def _item_to_table(iterator, resource):
"""Convert a JSON table to the native object.
:type iterator: :class:`~google.api.core.page_iterator.Iterator`
:param iterator: The iterator that is currently in use.
:type resource: dict
:param resource: An item to be converted to a table.
:rtype: :class:`~google.cloud.bigquery.table.Table`
:returns: The next table in the page.
"""
return Table.from_api_repr(resource, iterator.dataset)
def _item_to_table(iterator, resource):
"""Convert a JSON table to the native object.
:type iterator: :class:`~google.cloud.iterator.Iterator`
:param iterator: The iterator that is currently in use.
:type resource: dict
:param resource: An item to be converted to a table.
:rtype: :class:`~google.cloud.bigquery.table.Table`
:returns: The next table in the page.
"""
return Table.from_api_repr(resource, iterator.dataset)
def list_tables(self, max_results=None, page_token=None):
"""List tables for the project associated with this client.
See:
https://cloud.google.com/bigquery/docs/reference/v2/tables/list
:type max_results: int
:param max_results: maximum number of tables to return, If not
passed, defaults to a value set by the API.
:type page_token: string
:param page_token: opaque marker for the next "page" of datasets. If
not passed, the API will return the first page of
datasets.
:rtype: tuple, (list, str)
:returns: list of :class:`google.cloud.bigquery.table.Table`, plus a
"next page token" string: if not ``None``, indicates that
more tables can be retrieved with another call (pass that
value as ``page_token``).
"""
params = {}
if max_results is not None:
params['maxResults'] = max_results
if page_token is not None:
params['pageToken'] = page_token
path = '/projects/%s/datasets/%s/tables' % (self.project, self.name)
connection = self._client.connection
resp = connection.api_request(method='GET',
path=path,
query_params=params)
tables = [
Table.from_api_repr(resource, self)
for resource in resp.get('tables', ())
]
return tables, resp.get('nextPageToken')
def list_tables(self, max_results=None, page_token=None):
"""List tables for the project associated with this client.
See:
https://cloud.google.com/bigquery/docs/reference/v2/tables/list
:type max_results: int
:param max_results: maximum number of tables to return, If not
passed, defaults to a value set by the API.
:type page_token: str
:param page_token: opaque marker for the next "page" of datasets. If
not passed, the API will return the first page of
datasets.
:rtype: tuple, (list, str)
:returns: list of :class:`google.cloud.bigquery.table.Table`, plus a
"next page token" string: if not ``None``, indicates that
more tables can be retrieved with another call (pass that
value as ``page_token``).
"""
params = {}
if max_results is not None:
params['maxResults'] = max_results
if page_token is not None:
params['pageToken'] = page_token
path = '/projects/%s/datasets/%s/tables' % (self.project, self.name)
connection = self._client.connection
resp = connection.api_request(method='GET', path=path,
query_params=params)
tables = [Table.from_api_repr(resource, self)
for resource in resp.get('tables', ())]
return tables, resp.get('nextPageToken')
def create_temporary_data_source(source_uri):
"""Create a temporary data source so BigQuery can query the CSV in
Google Cloud Storage.
Nothing like this is currently implemented in the
google-cloud-python library.
Returns a table reference suitable for using in a BigQuery SQL
query (legacy format).
"""
schema = [
{
"name": "Regional_Office_Name",
"type": "string"
},
{
"name": "Regional_Office_Code",
"type": "string"
},
{
"name": "Area_Team_Name",
"type": "string"
},
{
"name": "Area_Team_Code",
"type": "string",
"mode": "required"
},
{
"name": "PCO_Name",
"type": "string"
},
{
"name": "PCO_Code",
"type": "string"
},
{
"name": "Practice_Name",
"type": "string"
},
{
"name": "Practice_Code",
"type": "string",
"mode": "required"
},
{
"name": "BNF_Code",
"type": "string",
"mode": "required"
},
{
"name": "BNF_Description",
"type": "string",
"mode": "required"
},
{
"name": "Items",
"type": "integer",
"mode": "required"
},
{
"name": "Quantity",
"type": "integer",
"mode": "required"
},
{
"name": "ADQ_Usage",
"type": "float"
},
{
"name": "NIC",
"type": "float",
"mode": "required"
},
{
"name": "Actual_Cost",
"type": "float",
"mode": "required"
},
]
resource = {
"tableReference": {
"tableId": TEMP_SOURCE_NAME
},
"externalDataConfiguration": {
"csvOptions": {
"skipLeadingRows": "1"
},
"sourceFormat": "CSV",
"sourceUris": [source_uri],
"schema": {
"fields": schema
}
}
}
client = bigquery.client.Client(project='ebmdatalab')
# delete the table if it exists
dataset = Dataset("tmp_eu", client)
table = Table.from_api_repr(resource, dataset)
try:
table.delete()
except NotFound:
pass
# Now create it
path = "/projects/ebmdatalab/datasets/%s/tables" % TEMP_DATASET
client._connection.api_request(method='POST', path=path, data=resource)
return "[ebmdatalab:%s.%s]" % (TEMP_DATASET, TEMP_SOURCE_NAME)
