Skip to content

Fix issue #36271 - pd.read_json() fails for strings that look similar to fsspec_url #44619

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
merged 7 commits into from
Dec 27, 2021
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/v1.4.0.rst
Original file line number Diff line number Diff line change
Expand Up @@ -780,6 +780,7 @@ I/O
- Bug in :func:`read_csv` not setting name of :class:`MultiIndex` columns correctly when ``index_col`` is not the first column (:issue:`38549`)
- Bug in :func:`read_csv` silently ignoring errors when failing to create a memory-mapped file (:issue:`44766`)
- Bug in :func:`read_csv` when passing a ``tempfile.SpooledTemporaryFile`` opened in binary mode (:issue:`44748`)
- Bug in :func:`read_json` raising ``ValueError`` when attempting to parse json strings containing "://" (:issue:`36271`)
-

Period
Expand Down
4 changes: 3 additions & 1 deletion pandas/io/common.py
Original file line number Diff line number Diff line change
Expand Up @@ -18,6 +18,7 @@
import mmap
import os
from pathlib import Path
import re
from typing import (
IO,
Any,
Expand Down Expand Up @@ -59,6 +60,7 @@

_VALID_URLS = set(uses_relative + uses_netloc + uses_params)
_VALID_URLS.discard("")
_RFC_3986_PATTERN = re.compile(r"^[A-Za-z][A-Za-z0-9+\-+.]*://")

BaseBufferT = TypeVar("BaseBufferT", bound=BaseBuffer)

Expand Down Expand Up @@ -244,7 +246,7 @@ def is_fsspec_url(url: FilePath | BaseBuffer) -> bool:
"""
return (
isinstance(url, str)
and "://" in url
and bool(_RFC_3986_PATTERN.match(url))
and not url.startswith(("http://", "https://"))
)

Expand Down
15 changes: 15 additions & 0 deletions pandas/tests/io/json/test_pandas.py
Original file line number Diff line number Diff line change
Expand Up @@ -1527,6 +1527,21 @@ def test_read_timezone_information(self):
expected = Series([88], index=DatetimeIndex(["2019-01-01 11:00:00"], tz="UTC"))
tm.assert_series_equal(result, expected)

@pytest.mark.parametrize(
"url",
[
"s3://example-fsspec/",
"gcs://another-fsspec/file.json",
"https://example-site.com/data",
"some-protocol://data.txt",
],
)
def test_read_json_with_url_value(self, url):
# GH 36271
result = read_json(f'{{"url":{{"0":"{url}"}}}}')
expected = DataFrame({"url": [url]})
tm.assert_frame_equal(result, expected)

@pytest.mark.parametrize(
"date_format,key", [("epoch", 86400000), ("iso", "P1DT0H0M0S")]
)
Expand Down
5 changes: 5 additions & 0 deletions pandas/tests/io/test_common.py
Original file line number Diff line number Diff line change
Expand Up @@ -494,6 +494,11 @@ def test_is_fsspec_url():
assert not icom.is_fsspec_url("random:pandas/somethingelse.com")
assert not icom.is_fsspec_url("/local/path")
assert not icom.is_fsspec_url("relative/local/path")
# fsspec URL in string should not be recognized
assert not icom.is_fsspec_url("this is not fsspec://url")
assert not icom.is_fsspec_url("{'url': 'gs://pandas/somethingelse.com'}")
# accept everything that conforms to RFC 3986 schema
assert icom.is_fsspec_url("RFC-3986+compliant.spec://something")


@pytest.mark.parametrize("encoding", [None, "utf-8"])
Expand Down