Compare commits

..

5 Commits

Author SHA1 Message Date
unkin-agent 841b9f1547 fix vacuous e2e dedupe assertion
ci/woodpecker/pr/pre-commit Pipeline was successful
ci/woodpecker/pr/test Pipeline was successful
ci/woodpecker/pr/build Pipeline was successful
2026-10-17 12:56:42 +11:00
unkin-agent ed6216d78b Serve deb virtual indexes by hash and bound cached suites
ci/woodpecker/pr/pre-commit Pipeline was successful
ci/woodpecker/pr/test Pipeline was successful
ci/woodpecker/pr/build Pipeline was successful
2026-10-17 12:46:14 +11:00
unkin-agent eca686b7bb Merge remote-tracking branch 'origin/benvin/virtual-shared-cache' into benvin/virtual-deb
# Conflicts:
#	internal/virtual/engine.go
#	internal/virtual/engine_test.go
2026-10-17 12:32:38 +11:00
unkin-agent ceae176089 Share the virtual merge cache across index types
ci/woodpecker/pr/pre-commit Pipeline was successful
ci/woodpecker/pr/test Pipeline was successful
ci/woodpecker/pr/build Pipeline was successful
2026-10-17 12:31:49 +11:00
unkin-agent 78d24f7752 Add deb virtual repositories
ci/woodpecker/pr/pre-commit Pipeline was successful
ci/woodpecker/pr/test Pipeline was successful
ci/woodpecker/pr/build Pipeline was successful
- merge member Packages indexes (flat and dists/<suite>) into one apt repo with a generated unsigned Release
- prefix Filename with the member name and 302 downloads to the member route
- share the rpm merge cache, singleflight and fail-closed member fetch
2026-10-16 23:06:56 +11:00
21 changed files with 916 additions and 1573 deletions
-36
View File
@@ -262,42 +262,6 @@ there's nothing to provision. To bring your own key instead, point
`TF_SIGNING_KEY_PASSPHRASE`), which takes precedence over the generated one.
`TF_PROVIDER_PROTOCOLS` (default `5.0,6.0`) sets the advertised plugin protocols.
### Local Go module proxy
A local `goproxy` repo serves private modules over the GOPROXY protocol
(`@v/list`, `@latest`, `@v/<ver>.info|.mod|.zip`). Publish a version by
uploading its files under the case-encoded module path (uppercase as `!lower`):
```sh
for ext in zip mod info; do
curl -fsSL --upload-file v0.1.0.$ext \
https://artifactapi.k8s.syd1.au.unkin.net/api/v2/remotes/go-internal/files/example.unkin.net/hello/@v/v0.1.0.$ext
done
GOPROXY=https://artifactapi.k8s.syd1.au.unkin.net/api/v1/local/go-internal,https://proxy.golang.org,direct \
GONOSUMDB=example.unkin.net go get example.unkin.net/hello@latest
```
Build the zip with `golang.org/x/mod/zip` or reuse the files `go mod download`
leaves in `$(go env GOMODCACHE)/cache/download`. Uploads are validated: zips must
pass `zip.CheckZip` (every file under `module@version/`), `.mod` must declare the
module, and `.info` must match the version. `.info` is optional; it is
synthesized from the version when absent. `@v/list` lists versions with a `.mod`.
### Local puppet forge
A local `puppet` repo is a Forge: `PUT` a module tarball to
`/api/v2/remotes/<repo>/files/<owner>-<module>-<version>.tar.gz` and the Forge
v3 API (`/v3/modules`, `/v3/releases`, `/v3/files`) is served from each
release's `metadata.json` at `/api/v1/local/<repo>`. Versions are immutable.
```bash
puppet module build ./hello
curl -fsSL --upload-file pkg/unkin-hello-0.1.0.tar.gz \
https://artifactapi.k8s.syd1.au.unkin.net/api/v2/remotes/<repo>/files/unkin-hello-0.1.0.tar.gz
puppet module install unkin-hello \
--module_repository https://artifactapi.k8s.syd1.au.unkin.net/api/v1/local/<repo>
```
### Local docker registry
A local `docker` repo is a real container registry, not a mirror: it serves the
+1 -2
View File
@@ -26,8 +26,7 @@ already-running stack.
helm, pypi, npm, rpm, alpine, puppet, terraform, goproxy, cargo, nuget) proxied through the
mock upstream: first fetch `X-Artifact-Source: remote`, second `cache`, bytes
verified against the origin fixture.
- **Local uploads** — puppet (Forge v3 API via real `r10k` and `puppet module install`),
generic (upload/download), pypi (wheel + generated `simple/`
- **Local uploads** — generic (upload/download), pypi (wheel + generated `simple/`
index), rpm (real package + **automatic repodata** generation).
- **Virtual repositories** — pypi simple-index merge and helm `index.yaml` merge
across two members.
-57
View File
@@ -1,57 +0,0 @@
//go:build dockere2e
package e2edocker
import (
"bytes"
"net/http"
"os"
"path/filepath"
"testing"
"golang.org/x/mod/module"
modzip "golang.org/x/mod/zip"
)
// TestLocalGoProxy publishes two module versions and reads them back over the
// GOPROXY protocol.
