fsspec 2025.9.0__tar.gz → 2025.12.0__tar.gz

{fsspec-2025.9.0 → fsspec-2025.12.0}/.github/workflows/main.yaml

@@ -14,18 +14,18 @@ jobs:
       fail-fast: false
       matrix:
         PY:
-          - "3.9"
           - "3.10"
           - "3.11"
           - "3.12"
           - "3.13"
+          - "3.14"
 
     env:
       CIRUN: true
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
         with:
           fetch-depth: 0
 
@@ -50,7 +50,7 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
         with:
           fetch-depth: 0
 
@@ -81,7 +81,7 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
         with:
           fetch-depth: 0
 
@@ -124,7 +124,7 @@ jobs:
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v5
 
       - name: Setup conda
         uses: conda-incubator/setup-miniconda@v3
@@ -145,5 +145,5 @@ jobs:
         shell: bash -l {0}
         run: |
           cd ${{ matrix.FRIEND }}
-          pytest -v
+          pytest -v -W ignore::pytest.PytestRemovedIn9Warning
           cd ..

{fsspec-2025.9.0 → fsspec-2025.12.0}/.github/workflows/pypipublish.yaml

@@ -8,9 +8,9 @@ jobs:
   deploy:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v4
+      - uses: actions/checkout@v5
       - name: Set up Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v6
         with:
           python-version: "3.x"
       - name: Install dependencies

{fsspec-2025.9.0 → fsspec-2025.12.0}/.pre-commit-config.yaml

@@ -13,9 +13,8 @@ repos:
       - id: check-json
       - id: check-yaml
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.12.2
+    rev: v0.14.3
     hooks:
-      # Run the linter.
       - id: ruff-check
         args: [ --fix, "--show-fixes"]
       - id: ruff-format

{fsspec-2025.9.0 → fsspec-2025.12.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: fsspec
-Version: 2025.9.0
+Version: 2025.12.0
 Summary: File-system specification
 Project-URL: Changelog, https://filesystem-spec.readthedocs.io/en/latest/changelog.html
 Project-URL: Documentation, https://filesystem-spec.readthedocs.io/en/latest/
@@ -12,12 +12,12 @@ Keywords: file
 Classifier: Development Status :: 4 - Beta
 Classifier: Intended Audience :: Developers
 Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
-Requires-Python: >=3.9
+Classifier: Programming Language :: Python :: 3.14
+Requires-Python: >=3.10
 Provides-Extra: abfs
 Requires-Dist: adlfs; extra == 'abfs'
 Provides-Extra: adl
@@ -197,7 +197,7 @@ CI runtime. For local use, pick a version suitable for you.
 
 ```bash
 # For a new environment (mamba / conda).
-mamba create -n fsspec -c conda-forge  python=3.9 -y
+mamba create -n fsspec -c conda-forge  python=3.10 -y
 conda activate fsspec
 
 # Standard dev install with docs and tests.

{fsspec-2025.9.0 → fsspec-2025.12.0}/README.md

@@ -47,7 +47,7 @@ CI runtime. For local use, pick a version suitable for you.
 
 ```bash
 # For a new environment (mamba / conda).
-mamba create -n fsspec -c conda-forge  python=3.9 -y
+mamba create -n fsspec -c conda-forge  python=3.10 -y
 conda activate fsspec
 
 # Standard dev install with docs and tests.

{fsspec-2025.9.0 → fsspec-2025.12.0}/docs/environment.yml

@@ -2,4 +2,4 @@ name: fsspec
 channels:
   - defaults
 dependencies:
-  - python=3.9
+  - python=3.10

