From 276682b3b3cd4e20451c25e7c5613e236f0deecd Mon Sep 17 00:00:00 2001
From: Chelsea Lin <chelsealin@google.com>
Date: Thu, 7 Nov 2024 23:23:51 +0000
Subject: [PATCH] fix: dbjson serialization with most compact JSON
representation
---
db_dtypes/json.py | 4 +++-
tests/compliance/json/test_json_compliance.py | 12 ++++++++----
2 files changed, 11 insertions(+), 5 deletions(-)
diff --git a/db_dtypes/json.py b/db_dtypes/json.py
index a00fe2b..d0bc6ca 100644
--- a/db_dtypes/json.py
+++ b/db_dtypes/json.py
@@ -143,7 +143,9 @@ def _serialize_json(value):
else:
# `sort_keys=True` sorts dictionary keys before serialization, making
# JSON comparisons deterministic.
- return json.dumps(value, sort_keys=True)
+ # `separators=(',', ':')` eliminate whitespace to get the most compact
+ # JSON representation.
+ return json.dumps(value, sort_keys=True, separators=(",", ":"))
@staticmethod
def _deserialize_json(value):
diff --git a/tests/compliance/json/test_json_compliance.py b/tests/compliance/json/test_json_compliance.py
index 18610a0..2a8e69a 100644
--- a/tests/compliance/json/test_json_compliance.py
+++ b/tests/compliance/json/test_json_compliance.py
@@ -31,7 +31,8 @@ def test_astype_str(self, data):
# Use `json.dumps(str)` instead of passing `str(obj)` directly to the super method.
result = pd.Series(data[:5]).astype(str)
expected = pd.Series(
- [json.dumps(x, sort_keys=True) for x in data[:5]], dtype=str
+ [json.dumps(x, sort_keys=True, separators=(",", ":")) for x in data[:5]],
+ dtype=str,
)
tm.assert_series_equal(result, expected)
@@ -46,7 +47,7 @@ def test_astype_string(self, data, nullable_string_dtype):
# Use `json.dumps(str)` instead of passing `str(obj)` directly to the super method.
result = pd.Series(data[:5]).astype(nullable_string_dtype)
expected = pd.Series(
- [json.dumps(x, sort_keys=True) for x in data[:5]],
+ [json.dumps(x, sort_keys=True, separators=(",", ":")) for x in data[:5]],
dtype=nullable_string_dtype,
)
tm.assert_series_equal(result, expected)
@@ -119,11 +120,14 @@ class TestJSONArrayInterface(base.BaseInterfaceTests):
def test_array_interface(self, data):
result = np.array(data)
# Use `json.dumps(data[0])` instead of passing `data[0]` directly to the super method.
- assert result[0] == json.dumps(data[0])
+ assert result[0] == json.dumps(data[0], sort_keys=True, separators=(",", ":"))
result = np.array(data, dtype=object)
# Use `json.dumps(x)` instead of passing `x` directly to the super method.
- expected = np.array([json.dumps(x) for x in data], dtype=object)
+ expected = np.array(
+ [json.dumps(x, sort_keys=True, separators=(",", ":")) for x in data],
+ dtype=object,
+ )
# if expected.ndim > 1:
# # nested data, explicitly construct as 1D
# expected = construct_1d_object_array_from_listlike(list(data))