func TestLocalGoProxy(t *testing.T) {
createRepo(t, `{"name":"local-go","package_type":"goproxy","repo_type":"local"}`)
defer deleteRepo(t, "local-go")
const mod = "example.unkin.net/!hello"
gomod := []byte("module example.unkin.net/Hello\n\ngo 1.25\n")
var zip010 []byte
for _, ver := range []string{"v0.1.0", "v0.2.0"} {
dir := t.TempDir()
os.WriteFile(filepath.Join(dir, "go.mod"), gomod, 0o600)
os.WriteFile(filepath.Join(dir, "hello.go"), []byte("package hello\n"), 0o600)
var buf bytes.Buffer
if err := modzip.CreateFromDir(&buf, module.Version{Path: "example.unkin.net/Hello", Version: ver}, dir); err != nil {
t.Fatal(err)
}
if ver == "v0.1.0" {
zip010 = buf.Bytes()
}
uploadFile(t, "local-go", mod+"/@v/"+ver+".zip", buf.Bytes(), "application/zip")
uploadFile(t, "local-go", mod+"/@v/"+ver+".mod", gomod, "text/plain")
}
resp, body := doRequest(t, http.MethodPut, api("/api/v2/remotes/local-go/files/"+mod+"/@v/v0.3.0.zip"), []byte("junk"), "application/zip")
if resp.StatusCode != http.StatusBadRequest {
t.Fatalf("invalid zip: status %d: %s", resp.StatusCode, body)
}
for path, want := range map[string]string{
"/@v/list": "v0.1.0\nv0.2.0\n",
"/@latest": `{"Version":"v0.2.0"}`,
"/@v/v0.1.0.info": `{"Version":"v0.1.0"}`,
"/@v/v0.1.0.mod": string(gomod),
"/@v/v0.1.0.zip": string(zip010),
} {
resp, body := doRequest(t, http.MethodGet, api("/api/v1/local/local-go/"+mod+path), nil, "")
if resp.StatusCode != http.StatusOK || string(body) != want {
t.Errorf("%s: status %d body %q", path, resp.StatusCode, body)
}
}
}
-88
View File
@@ -1,88 +0,0 @@
//go:build dockere2e
package e2edocker
import (
"archive/tar"
"bytes"
"compress/gzip"
"net/http"
"os"
"os/exec"
"strings"
"testing"
"time"
)
const puppetHelloMetadata = `{"name":"unkin-hello","version":"0.1.0","author":"unkin","summary":"e2e","license":"Apache-2.0","source":"https://example.invalid","dependencies":[{"name":"puppetlabs/stdlib","version_requirement":">= 4.0.0 < 10.0.0"}]}`
func puppetModuleTarball(t *testing.T) []byte {
t.Helper()
var buf bytes.Buffer
zw := gzip.NewWriter(&buf)
tw := tar.NewWriter(zw)
for name, body := range map[string]string{
"unkin-hello-0.1.0/metadata.json": puppetHelloMetadata,
"unkin-hello-0.1.0/manifests/init.pp": "class hello {}\n",
} {
if err := tw.WriteHeader(&tar.Header{Name: name, Mode: 0o644, Size: int64(len(body)), ModTime: time.Now()}); err != nil {
t.Fatal(err)
}
_, _ = tw.Write([]byte(body))
}
_ = tw.Close()
_ = zw.Close()
return buf.Bytes()
}
// TestLocalPuppetRealClient publishes a module to a puppet local and installs
// it with the real r10k and puppet module tool. The stdlib dependency is not on
// a local-only forge, so puppet runs with --ignore-dependencies.
func TestLocalPuppetRealClient(t *testing.T) {
network := os.Getenv("COMPOSE_NETWORK")
internal := strings.TrimRight(os.Getenv("ARTIFACTAPI_INTERNAL"), "/")
if network == "" || internal == "" {
t.Skip("COMPOSE_NETWORK/ARTIFACTAPI_INTERNAL not set; run via scripts/docker-e2e.sh")
}
if _, err := exec.LookPath("docker"); err != nil {
t.Skip("docker not available on the test host")
}
createRepo(t, `{"name":"local-puppet","package_type":"puppet","repo_type":"local"}`)
defer deleteRepo(t, "local-puppet")
upload := api("/api/v2/remotes/local-puppet/files/unkin-hello-0.1.0.tar.gz")
defer doRequest(t, http.MethodDelete, api("/api/v2/remotes/local-puppet/files/v3/files/unkin-hello-0.1.0.tar.gz"), nil, "")
tarball := puppetModuleTarball(t)
if resp, body := doRequest(t, http.MethodPut, upload, tarball, "application/gzip"); resp.StatusCode != http.StatusCreated {
t.Fatalf("upload: %d %s", resp.StatusCode, body)
}
if resp, _ := doRequest(t, http.MethodPut, upload, tarball, "application/gzip"); resp.StatusCode != http.StatusConflict {
t.Fatalf("re-upload of an existing version: %d, want 409", resp.StatusCode)
}
if resp, body := getEventually(t, api("/api/v1/local/local-puppet/v3/releases/unkin-hello-0.1.0"), 15*time.Second); resp.StatusCode != http.StatusOK || !strings.Contains(string(body), `"file_md5"`) {
t.Fatalf("release never indexed: %d %s", resp.StatusCode, body)
}
forge := internal + "/api/v1/local/local-puppet"
run := func(image, script string) string {
t.Helper()
out, err := exec.Command("docker", "run", "--rm", "--network", network, "--entrypoint", "sh", image, "-c", "set -eu; "+script).CombinedOutput()
if err != nil {
t.Fatalf("%s failed: %v\n%s", image, err, out)
}
return string(out)
}
out := run("ghcr.io/voxpupuli/r10k:latest", "cd /tmp && printf 'forge:\\n baseurl: "+forge+"\\n' > r10k.yaml && "+
"printf \"forge '"+forge+"'\\nmod 'unkin-hello', '0.1.0'\\n\" > Puppetfile && "+
"r10k puppetfile install -c r10k.yaml --verbose && cat modules/hello/metadata.json")
if !strings.Contains(out, `"unkin-hello"`) {
t.Fatalf("r10k did not install unkin-hello:\n%s", out)
}
out = run("ghcr.io/openvoxproject/openvoxagent:latest", "export PATH=/opt/puppetlabs/bin:$PATH; puppet module install unkin-hello --module_repository "+forge+" --ignore-dependencies --target-dir /tmp/mods && puppet module list --color=false --modulepath /tmp/mods")
if !strings.Contains(out, "unkin-hello (v0.1.0)") {
t.Fatalf("puppet module install did not install unkin-hello:\n%s", out)
}
}
+103
View File
@@ -14,6 +14,8 @@ import (
"strings"
"testing"
"time"
"git.unkin.net/unkin/artifactapi/internal/testsupport"
)
// TestVirtualPyPIMerge uploads different packages to two pypi locals and
@@ -136,3 +138,104 @@ func TestVirtualRPMMerge(t *testing.T) {
t.Fatalf("real dnf against rpm virtual failed: %v\n%s", err, out)
}
}
// TestVirtualDebMerge merges two local deb repos carrying the same package: the
// first member wins the duplicate, and a real apt sees both members' packages
// and installs through the virtual.
