bigdata-corp-api 0.16__tar.gz → 0.18.3__tar.gz

bigdata_corp_api-0.18.3/PKG-INFO

@@ -0,0 +1,157 @@
+Metadata-Version: 2.4
+Name: bigdata-corp-api
+Version: 0.18.3
+Summary: Python API to facilitate interaction with BigDataCorp end-points
+License: BSD-3-Clause License
+License-File: LICENSE
+Author: Murabei Data Science
+Author-email: a.baceti@murabei.com
+Requires-Python: >=3.6
+Classifier: Programming Language :: Python :: 3
+Classifier: Operating System :: OS Independent
+Requires-Dist: requests
+Project-URL: Homepage, https://github.com/Murabei-OpenSource-Codes/bigdata-corp-api
+Description-Content-Type: text/markdown
+
+# bigdata-corp-api
+
+Python client library for BigDataCorp API endpoints used in Murabei data
+enrichment and due-diligence workflows.
+
+## Objective and motivation
+
+This package wraps BigDataCorp REST endpoints behind a typed Python API with
+domain-specific exceptions and dataset discovery helpers.
+
+### Why this exists
+
+Murabei services query BigDataCorp for CPF, CNPJ, and process data during
+enrichment pipelines. A shared client avoids duplicating authentication,
+retry logic, and error mapping across workers and applications.
+
+### How it is used
+
+Install the package in workers or apps that call BigDataCorp during batch or
+on-demand enrichment. Instantiate `BigDataCorpAPI` with an auth token, then
+call dataset list or fetch methods.
+
+### Scope
+
+Owns HTTP communication, dataset constants, exception types, usage
+reporting, and certificate file downloads from on-demand responses.
+Credential storage, orchestration, and downstream persistence live in
+consuming services.
+
+## Install
+
+From PyPI (when published):
+
+```bash
+pip install bigdata-corp-api
+```
+
+From a built wheel or sdist:
+
+```bash
+pip install dist/bigdata_corp_api-*.whl
+```
+
+From source (requires Poetry):
+
+```bash
+pip install poetry
+export VERSION=$(grep -E '^VERSION=' VERSION | cut -d'=' -f2-)
+sed -e 's#{VERSION}#'"${VERSION}"'#g' pyproject_template.toml > pyproject.toml
+poetry build
+pip install dist/bigdata_corp_api-*.whl
+```
+
+## Quick start
+
+```python
+from bigdatacorp_api.data import BigDataCorpAPI
+
+api = BigDataCorpAPI(bigdata_auth_token="YOUR_TOKEN")
+
+# List available CPF datasets
+datasets = api.list_cpf_dataset()
+
+# Fetch one dataset
+result = api.get_cpf_dataset(
+    cpf="12345678901",
+    dataset="basic_data",
+)
+
+# Fetch multiple datasets
+batch = api.get_cpf_datasets(
+    cpf="12345678901",
+    datasets=["basic_data", "occupation_data"],
+)
+```
+
+CNPJ and process queries follow the same pattern via `list_cnpj_dataset`,
+`get_cnpj_dataset`, `list_process_dataset`, and `get_process_dataset`.
+
+Usage reporting for a date range:
+
+```python
+usage = api.get_usage(
+    initial_date="2025-01-01",
+    final_date="2025-01-31",
+)
+```
+
+Download a certificate file from an on-demand dataset response:
+
+```python
+cert_response = api.get_cpf_dataset(
+    cpf="12345678901",
+    dataset="ondemand_cert_debt_absence_by_state_person",
+)
+file_data = api.get_result_file(
+    dataset="ondemand_cert_debt_absence_by_state_person",
+    json_data=cert_response,
+)
+# file_data["file_type"] and file_data["file_content"]
+```
+
+## Configuration
+
+| Variable | Required | Description |
+|----------|----------|-------------|
+| `BIGDATA_AUTH_TOKEN` | Yes (for tests) | BigDataCorp API token passed to `BigDataCorpAPI` |
+| `TEST_CPF` | Tests only | Valid CPF used by integration tests |
+
+The token is supplied at construction time; this package does not read
+environment variables during normal API calls.
+
+## Development
+
+Build a release (bumps patch in `VERSION`, renders `pyproject.toml`, tags,
+and pushes):
+
+```bash
+./build.sh
+```
+
+Run tests (integration tests call the live API when env vars are set):
+
+```bash
+export BIGDATA_AUTH_TOKEN="your-token"
+export TEST_CPF="valid-cpf"
+python -m unittest discover -s src/bigdatacorp_api/tests
+```
+
+Lint with Ruff (configuration in `pyproject.toml`):
+
+```bash
+ruff check src/
+```
+
+CI on `main` builds from `VERSION` and `pyproject_template.toml`, then
+publishes to PyPI when `PYPI_API_TOKEN` is configured.
+
+## License
+
+BSD-3-Clause — see [LICENSE](LICENSE).
+

