000000` read as null.
+
+```python
+from filings_rfb import read_simples
+
+for df_chunk in read_simples("2026-10"):
+    ...
+```
+
+**Lookups.** `read_lookup` reads one downloaded lookup ZIP (one of `CNPJ_LOOKUP_NAMES`).
+
+```python
+from pathlib import Path
+
+from filings_rfb import read_lookup
+from filings_rfb._internal.utils.stream_downloader import download_file_streaming
+from filings_rfb.ingestion.cnpj._share import file_url, latest_reference_month
+
+str_url = file_url(latest_reference_month(), "Cnaes.zip")
+path_zip, str_etag = download_file_streaming(str_url, Path("data/raw/Cnaes.zip"))
+df_cnaes = read_lookup("Cnaes", path_zip, str_url, str_etag)
+```
+
+**Parquet.** `export_companies_parquet("2026-10", path)` writes `Empresas` to one Parquet file
+for lazy querying (DuckDB, Polars `scan_parquet`); it needs the `parquet` extra.
+
+⚠️ Do not read these files with Polars directly: it silently misparses the `.zip` and corrupts
+latin-1 text.
+
+<!-- slug: project-structure -->
+## Project Structure
+
+```text
+filings-rfb/
+├── .github/              workflows, CODEOWNERS, PR template
+├── assets/               logo
+├── bin/                  gate scripts and helpers
+├── docs/                 published documentation (mkdocs)
+├── src/filings_rfb/
+│   ├── __init__.py       the public API (__all__)
+│   ├── ingestion/cnpj/   one reader per RFB dataset
+│   └── _internal/        private: contracts, utils, ports
+├── tests/
+│   ├── unit/
+│   └── integration/
+├── pyproject.toml
+└── poe_tasks.toml        task runner entry points
+```
+
+<!-- slug: development -->
+## Development
+
+```bash
+git clone https://github.com/guilhermegor/filings-rfb.git
+cd filings-rfb
+bash bin/venv.sh                           # bootstrap: Poetry venv and all deps (poe included)
+bash bin/precommit.sh                      # install the git hooks
+bash bin/poe_exec.sh unit_tests            # unit suite
+bash bin/poe_exec.sh integration_tests     # integration suite
+bash bin/poe_exec.sh lint                  # ruff, codespell and the structure gates
+bash bin/poe_exec.sh docs_serve            # serve the docs locally
+```
+
+<!-- slug: public-api -->
+## Public API
+
+The public surface is whatever the package `__init__.py` lists in `__all__`; everything
+under `_internal/` is private.
+
+- `read_companies(str_month, int_chunk_rows=500_000, path_workdir=None)`: `Empresas` chunks.
+- `read_establishments(...)`: `Estabelecimentos` chunks, same signature.
+- `read_partners(...)`: `Socios` chunks, same signature.
+- `read_simples(...)`: `Simples` chunks, same signature.
+- `export_companies_parquet(str_month, path_dest, int_chunk_rows=500_000, path_workdir=None)`:
+  `Empresas` to one Parquet file (needs the `parquet` extra).
+- `read_lookup(str_table, path_zip, str_url, str_etag)`: one of the six lookup tables
+  (`CNPJ_LOOKUP_NAMES`) as a typed DataFrame.
+- `CNPJ_LOOKUP_NAMES`, `__version__`.
+
+<!-- slug: publishing -->
+## Publishing
+
+Releases go out from the release workflows under `.github/workflows/` through PyPI trusted
+publishing (OIDC); the git tag is the version.
+
+<!-- slug: contributing -->
+## Contributing
+
+See [CONTRIBUTING.md](CONTRIBUTING.md) for the branch, commit and review rules.
+
+<!-- slug: license -->
+## License
+
+This project is licensed under MIT; see [LICENSE](LICENSE).
+
+<!-- slug: authors -->
+## Authors
+
+- guilhermegor — [GitHub](https://github.com/guilhermegor) | [LinkedIn](https://www.linkedin.com/in/guilhermegor)
+
+<!-- slug: useful-links -->
+## Useful Links
+
+- [Documentation](https://guilhermegor.github.io/filings-rfb/)
+- [PyPI](https://pypi.org/project/filings-rfb/)
+- [GitHub Repository](https://github.com/guilhermegor/filings-rfb)
+- [Issue Tracker](https://github.com/guilhermegor/filings-rfb/issues)
+
+---
+
+<sub>Generated from the lib-minimal template via [BlueprintX](https://github.com/guilhermegor/blueprintx).
+Unofficial, community library. Not affiliated with or endorsed by the Receita Federal do Brasil;
+the emblem is theirs.</sub>