func TestVirtualDebMerge(t *testing.T) {
createRepo(t, `{"name":"vdeb-a","package_type":"deb","repo_type":"local"}`)
createRepo(t, `{"name":"vdeb-b","package_type":"deb","repo_type":"local"}`)
defer deleteRepo(t, "vdeb-a")
defer deleteRepo(t, "vdeb-b")
uploadFile(t, "vdeb-a", "vdeb-one_1.0.0_amd64.deb", testsupport.MinimalDeb("vdeb-one", "1.0.0", "amd64"), "application/vnd.debian.binary-package")
uploadFile(t, "vdeb-b", "vdeb-one_1.0.0_amd64.deb", testsupport.MinimalDeb("vdeb-one", "1.0.0", "amd64"), "application/vnd.debian.binary-package")
uploadFile(t, "vdeb-b", "vdeb-two_2.0.0_amd64.deb", testsupport.MinimalDeb("vdeb-two", "2.0.0", "amd64"), "application/vnd.debian.binary-package")
// Local indexes regenerate asynchronously; merge only once vdeb-b lists both.
deadline := time.Now().Add(15 * time.Second)
for {
resp, body := doRequest(t, http.MethodGet, api("/api/v1/local/vdeb-b/Packages"), nil, "")
if resp.StatusCode == http.StatusOK && strings.Contains(string(body), "vdeb-two") || time.Now().After(deadline) {
break
}
time.Sleep(500 * time.Millisecond)
}
createVirtual(t, `{"name":"vdeb","package_type":"deb","members":["vdeb-a","vdeb-b"]}`)
defer deleteVirtual(t, "vdeb")
_, body := doRequest(t, http.MethodGet, api("/api/v1/virtual/vdeb/Packages"), nil, "")
pk := string(body)
if strings.Count(pk, "Package: vdeb-one\n") != 1 || !strings.Contains(pk, "Filename: vdeb-a/pool/vdeb-one_1.0.0_amd64.deb") ||
!strings.Contains(pk, "Filename: vdeb-b/pool/vdeb-two_2.0.0_amd64.deb") {
t.Fatalf("merged Packages should hold vdeb-one from the first member and vdeb-two:\n%s", pk)
}
network := os.Getenv("COMPOSE_NETWORK")
internal := os.Getenv("ARTIFACTAPI_INTERNAL")
if network == "" || internal == "" {
t.Skip("COMPOSE_NETWORK/ARTIFACTAPI_INTERNAL not set; skipping real apt")
}
if _, err := exec.LookPath("docker"); err != nil {
t.Skip("docker not available on the test host")
}
script := "set -euo pipefail; " +
"rm -f /etc/apt/sources.list.d/*; " +
"echo \"deb [trusted=yes] $URL ./\" > /etc/apt/sources.list.d/vdeb.list; " +
"apt-get update; " +
"apt-cache policy vdeb-one vdeb-two | tee /dev/stderr | grep -c virtual/vdeb | grep -qx 2; " +
"apt-get install -y vdeb-one vdeb-two; " +
"dpkg -s vdeb-one vdeb-two"
out, err := exec.Command("docker", "run", "--rm", "--network", network,
"-e", "URL="+strings.TrimRight(internal, "/")+"/api/v1/virtual/vdeb/",
"debian:13", "bash", "-c", script).CombinedOutput()
if err != nil {
t.Fatalf("real apt against deb virtual failed: %v\n%s", err, out)
}
}
// TestVirtualDebSuite merges two proxied deb.debian.org remotes and drives a
// real apt through the virtual's dists/<suite> layout (by-hash indexes).