{fsspec-2025.9.0 → fsspec-2025.12.0}/docs/source/api.rst

@@ -7,17 +7,17 @@ User Functions
 --------------
 
 .. autosummary::
-   fsspec.available_compressions
-   fsspec.available_protocols
-   fsspec.filesystem
-   fsspec.fuse.run
-   fsspec.generic.rsync
-   fsspec.get_filesystem_class
-   fsspec.get_mapper
-   fsspec.gui.FileSelector
-   fsspec.open
-   fsspec.open_files
-   fsspec.open_local
+   available_compressions
+   available_protocols
+   filesystem
+   fuse.run
+   generic.rsync
+   get_filesystem_class
+   get_mapper
+   gui.FileSelector
+   open
+   open_files
+   open_local
 
 .. autofunction:: fsspec.available_compressions
 .. autofunction:: fsspec.available_protocols
@@ -36,24 +36,24 @@ Base Classes
 ------------
 
 .. autosummary::
-   fsspec.archive.AbstractArchiveFileSystem
-   fsspec.asyn.AsyncFileSystem
-   fsspec.callbacks.Callback
-   fsspec.callbacks.DotPrinterCallback
-   fsspec.callbacks.NoOpCallback
-   fsspec.callbacks.TqdmCallback
-   fsspec.core.BaseCache
-   fsspec.core.OpenFile
-   fsspec.core.OpenFiles
-   fsspec.core.get_fs_token_paths
-   fsspec.core.url_to_fs
-   fsspec.dircache.DirCache
-   fsspec.FSMap
-   fsspec.generic.GenericFileSystem
-   fsspec.registry.register_implementation
-   fsspec.spec.AbstractBufferedFile
-   fsspec.spec.AbstractFileSystem
-   fsspec.spec.Transaction
+   archive.AbstractArchiveFileSystem
+   asyn.AsyncFileSystem
+   callbacks.Callback
+   callbacks.DotPrinterCallback
+   callbacks.NoOpCallback
+   callbacks.TqdmCallback
+   core.BaseCache
+   core.OpenFile
+   core.OpenFiles
+   core.get_fs_token_paths
+   core.url_to_fs
+   dircache.DirCache
+   FSMap
+   generic.GenericFileSystem
+   registry.register_implementation
+   spec.AbstractBufferedFile
+   spec.AbstractFileSystem
+   spec.Transaction
 
 .. autoclass:: fsspec.archive.AbstractArchiveFileSystem
    :members:
@@ -107,31 +107,31 @@ Built-in Implementations
 ------------------------
 
 .. autosummary::
-   fsspec.implementations.arrow.ArrowFSWrapper
-   fsspec.implementations.arrow.HadoopFileSystem
-   fsspec.implementations.cached.CachingFileSystem
-   fsspec.implementations.cached.SimpleCacheFileSystem
-   fsspec.implementations.cached.WholeFileCacheFileSystem
-   fsspec.implementations.dask.DaskWorkerFileSystem
-   fsspec.implementations.data.DataFileSystem
-   fsspec.implementations.dbfs.DatabricksFileSystem
-   fsspec.implementations.dirfs.DirFileSystem
-   fsspec.implementations.ftp.FTPFileSystem
-   fsspec.implementations.gist.GistFileSystem
-   fsspec.implementations.git.GitFileSystem
-   fsspec.implementations.github.GithubFileSystem
-   fsspec.implementations.http.HTTPFileSystem
-   fsspec.implementations.jupyter.JupyterFileSystem
-   fsspec.implementations.libarchive.LibArchiveFileSystem
-   fsspec.implementations.local.LocalFileSystem
-   fsspec.implementations.memory.MemoryFileSystem
-   fsspec.implementations.reference.ReferenceFileSystem
-   fsspec.implementations.reference.LazyReferenceMapper
-   fsspec.implementations.sftp.SFTPFileSystem
-   fsspec.implementations.smb.SMBFileSystem
-   fsspec.implementations.tar.TarFileSystem
-   fsspec.implementations.webhdfs.WebHDFS
-   fsspec.implementations.zip.ZipFileSystem
+   implementations.arrow.ArrowFSWrapper
+   implementations.arrow.HadoopFileSystem
+   implementations.cached.CachingFileSystem
+   implementations.cached.SimpleCacheFileSystem
+   implementations.cached.WholeFileCacheFileSystem
+   implementations.dask.DaskWorkerFileSystem
+   implementations.data.DataFileSystem
+   implementations.dbfs.DatabricksFileSystem
+   implementations.dirfs.DirFileSystem
+   implementations.ftp.FTPFileSystem
+   implementations.gist.GistFileSystem
+   implementations.git.GitFileSystem
+   implementations.github.GithubFileSystem
+   implementations.http.HTTPFileSystem
+   implementations.jupyter.JupyterFileSystem
+   implementations.libarchive.LibArchiveFileSystem
+   implementations.local.LocalFileSystem
+   implementations.memory.MemoryFileSystem
+   implementations.reference.ReferenceFileSystem
+   implementations.reference.LazyReferenceMapper
+   implementations.sftp.SFTPFileSystem
+   implementations.smb.SMBFileSystem
+   implementations.tar.TarFileSystem
+   implementations.webhdfs.WebHDFS
+   implementations.zip.ZipFileSystem
 
