unsloth/tests/version_compat/_fetch.py
Daniel Han a6dc10dad2
Reduce and tighten comments and docstrings across the test suite (#6429)
* Reduce and tighten comments and docstrings in tests

Shorten verbose comments and docstrings across the test suite without
changing any test logic. Remove narration that restates the next line,
collapse long module and test docstrings to a single line, and drop banner
separators. Keep regression context (issue and PR references, run ids),
skip reasons, mocking and timing rationale, license headers, lint and type
directives, and commented-out code.

Comments and docstrings only: an AST signature check confirms no code,
assertions, or string literals changed, and the suite byte-compiles cleanly.

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
2026-06-18 01:07:09 -07:00

58 lines
1.9 KiB
Python

# SPDX-License-Identifier: AGPL-3.0-only
# Copyright 2026-present the Unsloth AI Inc. team.
"""Shared helpers for version-compat suites: GitHub raw fetch + regex symbol grep."""
from __future__ import annotations
import os
import re
import urllib.error
import urllib.request
import pytest
def fetch_text(repo: str, ref: str, path: str) -> str | None:
"""Fetch a file from GitHub raw. None on 404; skips on transient network errors."""
url = f"https://raw.githubusercontent.com/{repo}/{ref}/{path}"
req = urllib.request.Request(url)
token = os.environ.get("GITHUB_TOKEN") or os.environ.get("GH_TOKEN")
if token:
req.add_header("Authorization", f"Bearer {token}")
try:
with urllib.request.urlopen(req, timeout = 15) as r:
return r.read().decode("utf-8", errors = "replace")
except urllib.error.HTTPError as e:
if e.code == 404:
return None
pytest.skip(f"GitHub fetch failed ({e.code}) for {url}")
except (urllib.error.URLError, TimeoutError) as e:
pytest.skip(f"GitHub fetch failed ({e}) for {url}")
def has_def(
src: str,
name: str,
kind: str = "any",
) -> bool:
"""Grep for `class Name`, `def name`, or `Name = ...` at any indent (no ast.parse)."""
if kind in ("any", "class") and re.search(
rf"^\s*class\s+{re.escape(name)}\b", src, re.MULTILINE
):
return True
if kind in ("any", "func") and re.search(
rf"^\s*(?:async\s+)?def\s+{re.escape(name)}\b", src, re.MULTILINE
):
return True
if kind == "any" and re.search(rf"^\s*{re.escape(name)}\s*[:=]", src, re.MULTILINE):
return True
return False
def first_match(repo: str, ref: str, paths: list[str]) -> tuple[str, str] | None:
"""Return (path, src) for the first existing candidate path, else None."""
for p in paths:
src = fetch_text(repo, ref, p)
if src is not None:
return (p, src)
return None