func TestVirtualDebSuite(t *testing.T) {
network := os.Getenv("COMPOSE_NETWORK")
internal := os.Getenv("ARTIFACTAPI_INTERNAL")
if network == "" || internal == "" {
t.Skip("COMPOSE_NETWORK/ARTIFACTAPI_INTERNAL not set; skipping real apt")
}
if _, err := exec.LookPath("docker"); err != nil {
t.Skip("docker not available on the test host")
}
for _, n := range []string{"vdebs-a", "vdebs-b"} {
createRepo(t, `{"name":"`+n+`","package_type":"deb","repo_type":"remote","base_url":"http://deb.debian.org/debian"}`)
defer deleteRepo(t, n)
}
createVirtual(t, `{"name":"vdebs","package_type":"deb","members":["vdebs-a","vdebs-b"]}`)
defer deleteVirtual(t, "vdebs")
resp, rel := doRequest(t, http.MethodGet, api("/api/v1/virtual/vdebs/dists/trixie-updates/Release"), nil, "")
if resp.StatusCode != http.StatusOK || !strings.Contains(string(rel), "Acquire-By-Hash: yes\n") ||
!strings.Contains(string(rel), " main/binary-amd64/Packages.gz\n") {
t.Fatalf("merged suite Release: status %d:\n%s", resp.StatusCode, rel)
}
script := "set -euo pipefail; " +
"rm -f /etc/apt/sources.list.d/*; " +
"echo \"deb [trusted=yes] $URL trixie-updates main\" > /etc/apt/sources.list.d/vdebs.list; " +
"apt-get update; " +
"idx=/tmp/avail; apt-cache dumpavail > $idx; " +
"grep -q '^Filename: vdebs-a/pool/' $idx; if grep -q '^Filename: vdebs-b/' $idx; then echo 'vdebs-b not deduped'; exit 1; fi; " +
"pkg=$(awk '/^Package:/{p=$2} /^Size:/{if(!m||$2<m){m=$2;b=p}} END{print b}' $idx); " +
"cd /tmp && apt-get download $pkg && ls -l /tmp/*.deb"
out, err := exec.Command("docker", "run", "--rm", "--network", network,
"-e", "URL="+strings.TrimRight(internal, "/")+"/api/v1/virtual/vdebs/",
"debian:13", "bash", "-c", script).CombinedOutput()
if err != nil {
t.Fatalf("real apt against deb virtual suite failed: %v\n%s", err, out)
}
t.Logf("%s", out)
resp, _ = doRequest(t, http.MethodGet, api("/api/v1/remote/vdebs-a/dists/trixie-updates/main/binary-amd64/Packages.xz"), nil, "")
if src := resp.Header.Get("X-Artifact-Source"); resp.StatusCode != http.StatusOK || src != "cache" {
t.Fatalf("member index the virtual merged should be cached: status %d source %q", resp.StatusCode, src)
}
}
-1
View File
@@ -20,7 +20,6 @@ require (
github.com/testcontainers/testcontainers-go/modules/redis v0.42.0
github.com/ulikunitz/xz v0.5.16
golang.org/x/crypto v0.54.0
golang.org/x/mod v0.37.0
golang.org/x/sync v0.22.0
golang.org/x/time v0.15.0
gopkg.in/yaml.v3 v3.0.1
-4
View File
@@ -227,8 +227,6 @@ golang.org/x/crypto v0.54.0 h1:YLIA59K4fiNzHzjnZt2tUJQjQtUWfWbeHBqKtk3eScw=
golang.org/x/crypto v0.54.0/go.mod h1:KWL8ny2AZdGR2cWmzeHrp2azQPGogOv+HeQaVEXC2dk=
golang.org/x/exp v0.0.0-20231006140011-7918f672742d h1:jtJma62tbqLibJ5sFQz8bKtEM8rJBtfilJ2qTU199MI=
golang.org/x/exp v0.0.0-20231006140011-7918f672742d/go.mod h1:ldy0pHrwJyGW56pPQzzkH36rKxoZW1tw7ZJpeKx+hdo=
golang.org/x/mod v0.37.0 h1:vF1DjpVEshcIqoEaauuHebaLk1O1forxjxBaVn884JQ=
golang.org/x/mod v0.37.0/go.mod h1:m8S8VeM9r4dzDwjrKO0a1sZP3YjeMamRRlD+fmR2Q/0=
golang.org/x/net v0.56.0 h1:Rw8j/hFzGvJUZwNBXnAtf5sVDVt+65SK2C7IxCxZt5o=
golang.org/x/net v0.56.0/go.mod h1:D3Ku6r+V6JROoZK144D2XfMHFcMq/0zSfLelVTCFKec=
golang.org/x/oauth2 v0.36.0 h1:peZ/1z27fi9hUOFCAZaHyrpWG5lwe0RJEEEeH0ThlIs=
@@ -249,8 +247,6 @@ golang.org/x/text v0.40.0 h1:Ub2Z6/xjgF1WrYQz2nuITOEegKFtiIy+rieRJ5lHZKs=
golang.org/x/text v0.40.0/go.mod h1:hpnzDAfGV753zIKo+wk3u1bVKCGPbrnF7+7LBF/UHVY=
golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U=
golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno=
golang.org/x/tools v0.47.0 h1:7Kn5x/d1svx/PzryTsqeoZN4TZwqeH5pGWjefhLi/1Q=
golang.org/x/tools v0.47.0/go.mod h1:dFHnyTvFWY212G+h7ZY4Vsp/K3U4/7W9TyVaAul8uCA=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
+1 -38
View File
@@ -6,7 +6,6 @@ import (
"fmt"
"io"
"net/http"
"os"
"github.com/go-chi/chi/v5"
@@ -84,22 +83,7 @@ func (h *LocalHandler) uploadValidated(w http.ResponseWriter, r *http.Request, r
return
}
var body io.Reader = r.Body
if cv, ok := prov.(provider.ContentValidator); ok {
f, err := spoolBody(r.Body)
if err != nil {
http.Error(w, fmt.Sprintf("read upload: %v", err), http.StatusInternalServerError)
return
}
defer discard(f)
if err := cv.ValidateContent(storagePath, f.Name()); err != nil {
http.Error(w, err.Error(), http.StatusBadRequest)
return
}
body = f
}
result, err := h.cas.Store(r.Context(), body, contentType)
result, err := h.cas.Store(r.Context(), r.Body, contentType)
if err != nil {
http.Error(w, fmt.Sprintf("store failed: %v", err), http.StatusInternalServerError)
return
@@ -126,27 +110,6 @@ func (h *LocalHandler) uploadValidated(w http.ResponseWriter, r *http.Request, r
writeJSON(w, http.StatusCreated, uploader.UploadResponse(storagePath, result.ContentHash, result.SizeBytes))
}
func spoolBody(r io.Reader) (*os.File, error) {
f, err := os.CreateTemp("", "artifactapi-upload-*")
if err != nil {
return nil, err
}
if _, err := io.Copy(f, r); err != nil {
discard(f)
return nil, err
}
if _, err := f.Seek(0, io.SeekStart); err != nil {
discard(f)
return nil, err
}
return f, nil
}
func discard(f *os.File) {
_ = f.Close()
_ = os.Remove(f.Name())
}
func (h *LocalHandler) uploadGeneric(w http.ResponseWriter, r *http.Request, remote *models.Remote, filePath string) {
existing, err := h.db.GetLocalFile(r.Context(), remote.Name, filePath)
if err != nil {
-55
View File
@@ -1,55 +0,0 @@
package v2
import (
"context"
"net/http/httptest"
"strings"
"testing"
"github.com/go-chi/chi/v5"
"git.unkin.net/unkin/artifactapi/internal/database"
_ "git.unkin.net/unkin/artifactapi/internal/provider/goproxy"
"git.unkin.net/unkin/artifactapi/pkg/models"
)
// TestLocalUploadContentRejected verifies a ContentValidator provider rejects
// bad bytes with 400 before anything is stored.
