feat: v3 Go rewrite — full artifact proxy with web UI, TUI, and Terraform provider
Complete rewrite of ArtifactAPI from Python/FastAPI to Go as a single binary. Core engine: - 10 package providers: generic, docker, helm, pypi, npm, rpm, alpine, puppet, terraform, goproxy — each with built-in mutable patterns - Content-addressable storage (SHA256 dedup across all remotes) - Three-tier caching: Redis (TTL/locks) → S3/MinIO (blobs) → upstream - Classifier with allowlist/blocklist per-remote (empty = allow all) - Circuit breaker, conditional revalidation, stale-on-error - Background garbage collection for orphaned blobs - Access logging to PostgreSQL API: - v1 proxy endpoints (backwards compatible) - v2 management API: CRUD remotes/virtuals, object browser, stats, health, SSE events, probe/test endpoint - Virtual repos with index merging (Helm YAML + PyPI HTML) Frontend (React + Vite, separate Dockerfile): - Dashboard with stats, health indicators, top remotes - Remotes list with type filter, remote detail with config/patterns - Object browser with pagination and evict - Test Remote page: probe any remote path, see headers/size/timing - Virtuals page with expandable member lists TUI (Bubble Tea): - Dashboard, remotes list/detail, object browser, virtuals - Vim-style navigation, artifactapi tui --endpoint <url> Infrastructure: - S3 client supports MinIO, Ceph RGW, AWS S3 (minio-go) - PostgreSQL schema with migrations - Docker Compose: API + UI + Postgres 17 + Redis 7 + MinIO - Makefile with Go version check, build/test/lint/fmt/e2e targets - Distroless Docker image (~15MB) Testing: - Unit tests for models, classifier, providers, mergers - E2E tests with testcontainers-go (real Postgres/Redis/MinIO) Terraform config: - All 40 production remotes + helm virtual as HCL - Provider repo: terraform-provider-artifactapi v0.0.1 (separate)
This commit is contained in:
@@ -0,0 +1,153 @@
|
||||
package database
|
||||
|
||||
import (
|
||||
"context"
|
||||
"time"
|
||||
|
||||
"git.unkin.net/unkin/artifactapi/pkg/models"
|
||||
)
|
||||
|
||||
func (db *DB) UpsertBlob(ctx context.Context, contentHash, s3Key string, sizeBytes int64, contentType string) error {
|
||||
_, err := db.Pool.Exec(ctx, `
|
||||
INSERT INTO blobs (content_hash, s3_key, size_bytes, content_type)
|
||||
VALUES ($1, $2, $3, $4)
|
||||
ON CONFLICT (content_hash) DO NOTHING
|
||||
`, contentHash, s3Key, sizeBytes, contentType)
|
||||
return err
|
||||
}
|
||||
|
||||
func (db *DB) UpsertArtifact(ctx context.Context, remoteName, path, contentHash, upstreamETag string) error {
|
||||
_, err := db.Pool.Exec(ctx, `
|
||||
INSERT INTO artifacts (remote_name, path, content_hash, upstream_etag)
|
||||
VALUES ($1, $2, $3, $4)
|
||||
ON CONFLICT (remote_name, path) DO UPDATE SET
|
||||
content_hash = EXCLUDED.content_hash,
|
||||
upstream_etag = EXCLUDED.upstream_etag,
|
||||
last_fetched_at = NOW(),
|
||||
fetch_count = artifacts.fetch_count + 1
|
||||
`, remoteName, path, contentHash, upstreamETag)
|
||||
return err
|
||||
}
|
||||
|
||||
func (db *DB) GetArtifact(ctx context.Context, remoteName, path string) (*models.Artifact, error) {
|
||||
row := db.Pool.QueryRow(ctx, `
|
||||
SELECT a.id, a.remote_name, a.path, a.content_hash, a.upstream_etag,
|
||||
a.upstream_last_modified, a.first_seen_at, a.last_fetched_at,
|
||||
a.last_accessed_at, a.fetch_count, a.access_count,
|
||||
b.size_bytes, b.content_type
|
||||
FROM artifacts a
|
||||
JOIN blobs b ON a.content_hash = b.content_hash
|
||||
WHERE a.remote_name = $1 AND a.path = $2
|
||||
`, remoteName, path)
|
||||
|
||||
var a models.Artifact
|
||||
err := row.Scan(
|
||||
&a.ID, &a.RemoteName, &a.Path, &a.ContentHash, &a.UpstreamETag,
|
||||
&a.UpstreamLastModified, &a.FirstSeenAt, &a.LastFetchedAt,
|
||||