 .. autoclass:: fsspec.implementations.arrow.ArrowFSWrapper
    :members: __init__
@@ -296,12 +296,12 @@ Read Buffering
 --------------
 
 .. autosummary::
-   fsspec.caching.BlockCache
-   fsspec.caching.BytesCache
-   fsspec.caching.MMapCache
-   fsspec.caching.ReadAheadCache
-   fsspec.caching.FirstChunkCache
-   fsspec.caching.BackgroundBlockCache
+   caching.BlockCache
+   caching.BytesCache
+   caching.MMapCache
+   caching.ReadAheadCache
+   caching.FirstChunkCache
+   caching.BackgroundBlockCache
 
 .. autoclass:: fsspec.caching.BlockCache
    :members:
@@ -326,7 +326,7 @@ Utilities
 
 .. autosummary::
 
-   fsspec.utils.read_block
+   utils.read_block
 
 .. autofunction:: fsspec.utils.read_block
 

{fsspec-2025.9.0 → fsspec-2025.12.0}/docs/source/changelog.rst

@@ -1,6 +1,53 @@
 Changelog
 =========
 
+2025.12.0
+---------
+
+Enhancements
+
+- fsspec.parquet to support filters and multiple files (#1945)
+
+Fixes
+
+- passing withdirs in aync _glob() (#1953)
+- fix _rm_file/_rm redirection in async (#1951)
+- allow arrowFile to be seekable (#1950)
+- add size attribute to arrowFile (#1944)
+
+
+Other
+
+- support py3.14 and drop 3.9 (#1946)
+- avoid ruff warning (#1942)
+
+2025.10.0
+---------
+
+Enhancements
+
+- specify storage_options not use use for tokenising; test instance cache (#1933)
+- base class "chained" for FSs that pass through operations (#1929)
+
+Fixes
+
+- strip protocol for sftp (#1940)
+- use one-step mv in jupyterfs (#1937)
+- raise errors in jupyterfs, not return (#1936)
+- add protocol attribute to http(#1935)
+- allow ls() on a single file for arrowFS (#1931)
+- support kwargs in webhdfs ls() (#1928)
+- better discrimination for parquet in referenceFS (#1923)
+- accept all mode= types in memoryFS (#1922)
+- pass path list to put() in localtempfile for efficiency (#1920)
+- fix docs errors (#1917)
+
+Other
+
+- add CoC (#1924)
+- restrict github/gist tests because of rate limiting (#1918)
+
+
 2025.9.0
 --------
 

