feat: synchronize GitHub releases with Gitea

Gitea pull mirrors preserve Git refs but leave release notes and uploaded artifacts outside the backup. Without a separate synchronization path, restoring a repository would still depend on GitHub for important release context and binaries.
This commit is contained in:
Andre
2026-08-08 09:26:35 +02:00
parent d7f5097d1f
commit ecc8aa1c1a
5 changed files with 630 additions and 24 deletions
+375 -5
View File
@@ -1,18 +1,23 @@
#!/usr/bin/env python3
"""Mirror all GitHub repositories of a user into Gitea as pull mirrors.
Existing mirrors are left to Gitea's own cron; this script only creates the
ones that are missing and keeps the mirror interval aligned with the config.
It never deletes anything on the Gitea side -- a mirror that vanished upstream
is exactly what a backup is supposed to keep.
Existing git mirrors are left to Gitea's own cron. This script creates the ones
that are missing, aligns their interval, and synchronizes GitHub release
metadata and assets because Gitea's native mirror does not. It never deletes
anything on the Gitea side -- retained history is the point of a backup.
"""
import json
import http.client
import io
import os
import re
import sys
import tempfile
import urllib.error
import urllib.parse
import urllib.request
import uuid
from datetime import datetime, timezone
KNOWN_KEYS = (
@@ -24,6 +29,8 @@ KNOWN_KEYS = (
"MIRROR_INTERVAL",
"INCLUDE_FORKS",
"INCLUDE_ARCHIVED",
"SYNC_RELEASES",
"SYNC_RELEASE_ASSETS",
"DRY_RUN",
)
@@ -54,6 +61,8 @@ def load_config():
"MIRROR_INTERVAL": "24h",
"INCLUDE_FORKS": "false",
"INCLUDE_ARCHIVED": "true",
"SYNC_RELEASES": "true",
"SYNC_RELEASE_ASSETS": "true",
"DRY_RUN": "false",
}
if os.path.exists(CONFIG_PATH):
@@ -102,6 +111,109 @@ def api(url, token=None, scheme="token", method="GET", payload=None):
return resp.status, (json.loads(body) if body.strip() else None)
def path_part(value):
"""Quote one URL path component, including slashes used inside tag names."""
return urllib.parse.quote(str(value), safe="")
class SafeRedirectHandler(urllib.request.HTTPRedirectHandler):
"""Do not forward API credentials to a cross-host download redirect."""
def redirect_request(self, req, fp, code, msg, headers, newurl):
redirected = super().redirect_request(req, fp, code, msg, headers, newurl)
if redirected is None:
return None
old_host = urllib.parse.urlsplit(req.full_url).netloc.lower()
new_host = urllib.parse.urlsplit(newurl).netloc.lower()
if old_host != new_host:
redirected.remove_header("Authorization")
return redirected
safe_download_opener = urllib.request.build_opener(SafeRedirectHandler())
def download_github_asset(cfg, asset):
"""Download a release asset into a temporary file without buffering it in RAM."""
headers = {
"Accept": "application/octet-stream",
"User-Agent": "gitea-github-mirror/1.0",
}
if cfg["GITHUB_TOKEN"]:
headers["Authorization"] = "Bearer %s" % cfg["GITHUB_TOKEN"]
req = urllib.request.Request(asset["url"], headers=headers)
tmp = tempfile.TemporaryFile()
size = 0
try:
with safe_download_opener.open(req, timeout=180) as resp:
while True:
chunk = resp.read(1024 * 1024)
if not chunk:
break
tmp.write(chunk)
size += len(chunk)
expected = int(asset.get("size") or 0)
if expected and size != expected:
raise IOError("downloaded %d bytes, expected %d" % (size, expected))
tmp.seek(0)
return tmp, size
except Exception:
tmp.close()
raise
def upload_release_asset(cfg, repo_name, release_id, asset, source, size):
"""Stream a temporary file to Gitea as multipart/form-data."""
