primera corrida de pep8

pydatajson/ckan_reader.py

@@ -99,7 +99,7 @@ def map_status_to_catalog(status):
     for status_key, catalog_key in iteritems(catalog_mapping):
         try:
             catalog[catalog_key] = status[status_key]
-        except:
+        except BaseException:
             logger.exception("""
 La clave '%s' no está en el endpoint de status. No se puede completar
 catalog['%s'].""", status_key, catalog_key)
@@ -114,7 +114,7 @@ def map_status_to_catalog(status):
         for status_key, publisher_key in iteritems(publisher_mapping):
             try:
                 catalog['publisher'][publisher_key] = status[status_key]
-            except:
+            except BaseException:
                 logger.exception("""
 La clave '%s' no está en el endpoint de status. No se puede completar
 catalog['publisher'['%s'].""", status_key, publisher_key)
@@ -156,11 +156,11 @@ def map_package_to_dataset(package, portal_url):
     for package_key, dataset_key in iteritems(dataset_mapping):
         try:
             dataset[dataset_key] = package[package_key]
-        except:
+        except BaseException:
             logger.exception("""
 La clave '%s' no está en el endpoint 'package_show' para el package '%s'. No
 se puede completar dataset['%s'].""",
-                         package_key, package['name'], dataset_key)
+                             package_key, package['name'], dataset_key)
 
     publisher_mapping = {
         'author': 'name',
@@ -172,11 +172,11 @@ def map_package_to_dataset(package, portal_url):
         for package_key, publisher_key in iteritems(publisher_mapping):
             try:
                 dataset['publisher'][publisher_key] = package[package_key]
-            except:
+            except BaseException:
                 logger.exception("""
 La clave '%s' no está en el endpoint 'package_show' para el package '%s'. No
 se puede completar dataset['publisher']['%s'].""",
-                             package_key, package['name'], publisher_key)
+                                 package_key, package['name'], publisher_key)
 
     contact_point_mapping = {
         'maintainer': 'fn',
@@ -188,11 +188,11 @@ def map_package_to_dataset(package, portal_url):
         for package_key, contact_key in iteritems(contact_point_mapping):
             try:
                 dataset['contactPoint'][contact_key] = package[package_key]
-            except:
+            except BaseException:
                 logger.exception("""
 La clave '%s' no está en el endpoint 'package_show' para el package '%s'. No
 se puede completar dataset['contactPoint']['%s'].""",
-                             package_key, package['name'], contact_key)
+                                 package_key, package['name'], contact_key)
 
     # Si existen campos extras en la información del package, busco las claves
     # "Frecuencia de actualización" y "Temática global" para completar los
@@ -221,7 +221,7 @@ def add_temporal(dataset, package):
         logger.info("""
 Se encontro mas de un valor de cobertura temporal en 'extras' para el
 'package' '%s'. No se puede completar dataset['temporal'].\n %s""",
-                     package['name'], temporal)
+                    package['name'], temporal)
     elif len(temporal) == 1:
         try:
             dataset["temporal"] = temporal[0]
@@ -256,12 +256,12 @@ def add_superTheme(dataset, package):
         logger.info("""
 No se encontraron valores de temática global en 'extras' para el
 'package' '%s'. No se puede completar dataset['superTheme'].""",
-                     package['name'])
+                    package['name'])
     elif len(super_theme) > 1:
         logger.info("""
 Se encontro mas de un valor de temática global en 'extras' para el
 'package' '%s'. No se puede completar dataset['superTheme'].\n %s""",
-                     package['name'], super_theme)
+                    package['name'], super_theme)
     else:
         try:
             dataset["superTheme"] = [SUPER_THEMES[super_theme[0]]]
@@ -296,12 +296,12 @@ def add_accrualPeriodicity(dataset, package):
         logger.info("""
 No se encontraron valores de frecuencia de actualización en 'extras' para el
 'package' '%s'. No se puede completar dataset['accrualPeriodicity'].""",
-                     package['name'])
+                    package['name'])
     elif len(accrual) > 1:
         logger.info("""
 Se encontro mas de un valor de frecuencia de actualización en 'extras' para el
 'package' '%s'. No se puede completar dataset['accrualPeriodicity'].\n %s""",
-                     package['name'], accrual)
+                    package['name'], accrual)
     else:
         try:
             dataset["accrualPeriodicity"] = FREQUENCIES[accrual[0]]
@@ -349,17 +349,20 @@ def map_resource_to_distribution(resource, portal_url):
     for resource_key, distribution_key in iteritems(distribution_mapping):
         try:
             distribution[distribution_key] = resource[resource_key]
-        except:
+        except BaseException:
             logger.exception("""
 La clave '%s' no está en la metadata del 'resource' '%s'. No
 se puede completar distribution['%s'].""",
-                         resource_key, resource['name'], distribution_key)
+                             resource_key, resource['name'], distribution_key)
 
