def setUp(cls):
cls.dj = DataJson(cls.get_sample("full_data.json"))
cls.catalog = readers.read_catalog(
cls.get_sample("full_data.json"))
cls.maxDiff = None
cls.longMessage = True
cls.requests_mock = requests_mock.Mocker()
cls.requests_mock.start()
cls.requests_mock.get(requests_mock.ANY, real_http=True)
cls.requests_mock.head(requests_mock.ANY, status_code=200)
def process_catalog(org, datajson):
"""Descarga y procesa el catálogo correspondiente a la organización."""
logger.info('=== Catálogo %s ===', org.upper())
os.chdir(org)
try:
config = ORGANISMS[org]
logger.info('- Lectura de catálogo')
# For XLSX catalogs, creates corresponding JSON
file_ext = config["formato"]
if file_ext == 'xlsx':
res = requests.get(config['url'])
with open('data.xlsx', 'w') as xlsx_file:
xlsx_file.write(res.content)
logger.info('- Transformación de XLSX a JSON')
catalog = read_catalog('data.xlsx')
elif file_ext == 'json':
catalog = read_catalog(config['url'])
elif file_ext == 'ckan':
catalog = read_ckan_catalog(config['url'])
else:
raise ValueError('%s no es una extension valida para un catalogo.',
file_ext)
logger.info('- Escritura de catálogo')
write_json_catalog(catalog, 'data.json')
# Creates README and auxiliary reports
logger.info('- Generación de reportes')
datajson.generate_catalog_readme(catalog, export_path='README.md')
datajson.generate_datasets_summary(catalog, export_path='datasets.csv')
except:
logger.error('Error al procesar el catálogo de %s', org, exc_info=True)
finally:
os.chdir('..') # Returns to parent dir.
def __init__(self,
catalog,
validator=None,
verify_ssl=True,
url_check_timeout=1,
threads_count=1):
self.download_url_ok = None
self.catalog = read_catalog(catalog)
self.summary = generate_datasets_summary(self.catalog,
validator=validator,
verify_ssl=verify_ssl)
self.verify_url = verify_ssl
self.url_check_timeout = url_check_timeout
self.threads_count = threads_count
def generate_readme(catalog, export_path=None):
"""Genera una descripción textual en formato Markdown sobre los
metadatos generales de un catálogo (título, editor, fecha de
publicación, et cetera), junto con:
- estado de los metadatos a nivel catálogo,
- estado global de los metadatos,
- cantidad de datasets federados y no federados,
- detalles de los datasets no federados
- cantidad de datasets y distribuciones incluidas
Es utilizada por la rutina diaria de `libreria-catalogos` para generar
un README con información básica sobre los catálogos mantenidos.
Args:
catalog (str o dict): Path a un catálogo en cualquier formato,
JSON, XLSX, o diccionario de python.
export_path (str): Path donde exportar el texto generado (en
formato Markdown). Si se especifica, el método no devolverá
nada.
Returns:
str: Texto de la descripción generada.
"""
# Si se paso una ruta, guardarla
if isinstance(catalog, string_types):
catalog_path_or_url = catalog
else:
catalog_path_or_url = None
catalog = read_catalog(catalog)
validation = validate_catalog(catalog)
# Solo necesito indicadores para un catalogo
indicators = generate_catalogs_indicators(catalog, CENTRAL_CATALOG)[0][0]
with io.open(os.path.join(TEMPLATES_PATH, 'catalog_readme.txt'),
'r',
encoding='utf-8') as template_file:
readme_template = template_file.read()
not_federated_datasets_list = "\n".join([
"- [{}]({})".format(dataset[0], dataset[1])
for dataset in indicators["datasets_no_federados"]
])
federated_removed_datasets_list = "\n".join([
"- [{}]({})".format(dataset[0], dataset[1])
for dataset in indicators["datasets_federados_eliminados"]
])
federated_datasets_list = "\n".join([
"- [{}]({})".format(dataset[0], dataset[1])
for dataset in indicators["datasets_federados"]
])
non_federated_pct = 1.0 - indicators["datasets_federados_pct"] if \
indicators["datasets_federados_pct"] is not None else \
indicators["datasets_federados_pct"]
content = {
"title":
catalog.get("title"),
"publisher_name":
traverse_dict(catalog, ["publisher", "name"]),
"publisher_mbox":
traverse_dict(catalog, ["publisher", "mbox"]),
"catalog_path_or_url":
catalog_path_or_url,
"description":
catalog.get("description"),
"global_status":
validation["status"],
"catalog_status":
validation["error"]["catalog"]["status"],
"no_of_datasets":
len(catalog["dataset"]),
"no_of_distributions":
sum([
len(dataset["distribution"]) for dataset in catalog["dataset"]
]),
"federated_datasets":
indicators["datasets_federados_cant"],
"not_federated_datasets":
indicators["datasets_no_federados_cant"],
"not_federated_datasets_pct":
non_federated_pct,
"not_federated_datasets_list":
not_federated_datasets_list,
"federated_removed_datasets_list":
federated_removed_datasets_list,
"federated_datasets_list":
federated_datasets_list,
}
catalog_readme = readme_template.format(**content)
if export_path:
with io.open(export_path, 'w+', encoding='utf-8') as target:
target.write(catalog_readme)
else:
return catalog_readme
def __init__(self, central_catalog, catalog):
self.central_catalog = read_catalog(central_catalog)
self.catalog = read_catalog(catalog)
self.filtered_central = filter_by_likely_publisher(
self.central_catalog.get('dataset', []),
self.catalog.get('dataset', []))
def setUp(cls):
cls.dj = DataJson(cls.get_sample("full_data.json"))
cls.catalog = readers.read_catalog(cls.get_sample("full_data.json"))
cls.maxDiff = None
cls.longMessage = True