func TestLocalUploadContentRejected(t *testing.T) {
if testDSN == "" {
t.Skip("Docker unavailable")
}
ctx := context.Background()
db, err := database.New(testDSN)
if err != nil {
t.Fatal(err)
}
defer db.Close()
const repo = "go-local-validate"
if err := db.CreateRemote(ctx, &models.Remote{Name: repo, PackageType: models.PackageGoProxy, RepoType: models.RepoTypeLocal}); err != nil {
t.Fatal(err)
}
router := chi.NewRouter()
router.Route("/remotes/{name}/files", func(r chi.Router) {
r.Put("/*", NewLocalHandler(db, nil).Routes().ServeHTTP)
})
cases := map[string]string{
"example.unkin.net/hello/@v/v0.1.0.zip": "not a zip",
"example.unkin.net/hello/@v/v0.1.0.mod": "module example.unkin.net/other\n",
"example.unkin.net/hello/@v/v0.1.0.info": `{"Version":"v9.9.9"}`,
"example.unkin.net/Hello/@v/v0.1.0.mod": "module example.unkin.net/Hello\n",
}
for path, body := range cases {
w := httptest.NewRecorder()
router.ServeHTTP(w, httptest.NewRequest("PUT", "/remotes/"+repo+"/files/"+path, strings.NewReader(body)))
if w.Code != 400 {
t.Errorf("%s: status %d, want 400 (%s)", path, w.Code, w.Body.String())
}
if f, _ := db.GetLocalFile(ctx, repo, path); f != nil {
t.Errorf("%s: rejected upload was recorded", path)
}
}
}
-46
View File
@@ -1,46 +0,0 @@
package database
import (
"context"
"git.unkin.net/unkin/artifactapi/internal/provider"
)
func (db *DB) InsertPuppetMetadata(ctx context.Context, meta *provider.PuppetMetadata) error {
_, err := db.Pool.Exec(ctx, `
INSERT INTO puppet_metadata (repo_name, file_path, content_hash, slug, version, metadata_json, file_size, file_md5)
VALUES ($1,$2,$3,$4,$5,$6,$7,$8)
ON CONFLICT (repo_name, file_path) DO NOTHING
`, meta.RepoName, meta.FilePath, meta.ContentHash, meta.Slug, meta.Version, meta.MetadataJSON, meta.Size, meta.MD5)
return err
}
func (db *DB) DeletePuppetMetadata(ctx context.Context, repoName, filePath string) error {
_, err := db.Pool.Exec(ctx, `DELETE FROM puppet_metadata WHERE repo_name = $1 AND file_path = $2`, repoName, filePath)
return err
}
// ListPuppetMetadataEntries returns a repo's releases, optionally narrowed to
// one module slug (empty slug lists every module).
func (db *DB) ListPuppetMetadataEntries(ctx context.Context, repoName, slug string) ([]provider.PuppetMetadata, error) {
rows, err := db.Pool.Query(ctx, `
SELECT repo_name, file_path, content_hash, slug, version, metadata_json, file_size, file_md5, created_at
FROM puppet_metadata
WHERE repo_name = $1 AND ($2 = '' OR slug = $2)
ORDER BY slug, file_path
`, repoName, slug)
if err != nil {
return nil, err
}
defer rows.Close()
var result []provider.PuppetMetadata
for rows.Next() {
var m provider.PuppetMetadata
if err := rows.Scan(&m.RepoName, &m.FilePath, &m.ContentHash, &m.Slug, &m.Version, &m.MetadataJSON, &m.Size, &m.MD5, &m.CreatedAt); err != nil {
return nil, err
}
result = append(result, m)
}
return result, rows.Err()
}
-222
View File
@@ -1,222 +0,0 @@
package goproxy
import (
"context"
"encoding/json"
"fmt"
"net/http"
"os"
"slices"
"strings"
"golang.org/x/mod/modfile"
"golang.org/x/mod/module"
"golang.org/x/mod/semver"
modzip "golang.org/x/mod/zip"
"git.unkin.net/unkin/artifactapi/internal/provider"
)
type versionFile struct {
module string
version string
ext string
}
// parseVersionFile splits "<escaped module>/@v/<version>.<ext>" into its parts.
func parseVersionFile(path string) (versionFile, error) {
escMod, file, ok := strings.Cut(strings.TrimPrefix(path, "/"), "/@v/")
if !ok || escMod == "" || strings.Contains(file, "/") {
return versionFile{}, fmt.Errorf("path %q must be <module>/@v/<version>.{zip,mod,info}", path)
}
dot := strings.LastIndex(file, ".")
