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.

Sign up for GitHub

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

Jump to bottom

BigQuery: Add to_standard_sql() method to SchemaField #8880

Merged
merged 3 commits into from
Aug 5, 2019
Merged

BigQuery: Add to_standard_sql() method to SchemaField #8880

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
abe939a
Add to_standard_sql() method to SchemaField
plamut Jul 31, 2019
3f03054
Support standard SQL names in to_standard_sql()
plamut Aug 2, 2019
27a4fc3
Add support for ARRAY type in to_standard_sql()
plamut Aug 2, 2019
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
41 changes: 41 additions & 0 deletions bigquery/google/cloud/bigquery/schema.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,27 @@

"""Schemas for BigQuery tables / queries."""

from google.cloud.bigquery_v2 import types


# SQL types reference:
# https://cloud.google.com/bigquery/data-types#legacy_sql_data_types
# https://cloud.google.com/bigquery/docs/reference/standard-sql/data-types
LEGACY_TO_STANDARD_TYPES = {
"STRING": types.StandardSqlDataType.STRING,
"BYTES": types.StandardSqlDataType.BYTES,
"INTEGER": types.StandardSqlDataType.INT64,
plamut marked this conversation as resolved.
Show resolved Hide resolved
"FLOAT": types.StandardSqlDataType.FLOAT64,
"NUMERIC": types.StandardSqlDataType.NUMERIC,
"BOOLEAN": types.StandardSqlDataType.BOOL,
"RECORD": types.StandardSqlDataType.STRUCT,
"TIMESTAMP": types.StandardSqlDataType.TIMESTAMP,
"DATE": types.StandardSqlDataType.DATE,
"TIME": types.StandardSqlDataType.TIME,
"DATETIME": types.StandardSqlDataType.DATETIME,
}
"""String names of the legacy SQL types to integer codes of Standard SQL types."""


class SchemaField(object):
"""Describe a single field within a table schema.
Expand Down Expand Up @@ -146,6 +167,26 @@ def _key(self):
self._fields,
)

def to_standard_sql(self):
"""Return the field as the standard SQL field representation object.

Returns:
An instance of :class:`~google.cloud.bigquery_v2.types.StandardSqlField`.
"""
sql_type = types.StandardSqlDataType()
sql_type.type_kind = LEGACY_TO_STANDARD_TYPES.get(
self.field_type, types.StandardSqlDataType.TYPE_KIND_UNSPECIFIED
)

# NOTE: No need to also handle the "ARRAY" composed type, the latter
plamut marked this conversation as resolved.
Show resolved Hide resolved
# does not exist in legacy SQL types.
if sql_type.type_kind == types.StandardSqlDataType.STRUCT: # noqa: E721
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

False positive here, flake8 thinks that is about comparing types and wants to enforce isinstance() - but that would not work, as we actually compare integers here.

sql_type.struct_type.fields.extend(
field.to_standard_sql() for field in self.fields
)

return types.StandardSqlField(name=self.name, type=sql_type)

def __eq__(self, other):
if not isinstance(other, SchemaField):
return NotImplemented
Expand Down
107 changes: 107 additions & 0 deletions bigquery/tests/unit/test_schema.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,12 @@ def _get_target_class():

return SchemaField

@staticmethod
def _get_standard_sql_data_type_class():
from google.cloud.bigquery_v2 import types

return types.StandardSqlDataType

def _make_one(self, *args, **kw):
return self._get_target_class()(*args, **kw)

Expand Down Expand Up @@ -151,6 +157,107 @@ def test_fields_property(self):
schema_field = self._make_one("boat", "RECORD", fields=fields)
self.assertIs(schema_field.fields, fields)

def test_to_standard_sql_simple_type(self):
sql_type = self._get_standard_sql_data_type_class()
examples = (
("INTEGER", sql_type.INT64),
("FLOAT", sql_type.FLOAT64),
("BOOLEAN", sql_type.BOOL),
("DATETIME", sql_type.DATETIME),
)
for legacy_type, standard_type in examples:
field = self._make_one("some_field", legacy_type)
standard_field = field.to_standard_sql()
self.assertEqual(standard_field.name, "some_field")
self.assertEqual(standard_field.type.type_kind, standard_type)
self.assertFalse(standard_field.type.HasField("sub_type"))

def test_to_standard_sql_complex_type(self):
from google.cloud.bigquery_v2 import types

# Expected result object:
#
# name: "image_usage"
# type {
# type_kind: STRUCT
# struct_type {
# fields {
# name: "image_content"
# type {type_kind: BYTES}
# }
# fields {
# name: "last_used"
# type {
# type_kind: STRUCT
# struct_type {
# fields {
# name: "date_field"
# type {type_kind: DATE}
# }
# fields {
# name: "time_field"
# type {type_kind: TIME}
# }
# }
# }
# }
# }
# }

sql_type = self._get_standard_sql_data_type_class()

# level 2 fields
sub_sub_field_date = types.StandardSqlField(
name="date_field", type=sql_type(type_kind=sql_type.DATE)
)
sub_sub_field_time = types.StandardSqlField(
name="time_field", type=sql_type(type_kind=sql_type.TIME)
)

# level 1 fields
sub_field_struct = types.StandardSqlField(
name="last_used", type=sql_type(type_kind=sql_type.STRUCT)
)
sub_field_struct.type.struct_type.fields.extend(
[sub_sub_field_date, sub_sub_field_time]
)
sub_field_bytes = types.StandardSqlField(
name="image_content", type=sql_type(type_kind=sql_type.BYTES)
)

# level 0 (top level)
expected_result = types.StandardSqlField(
name="image_usage", type=sql_type(type_kind=sql_type.STRUCT)
)
expected_result.type.struct_type.fields.extend(
[sub_field_bytes, sub_field_struct]
)

# construct legacy SchemaField object
sub_sub_field1 = self._make_one("date_field", "DATE")
sub_sub_field2 = self._make_one("time_field", "TIME")
sub_field_record = self._make_one(
"last_used", "RECORD", fields=(sub_sub_field1, sub_sub_field2)
)
sub_field_bytes = self._make_one("image_content", "BYTES")
schema_field = self._make_one(
"image_usage", "RECORD", fields=(sub_field_bytes, sub_field_record)
)

standard_field = schema_field.to_standard_sql()

self.assertEqual(standard_field, expected_result)

def test_to_standard_sql_unknown_type(self):
sql_type = self._get_standard_sql_data_type_class()
field = self._make_one("weird_field", "TROOLEAN")

standard_field = field.to_standard_sql()

self.assertEqual(standard_field.name, "weird_field")
self.assertEqual(standard_field.type.type_kind, sql_type.TYPE_KIND_UNSPECIFIED)
self.assertFalse(standard_field.type.HasField("sub_type"))

def test___eq___wrong_type(self):
field = self._make_one("test", "STRING")
other = object()
Expand Down