fsspec-2025.12.0/docs/source/code-of-conduct.rst

@@ -0,0 +1,126 @@
+Code of Conduct
+===============
+
+All participants in the fsspec community are expected to adhere to a Code of Conduct.
+
+As contributors and maintainers of this project, and in the interest of
+fostering an open and welcoming community, we pledge to respect all people who
+contribute through reporting issues, posting feature requests, updating
+documentation, submitting pull requests or patches, and other activities.
+
+We are committed to making participation in this project a harassment-free
+experience for everyone, treating everyone as unique humans deserving of
+respect.
+
+Examples of unacceptable behaviour by participants include:
+
+- The use of sexualized language or imagery
+- Personal attacks
+- Trolling or insulting/derogatory comments
+- Public or private harassment
+- Publishing other's private information, such as physical or electronic
+  addresses, without explicit permission
+- Other unethical or unprofessional conduct
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviours that they deem inappropriate,
+threatening, offensive, or harmful.
+
+By adopting this Code of Conduct, project maintainers commit themselves
+to fairly and consistently applying these principles to every aspect of
+managing this project. Project maintainers who do not follow or enforce
+the Code of Conduct may be permanently removed from the project team.
+
+This code of conduct applies both within project spaces and in public
+spaces when an individual is representing the project or its community.
+
+If you feel the code of conduct has been violated, please report the
+incident to the fsspec core team.
+
+Reporting
+---------
+
+If you believe someone is violating theCode of Conduct we ask that you report it
+to the  Project by emailing community@anaconda.com. All reports will be kept
+confidential. In some cases we may determine that a public statement will need
+to be made. If that's the case, the identities of all victims and reporters
+will remain confidential unless those individuals instruct us otherwise.
+If you believe anyone is in physical danger, please notify appropriate law
+enforcement first.
+
+In your report please include:
+
+- Your contact info
+- Names (real, nicknames, or pseudonyms) of any individuals involved.
+  If there were other witnesses besides you, please try to include them as well.
+- When and where the incident occurred. Please be as specific as possible.
+- Your account of what occurred. If there is a publicly available record
+  please include a link.
+- Any extra context you believe existed for the incident.
+- If you believe this incident is ongoing.
+- If you believe any member of the core team has a conflict of interest
+  in adjudicating the incident.
+- What, if any, corrective response you believe would be appropriate.
+- Any other information you believe we should have.
+
+Core team members are obligated to maintain confidentiality with regard
+to the reporter and details of an incident.
+
+What happens next?
+~~~~~~~~~~~~~~~~~~
+
+You will receive an email acknowledging receipt of your complaint.
+The core team will immediately meet to review the incident and determine:
+
+- What happened.
+- Whether this event constitutes a code of conduct violation.
+- Who the bad actor was.
+- Whether this is an ongoing situation, or if there is a threat to anyone's
+  physical safety.
+- If this is determined to be an ongoing incident or a threat to physical safety,
+  the working groups' immediate priority will be to protect everyone involved.
+
+If a member of the core team is one of the named parties, they will not be
+included in any discussions, and will not be provided with any confidential
+details from the reporter.
+
+If anyone on the core team believes they have a conflict of interest in
+adjudicating on a reported issue, they will inform the other core team
+members, and exempt themselves from any discussion about the issue.
+Following this declaration, they will not be provided with any confidential
+details from the reporter.
+
+Once the working group has a complete account of the events they will make a
+decision as to how to response. Responses may include:
+
+- Nothing (if we determine no violation occurred).
+- A private reprimand from the working group to the individual(s) involved.
+- A public reprimand.
+- An imposed vacation
+- A permanent or temporary ban from some or all spaces (GitHub repositories, etc.)
+- A request for a public or private apology.
+
+We'll respond within one week to the person who filed the report with either a
+resolution or an explanation of why the situation is not yet resolved.
+
+Once we've determined our final action, we'll contact the original reporter
+to let them know what action (if any) we'll be taking. We'll take into account
+feedback from the reporter on the appropriateness of our response, but we
+don't guarantee we'll act on it.
+
+Acknowledgement
+---------------
+
+This CoC is modified from the one by `BeeWare`_, which in turn refers to
+the `Contributor Covenant`_ and the `Django`_ project.
+
+.. _BeeWare: https://beeware.org/community/behavior/code-of-conduct/
+.. _Contributor Covenant: https://www.contributor-covenant.org/version/1/3/0/code-of-conduct/
+.. _Django: https://www.djangoproject.com/conduct/reporting/
+
+.. raw:: html
+
+    <script data-goatcounter="https://projspec.goatcounter.com/count"
+        async src="//gc.zgo.at/count.js"></script>

