Merge branch 'main' into issue-60550-fix-v2

Author: Abhibhav2003

Dockerfile

@@ -13,5 +13,5 @@ COPY requirements-dev.txt /tmp
 RUN python -m pip install -r /tmp/requirements-dev.txt
 RUN git config --global --add safe.directory /home/pandas
 
-ENV SHELL "/bin/bash"
+ENV SHELL="/bin/bash"
 CMD ["/bin/bash"]

doc/source/whatsnew/v3.0.0.rst

@@ -718,6 +718,7 @@ I/O
 ^^^
 - Bug in :class:`DataFrame` and :class:`Series` ``repr`` of :py:class:`collections.abc.Mapping`` elements. (:issue:`57915`)
 - Bug in :meth:`.DataFrame.to_json` when ``"index"`` was a value in the :attr:`DataFrame.column` and :attr:`Index.name` was ``None``. Now, this will fail with a ``ValueError`` (:issue:`58925`)
+- Bug in :meth:`.io.common.is_fsspec_url` not recognizing chained fsspec URLs (:issue:`48978`)
 - Bug in :meth:`DataFrame._repr_html_` which ignored the ``"display.float_format"`` option (:issue:`59876`)
 - Bug in :meth:`DataFrame.from_records` where ``columns`` parameter with numpy structured array was not reordering and filtering out the columns (:issue:`59717`)
 - Bug in :meth:`DataFrame.to_dict` raises unnecessary ``UserWarning`` when columns are not unique and ``orient='tight'``. (:issue:`58281`)

pandas/io/common.py

@@ -71,7 +71,7 @@
 
 _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+\-+.]*://")
+_FSSPEC_URL_PATTERN = re.compile(r"^[A-Za-z][A-Za-z0-9+\-+.]*(::[A-Za-z0-9+\-+.]+)*://")
 
 BaseBufferT = TypeVar("BaseBufferT", bound=BaseBuffer)
 
@@ -291,7 +291,7 @@ def is_fsspec_url(url: FilePath | BaseBuffer) -> bool:
     """
     return (
         isinstance(url, str)
-        and bool(_RFC_3986_PATTERN.match(url))
+        and bool(_FSSPEC_URL_PATTERN.match(url))
         and not url.startswith(("http://", "https://"))
     )
 

pandas/tests/io/json/test_pandas.py

@@ -1753,6 +1753,7 @@ def test_read_timezone_information(self):
         [
             "s3://example-fsspec/",
             "gcs://another-fsspec/file.json",
+            "filecache::s3://yet-another-fsspec/file.json",
             "https://example-site.com/data",
             "some-protocol://data.txt",
         ],

pandas/tests/io/test_common.py

@@ -501,6 +501,18 @@ def test_is_fsspec_url():
     assert icom.is_fsspec_url("RFC-3986+compliant.spec://something")
 
 
+def test_is_fsspec_url_chained():
+    # GH#48978 Support chained fsspec URLs
+    # See https://filesystem-spec.readthedocs.io/en/latest/features.html#url-chaining.
+    assert icom.is_fsspec_url("filecache::s3://pandas/test.csv")
+    assert icom.is_fsspec_url("zip://test.csv::filecache::gcs://bucket/file.zip")
+    assert icom.is_fsspec_url("filecache::zip://test.csv::gcs://bucket/file.zip")
+    assert icom.is_fsspec_url("filecache::dask::s3://pandas/test.csv")
+    assert not icom.is_fsspec_url("filecache:s3://pandas/test.csv")
+    assert not icom.is_fsspec_url("filecache:::s3://pandas/test.csv")
+    assert not icom.is_fsspec_url("filecache::://pandas/test.csv")
+
+
 @pytest.mark.parametrize("encoding", [None, "utf-8"])
 @pytest.mark.parametrize("format", ["csv", "json"])
 def test_codecs_encoding(encoding, format):

web/pandas/community/ecosystem.md

@@ -590,7 +590,7 @@ df = pd.read_csv("big.csv")  # use all your cores!
 ### [Pandarallel](https://github.com/nalepae/pandarallel)
 
 Pandarallel provides a simple way to parallelize your pandas operations on all your CPUs by changing only one line of code.
-If also displays progress bars.
+It also displays progress bars.
 
 ```python
 from pandarallel import pandarallel