if dot <= 0 {
return versionFile{}, fmt.Errorf("path %q must end in .zip, .mod or .info", path)
}
ext := file[dot+1:]
if ext != "zip" && ext != "mod" && ext != "info" {
return versionFile{}, fmt.Errorf("path %q must end in .zip, .mod or .info", path)
}
mod, err := module.UnescapePath(escMod)
if err != nil {
return versionFile{}, fmt.Errorf("module path must be case-encoded (uppercase as !lower): %w", err)
}
ver, err := module.UnescapeVersion(file[:dot])
if err != nil {
return versionFile{}, err
}
if err := module.Check(mod, ver); err != nil {
return versionFile{}, err
}
if semver.Canonical(ver) != ver {
return versionFile{}, fmt.Errorf("version %q is not canonical semver", ver)
}
return versionFile{module: mod, version: ver, ext: ext}, nil
}
func (v versionFile) storagePath() string {
escMod, _ := module.EscapePath(v.module)
escVer, _ := module.EscapeVersion(v.version)
return escMod + "/@v/" + escVer + "." + v.ext
}
func (p *Provider) ValidateUpload(filePath string) (storagePath, contentType string, err error) {
vf, err := parseVersionFile(filePath)
if err != nil {
return "", "", err
}
sp := vf.storagePath()
return sp, p.ContentType(sp), nil
}
func (p *Provider) ValidateContent(storagePath, localFile string) error {
vf, err := parseVersionFile(storagePath)
if err != nil {
return err
}
switch vf.ext {
case "zip":
if _, err := modzip.CheckZip(module.Version{Path: vf.module, Version: vf.version}, localFile); err != nil {
return fmt.Errorf("invalid module zip (files must sit under %s@%s/): %w", vf.module, vf.version, err)
}
case "mod":
data, err := os.ReadFile(localFile)
if err != nil {
return err
}
mf, err := modfile.ParseLax("go.mod", data, nil)
if err != nil {
return fmt.Errorf("invalid go.mod: %w", err)
}
if mf.Module == nil || mf.Module.Mod.Path != vf.module {
return fmt.Errorf("go.mod must declare module %s", vf.module)
}
case "info":
data, err := os.ReadFile(localFile)
if err != nil {
return err
}
var info struct{ Version string }
if err := json.Unmarshal(data, &info); err != nil {
return fmt.Errorf("invalid .info JSON: %w", err)
}
if info.Version != vf.version {
return fmt.Errorf(".info Version %q does not match %s", info.Version, vf.version)
}
}
return nil
}
func (p *Provider) UploadResponse(storagePath, contentHash string, sizeBytes int64) map[string]any {
vf, _ := parseVersionFile(storagePath)
return map[string]any{
"module": vf.module,
"version": vf.version,
"path": storagePath,
"content_hash": contentHash,
"size_bytes": sizeBytes,
}
}
// versions returns the canonical versions of escMod that have a .mod uploaded, sorted ascending.
func versions(ctx context.Context, files provider.FileStore, repoName, escMod string) (versions []string, infos map[string]bool, err error) {
entries, err := files.ListFilesByPrefix(ctx, repoName, escMod+"/@v/")
if err != nil {
return nil, nil, err
}
infos = map[string]bool{}
for _, e := range entries {
vf, err := parseVersionFile(e.FilePath)
if err != nil || vf.storagePath() != e.FilePath {
continue
}
switch vf.ext {
case "mod":
versions = append(versions, vf.version)
case "info":
infos[vf.version] = true
}
}
semver.Sort(versions)
return versions, infos, nil
}
func latest(vs []string) string {
for i := len(vs) - 1; i >= 0; i-- {
if semver.Prerelease(vs[i]) == "" {
return vs[i]
}
}
if len(vs) == 0 {
return ""
}
return vs[len(vs)-1]
}
func infoJSON(version string) []byte {
b, _ := json.Marshal(map[string]string{"Version": version})
return b
}
func (p *Provider) ServeLocalIndex(w http.ResponseWriter, r *http.Request, files provider.FileStore, repoName, path string) bool {
path = strings.TrimPrefix(path, "/")
switch {
case strings.HasSuffix(path, "/@v/list"), strings.HasSuffix(path, "/@latest"):
case strings.HasSuffix(path, ".info"):
vf, err := parseVersionFile(path)
if err != nil {
return false
}
escMod, _ := module.EscapePath(vf.module)
vs, infos, err := versions(r.Context(), files, repoName, escMod)
if err != nil || infos[vf.version] || !slices.Contains(vs, vf.version) {
return false
}
default:
return false
}
body, err := p.GenerateLocalIndex(r.Context(), files, repoName, path)
if err != nil {
http.Error(w, err.Error(), http.StatusNotFound)
return true
}
w.Header().Set("Content-Type", p.ContentType(path))
w.WriteHeader(http.StatusOK)
_, _ = w.Write(body)
return true
}
func (p *Provider) GenerateLocalIndex(ctx context.Context, files provider.FileStore, repoName, path string) ([]byte, error) {
path = strings.TrimPrefix(path, "/")
if escMod, ok := strings.CutSuffix(path, "/@v/list"); ok {
vs, _, err := versions(ctx, files, repoName, escMod)
if err != nil {
return nil, err
}
var b strings.Builder
for _, v := range vs {
b.WriteString(v + "\n")
}
return []byte(b.String()), nil
}
if escMod, ok := strings.CutSuffix(path, "/@latest"); ok {
vs, _, err := versions(ctx, files, repoName, escMod)
if err != nil {
return nil, err
}
v := latest(vs)
if v == "" {
return nil, fmt.Errorf("no versions of %s", escMod)
}
return infoJSON(v), nil
}
if strings.HasSuffix(path, ".info") {
vf, err := parseVersionFile(path)
if err != nil {
return nil, err
}
return infoJSON(vf.version), nil
}
return nil, fmt.Errorf("unsupported index path: %q", path)
}
-198
View File
@@ -1,198 +0,0 @@
package goproxy
import (
"archive/zip"
"context"
"net/http/httptest"
"os"
"path/filepath"
"strings"
"testing"
"golang.org/x/mod/module"
modzip "golang.org/x/mod/zip"
"git.unkin.net/unkin/artifactapi/internal/provider"
)
type fakeFileStore struct{ paths []string }
func (f *fakeFileStore) ListPackages(context.Context, string) ([]string, error) { return nil, nil }
func (f *fakeFileStore) ListFilesByPrefix(_ context.Context, _, prefix string) ([]provider.FileEntry, error) {
var out []provider.FileEntry
for _, p := range f.paths {
if strings.HasPrefix(p, prefix) {
out = append(out, provider.FileEntry{FilePath: p, ContentHash: "sha256:x"})
}
}
return out, nil
}