&a.LastAccessedAt, &a.FetchCount, &a.AccessCount,
|
||||
&a.SizeBytes, &a.ContentType,
|
||||
)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return &a, nil
|
||||
}
|
||||
|
||||
func (db *DB) TouchArtifactAccess(ctx context.Context, remoteName, path string) error {
|
||||
_, err := db.Pool.Exec(ctx, `
|
||||
UPDATE artifacts SET
|
||||
last_accessed_at = NOW(),
|
||||
access_count = access_count + 1
|
||||
WHERE remote_name = $1 AND path = $2
|
||||
`, remoteName, path)
|
||||
return err
|
||||
}
|
||||
|
||||
func (db *DB) ListArtifacts(ctx context.Context, remoteName string, limit, offset int) ([]models.Artifact, error) {
|
||||
rows, err := db.Pool.Query(ctx, `
|
||||
SELECT a.id, a.remote_name, a.path, a.content_hash, a.upstream_etag,
|
||||
a.upstream_last_modified, a.first_seen_at, a.last_fetched_at,
|
||||
a.last_accessed_at, a.fetch_count, a.access_count,
|
||||
b.size_bytes, b.content_type
|
||||
FROM artifacts a
|
||||
JOIN blobs b ON a.content_hash = b.content_hash
|
||||
WHERE a.remote_name = $1
|
||||
ORDER BY a.path
|
||||
LIMIT $2 OFFSET $3
|
||||
`, remoteName, limit, offset)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
defer rows.Close()
|
||||
|
||||
var artifacts []models.Artifact
|
||||
for rows.Next() {
|
||||
var a models.Artifact
|
||||
if err := rows.Scan(
|
||||
&a.ID, &a.RemoteName, &a.Path, &a.ContentHash, &a.UpstreamETag,
|
||||
&a.UpstreamLastModified, &a.FirstSeenAt, &a.LastFetchedAt,
|
||||
&a.LastAccessedAt, &a.FetchCount, &a.AccessCount,
|
||||
&a.SizeBytes, &a.ContentType,
|
||||
); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
artifacts = append(artifacts, a)
|
||||
}
|
||||
return artifacts, rows.Err()
|
||||
}
|
||||
|
||||
func (db *DB) DeleteArtifact(ctx context.Context, remoteName, path string) error {
|
||||
_, err := db.Pool.Exec(ctx, `DELETE FROM artifacts WHERE remote_name = $1 AND path = $2`, remoteName, path)
|
||||
return err
|
||||
}
|
||||
|
||||
func (db *DB) InsertAccessLog(ctx context.Context, remoteName, path string, cacheHit bool, sizeBytes int64, upstreamMS int, clientIP string) error {
|
||||
_, err := db.Pool.Exec(ctx, `
|
||||
INSERT INTO access_log (remote_name, path, cache_hit, size_bytes, upstream_ms, client_ip)
|
||||
VALUES ($1, $2, $3, $4, $5, $6)
|
||||
`, remoteName, path, cacheHit, sizeBytes, upstreamMS, clientIP)
|
||||
return err
|
||||
}
|
||||
|
||||
func (db *DB) FindOrphanedBlobs(ctx context.Context) ([]models.Blob, error) {
|
||||
rows, err := db.Pool.Query(ctx, `
|
||||
SELECT b.content_hash, b.s3_key, b.size_bytes, b.content_type, b.created_at
|
||||
FROM blobs b
|
||||
WHERE b.content_hash NOT IN (
|
||||
SELECT content_hash FROM artifacts
|
||||
UNION
|
||||
SELECT content_hash FROM local_files
|
||||
)
|
||||
`)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
defer rows.Close()
|
||||
|
||||
var blobs []models.Blob
|
||||
for rows.Next() {
|
||||
var b models.Blob
|
||||
if err := rows.Scan(&b.ContentHash, &b.S3Key, &b.SizeBytes, &b.ContentType, &b.CreatedAt); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
blobs = append(blobs, b)
|
||||
}
|
||||
return blobs, rows.Err()
|
||||
}
|
||||
|
||||
func (db *DB) DeleteBlob(ctx context.Context, contentHash string) error {
|
||||
_, err := db.Pool.Exec(ctx, `DELETE FROM blobs WHERE content_hash = $1`, contentHash)
|
||||
return err
|
||||
}
|
||||
|
||||
func (db *DB) DeleteColdArtifacts(ctx context.Context, remoteName string, olderThan time.Duration) (int64, error) {
|
||||
cutoff := time.Now().Add(-olderThan)
|
||||
tag, err := db.Pool.Exec(ctx, `
|
||||
DELETE FROM artifacts
|
||||
WHERE remote_name = $1 AND last_accessed_at < $2
|
||||
`, remoteName, cutoff)
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
return tag.RowsAffected(), nil
|
||||
}
|
||||
Reference in New Issue
Block a user