{fsspec-2025.9.0 → fsspec-2025.12.0}/docs/source/features.rst

@@ -241,7 +241,9 @@ reads the same zip-file, but extracts the CSV files and stores them locally in t
 **For developers**: this "chaining" methods works by formatting the arguments passed to ``open_*``
 into ``target_protocol`` (a simple string) and ``target_options`` (a dict) and also optionally
 ``fo`` (target path, if a specific file is required). In order for an implementation to chain
-successfully like this, it must look for exactly those named arguments.
+successfully like this, it must look for exactly those named arguments. Implementations that
+require access to the target path of their nested targets should inherit from ``ChainedFileSystem``,
+which will trigger pass-through of the nested path automatically.
 
 Caching Files Locally
 ---------------------

{fsspec-2025.9.0 → fsspec-2025.12.0}/docs/source/index.rst

@@ -119,6 +119,11 @@ The current list of known implementations can be found as follows
    async.rst
    api.rst
    changelog.rst
+   code-of-conduct.rst
+
+
+These docs pages collect anonymous tracking data using goatcounter, and the
+dashboard is available to the public: https://fsspec.goatcounter.com/ .
 
 .. raw:: html
 

{fsspec-2025.9.0 → fsspec-2025.12.0}/fsspec/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '2025.9.0'
-__version_tuple__ = version_tuple = (2025, 9, 0)
+__version__ = version = '2025.12.0'
+__version_tuple__ = version_tuple = (2025, 12, 0)
 
 __commit_id__ = commit_id = None

{fsspec-2025.9.0 → fsspec-2025.12.0}/fsspec/asyn.py

@@ -328,6 +328,11 @@ class AsyncFileSystem(AbstractFileSystem):
         return self._loop
 
     async def _rm_file(self, path, **kwargs):
+        if (
+            inspect.iscoroutinefunction(self._rm)
+            and type(self)._rm is not AsyncFileSystem._rm
+        ):
+            return await self._rm(path, recursive=False, batch_size=1, **kwargs)
         raise NotImplementedError
 
     async def _rm(self, path, recursive=False, batch_size=None, **kwargs):
@@ -776,6 +781,7 @@ class AsyncFileSystem(AbstractFileSystem):
         min_idx = min(idx_star, idx_qmark, idx_brace)
 
         detail = kwargs.pop("detail", False)
+        withdirs = kwargs.pop("withdirs", True)
 
         if not has_magic(path):
             if await self._exists(path, **kwargs):
@@ -805,7 +811,7 @@ class AsyncFileSystem(AbstractFileSystem):
                 depth = None
 
         allpaths = await self._find(
-            root, maxdepth=depth, withdirs=True, detail=True, **kwargs
+            root, maxdepth=depth, withdirs=withdirs, detail=True, **kwargs
         )
 
         pattern = glob_translate(path + ("/" if ends_with_sep else ""))

