Merge branch 'main' into energy-usage

CHANGELOG.rst

@@ -14,10 +14,13 @@ Bug fixes
 ^^^^^^^^^
 * Fixed pickling issue with ``xclim.sdba.Grouper`` and other classes for usage with `dask>=2024.11`. (:issue:`1992`, :pull:`1993`).
 * Fixed an issue with ``nimbus`` that was causing URL path components to be improperly joined. (:pull:`1997`).
+* `base_kws_vars` in `MBCn` is now copied inside the `adjust` function so that in-place changes do not change the dict globally. (:pull:`1999`).
+* Fixed a bug in the logic of ``xclim.testing.utils.load_registry`` that impacted the ability to load a `registry.txt` from a non-default repository. (:pull:`2001`).
 
 Internal changes
 ^^^^^^^^^^^^^^^^
-* Changed French translations with word "pluvieux" to "avec précipitations". (:issue:`1960`, :pull:`1994`).
+* Changed french translations with word "pluvieux" to "avec précipitations". (:issue:`1960`, :pull:`1994`).
+* In order to address 403 (forbidden) request errors when retrieving data from GitHub via ReadTheDocs, the ``nimbus`` class has been modified to use an overloaded `fetch` method that appends a User-Agent header to the request. (:pull:`2001`).
 * Addressed a very rare race condition that can happen if `pytest` is tearing down the test environment when running across multiple workers. (:pull:`1863`).
 
 CI changes

CI/requirements_ci.in

@@ -1,5 +1,5 @@
 bump-my-version==0.28.1
-deptry==0.21.0
+deptry==0.21.1
 flit==3.10.1
 pip==24.3.1
 pylint==3.3.1

pyproject.toml

@@ -65,7 +65,7 @@ dev = [
   "codespell ==2.3.0",
   "coverage[toml] >=7.5.0",
   "coveralls >=4.0.1", # coveralls is not yet compatible with Python 3.13
-  "deptry ==0.21.0",
+  "deptry ==0.21.1",
   "flake8 >=7.1.1",
   "flake8-rst-docstrings >=0.3.0",
   "h5netcdf>=1.3.0",
@@ -134,7 +134,7 @@ target-version = [
 ]
 
 [tool.bumpversion]
-current_version = "0.53.3-dev.2"
+current_version = "0.53.3-dev.4"
 commit = true
 commit_args = "--no-verify"
 tag = false

xclim/__init__.py

@@ -13,7 +13,7 @@
 
 __author__ = """Travis Logan"""
 __email__ = "[email protected]"
-__version__ = "0.53.3-dev.2"
+__version__ = "0.53.3-dev.4"
 
 
 with _resources.as_file(_resources.files("xclim.data")) as _module_data:

xclim/sdba/adjustment.py

@@ -5,6 +5,7 @@
 """
 from __future__ import annotations
 
+from copy import deepcopy
 from importlib.util import find_spec
 from inspect import signature
 from typing import Any
@@ -1818,7 +1819,7 @@ def _adjust(
         period_dim=None,
     ):
         # set default values for non-specified parameters
-        base_kws_vars = base_kws_vars or {}
+        base_kws_vars = {} if base_kws_vars is None else deepcopy(base_kws_vars)
         pts_dim = self.pts_dims[0]
         for v in sim[pts_dim].values:
             base_kws_vars.setdefault(v, {})

xclim/testing/utils.py

@@ -13,13 +13,14 @@
 import sys
 import time
 import warnings
-from collections.abc import Sequence
+from collections.abc import Callable, Sequence
 from datetime import datetime as dt
+from functools import wraps
 from importlib import import_module
 from io import StringIO
 from pathlib import Path
 from shutil import copytree
-from typing import TextIO
+from typing import IO, TextIO
 from urllib.error import HTTPError, URLError
 from urllib.parse import urljoin, urlparse
 from urllib.request import urlretrieve
@@ -435,26 +436,38 @@ def load_registry(
     dict
         Dictionary of filenames and hashes.
     """
+    if not repo.endswith("/"):
+        repo = f"{repo}/"
     remote_registry = audit_url(
         urljoin(
             urljoin(repo, branch if branch.endswith("/") else f"{branch}/"),
             "data/registry.txt",
         )
     )
 
-    if branch != default_testdata_version:
+    if repo != default_testdata_repo_url:
+        external_repo_name = urlparse(repo).path.split("/")[-2]
+        external_branch_name = branch.split("/")[-1]
+        registry_file = Path(
+            str(
+                ilr.files("xclim").joinpath(
+                    f"testing/registry.{external_repo_name}.{external_branch_name}.txt"
+                )
+            )
+        )
+        urlretrieve(remote_registry, registry_file)  # noqa: S310
+
+    elif branch != default_testdata_version:
         custom_registry_folder = Path(
             str(ilr.files("xclim").joinpath(f"testing/{branch}"))
         )
         custom_registry_folder.mkdir(parents=True, exist_ok=True)
         registry_file = custom_registry_folder.joinpath("registry.txt")
         urlretrieve(remote_registry, registry_file)  # noqa: S310
 
-    elif repo != default_testdata_repo_url:
+    else:
         registry_file = Path(str(ilr.files("xclim").joinpath("testing/registry.txt")))
-        urlretrieve(remote_registry, registry_file)  # noqa: S310
 
-    registry_file = Path(str(ilr.files("xclim").joinpath("testing/registry.txt")))
     if not registry_file.exists():
         raise FileNotFoundError(f"Registry file not found: {registry_file}")
 
@@ -516,10 +529,13 @@ def nimbus(  # noqa: PR01
             "The `pooch` package is required to fetch the xclim testing data. "
             "You can install it with `pip install pooch` or `pip install xclim[dev]`."
         )
+    if not repo.endswith("/"):
+        repo = f"{repo}/"
     remote = audit_url(
         urljoin(urljoin(repo, branch if branch.endswith("/") else f"{branch}/"), "data")
     )
-    return pooch.create(
+
+    _nimbus = pooch.create(
         path=cache_dir,
         base_url=remote,
         version=default_testdata_version,
@@ -528,6 +544,35 @@ def nimbus(  # noqa: PR01
         registry=load_registry(branch=branch, repo=repo),
     )
 
+    # Add a custom fetch method to the Pooch instance
+    # Needed to address: https://github.com/readthedocs/readthedocs.org/issues/11763
+    # Fix inspired by @bjlittle (https://github.com/bjlittle/geovista/pull/1202)
+    _nimbus.fetch_diversion = _nimbus.fetch
+
+    # Overload the fetch method to add user-agent headers
+    @wraps(_nimbus.fetch_diversion)
+    def _fetch(*args: str, **kwargs: bool | Callable) -> str:  # numpydoc ignore=GL08
+
+        def _downloader(
+            url: str,
+            output_file: str | IO,
+            poocher: pooch.Pooch,
+            check_only: bool | None = False,
+        ) -> None:
+            """Download the file from the URL and save it to the save_path."""
+            headers = {"User-Agent": f"xclim ({__xclim_version__})"}
+            downloader = pooch.HTTPDownloader(headers=headers)
+            return downloader(url, output_file, poocher, check_only=check_only)
+
+        # default to our http/s downloader with user-agent headers
+        kwargs.setdefault("downloader", _downloader)
+        return _nimbus.fetch_diversion(*args, **kwargs)
+
+    # Replace the fetch method with the custom fetch method
+    _nimbus.fetch = _fetch
+
+    return _nimbus
+
 
 # idea copied from raven that it borrowed from xclim that borrowed it from xarray that was borrowed from Seaborn
 def open_dataset(