query = urllib.parse.urlencode({"name": asset["name"]})
url = ("%s/api/v1/repos/%s/%s/releases/%s/assets?%s"
% (cfg["GITEA_URL"], path_part(cfg["GITEA_OWNER"]), path_part(repo_name),
release_id, query))
parsed = urllib.parse.urlsplit(url)
boundary = "----gitea-github-mirror-%s" % uuid.uuid4().hex
safe_name = str(asset["name"]).replace("\\", "_").replace('"', "_")
safe_name = safe_name.replace("\r", "_").replace("\n", "_")
content_type = asset.get("content_type") or "application/octet-stream"
content_type = str(content_type).replace("\r", "").replace("\n", "")
preamble = (
"--%s\r\n"
"Content-Disposition: form-data; name=\"attachment\"; filename=\"%s\"\r\n"
"Content-Type: %s\r\n\r\n" % (boundary, safe_name, content_type)
).encode("utf-8")
ending = ("\r\n--%s--\r\n" % boundary).encode("ascii")
request_path = parsed.path + (("?" + parsed.query) if parsed.query else "")
if parsed.scheme == "https":
conn = http.client.HTTPSConnection(parsed.hostname, parsed.port, timeout=180)
elif parsed.scheme == "http":
conn = http.client.HTTPConnection(parsed.hostname, parsed.port, timeout=180)
else:
raise ValueError("Unsupported Gitea URL scheme: %s" % parsed.scheme)
try:
conn.putrequest("POST", request_path)
conn.putheader("Authorization", "token %s" % cfg["GITEA_TOKEN"])
conn.putheader("Accept", "application/json")
conn.putheader("Content-Type", "multipart/form-data; boundary=%s" % boundary)
conn.putheader("Content-Length", str(len(preamble) + size + len(ending)))
conn.putheader("User-Agent", "gitea-github-mirror/1.0")
conn.endheaders()
conn.send(preamble)
while True:
chunk = source.read(1024 * 1024)
if not chunk:
break
conn.send(chunk)
conn.send(ending)
response = conn.getresponse()
body = response.read()
if response.status >= 400:
raise urllib.error.HTTPError(
url, response.status, response.reason, response.headers, io.BytesIO(body))
return json.loads(body.decode("utf-8")) if body.strip() else None
finally:
conn.close()
def github_repos(cfg):
"""All repos owned by the user; private ones included when a token is set."""
token = cfg["GITHUB_TOKEN"]
@@ -229,6 +341,229 @@ def align_interval(cfg, name, existing, dry_run):
log("OK", "interval of %s set to %s" % (name, cfg["MIRROR_INTERVAL"]))
def github_releases(cfg, repo_name):
releases = []
page = 1
while True:
url = ("https://api.github.com/repos/%s/%s/releases?per_page=100&page=%d"
% (path_part(cfg["GITHUB_USER"]), path_part(repo_name), page))
_, batch = api(url, token=cfg["GITHUB_TOKEN"], scheme="Bearer")
if not batch:
break
releases.extend(batch)
if len(batch) < 100:
break
page += 1
return releases
def github_release_assets(cfg, repo_name, release_id):
assets = []
page = 1
while True:
url = ("https://api.github.com/repos/%s/%s/releases/%s/assets"
"?per_page=100&page=%d"
% (path_part(cfg["GITHUB_USER"]), path_part(repo_name), release_id, page))
_, batch = api(url, token=cfg["GITHUB_TOKEN"], scheme="Bearer")
if not batch:
break
assets.extend(batch)
if len(batch) < 100:
break
page += 1
return assets
def gitea_releases(cfg, repo_name):
releases = []
page = 1
while True:
url = ("%s/api/v1/repos/%s/%s/releases?limit=50&page=%d"
% (cfg["GITEA_URL"], path_part(cfg["GITEA_OWNER"]),
path_part(repo_name), page))
_, batch = api(url, token=cfg["GITEA_TOKEN"])
if not batch:
break
releases.extend(batch)
if len(batch) < 50:
break
page += 1
return releases
def gitea_tags(cfg, repo_name):
tags = set()
page = 1
while True:
url = ("%s/api/v1/repos/%s/%s/tags?limit=50&page=%d"
% (cfg["GITEA_URL"], path_part(cfg["GITEA_OWNER"]),
path_part(repo_name), page))
_, batch = api(url, token=cfg["GITEA_TOKEN"])
if not batch:
break
tags.update(tag["name"] for tag in batch)
if len(batch) < 50:
break
page += 1
return tags
def release_payload(release):
return {
"tag_name": release["tag_name"],
"target_commitish": release.get("target_commitish") or "",
"name": release.get("name") or "",
"body": release.get("body") or "",
"draft": bool(release.get("draft")),
"prerelease": bool(release.get("prerelease")),
}
def release_needs_update(source, target):
"""Return true for fields Gitea's PATCH endpoint can actually change."""