func TestValidateUpload(t *testing.T) {
p := &Provider{}
cases := []struct {
in, want string
ok bool
}{
{"example.unkin.net/hello/@v/v0.1.0.zip", "example.unkin.net/hello/@v/v0.1.0.zip", true},
{"/example.unkin.net/hello/@v/v0.1.0.mod", "example.unkin.net/hello/@v/v0.1.0.mod", true},
{"github.com/!burnt!sushi/toml/@v/v1.2.0.info", "github.com/!burnt!sushi/toml/@v/v1.2.0.info", true},
{"example.unkin.net/hello/v2/@v/v2.0.0-rc.1.zip", "example.unkin.net/hello/v2/@v/v2.0.0-rc.1.zip", true},
{"github.com/BurntSushi/toml/@v/v1.2.0.zip", "", false},
{"example.unkin.net/hello/@v/v0.1.zip", "", false},
{"example.unkin.net/hello/@v/v2.0.0.zip", "", false},
{"example.unkin.net/hello/@v/v0.1.0.tar.gz", "", false},
{"example.unkin.net/hello/v0.1.0.zip", "", false},
{"example.unkin.net/hello/@v/list", "", false},
}
for _, c := range cases {
got, ct, err := p.ValidateUpload(c.in)
if (err == nil) != c.ok {
t.Errorf("%s: err=%v, want ok=%v", c.in, err, c.ok)
continue
}
if c.ok && (got != c.want || ct == "") {
t.Errorf("%s: got %q %q, want %q", c.in, got, ct, c.want)
}
}
}
func writeZip(t *testing.T, files map[string]string) string {
t.Helper()
path := filepath.Join(t.TempDir(), "m.zip")
f, err := os.Create(path)
if err != nil {
t.Fatal(err)
}
zw := zip.NewWriter(f)
for name, body := range files {
w, err := zw.Create(name)
if err != nil {
t.Fatal(err)
}
if _, err := w.Write([]byte(body)); err != nil {
t.Fatal(err)
}
}
if err := zw.Close(); err != nil {
t.Fatal(err)
}
if err := f.Close(); err != nil {
t.Fatal(err)
}
return path
}
func writeFile(t *testing.T, body string) string {
t.Helper()
path := filepath.Join(t.TempDir(), "f")
if err := os.WriteFile(path, []byte(body), 0o600); err != nil {
t.Fatal(err)
}
return path
}
func TestValidateContentZip(t *testing.T) {
p := &Provider{}
sp := "example.unkin.net/hello/@v/v0.1.0.zip"
dir := t.TempDir()
os.WriteFile(filepath.Join(dir, "go.mod"), []byte("module example.unkin.net/hello\n"), 0o600)
os.WriteFile(filepath.Join(dir, "main.go"), []byte("package main\n"), 0o600)
good := filepath.Join(t.TempDir(), "good.zip")
f, _ := os.Create(good)
if err := modzip.CreateFromDir(f, module.Version{Path: "example.unkin.net/hello", Version: "v0.1.0"}, dir); err != nil {
t.Fatal(err)
}
f.Close()
if err := p.ValidateContent(sp, good); err != nil {
t.Errorf("valid zip rejected: %v", err)
}
bad := map[string]map[string]string{
"no prefix": {"go.mod": "module example.unkin.net/hello\n"},
"wrong version": {"example.unkin.net/hello@v0.2.0/go.mod": "module example.unkin.net/hello\n"},
"wrong module": {"example.unkin.net/other@v0.1.0/go.mod": "module example.unkin.net/other\n"},
}
for name, files := range bad {
if err := p.ValidateContent(sp, writeZip(t, files)); err == nil {
t.Errorf("%s: expected rejection", name)
}
}
if err := p.ValidateContent(sp, writeFile(t, "not a zip")); err == nil {
t.Error("non-zip accepted")
}
}
func TestValidateContentModInfo(t *testing.T) {
p := &Provider{}
mod := "example.unkin.net/hello/@v/v0.1.0.mod"
info := "example.unkin.net/hello/@v/v0.1.0.info"
cases := []struct {
path, body string
ok bool
}{
{mod, "module example.unkin.net/hello\n\ngo 1.25\n", true},
{mod, "module example.unkin.net/other\n", false},
{mod, "go 1.25\n", false},
{mod, "module (\n", false},
{info, `{"Version":"v0.1.0","Time":"2026-01-01T00:00:00Z"}`, true},
{info, `{"Version":"v0.2.0"}`, false},
{info, `nope`, false},
}
for _, c := range cases {
if err := p.ValidateContent(c.path, writeFile(t, c.body)); (err == nil) != c.ok {
t.Errorf("%s %q: err=%v, want ok=%v", c.path, c.body, err, c.ok)
}
}
}
func serve(t *testing.T, fs provider.FileStore, path string) (bool, int, string) {
t.Helper()
rec := httptest.NewRecorder()
handled := (&Provider{}).ServeLocalIndex(rec, httptest.NewRequest("GET", "/"+path, nil), fs, "go-local", path)
return handled, rec.Code, rec.Body.String()
}
func TestServeLocalIndex(t *testing.T) {
fs := &fakeFileStore{paths: []string{
"example.unkin.net/hello/@v/v0.10.0.mod",
"example.unkin.net/hello/@v/v0.10.0.zip",
"example.unkin.net/hello/@v/v0.2.0.mod",
"example.unkin.net/hello/@v/v0.2.0.zip",
"example.unkin.net/hello/@v/v0.2.0.info",
"example.unkin.net/hello/@v/v0.11.0-rc.1.mod",
"example.unkin.net/hello/@v/v0.3.0.zip",
"example.unkin.net/hello/v2/@v/v2.0.0.mod",
"example.unkin.net/!pre/@v/v1.0.0-beta.mod",
}}
if h, code, body := serve(t, fs, "example.unkin.net/hello/@v/list"); !h || code != 200 || body != "v0.2.0\nv0.10.0\nv0.11.0-rc.1\n" {
t.Errorf("list: %v %d %q", h, code, body)
}
if h, code, body := serve(t, fs, "example.unkin.net/hello/@latest"); !h || code != 200 || body != `{"Version":"v0.10.0"}` {
t.Errorf("latest: %v %d %q", h, code, body)
}
if h, _, body := serve(t, fs, "example.unkin.net/!pre/@latest"); !h || body != `{"Version":"v1.0.0-beta"}` {
t.Errorf("prerelease-only latest: %q", body)
}
if h, code, _ := serve(t, fs, "example.unkin.net/missing/@latest"); !h || code != 404 {
t.Errorf("missing latest: %v %d", h, code)
}
if h, code, body := serve(t, fs, "example.unkin.net/missing/@v/list"); !h || code != 200 || body != "" {
t.Errorf("missing list: %v %d %q", h, code, body)
}
if h, _, body := serve(t, fs, "example.unkin.net/hello/@v/v0.10.0.info"); !h || body != `{"Version":"v0.10.0"}` {
t.Errorf("synthesized info: %v %q", h, body)
}
if h, _, _ := serve(t, fs, "example.unkin.net/hello/@v/v0.2.0.info"); h {
t.Error("uploaded .info must be served from storage")
}
if h, _, _ := serve(t, fs, "example.unkin.net/hello/@v/v0.3.0.info"); h {
t.Error(".info without a .mod must not be synthesized")
}
if h, _, _ := serve(t, fs, "example.unkin.net/hello/@v/v0.10.0.zip"); h {
t.Error(".zip must be served from storage")
}
}
-31
View File
@@ -41,11 +41,6 @@ type LocalUploader interface {
UploadResponse(storagePath, contentHash string, sizeBytes int64) map[string]any
}
// ContentValidator checks an upload's bytes (spooled to localFile) before it is stored.