opendata_rfb-1.0.0/pyproject.toml

@@ -0,0 +1,86 @@
+[tool.poetry]
+name = "opendata-rfb"
+version = "1.0.0"
+description = "Typed pandas readers for the Receita Federal do Brasil (RFB) CNPJ open data"
+authors = ["guilhermegor"]
+readme = "README.md"
+license = "MIT"
+homepage = "https://guilhermegor.github.io/filings-rfb/"
+documentation = "https://guilhermegor.github.io/filings-rfb/"
+repository = "https://github.com/guilhermegor/filings-rfb"
+keywords = ["filings-rfb", "python", "library"]
+packages = [{ include = "filings_rfb", from = "src" }]
+exclude = ["src/**/CLAUDE.md"]
+package-mode = true
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Operating System :: OS Independent",
+    "License :: OSI Approved :: MIT License",
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Topic :: Software Development :: Libraries",
+]
+
+[tool.poetry.urls]
+"Bug Reports" = "https://github.com/guilhermegor/filings-rfb/issues"
+"Source" = "https://github.com/guilhermegor/filings-rfb"
+"Documentation" = "https://guilhermegor.github.io/filings-rfb/"
+
+[tool.poetry.dependencies]
+python = ">=3.10,<4.0"
+beartype = ">=0.22"
+pandas = ">=2.1.0"
+numpy = ">=1.22"
+openpyxl = ">=3.1.0"
+defusedxml = ">=0.7"
+pyarrow = { version = ">=15.0", optional = true }
+
+[tool.poetry.extras]
+parquet = ["pyarrow"]
+
+[tool.poetry.group.dev.dependencies]
+poethepoet = ">=0.35"
+pre-commit = ">=4.1.0"
+pretty-errors = ">=1.2.25"
+commitizen = ">=4.4.1"
+build = ">=1.2.2"
+twine = ">=6.1.0"
+ruff = ">=0.11.13,<0.12"
+codespell = ">=2.4.1"
+pydocstyle = ">=6.3.0"
+pytest = ">=8.0.0"
+pytest-cov = ">=6.0.0"
+pytest-randomly = ">=3.15.0"
+coverage = ">=7.6.0"
+genbadge = {extras = ["coverage"], version = ">=1.1.0"}
+mypy = ">=1.8.0"
+sqlfluff = ">=3.0.0"
+yamllint = ">=1.35.0"
+shfmt-py = ">=3.7.0"
+shellcheck-py = ">=0.10.0"
+deptry = ">=0.20"
+tomli = { version = ">=2.0.1", python = "<3.11" }
+pytest-mock = "^3.17.0"
+pyarrow = ">=15.0"
+
+[tool.poetry.group.docs.dependencies]
+mkdocs = ">=1.6.0"
+mkdocs-material = ">=9.5.0"
+pymdown-extensions = ">=10.0"
+mike = ">=2.1.0"
+
+[tool.deptry.per_rule_ignores]
+DEP002 = ["openpyxl"]
+
+[tool.poetry-dynamic-versioning]
+# Published version is derived from the latest git tag matching `v$version` (e.g. v0.2.0). On
+# an exact tag the build is clean (0.2.0); off-tag builds get a PEP 440 dev version. The CI
+# release workflows pass POETRY_DYNAMIC_VERSIONING_BYPASS to build a specific version. Needs
+# `python -m build` (a PEP 517 frontend), not `poetry build` (which ignores the backend).
+enable = false
+vcs = "git"
+style = "pep440"
+
+[build-system]
+requires = ["poetry-core>=1.7.0", "poetry-dynamic-versioning>=1.4.0,<2.0.0"]
+build-backend = "poetry_dynamic_versioning.backend"

opendata_rfb-1.0.0/src/filings_rfb/__init__.py

@@ -0,0 +1,27 @@
+"""filings-rfb package."""
+
+from importlib.metadata import PackageNotFoundError, version
+
+from .ingestion.cnpj.companies import export_companies_parquet, read_companies
+from .ingestion.cnpj.establishments import read_establishments
+from .ingestion.cnpj.lookups import CNPJ_LOOKUP_NAMES, read_lookup
+from .ingestion.cnpj.partners import read_partners
+from .ingestion.cnpj.simples import read_simples
+
+
+try:
+    __version__ = version("opendata-rfb")
+except PackageNotFoundError:  # pragma: no cover - source tree without an installed dist
+    __version__ = "0.0.0"
+
+
+__all__ = [
+    "CNPJ_LOOKUP_NAMES",
+    "__version__",
+    "export_companies_parquet",
+    "read_companies",
+    "read_establishments",
+    "read_lookup",
+    "read_partners",
+    "read_simples",
+]

opendata_rfb-1.0.0/src/filings_rfb/_internal/__init__.py

@@ -0,0 +1 @@
+"""Private internals of the filings_rfb package (not a public API)."""

opendata_rfb-1.0.0/src/filings_rfb/_internal/config/__init__.py

@@ -0,0 +1 @@
+"""Private configuration internals (data contracts) of filings_rfb."""