wanted = release_payload(source)
if bool(target.get("draft")) != wanted["draft"]:
return True
if bool(target.get("prerelease")) != wanted["prerelease"]:
return True
# Gitea ignores empty strings in release PATCH requests. Retaining old text
# also follows this script's policy of never deleting backup information.
if wanted["name"] and (target.get("name") or "") != wanted["name"]:
return True
if wanted["body"] and (target.get("body") or "") != wanted["body"]:
return True
return False
def release_update_payload(source):
wanted = release_payload(source)
payload = {
"draft": wanted["draft"],
"prerelease": wanted["prerelease"],
}
for key in ("target_commitish", "name", "body"):
if wanted[key]:
payload[key] = wanted[key]
return payload
def sync_release_assets(cfg, repo_name, source_release, target_release, dry_run):
copied = preserved = 0
source_assets = github_release_assets(cfg, repo_name, source_release["id"])
target_assets = {asset["name"]: asset for asset in target_release.get("assets", [])}
for asset in source_assets:
name = asset["name"]
existing = target_assets.get(name)
if existing is not None:
source_size = int(asset.get("size") or 0)
target_size = int(existing.get("size") or 0)
if source_size and target_size and source_size != target_size:
preserved += 1
log("WARN", "%s release %s asset %s differs (%d vs %d bytes) - "
"Gitea copy left untouched"
% (repo_name, source_release["tag_name"], name,
source_size, target_size))
continue
if dry_run:
log("DRY", "would copy %s release %s asset %s (%d bytes)"
% (repo_name, source_release["tag_name"], name,
int(asset.get("size") or 0)))
copied += 1
continue
tmp = None
try:
tmp, size = download_github_asset(cfg, asset)
upload_release_asset(cfg, repo_name, target_release["id"], asset, tmp, size)
copied += 1
log("OK", "copied %s release %s asset %s (%d bytes)"
% (repo_name, source_release["tag_name"], name, size))
except urllib.error.HTTPError as exc:
detail = exc.read().decode("utf-8", "replace")[:300]
fail("%s release %s asset %s failed (HTTP %s): %s"
% (repo_name, source_release["tag_name"], name, exc.code, detail))
except Exception as exc:
fail("%s release %s asset %s failed: %s"
% (repo_name, source_release["tag_name"], name, exc))
finally:
if tmp is not None:
tmp.close()
return copied, preserved
def sync_releases(cfg, repo_name, dry_run):
stats = {"created": 0, "updated": 0, "assets": 0, "preserved": 0, "waiting": 0}
source_releases = github_releases(cfg, repo_name)
target_releases = gitea_releases(cfg, repo_name)
by_tag = {release["tag_name"]: release for release in target_releases}
tags_to_check = [
release["tag_name"] for release in source_releases
if not release.get("draft")
and (release["tag_name"] not in by_tag
or by_tag[release["tag_name"]].get("draft"))
]
available_tags = gitea_tags(cfg, repo_name) if tags_to_check else set()
source_tags = {release["tag_name"] for release in source_releases}
orphaned = sorted(tag for tag in by_tag if tag not in source_tags)
if orphaned:
log("WARN", "%s Gitea release(s) with no GitHub counterpart left untouched: %s"
% (repo_name, ", ".join(orphaned)))
for source in source_releases:
tag = source["tag_name"]
target = by_tag.get(tag)
needs_mirrored_tag = (not source.get("draft")
and (target is None or target.get("draft")))
if needs_mirrored_tag and tag not in available_tags:
stats["waiting"] += 1
log("WARN", "%s release %s waits for its tag to reach the Gitea mirror"
% (repo_name, tag))
continue
try:
if target is None:
if dry_run:
target = {"id": source["id"], "tag_name": tag, "assets": []}
