Skip to content

Backport PR #31524 on branch 1.0.x (BUG: non-iterable value in meta raise error in json_normalize) #32629

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

Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
1 change: 1 addition & 0 deletions doc/source/whatsnew/v1.0.2.rst
Original file line number Diff line number Diff line change
Expand Up @@ -78,6 +78,7 @@ Bug fixes
**I/O**

- Using ``pd.NA`` with :meth:`DataFrame.to_json` now correctly outputs a null value instead of an empty object (:issue:`31615`)
- Bug in :meth:`pandas.json_normalize` when value in meta path is not iterable (:issue:`31507`)
- Fixed pickling of ``pandas.NA``. Previously a new object was returned, which broke computations relying on ``NA`` being a singleton (:issue:`31847`)
- Fixed bug in parquet roundtrip with nullable unsigned integer dtypes (:issue:`31896`).

Expand Down
20 changes: 17 additions & 3 deletions pandas/io/json/_normalize.py
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@
import numpy as np

from pandas._libs.writers import convert_json_to_lines
from pandas._typing import Scalar
from pandas.util._decorators import deprecate

import pandas as pd
Expand Down Expand Up @@ -230,14 +231,28 @@ def _json_normalize(
Returns normalized data with columns prefixed with the given string.
"""

def _pull_field(js: Dict[str, Any], spec: Union[List, str]) -> Iterable:
def _pull_field(
js: Dict[str, Any], spec: Union[List, str]
) -> Union[Scalar, Iterable]:
"""Internal function to pull field"""
result = js # type: ignore
if isinstance(spec, list):
for field in spec:
result = result[field]
else:
result = result[spec]
return result

def _pull_records(js: Dict[str, Any], spec: Union[List, str]) -> Iterable:
"""
Interal function to pull field for records, and similar to
_pull_field, but require to return Iterable. And will raise error
if has non iterable value.
"""
result = _pull_field(js, spec)

# GH 31507 GH 30145, if result is not Iterable, raise TypeError if not
# null, otherwise return an empty list
if not isinstance(result, Iterable):
if pd.isnull(result):
result = [] # type: ignore
Expand All @@ -246,7 +261,6 @@ def _pull_field(js: Dict[str, Any], spec: Union[List, str]) -> Iterable:
f"{js} has non iterable value {result} for path {spec}. "
"Must be iterable or null."
)

return result

if isinstance(data, list) and not data:
Expand Down Expand Up @@ -296,7 +310,7 @@ def _recursive_extract(data, path, seen_meta, level=0):
_recursive_extract(obj[path[0]], path[1:], seen_meta, level=level + 1)
else:
for obj in data:
recs = _pull_field(obj, path[0])
recs = _pull_records(obj, path[0])
recs = [
nested_to_record(r, sep=sep, max_level=max_level)
if isinstance(r, dict)
Expand Down
10 changes: 10 additions & 0 deletions pandas/tests/io/json/test_normalize.py
Original file line number Diff line number Diff line change
Expand Up @@ -486,6 +486,16 @@ def test_non_interable_record_path_errors(self):
with pytest.raises(TypeError, match=msg):
json_normalize([test_input], record_path=[test_path])

def test_meta_non_iterable(self):
# GH 31507
data = """[{"id": 99, "data": [{"one": 1, "two": 2}]}]"""

result = json_normalize(json.loads(data), record_path=["data"], meta=["id"])
expected = DataFrame(
{"one": [1], "two": [2], "id": np.array([99], dtype=object)}
)
tm.assert_frame_equal(result, expected)


class TestNestedToRecord:
def test_flat_stays_flat(self):
Expand Down