Files
artifactapi/internal/provider/pypi/pypi.go
T
unkinben 3a6721c2a7
ci/woodpecker/tag/docker Pipeline was successful
refactor: modular local provider interfaces (#52)
## Summary
Move package-type-specific local repo logic out of centralized handlers into provider packages via optional Go interfaces.

**New interfaces in `provider` package:**
- \`LocalUploader\`: \`ValidateUpload(filePath) → (storagePath, contentType, error)\` + \`UploadResponse(...)\`
- \`LocalIndexer\`: \`ServeLocalIndex(w, r, files, repoName, path) → bool\` + \`GenerateLocalIndex(ctx, files, repoName, path) → ([]byte, error)\`
- \`FileStore\`: \`ListFilesByPrefix\` + \`ListPackages\` (implemented by database.DB)

**Providers implement these interfaces:**
- PyPI: upload validation (wheel/sdist naming), simple index serving + generation
- Terraform: upload validation (provider zip naming), mirror protocol serving

**Handlers simplified to generic dispatch:**
- \`local.go\`: type-asserts to \`LocalUploader\`, falls back to generic upload
- \`proxy.go\`: type-asserts to \`LocalIndexer\`, falls back to raw file serving
- \`engine.go\`: type-asserts to \`LocalIndexer\` for local virtual members

Adding a new local repo type (e.g. RPM) = implement the interfaces in its provider package. Zero handler changes.

## Test plan
- [x] Build + unit tests pass
- [x] E2E: PyPI local upload → simple index → uv pip install (smoke test after refactor)

Reviewed-on: #52
Co-authored-by: Ben Vincent <ben@unkin.net>
Co-committed-by: Ben Vincent <ben@unkin.net>
2026-06-23 22:56:25 +10:00

