GH-45295: [Python][CI] Make download_tzdata_on_windows more robust and use tzdata package for tzinfo database on Windows for ORC (#45425)

We have two Windows issues and this PR is addressing both:

1. PyArrow's `download_tzdata_on_windows` can fail due to TLS issues in certain CI environments.
2. The Python wheel test infrastructure needs a tzinfo database for ORC and the automation fetching that started failing because the URL was made invalid upstream.

These two issues are being solved in one PR simply because they appeared together during the 19.0.1 release process but they're separate.

1. Makes `download_tzdata_on_windows` more robust to TLS errors by attempting to use `requests` if it's available and falling back to urllib otherwise.
2. Switches our Windows wheel test infrastructure to grab a tzinfo database from the tzdata package on PyPi instead of from a mirror URL. This should be much more stable for us over time.

Yes.

No.
* GitHub Issue: #45295

Lead-authored-by: Bryce Mecum <[email protected]>
Co-authored-by: Joris Van den Bossche <[email protected]>
Signed-off-by: Bryce Mecum <[email protected]>

Author: amoeba

ci/scripts/python_wheel_windows_test.bat

@@ -67,11 +67,5 @@ set PYTHON_CMD=py -%PYTHON%
 @REM Validate wheel contents
 %PYTHON_CMD% C:\arrow\ci\scripts\python_wheel_validate_contents.py --path C:\arrow\python\repaired_wheels || exit /B 1
 
-@rem Download IANA Timezone Database for ORC C++
-curl https://cygwin.osuosl.org/noarch/release/tzdata/tzdata-2024a-1.tar.xz --output tzdata.tar.xz || exit /B
-mkdir %USERPROFILE%\Downloads\test\tzdata
-arc unarchive tzdata.tar.xz %USERPROFILE%\Downloads\test\tzdata
-set TZDIR=%USERPROFILE%\Downloads\test\tzdata\usr\share\zoneinfo
-
 @REM Execute unittest
 %PYTHON_CMD% -m pytest -r s --pyargs pyarrow || exit /B 1

python/pyarrow/tests/conftest.py

@@ -55,6 +55,22 @@
         set_timezone_db_path(tzdata_set_path)
 
 
+# GH-45295: For ORC, try to populate TZDIR env var from tzdata package resource
+# path.
+#
+# Note this is a different kind of database than what we allow to be set by
+# `PYARROW_TZDATA_PATH` and passed to set_timezone_db_path.
+if sys.platform == 'win32':
+    if os.environ.get('TZDIR', None) is None:
+        from importlib import resources
+        try:
+            os.environ['TZDIR'] = os.path.join(resources.files('tzdata'), 'zoneinfo')
+        except ModuleNotFoundError:
+            print(
+                'Package "tzdata" not found. Not setting TZDIR environment variable.'
+            )
+
+
 def pytest_addoption(parser):
     # Create options to selectively enable test groups
     def bool_env(name, default=None):

python/pyarrow/util.py

@@ -230,6 +230,20 @@ def _break_traceback_cycle_from_frame(frame):
     refs = frame = this_frame = None
 
 
+def _download_urllib(url, out_path):
+    from urllib.request import urlopen
+    with urlopen(url) as response:
+        with open(out_path, 'wb') as f:
+            f.write(response.read())
+
+
+def _download_requests(url, out_path):
+    import requests
+    with requests.get(url) as response:
+        with open(out_path, 'wb') as f:
+            f.write(response.content)
+
+
 def download_tzdata_on_windows():
     r"""
     Download and extract latest IANA timezone database into the
@@ -240,19 +254,23 @@ def download_tzdata_on_windows():
 
     import tarfile
 
+    tzdata_url = "https://data.iana.org/time-zones/tzdata-latest.tar.gz"
     tzdata_path = os.path.expandvars(r"%USERPROFILE%\Downloads\tzdata")
-    tzdata_compressed = os.path.join(tzdata_path, "tzdata.tar.gz")
+    tzdata_compressed_path = os.path.join(tzdata_path, "tzdata.tar.gz")
+    windows_zones_url = "https://raw.githubusercontent.com/unicode-org/cldr/master/common/supplemental/windowsZones.xml"  # noqa
+    windows_zones_path = os.path.join(tzdata_path, "windowsZones.xml")
     os.makedirs(tzdata_path, exist_ok=True)
 
-    from urllib.request import urlopen
-    with urlopen('https://data.iana.org/time-zones/tzdata-latest.tar.gz') as response:
-        with open(tzdata_compressed, 'wb') as f:
-            f.write(response.read())
-
-    assert os.path.exists(tzdata_compressed)
+    # Try to download the files with requests and then fall back to urllib. This
+    # works around possible issues in certain older environment (GH-45295)
+    try:
+        _download_requests(tzdata_url, tzdata_compressed_path)
+        _download_requests(windows_zones_url, windows_zones_path)
+    except ImportError:
+        _download_urllib(tzdata_url, tzdata_compressed_path)
+        _download_urllib(windows_zones_url, windows_zones_path)
 
-    tarfile.open(tzdata_compressed).extractall(tzdata_path)
+    assert os.path.exists(tzdata_compressed_path)
+    assert os.path.exists(windows_zones_path)
 
-    with urlopen('https://raw.githubusercontent.com/unicode-org/cldr/master/common/supplemental/windowsZones.xml') as response_zones:   # noqa
-        with open(os.path.join(tzdata_path, "windowsZones.xml"), 'wb') as f:
-            f.write(response_zones.read())
+    tarfile.open(tzdata_compressed_path).extractall(tzdata_path)

python/requirements-wheel-test.txt

@@ -4,6 +4,7 @@ hypothesis
 pytest
 pytz
 pyuwsgi; sys.platform != 'win32' and python_version < '3.13'
+requests; sys_platform == 'win32'
 tzdata; sys_platform == 'win32'
 
 # We generally test with the oldest numpy version that supports a given Python