log("DRY", "would create %s release %s" % (repo_name, tag))
else:
_, target = api(
"%s/api/v1/repos/%s/%s/releases"
% (cfg["GITEA_URL"], path_part(cfg["GITEA_OWNER"]),
path_part(repo_name)),
token=cfg["GITEA_TOKEN"], method="POST",
payload=release_payload(source))
log("OK", "created %s release %s" % (repo_name, tag))
stats["created"] += 1
elif release_needs_update(source, target):
if dry_run:
log("DRY", "would update %s release %s" % (repo_name, tag))
else:
_, target = api(
"%s/api/v1/repos/%s/%s/releases/%s"
% (cfg["GITEA_URL"], path_part(cfg["GITEA_OWNER"]),
path_part(repo_name), target["id"]),
token=cfg["GITEA_TOKEN"], method="PATCH",
payload=release_update_payload(source))
log("OK", "updated %s release %s" % (repo_name, tag))
stats["updated"] += 1
if truthy(cfg["SYNC_RELEASE_ASSETS"]):
copied, preserved = sync_release_assets(
cfg, repo_name, source, target, dry_run)
stats["assets"] += copied
stats["preserved"] += preserved
except urllib.error.HTTPError as exc:
detail = exc.read().decode("utf-8", "replace")[:300]
fail("%s release %s failed (HTTP %s): %s"
% (repo_name, tag, exc.code, detail))
except Exception as exc:
fail("%s release %s failed: %s" % (repo_name, tag, exc))
return stats
def main():
cfg = load_config()
dry_run = truthy(cfg["DRY_RUN"])
@@ -272,6 +607,8 @@ def main():
"not 'Public repositories'")
created = skipped = 0
release_totals = {"created": 0, "updated": 0, "assets": 0,
"preserved": 0, "waiting": 0}
for repo in sorted(repos, key=lambda r: r["name"].lower()):
name = repo["name"]
try:
@@ -281,14 +618,30 @@ def main():
continue
if existing is None:
mirror_created = False
try:
create_mirror(cfg, repo, dry_run)
created += 1
mirror_created = True
except urllib.error.HTTPError as exc:
detail = exc.read().decode("utf-8", "replace")[:300]
fail("%s: migrate failed (HTTP %s): %s" % (name, exc.code, detail))
except Exception as exc:
fail("%s: migrate failed: %s" % (name, exc))
if mirror_created and truthy(cfg["SYNC_RELEASES"]):
try:
if dry_run:
count = len(github_releases(cfg, name))
if count:
log("DRY", "would synchronize %d release(s) after creating %s"
% (count, name))
else:
stats = sync_releases(cfg, name, dry_run)
for key in release_totals:
release_totals[key] += stats[key]
except Exception as exc:
fail("%s: could not synchronize releases: %s" % (name, exc))
continue
skipped += 1
@@ -300,6 +653,18 @@ def main():
except Exception as exc:
fail("%s: could not update mirror interval: %s" % (name, exc))
if truthy(cfg["SYNC_RELEASES"]):
try:
stats = sync_releases(cfg, name, dry_run)
for key in release_totals:
release_totals[key] += stats[key]
except urllib.error.HTTPError as exc:
detail = exc.read().decode("utf-8", "replace")[:300]
fail("%s: release sync failed (HTTP %s): %s"
% (name, exc.code, detail))
except Exception as exc:
fail("%s: release sync failed: %s" % (name, exc))
github_names = {r["name"].lower() for r in repos}
try:
page, orphans = 1, []
@@ -323,7 +688,12 @@ def main():
except Exception as exc:
log("WARN", "Could not check for orphaned mirrors: %s" % exc)
log("INFO", "Done: %d created, %d already present, %d error(s)" % (created, skipped, errors))
log("INFO", "Done: %d mirror(s) created, %d already present; releases: "
"%d created, %d updated, %d asset(s) copied, %d preserved, "
"%d waiting for tags; %d error(s)"
% (created, skipped, release_totals["created"], release_totals["updated"],
release_totals["assets"], release_totals["preserved"],
release_totals["waiting"], errors))
return 1 if errors else 0