cpython/Lib/test/test_zoneinfo/data/update_test_data.py
Paul Ganssle 62972d9d73
bpo-40503: PEP 615: Tests and implementation for zoneinfo (GH-19909)
This is the initial implementation of PEP 615, the zoneinfo module,
ported from the standalone reference implementation (see
https://www.python.org/dev/peps/pep-0615/#reference-implementation for a
link, which has a more detailed commit history).

This includes (hopefully) all functional elements described in the PEP,
but documentation is found in a separate PR. This includes:

1. A pure python implementation of the ZoneInfo class
2. A C accelerated implementation of the ZoneInfo class
3. Tests with 100% branch coverage for the Python code (though C code
   coverage is less than 100%).
4. A compile-time configuration option on Linux (though not on Windows)

Differences from the reference implementation:

- The module is arranged slightly differently: the accelerated module is
  `_zoneinfo` rather than `zoneinfo._czoneinfo`, which also necessitates
  some changes in the test support function. (Suggested by Victor
  Stinner and Steve Dower.)
- The tests are arranged slightly differently and do not include the
  property tests. The tests live at test/test_zoneinfo/test_zoneinfo.py
  rather than test/test_zoneinfo.py or test/test_zoneinfo/__init__.py
  because we may do some refactoring in the future that would likely
  require this separation anyway; we may:
        - include the property tests
        - automatically run all the tests against both pure Python and C,
          rather than manually constructing C and Python test classes (similar
          to the way this works with test_datetime.py, which generates C
          and Python test cases from datetimetester.py).
- This includes a compile-time configuration option on Linux (though not
  on Windows); added with much help from Thomas Wouters.
- Integration into the CPython build system is obviously different from
  building a standalone zoneinfo module wheel.
- This includes configuration to install the tzdata package as part of
  CI, though only on the coverage jobs. Introducing a PyPI dependency as
  part of the CI build was controversial, and this is seen as less of a
  major change, since the coverage jobs already depend on pip and PyPI.

Additional changes that were introduced as part of this PR, most / all of
which were backported to the reference implementation:

- Fixed reference and memory leaks

    With much debugging help from Pablo Galindo

- Added smoke tests ensuring that the C and Python modules are built

    The import machinery can be somewhat fragile, and the "seamlessly falls
    back to pure Python" nature of this module makes it so that a problem
    building the C extension or a failure to import the pure Python version
    might easily go unnoticed.

- Adjustments to zoneinfo.__dir__

    Suggested by Petr Viktorin.

- Slight refactorings as suggested by Steve Dower.

- Removed unnecessary if check on std_abbr

    Discovered this because of a missing line in branch coverage.
2020-05-16 10:20:06 +02:00

122 lines
3.1 KiB
Python

"""
Script to automatically generate a JSON file containing time zone information.
This is done to allow "pinning" a small subset of the tzdata in the tests,
since we are testing properties of a file that may be subject to change. For
example, the behavior in the far future of any given zone is likely to change,
but "does this give the right answer for this file in 2040" is still an
important property to test.
This must be run from a computer with zoneinfo data installed.
"""
from __future__ import annotations
import base64
import functools
import json
import lzma
import pathlib
import textwrap
import typing
import zoneinfo
KEYS = [
"Africa/Abidjan",
"Africa/Casablanca",
"America/Los_Angeles",
"America/Santiago",
"Asia/Tokyo",
"Australia/Sydney",
"Europe/Dublin",
"Europe/Lisbon",
"Europe/London",
"Pacific/Kiritimati",
"UTC",
]
TEST_DATA_LOC = pathlib.Path(__file__).parent
@functools.lru_cache(maxsize=None)
def get_zoneinfo_path() -> pathlib.Path:
"""Get the first zoneinfo directory on TZPATH containing the "UTC" zone."""
key = "UTC"
for path in map(pathlib.Path, zoneinfo.TZPATH):
if (path / key).exists():
return path
else:
raise OSError("Cannot find time zone data.")
def get_zoneinfo_metadata() -> typing.Dict[str, str]:
path = get_zoneinfo_path()
tzdata_zi = path / "tzdata.zi"
if not tzdata_zi.exists():
# tzdata.zi is necessary to get the version information
raise OSError("Time zone data does not include tzdata.zi.")
with open(tzdata_zi, "r") as f:
version_line = next(f)
_, version = version_line.strip().rsplit(" ", 1)
if (
not version[0:4].isdigit()
or len(version) < 5
or not version[4:].isalpha()
):
raise ValueError(
"Version string should be YYYYx, "
+ "where YYYY is the year and x is a letter; "
+ f"found: {version}"
)
return {"version": version}
def get_zoneinfo(key: str) -> bytes:
path = get_zoneinfo_path()
with open(path / key, "rb") as f:
return f.read()
def encode_compressed(data: bytes) -> typing.List[str]:
compressed_zone = lzma.compress(data)
raw = base64.b85encode(compressed_zone)
raw_data_str = raw.decode("utf-8")
data_str = textwrap.wrap(raw_data_str, width=70)
return data_str
def load_compressed_keys() -> typing.Dict[str, typing.List[str]]:
output = {key: encode_compressed(get_zoneinfo(key)) for key in KEYS}
return output
def update_test_data(fname: str = "zoneinfo_data.json") -> None:
TEST_DATA_LOC.mkdir(exist_ok=True, parents=True)
# Annotation required: https://github.com/python/mypy/issues/8772
json_kwargs: typing.Dict[str, typing.Any] = dict(
indent=2, sort_keys=True,
)
compressed_keys = load_compressed_keys()
metadata = get_zoneinfo_metadata()
output = {
"metadata": metadata,
"data": compressed_keys,
}
with open(TEST_DATA_LOC / fname, "w") as f:
json.dump(output, f, **json_kwargs)
if __name__ == "__main__":
update_test_data()