bigdata_corp_api-0.18.3/README.md

@@ -0,0 +1,141 @@
+# bigdata-corp-api
+
+Python client library for BigDataCorp API endpoints used in Murabei data
+enrichment and due-diligence workflows.
+
+## Objective and motivation
+
+This package wraps BigDataCorp REST endpoints behind a typed Python API with
+domain-specific exceptions and dataset discovery helpers.
+
+### Why this exists
+
+Murabei services query BigDataCorp for CPF, CNPJ, and process data during
+enrichment pipelines. A shared client avoids duplicating authentication,
+retry logic, and error mapping across workers and applications.
+
+### How it is used
+
+Install the package in workers or apps that call BigDataCorp during batch or
+on-demand enrichment. Instantiate `BigDataCorpAPI` with an auth token, then
+call dataset list or fetch methods.
+
+### Scope
+
+Owns HTTP communication, dataset constants, exception types, usage
+reporting, and certificate file downloads from on-demand responses.
+Credential storage, orchestration, and downstream persistence live in
+consuming services.
+
+## Install
+
+From PyPI (when published):
+
+```bash
+pip install bigdata-corp-api
+```
+
+From a built wheel or sdist:
+
+```bash
+pip install dist/bigdata_corp_api-*.whl
+```
+
+From source (requires Poetry):
+
+```bash
+pip install poetry
+export VERSION=$(grep -E '^VERSION=' VERSION | cut -d'=' -f2-)
+sed -e 's#{VERSION}#'"${VERSION}"'#g' pyproject_template.toml > pyproject.toml
+poetry build
+pip install dist/bigdata_corp_api-*.whl
+```
+
+## Quick start
+
+```python
+from bigdatacorp_api.data import BigDataCorpAPI
+
+api = BigDataCorpAPI(bigdata_auth_token="YOUR_TOKEN")
+
+# List available CPF datasets
+datasets = api.list_cpf_dataset()
+
+# Fetch one dataset
+result = api.get_cpf_dataset(
+    cpf="12345678901",
+    dataset="basic_data",
+)
+
+# Fetch multiple datasets
+batch = api.get_cpf_datasets(
+    cpf="12345678901",
+    datasets=["basic_data", "occupation_data"],
+)
+```
+
+CNPJ and process queries follow the same pattern via `list_cnpj_dataset`,
+`get_cnpj_dataset`, `list_process_dataset`, and `get_process_dataset`.
+
+Usage reporting for a date range:
+
+```python
+usage = api.get_usage(
+    initial_date="2025-01-01",
+    final_date="2025-01-31",
+)
+```
+
+Download a certificate file from an on-demand dataset response:
+
+```python
+cert_response = api.get_cpf_dataset(
+    cpf="12345678901",
+    dataset="ondemand_cert_debt_absence_by_state_person",
+)
+file_data = api.get_result_file(
+    dataset="ondemand_cert_debt_absence_by_state_person",
+    json_data=cert_response,
+)
+# file_data["file_type"] and file_data["file_content"]
+```
+
+## Configuration
+
+| Variable | Required | Description |
+|----------|----------|-------------|
+| `BIGDATA_AUTH_TOKEN` | Yes (for tests) | BigDataCorp API token passed to `BigDataCorpAPI` |
+| `TEST_CPF` | Tests only | Valid CPF used by integration tests |
+
+The token is supplied at construction time; this package does not read
+environment variables during normal API calls.
+
+## Development
+
+Build a release (bumps patch in `VERSION`, renders `pyproject.toml`, tags,
+and pushes):
+
+```bash
+./build.sh
+```
+
+Run tests (integration tests call the live API when env vars are set):
+
+```bash
+export BIGDATA_AUTH_TOKEN="your-token"
+export TEST_CPF="valid-cpf"
+python -m unittest discover -s src/bigdatacorp_api/tests
+```
+
+Lint with Ruff (configuration in `pyproject.toml`):
+
+```bash
+ruff check src/
+```
+
+CI on `main` builds from `VERSION` and `pyproject_template.toml`, then
+publishes to PyPI when `PYPI_API_TOKEN` is configured.
+
+## License
+
+BSD-3-Clause — see [LICENSE](LICENSE).

{bigdata_corp_api-0.16 → bigdata_corp_api-0.18.3}/pyproject.toml

@@ -1,19 +1,20 @@
 [project]
 name = "bigdata-corp-api"
-version = "0.16"
+version = "0.18.3"
 description = "Python API to facilitate interaction with BigDataCorp end-points"
 readme = "README.md"
 requires-python = ">=3.6"
 license = { text = "BSD-3-Clause License" }
 authors = [
-    {name = "André Andrade Baceti", email = "a.baceti@murabei.com"}
+    {name = "Murabei Data Science", email = "a.baceti@murabei.com"}
 ]
+urls = { Homepage = "https://github.com/Murabei-OpenSource-Codes/bigdata-corp-api" }
 classifiers = [
     "Programming Language :: Python :: 3",
     "Operating System :: OS Independent",
 ]
 dependencies = [
-    "requests"
+    "requests",
 ]
 
 [tool.poetry]
@@ -31,8 +32,6 @@ indent-width = 4
 exclude = [
   "secrets/",
   "__init__.py",
-  "setup_template.py",
-  "setup.py"
 ]
 
 # Lista de linters que serão aplicados. o ruff da suporte a vários e eles podem ser adicionados aqui.
@@ -69,4 +68,4 @@ no-sections = true
 [dependency-groups]
 docs = [
     "mkdocs (>=1.6.1,<2.0.0)"
-]
+]

bigdata_corp_api-0.18.3/src/bigdatacorp_api/__init__.py

@@ -0,0 +1,13 @@
+"""BigDataCorp API client package.
+
+Provides ``BigDataCorpAPI`` for querying CPF, CNPJ, and process datasets,
+plus domain-specific exceptions for API error handling.
+
+Example:
+    Import the client from the ``data`` submodule::
+
+        from bigdatacorp_api.data import BigDataCorpAPI
+
+        api = BigDataCorpAPI(bigdata_auth_token="YOUR_TOKEN")
+        result = api.get_cpf_dataset(cpf="12345678901", dataset="basic_data")
+"""