243 lines
6.8 KiB
Go

package pypi
import (
"context"
"fmt"
"io"
"net/http"
"regexp"
"strings"
"git.unkin.net/unkin/artifactapi/internal/auth"
"git.unkin.net/unkin/artifactapi/internal/provider"
"git.unkin.net/unkin/artifactapi/pkg/models"
)
func init() {
provider.Register(&Provider{})
}
var fileRe = regexp.MustCompile(`^[a-zA-Z0-9][a-zA-Z0-9._-]*\.(whl|tar\.gz|zip)$`)
var normalizeRe = regexp.MustCompile(`[-_.]+`)
type Provider struct{}
func (p *Provider) Type() models.PackageType { return models.PackagePyPI }
func (p *Provider) Classify(path string) provider.Mutability {
if strings.Contains(path, "simple/") {
return provider.Mutable
}
return provider.Immutable
}
func (p *Provider) ContentType(path string) string {
lower := strings.ToLower(path)
if strings.HasSuffix(lower, ".whl") || strings.HasSuffix(lower, ".zip") {
return "application/zip"
}
if strings.HasSuffix(lower, ".tar.gz") {
return "application/gzip"
}
if strings.Contains(path, "simple/") {
return "text/html"
}
return "application/octet-stream"
}
func (p *Provider) UpstreamURL(remote models.Remote, path string) string {
if strings.HasPrefix(path, "simple/") {
return "https://pypi.org/" + path
}
return strings.TrimRight(remote.BaseURL, "/") + "/" + strings.TrimLeft(path, "/")
}
func (p *Provider) RewriteResponse(body []byte, remote models.Remote, proxyBaseURL string) ([]byte, error) {
if proxyBaseURL == "" {
return nil, nil
}
content := string(body)
proxyURL := strings.TrimRight(proxyBaseURL, "/") + "/api/v1/remote/" + remote.Name + "/"
content = strings.ReplaceAll(content, "https://files.pythonhosted.org/", proxyURL)
content = strings.ReplaceAll(content, "../../", proxyURL)
return []byte(content), nil
}
func (p *Provider) AuthHeaders(_ context.Context, remote models.Remote) (http.Header, error) {
return auth.BasicHeaders(remote), nil
}
func normalize(name string) string {
return strings.ToLower(normalizeRe.ReplaceAllString(name, "-"))
}
func packageFromWheel(filename string) string {
parts := strings.SplitN(filename, "-", 3)
if len(parts) < 2 {
return ""
}
return normalize(parts[0])
}
func packageFromSdist(filename string) string {
name := filename
for _, suffix := range []string{".tar.gz", ".zip"} {
if strings.HasSuffix(name, suffix) {
name = strings.TrimSuffix(name, suffix)
break
}
}
idx := strings.LastIndex(name, "-")
if idx <= 0 {
return ""
}
return normalize(name[:idx])
}
func (p *Provider) ValidateUpload(filePath string) (storagePath, contentType string, err error) {
filename := filePath
if idx := strings.LastIndex(filePath, "/"); idx >= 0 {
filename = filePath[idx+1:]
}
if !fileRe.MatchString(filename) {
return "", "", fmt.Errorf("filename %q must be a .whl, .tar.gz, or .zip file", filename)
}
var pkgName string
if strings.HasSuffix(filename, ".whl") {
pkgName = packageFromWheel(filename)
} else {
pkgName = packageFromSdist(filename)
}
if pkgName == "" {
return "", "", fmt.Errorf("cannot parse package name from %q", filename)
}
ct := "application/zip"
if strings.HasSuffix(filename, ".tar.gz") {
ct = "application/gzip"
}
return pkgName + "/" + filename, ct, nil
}
func (p *Provider) UploadResponse(storagePath, contentHash string, sizeBytes int64) map[string]any {
parts := strings.SplitN(storagePath, "/", 2)
filename := storagePath
if len(parts) == 2 {
filename = parts[1]
}
return map[string]any{
"package": parts[0],
"filename": filename,
"content_hash": contentHash,
"size_bytes": sizeBytes,
}
}
func (p *Provider) ServeLocalIndex(w http.ResponseWriter, r *http.Request, files provider.FileStore, repoName, path string) bool {
if path == "simple" || path == "simple/" {
p.servePackageList(w, r, files, repoName)
return true
}
if strings.HasPrefix(path, "simple/") {
pkg := strings.TrimPrefix(path, "simple/")
pkg = strings.TrimSuffix(pkg, "/")
if pkg != "" && !strings.Contains(pkg, "/") {
p.servePackageFiles(w, r, files, repoName, pkg)
return true
}
}
return false
}
func (p *Provider) GenerateLocalIndex(ctx context.Context, files provider.FileStore, repoName, path string) ([]byte, error) {
if !strings.HasPrefix(path, "simple/") {
return nil, fmt.Errorf("unsupported index path: %q", path)
}
pkg := strings.TrimPrefix(path, "simple/")
pkg = strings.TrimSuffix(pkg, "/")
if pkg == "" {
return p.generatePackageListHTML(ctx, files, repoName)
}
return p.generatePackageFilesHTML(ctx, files, repoName, pkg)
}
func (p *Provider) servePackageList(w http.ResponseWriter, r *http.Request, files provider.FileStore, repoName string) {
body, err := p.generatePackageListHTML(r.Context(), files, repoName)
if err != nil {
http.Error(w, err.Error(), http.StatusInternalServerError)
return
}
w.Header().Set("Content-Type", "text/html")
w.WriteHeader(http.StatusOK)
w.Write(body)
}
func (p *Provider) servePackageFiles(w http.ResponseWriter, r *http.Request, files provider.FileStore, repoName, packageName string) {
normalized := normalize(packageName)
prefix := normalized + "/"
entries, err := files.ListFilesByPrefix(r.Context(), repoName, prefix)
if err != nil {
http.Error(w, err.Error(), http.StatusInternalServerError)
return
}
if len(entries) == 0 {
http.Error(w, "not found", http.StatusNotFound)
return
}
var b strings.Builder
b.WriteString("<!DOCTYPE html>\n<html><body>\n")
for _, f := range entries {
filename := strings.TrimPrefix(f.FilePath, normalized+"/")
hash := strings.TrimPrefix(f.ContentHash, "sha256:")
fmt.Fprintf(&b, "<a href=\"../../%s/%s#sha256=%s\">%s</a>\n",
normalized, filename, hash, filename)
}
b.WriteString("</body></html>\n")
w.Header().Set("Content-Type", "text/html")
w.WriteHeader(http.StatusOK)
io.WriteString(w, b.String())
}
func (p *Provider) generatePackageListHTML(ctx context.Context, files provider.FileStore, repoName string) ([]byte, error) {
packages, err := files.ListPackages(ctx, repoName)
if err != nil {
return nil, err
}
var b strings.Builder
b.WriteString("<!DOCTYPE html>\n<html><body>\n")
for _, pkg := range packages {
fmt.Fprintf(&b, "<a href=\"%s/\">%s</a>\n", pkg, pkg)
}
b.WriteString("</body></html>\n")
return []byte(b.String()), nil
}
func (p *Provider) generatePackageFilesHTML(ctx context.Context, files provider.FileStore, repoName, packageName string) ([]byte, error) {
normalized := normalize(packageName)
prefix := normalized + "/"
entries, err := files.ListFilesByPrefix(ctx, repoName, prefix)
if err != nil {
return nil, err
}
var b strings.Builder
b.WriteString("<!DOCTYPE html>\n<html><body>\n")
for _, f := range entries {
filename := strings.TrimPrefix(f.FilePath, normalized+"/")
hash := strings.TrimPrefix(f.ContentHash, "sha256:")
fmt.Fprintf(&b, "<a href=\"%s/%s#sha256=%s\">%s</a>\n",
normalized, filename, hash, filename)
}
b.WriteString("</body></html>\n")
return []byte(b.String()), nil
}