{fsspec-2025.9.0 → fsspec-2025.12.0}/fsspec/caching.py

@@ -6,20 +6,12 @@ import logging
 import math
 import os
 import threading
-import warnings
 from collections import OrderedDict
+from collections.abc import Callable
 from concurrent.futures import Future, ThreadPoolExecutor
 from itertools import groupby
 from operator import itemgetter
-from typing import (
-    TYPE_CHECKING,
-    Any,
-    Callable,
-    ClassVar,
-    Generic,
-    NamedTuple,
-    TypeVar,
-)
+from typing import TYPE_CHECKING, Any, ClassVar, Generic, NamedTuple, TypeVar
 
 if TYPE_CHECKING:
     import mmap
@@ -629,7 +621,7 @@ class KnownPartsOfAFile(BaseCache):
         fetcher: Fetcher,
         size: int,
         data: dict[tuple[int, int], bytes] | None = None,
-        strict: bool = True,
+        strict: bool = False,
         **_: Any,
     ):
         super().__init__(blocksize, fetcher, size)
@@ -653,50 +645,65 @@ class KnownPartsOfAFile(BaseCache):
         else:
             self.data = {}
 
+    @property
+    def size(self):
+        return sum(_[1] - _[0] for _ in self.data)
+
+    @size.setter
+    def size(self, value):
+        pass
+
+    @property
+    def nblocks(self):
+        return len(self.data)
+
+    @nblocks.setter
+    def nblocks(self, value):
+        pass
+
     def _fetch(self, start: int | None, stop: int | None) -> bytes:
         if start is None:
             start = 0
         if stop is None:
             stop = self.size
+        self.total_requested_bytes += stop - start
 
         out = b""
-        for (loc0, loc1), data in self.data.items():
-            # If self.strict=False, use zero-padded data
-            # for reads beyond the end of a "known" buffer
+        started = False
+        loc_old = 0
+        for loc0, loc1 in sorted(self.data):
+            if (loc0 <= start < loc1) and (loc0 <= stop <= loc1):
+                # entirely within the block
+                off = start - loc0
+                self.hit_count += 1
+                return self.data[(loc0, loc1)][off : off + stop - start]
+            if stop <= loc0:
+                break
+            if started and loc0 > loc_old:
+                # a gap where we need data
+                self.miss_count += 1
+                if self.strict:
+                    raise ValueError
+                out += b"\x00" * (loc0 - loc_old)
             if loc0 <= start < loc1:
+                # found the start
+                self.hit_count += 1
                 off = start - loc0
-                out = data[off : off + stop - start]
-                if not self.strict or loc0 <= stop <= loc1:
-                    # The request is within a known range, or
-                    # it begins within a known range, and we
-                    # are allowed to pad reads beyond the
-                    # buffer with zero
-                    out += b"\x00" * (stop - start - len(out))
-                    self.hit_count += 1
-                    return out
-                else:
-                    # The request ends outside a known range,
-                    # and we are being "strict" about reads
-                    # beyond the buffer
-                    start = loc1
-                    break
-
-        # We only get here if there is a request outside the
-        # known parts of the file. In an ideal world, this
-        # should never happen
-        if self.fetcher is None:
-            # We cannot fetch the data, so raise an error
-            raise ValueError(f"Read is outside the known file parts: {(start, stop)}. ")
-        # We can fetch the data, but should warn the user
-        # that this may be slow
-        warnings.warn(
-            f"Read is outside the known file parts: {(start, stop)}. "
-            f"IO/caching performance may be poor!"
-        )
-        logger.debug(f"KnownPartsOfAFile cache fetching {start}-{stop}")
-        self.total_requested_bytes += stop - start
+                out = self.data[(loc0, loc1)][off : off + stop - start]
+                started = True
+            elif start < loc0 and stop > loc1:
+                # the whole block
+                self.hit_count += 1
+                out += self.data[(loc0, loc1)]
+            elif loc0 <= stop <= loc1:
+                # end block
+                self.hit_count += 1
+                return out + self.data[(loc0, loc1)][: stop - loc0]
+            loc_old = loc1
         self.miss_count += 1
-        return out + super()._fetch(start, stop)
+        if started and not self.strict:
+            return out + b"\x00" * (stop - loc_old)
+        raise ValueError
 
 
 class UpdatableLRU(Generic[P, T]):