Files
artifactapi/src/artifactapi/artifact/discovery.py
T
unkinben e6d9b175ce
ci/woodpecker/pr/pre-commit Pipeline was successful
ci/woodpecker/pr/test Pipeline was successful
ci/woodpecker/pr/build Pipeline was successful
refactor: extract route handler logic into artifact/ subpackage
Each route in main.py is now a single-line delegation to an artifact submodule:
- artifact/proxy.py  — remote artifact GET, caching, mutable revalidation
- artifact/local.py  — local repo upload/check/delete
- artifact/docker.py — Docker Registry v2 proxy + ping
- artifact/discovery.py — GitHub release discovery + bulk cache
- artifact/flush.py  — cache flush

UpstreamUnreachable, cache_single_artifact, _upstream_reachable and
check_upstream_changed moved from main.py to artifact/proxy.py.
Tests updated to patch at their new locations.

All 187 tests pass.
2026-04-28 22:21:01 +10:00

83 lines
3.0 KiB
Python

import logging
import re
from typing import Any
from urllib.parse import urlparse
import httpx
from fastapi import HTTPException
from .proxy import cache_single_artifact
logger = logging.getLogger(__name__)
async def _discover_github_releases(remote: str, include_pattern: str) -> list[str]:
match = re.match(r"github\.com/([^/]+)/([^/]+)", remote)
if not match:
raise HTTPException(status_code=400, detail="Invalid GitHub remote format")
owner, repo = match.groups()
async with httpx.AsyncClient(follow_redirects=True) as client:
response = await client.get(f"https://api.github.com/repos/{owner}/{repo}/releases")
if response.status_code != 200:
raise HTTPException(status_code=response.status_code, detail=f"Failed to fetch releases: {response.text}")
releases = response.json()
regex = re.compile(include_pattern.replace("*", ".*"))
return [
asset["browser_download_url"]
for release in releases
for asset in release.get("assets", [])
if regex.search(asset["browser_download_url"])
]
async def _discover(remote: str, include_pattern: str) -> list[str]:
if "github.com" in remote:
return await _discover_github_releases(remote, include_pattern)
raise HTTPException(status_code=400, detail=f"Unsupported remote: {remote}")
async def cache_artifacts(remote: str, include_pattern: str, storage) -> dict[str, Any]:
try:
matching_urls = await _discover(remote, include_pattern)
if not matching_urls:
return {"message": "No matching artifacts found", "cached_count": 0, "artifacts": []}
cached_artifacts = []
for url in matching_urls:
result = await cache_single_artifact(url, "", "", storage, {})
cached_artifacts.append(result)
cached_count = sum(1 for a in cached_artifacts if a["status"] in ["cached", "already_cached"])
return {
"message": f"Processed {len(matching_urls)} artifacts, {cached_count} successfully cached",
"cached_count": cached_count,
"artifacts": cached_artifacts,
}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))
async def list_artifacts(remote: str, include_pattern: str, storage) -> dict[str, Any]:
try:
matching_urls = await _discover(remote, include_pattern)
cached_artifacts = []
for url in matching_urls:
parsed = urlparse(url)
key = storage.get_object_key(remote, parsed.path)
if storage.exists(key):
cached_artifacts.append({"url": url, "cached_url": storage.get_url(key), "key": key})
return {
"remote": remote,
"pattern": include_pattern,
"total_found": len(matching_urls),
"cached_count": len(cached_artifacts),
"artifacts": cached_artifacts,
}
except Exception as e:
raise HTTPException(status_code=500, detail=str(e))