     if 'attributesDescription' in resource:
         try:
-            distribution['field'] = json.loads(resource['attributesDescription'])
-        except:
-            logger.exception("Error parseando los fields del resource '%s'", resource['name'])
+            distribution['field'] = json.loads(
+                resource['attributesDescription'])
+        except BaseException:
+            logger.exception(
+                "Error parseando los fields del resource '%s'",
+                resource['name'])
 
     url_path = ['dataset', resource['package_id'], 'resource', resource['id']]
     distribution["accessURL"] = urljoin(portal_url, "/".join(url_path))
@@ -386,10 +389,10 @@ def map_group_to_theme(group):
     for group_key, theme_key in iteritems(theme_mapping):
         try:
             theme[theme_key] = group[group_key]
-        except:
+        except BaseException:
             logger.exception("""
 La clave '%s' no está en la metadata del 'group' '%s'. No
 se puede completar theme['%s'].""",
-                         group_key, theme['name'], theme_key)
+                             group_key, theme['name'], theme_key)
 
     return theme

pydatajson/ckan_utils.py

@@ -65,7 +65,7 @@ def map_dataset_to_package(catalog, dataset, owner_org, catalog_id=None,
 
     spatial = dataset.get('spatial')
     if spatial:
-        serializable = type(spatial) is list
+        serializable = isinstance(spatial, list)
         append_attribute_to_extra(package, dataset, 'spatial', serializable)
 
     contact_point = dataset.get('contactPoint')
@@ -102,10 +102,10 @@ def _get_theme_label(catalog, theme):
     """Intenta conseguir el theme por id o por label."""
     try:
         label = catalog.get_theme(identifier=theme)['label']
-    except:
+    except BaseException:
         try:
             label = catalog.get_theme(label=theme)['label']
-        except:
+        except BaseException:
             raise ce.ThemeNonExistentError(theme)
 
     label = re.sub(r'[^\wá-úÁ-ÚñÑ .-]+', '',

pydatajson/core.py

@@ -215,8 +215,9 @@ def remove_distribution(self, identifier, dataset_identifier=None):
                         (not dataset_identifier or
                          dataset["identifier"] == dataset_identifier)):
                     dataset["distribution"].pop(index)
-                    logger.info("Distribution {} del dataset {} en posicion {} fue eliminada.".format(
-                        identifier, dataset["identifier"], index))
+                    logger.info(
+                        "Distribution {} del dataset {} en posicion {} fue eliminada.".format(
+                            identifier, dataset["identifier"], index))
                     return
 
         logger.warning("No se encontro la distribucion {}.".format(identifier))
@@ -635,7 +636,8 @@ def generate_datasets_report(
                 catalog_ids.append(catalog.get("identifier", ""))
         if isinstance(catalog_ids, string_types + (dict,)):
             catalog_ids = [catalog_ids] * len(catalogs)
-        if not catalog_orgs or isinstance(catalog_orgs, string_types + (dict,)):
+        if not catalog_orgs or isinstance(
+                catalog_orgs, string_types + (dict,)):
             catalog_orgs = [catalog_orgs] * len(catalogs)
         if not catalog_homepages or isinstance(catalog_homepages,
                                                string_types + (dict,)):

pydatajson/documentation.py

@@ -32,7 +32,8 @@ def dataset_to_markdown(dataset):
 """
 
     if "distribution" in dataset:
-        distributions = "".join(map(distribution_to_markdown, dataset["distribution"]))
+        distributions = "".join(
+            map(distribution_to_markdown, dataset["distribution"]))
     else:
         distributions = ""
 
