QT/superset2
1
0
Fork 0
mirror of https://github.com/apache/superset.git synced 2026-04-19 08:04:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: edit pyarrow stringify to better handle emojis and accents (#22881)

Browse Source
This commit is contained in:
Elizabeth Thompson
2023-01-30 12:29:19 -08:00
committed by GitHub
parent c839d0daf5
commit f2b61fca15
5 changed files with 97 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

82
tests/unit_tests/dataframe_test.py
View File

@@ -55,7 +55,87 @@ def test_df_to_records_NaT_type() -> None:
assert df_to_records(df) == [
{"date": None},
{"date": '"2023-01-06T20:50:31.749000+00:00"'},
{"date": "2023-01-06 20:50:31.749000+00:00"},
]
def test_df_to_records_mixed_emoji_type() -> None:
from superset.db_engine_specs import BaseEngineSpec
from superset.result_set import SupersetResultSet
data = [
("What's up?", "This is a string text", 1),
("What's up?", "This is a string with an 😍 added", 2),
("What's up?", NaT, 3),
("What's up?", "Last emoji 😁", 4),
]
cursor_descr: DbapiDescription = [
("question", "varchar", None, None, None, None, False),
("response", "varchar", None, None, None, None, False),
("count", "integer", None, None, None, None, False),
]
results = SupersetResultSet(data, cursor_descr, BaseEngineSpec)
df = results.to_pandas_df()
assert df_to_records(df) == [
{"question": "What's up?", "response": "This is a string text", "count": 1},
{
"question": "What's up?",
"response": "This is a string with an 😍 added",
"count": 2,
},
{
"question": "What's up?",
"response": None,
"count": 3,
},
{
"question": "What's up?",
"response": "Last emoji 😁",
"count": 4,
},
]
def test_df_to_records_mixed_accent_type() -> None:
from superset.db_engine_specs import BaseEngineSpec
from superset.result_set import SupersetResultSet
data = [
("What's up?", "This is a string text", 1),
("What's up?", "This is a string with áccent", 2),
("What's up?", NaT, 3),
("What's up?", "móre áccent", 4),
]
cursor_descr: DbapiDescription = [
("question", "varchar", None, None, None, None, False),
("response", "varchar", None, None, None, None, False),
("count", "integer", None, None, None, None, False),
]
results = SupersetResultSet(data, cursor_descr, BaseEngineSpec)
df = results.to_pandas_df()
assert df_to_records(df) == [
{"question": "What's up?", "response": "This is a string text", "count": 1},
{
"question": "What's up?",
"response": "This is a string with áccent",
"count": 2,
},
{
"question": "What's up?",
"response": None,
"count": 3,
},
{
"question": "What's up?",
"response": "móre áccent",
"count": 4,
},
]