Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Phase 1 for storing schemas for later use. #7761

Merged
merged 11 commits into from
Apr 25, 2019
47 changes: 47 additions & 0 deletions bigquery/google/cloud/bigquery/client.py
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,8 @@

import functools
import gzip
import io
import json
import os
import tempfile
import uuid
Expand Down Expand Up @@ -50,6 +52,7 @@
from google.cloud.bigquery.model import ModelReference
from google.cloud.bigquery.query import _QueryResults
from google.cloud.bigquery.retry import DEFAULT_RETRY
from google.cloud.bigquery.schema import SchemaField
from google.cloud.bigquery.table import _table_arg_to_table
from google.cloud.bigquery.table import _table_arg_to_table_ref
from google.cloud.bigquery.table import Table
Expand Down Expand Up @@ -1929,6 +1932,50 @@ def list_rows(
)
return row_iterator

def _schema_from_json_file_object(self, file_obj):
"""Helper function for schema_from_json that takes a
file object that describes a table schema.

Returns:
List of schema field objects.
"""
json_data = json.load(file_obj)
return [SchemaField.from_api_repr(field) for field in json_data]

def _schema_to_json_file_object(self, schema_list, file_obj):
"""Helper function for schema_to_json that takes a schema list and file
object and writes the schema list to the file object with json.dump
"""
json.dump(schema_list, file_obj, indent=2, sort_keys=True)

def schema_from_json(self, file_or_path):
"""Takes a file object or file path that contains json that describes
a table schema.

Returns:
List of schema field objects.
"""
if isinstance(file_or_path, io.IOBase):
return self._schema_from_json_file_object(file_or_path)

with open(file_or_path) as file_obj:
return self._schema_from_json_file_object(file_obj)

def schema_to_json(self, schema_list, destination):
"""Takes a list of schema field objects.

Serializes the list of schema field objects as json to a file.

Destination is a file path or a file object.
"""
json_schema_list = [f.to_api_repr() for f in schema_list]

if isinstance(destination, io.IOBase):
return self._schema_to_json_file_object(json_schema_list, destination)

with open(destination, mode="w") as file_obj:
return self._schema_to_json_file_object(json_schema_list, file_obj)


# pylint: disable=unused-argument
def _item_to_project(iterator, resource):
Expand Down
167 changes: 167 additions & 0 deletions bigquery/tests/unit/test_client.py
Original file line number Diff line number Diff line change
Expand Up @@ -5161,3 +5161,170 @@ def test__do_multipart_upload_wrong_size(self):

with pytest.raises(ValueError):
client._do_multipart_upload(file_obj, {}, file_obj_len + 1, None)

def test_schema_from_json_with_file_path(self):
from google.cloud.bigquery.schema import SchemaField

file_content = """[
{
"description": "quarter",
"mode": "REQUIRED",
"name": "qtr",
"type": "STRING"
},
{
"description": "sales representative",
"mode": "NULLABLE",
"name": "rep",
"type": "STRING"
},
{
"description": "total sales",
"mode": "NULLABLE",
"name": "sales",
"type": "FLOAT"
}
]"""

expected = [
SchemaField("qtr", "STRING", "REQUIRED", "quarter"),
SchemaField("rep", "STRING", "NULLABLE", "sales representative"),
SchemaField("sales", "FLOAT", "NULLABLE", "total sales"),
]

client = self._make_client()
mock_file_path = "/mocked/file.json"
tswast marked this conversation as resolved.
Show resolved Hide resolved

open_patch = mock.patch(
"builtins.open", new=mock.mock_open(read_data=file_content)
)

with open_patch as _mock_file:
actual = client.schema_from_json(mock_file_path)
_mock_file.assert_called_once_with(mock_file_path)
tswast marked this conversation as resolved.
Show resolved Hide resolved
# This assert is to make sure __exit__ is called in the context
# manager that opens the file in the function
_mock_file().__exit__.assert_called_once()

assert expected == actual

def test_schema_from_json_with_file_object(self):
from google.cloud.bigquery.schema import SchemaField

file_content = """[
{
"description": "quarter",
"mode": "REQUIRED",
"name": "qtr",
"type": "STRING"
},
{
"description": "sales representative",
"mode": "NULLABLE",
"name": "rep",
"type": "STRING"
},
{
"description": "total sales",
"mode": "NULLABLE",
"name": "sales",
"type": "FLOAT"
}
]"""

expected = [
SchemaField("qtr", "STRING", "REQUIRED", "quarter"),
SchemaField("rep", "STRING", "NULLABLE", "sales representative"),
SchemaField("sales", "FLOAT", "NULLABLE", "total sales"),
]

client = self._make_client()

fake_file = io.StringIO(file_content)
actual = client.schema_from_json(fake_file)

assert expected == actual

def test_schema_to_json_with_file_path(self):
from google.cloud.bigquery.schema import SchemaField

file_content = [
{
"description": "quarter",
"mode": "REQUIRED",
"name": "qtr",
"type": "STRING",
},
{
"description": "sales representative",
"mode": "NULLABLE",
"name": "rep",
"type": "STRING",
},
{
"description": "total sales",
"mode": "NULLABLE",
"name": "sales",
"type": "FLOAT",
},
]

schema_list = [
SchemaField("qtr", "STRING", "REQUIRED", "quarter"),
SchemaField("rep", "STRING", "NULLABLE", "sales representative"),
SchemaField("sales", "FLOAT", "NULLABLE", "total sales"),
]

client = self._make_client()
mock_file_path = "/mocked/file.json"

if six.PY2:
open_patch = mock.patch("__builtins__.open", mock.mock_open())
else:
open_patch = mock.patch("builtins.open", mock.mock_open())

with open_patch as mock_file, mock.patch("json.dump") as mock_dump:
client.schema_to_json(schema_list, mock_file_path)
mock_file.assert_called_once_with(mock_file_path, mode="w")
# This assert is to make sure __exit__ is called in the context
# manager that opens the file in the function
mock_file().__exit__.assert_called_once()
mock_dump.assert_called_with(
file_content, mock_file.return_value, indent=2, sort_keys=True
)

def test_schema_to_json_with_file_object(self):
from google.cloud.bigquery.schema import SchemaField

file_content = [
{
"description": "quarter",
"mode": "REQUIRED",
"name": "qtr",
"type": "STRING",
},
{
"description": "sales representative",
"mode": "NULLABLE",
"name": "rep",
"type": "STRING",
},
{
"description": "total sales",
"mode": "NULLABLE",
"name": "sales",
"type": "FLOAT",
},
]

schema_list = [
SchemaField("qtr", "STRING", "REQUIRED", "quarter"),
SchemaField("rep", "STRING", "NULLABLE", "sales representative"),
SchemaField("sales", "FLOAT", "NULLABLE", "total sales"),
]

fake_file = io.StringIO()
client = self._make_client()

client.schema_to_json(schema_list, fake_file)
assert file_content == json.loads(fake_file.getvalue())