@@ -65,7 +66,8 @@ def distribution_to_markdown(distribution):
 """
 
     if "field" in distribution:
-        fields = "- " + "\n- ".join(map(field_to_markdown, distribution["field"]))
+        fields = "- " + \
+            "\n- ".join(map(field_to_markdown, distribution["field"]))
     else:
         fields = ""
 

pydatajson/federation.py

@@ -88,7 +88,9 @@ def remove_harvested_ds_from_ckan(catalog, portal_url, apikey,
             remove_dataset_from_ckan(harvested_id, portal_url, apikey)
             logger.info("{} eliminado de {}".format(harvested_id, catalog_id))
         except Exception:
-            logger.exception("{} de {} no existe.".format(harvested_id, catalog_id))
+            logger.exception(
+                "{} de {} no existe.".format(
+                    harvested_id, catalog_id))
 
 
 def remove_datasets_from_ckan(portal_url, apikey, filter_in=None,
@@ -128,8 +130,9 @@ def remove_datasets_from_ckan(portal_url, apikey, filter_in=None,
                            for dataset in search_result['results']]
         start = 500
         while search_result['count'] > start:
-            search_result = ckan_portal.call_action('package_search',
-                                                    data_dict={'q': query, 'rows': 500, 'start': start})
+            search_result = ckan_portal.call_action(
+                'package_search', data_dict={
+                    'q': query, 'rows': 500, 'start': start})
             org_identifiers += [dataset['id']
                                 for dataset in search_result['results']]
             start += 500
@@ -265,7 +268,8 @@ def harvest_catalog_to_ckan(catalog, portal_url, apikey, catalog_id,
                 catalog, owner_org, dataset_id, portal_url, apikey, catalog_id)
             harvested.append(harvested_id)
         except Exception as e:
-            msg = "Error federando catalogo: %s, dataset: %s al portal: %s\n" % (catalog_id, dataset_id, portal_url)
+            msg = "Error federando catalogo: %s, dataset: %s al portal: %s\n" % (
+                catalog_id, dataset_id, portal_url)
             msg += str(e)
             logger.error(msg)
             errors[dataset_id] = str(e)

pydatajson/helpers.py

@@ -235,7 +235,8 @@ def sheet_to_table(worksheet):
 
 def string_to_list(string, sep=",", filter_empty=False):
     """Transforma una string con elementos separados por `sep` en una lista."""
-    return [value.strip() for value in string.split(sep) if (not filter_empty or value)]
+    return [value.strip() for value in string.split(sep)
+            if (not filter_empty or value)]
 
 
 def add_dicts(one_dict, other_dict):

pydatajson/indicators.py

@@ -317,7 +317,8 @@ def _generate_status_indicators(catalog, validator=None):
     try:
         summary = generate_datasets_summary(catalog, validator=validator)
     except Exception as e:
-        msg = u'Error generando resumen del catálogo {}: {}'.format(catalog['title'], str(e))
+        msg = u'Error generando resumen del catálogo {}: {}'.format(
+            catalog['title'], str(e))
         logger.error(msg)
         return result
 
@@ -388,7 +389,8 @@ def _generate_date_indicators(catalog, tolerance=0.2, only_numeric=False):
             dias_ultima_actualizacion
 
     except Exception as e:
-        msg = u'Error generando indicadores de fecha del catálogo {}: {}'.format(catalog['title'], str(e))
+        msg = u'Error generando indicadores de fecha del catálogo {}: {}'.format(
+            catalog['title'], str(e))
         logger.error(msg)
         return result
 

pydatajson/readers.py

@@ -39,7 +39,7 @@ def read_catalog_obj(catalog):
             return catalog
         else:
             return pydatajson.DataJson(catalog)
-    except:
+    except BaseException:
         return pydatajson.DataJson(catalog)
 
 
@@ -431,18 +431,20 @@ def read_local_xlsx_catalog(xlsx_path, logger=None):
             logger)
 
         if dataset_index is None:
-            logger.error("""No se encontro el dataset '{}' especificado para el campo
+            logger.error(
+                """No se encontro el dataset '{}' especificado para el campo
 '{}' (fila #{} de la hoja "Field"). Este campo no figurara en el data.json de salida.""".format(
-                unidecode(field["dataset_title"]),
-                unidecode(field["field_title"]),
-                idx + 2))
+                    unidecode(
+                        field["dataset_title"]), unidecode(
+                        field["field_title"]), idx + 2))
 
         elif distribution_index is None:
-            logger.error("""No se encontro la distribucion '{}' especificada para el campo
+            logger.error(
+                """No se encontro la distribucion '{}' especificada para el campo
 '{}' (fila #{} de la hoja "Field"). Este campo no figurara en el data.json de salida.""".format(
-                unidecode(field["distribution_title"]),
-                unidecode(field["field_title"]),
-                idx + 2))
+                    unidecode(
+                        field["distribution_title"]), unidecode(
+                        field["field_title"]), idx + 2))
 
         else:
             dataset = catalog["catalog_dataset"][dataset_index]
@@ -463,7 +465,8 @@ def read_local_xlsx_catalog(xlsx_path, logger=None):
                         "dataset_keyword", "dataset_language"]
         for field in array_fields:
             if field in dataset:
-                dataset[field] = helpers.string_to_list(dataset[field], filter_empty=True)
+                dataset[field] = helpers.string_to_list(
+                    dataset[field], filter_empty=True)
 
     # Elimino los prefijos de los campos a nivel catálogo
     _remove_prefixes_and_unprefixed_fields(catalog, 'catalog_')
@@ -480,7 +483,8 @@ def read_local_xlsx_catalog(xlsx_path, logger=None):
     # distribución
     for dataset in catalog["dataset"]:
         for distribution in dataset["distribution"]:
-            _remove_prefixes_and_unprefixed_fields(distribution, 'distribution_')
+            _remove_prefixes_and_unprefixed_fields(
+                distribution, 'distribution_')
 
     # Elimino campos auxiliares y los prefijos de los campos a nivel "campo"
     for dataset in catalog["dataset"]:

pydatajson/search.py

@@ -309,11 +309,11 @@ def get_dataset(catalog, identifier=None, title=None):
     if identifier:
         try:
             return _get_dataset_by_identifier(catalog, identifier)
-        except:
+        except BaseException:
             try:
                 catalog._build_index()
                 return _get_dataset_by_identifier(catalog, identifier)
-            except:
+            except BaseException:
                 filtered_datasets = get_datasets(
                     catalog, {"dataset": {"identifier": identifier}})
     elif title:  # TODO: is this required?
@@ -358,11 +358,11 @@ def get_distribution(catalog, identifier=None, title=None,
     if identifier:
         try:
             return _get_distribution_by_identifier(catalog, identifier)
-        except:
+        except BaseException:
             try:
                 catalog._build_index()
                 return _get_distribution_by_identifier(catalog, identifier)
-            except:
+            except BaseException:
                 filtered_distributions = get_distributions(
                     catalog, {"distribution": {"identifier": identifier}})
     # toma la distribution que tenga el título único, dentro de un dataset
@@ -406,7 +406,8 @@ def get_field_location(catalog, identifier=None, title=None,
         for distribution in dataset["distribution"]:
             if (not distribution_identifier or
                     distribution_identifier == distribution["identifier"]):
-                if "field" in distribution and isinstance(distribution["field"], list):
+                if "field" in distribution and isinstance(
+                        distribution["field"], list):
                     for field in distribution["field"]:
                         if (identifier and "id" in field and
                                 field["id"] == identifier
@@ -448,11 +449,11 @@ def get_field(catalog, identifier=None, title=None,
     if identifier:
         try:
             return _get_field_by_identifier(catalog, identifier)
-        except:
+        except BaseException:
             try:
                 catalog._build_index()
                 return _get_field_by_identifier(catalog, identifier)
-            except:
+            except BaseException:
                 filtered_fields = get_fields(
                     catalog, {"field": {"id": identifier}})
     elif title and distribution_identifier:

pydatajson/time_series.py

@@ -44,7 +44,8 @@ def get_distribution_time_index(distribution):
 
 def distribution_has_time_index(distribution):
     try:
-        return any([field.get('specialType') == 'time_index' for field in distribution.get('field', [])])
+        return any([field.get('specialType') ==
+                    'time_index' for field in distribution.get('field', [])])
     except AttributeError:
         return False