type ContentValidator interface {
ValidateContent(storagePath, localFile string) error
}
type LocalIndexer interface {
ServeLocalIndex(w http.ResponseWriter, r *http.Request, files FileStore, repoName, path string) bool
GenerateLocalIndex(ctx context.Context, files FileStore, repoName, path string) ([]byte, error)
@@ -252,29 +247,3 @@ func Get(t models.PackageType) (Provider, error) {
func All() map[models.PackageType]Provider {
return registry
}
type PuppetMetadataStore interface {
InsertPuppetMetadata(ctx context.Context, meta *PuppetMetadata) error
}
type PuppetMetadataDeleter interface {
DeletePuppetMetadata(ctx context.Context, repoName, filePath string) error
}
type PuppetMetadataReader interface {
ListPuppetMetadataEntries(ctx context.Context, repoName, slug string) ([]PuppetMetadata, error)
}
// PuppetMetadata is a local module release; MetadataJSON is the tarball's
// metadata.json verbatim so Forge release objects carry every field.
type PuppetMetadata struct {
RepoName string
FilePath string
ContentHash string
Slug string
Version string
MetadataJSON string
Size int64
MD5 string
CreatedAt time.Time
}
-393
View File
@@ -1,393 +0,0 @@
package puppet
import (
"archive/tar"
"compress/gzip"
"context"
"crypto/md5"
"encoding/hex"
"encoding/json"
"errors"
"fmt"
"io"
"log/slog"
"net/http"
"net/url"
"path"
"regexp"
"slices"
"strconv"
"strings"
"git.unkin.net/unkin/artifactapi/internal/provider"
"git.unkin.net/unkin/artifactapi/internal/storage"
)
const filesPrefix = "v3/files/"
// releaseRe matches <owner>-<name>-<semver>, the Forge release slug and the
// tarball basename that `puppet module build` produces.
var releaseRe = regexp.MustCompile(`^([a-z0-9]+)-([a-z][a-z0-9_]*)-(\d+\.\d+\.\d+(?:-[0-9a-z.-]+)?(?:\+[0-9a-z.-]+)?)$`)
func parseRelease(s string) (slug, version string, ok bool) {
m := releaseRe.FindStringSubmatch(strings.ToLower(s))
if m == nil {
return "", "", false
}
return m[1] + "-" + m[2], m[3], true
}
func normalizeSlug(s string) string {
return strings.ToLower(strings.ReplaceAll(s, "/", "-"))
}
// ValidateUpload stores tarballs under v3/files/ so Forge file_uri downloads
// resolve straight to the stored file.
func (p *Provider) ValidateUpload(filePath string) (storagePath, contentType string, err error) {
filename := strings.ToLower(path.Base(path.Clean("/" + filePath)))
if _, _, ok := parseRelease(strings.TrimSuffix(filename, ".tar.gz")); !ok || !strings.HasSuffix(filename, ".tar.gz") {
return "", "", fmt.Errorf("file must be named <owner>-<module>-<version>.tar.gz")
}
return filesPrefix + filename, "application/gzip", nil
}
func (p *Provider) UploadResponse(storagePath, contentHash string, sizeBytes int64) map[string]any {
return map[string]any{
"filename": path.Base(storagePath),
"content_hash": contentHash,
"size_bytes": sizeBytes,
}
}
func (p *Provider) AfterUpload(ctx context.Context, repoName, storagePath, contentHash string, blobs provider.BlobReader, db provider.MetadataStore) {
reader, size, err := blobs.Download(ctx, storage.BlobKey(strings.TrimPrefix(contentHash, "sha256:")))
if err != nil {
slog.Error("puppet metadata: download failed", "repo", repoName, "path", storagePath, "error", err)
return
}
defer func() { _ = reader.Close() }()
if size > maxModuleTarball {
slog.Error("puppet metadata: tarball too large", "repo", repoName, "path", storagePath, "size", size)
return
}
hash := md5.New()
src := io.TeeReader(io.LimitReader(reader, maxModuleTarball), hash)
meta, err := parseModule(src)
if err != nil {
slog.Error("puppet metadata: parse failed", "repo", repoName, "path", storagePath, "error", err)
return
}
if _, err := io.Copy(io.Discard, src); err != nil {
slog.Error("puppet metadata: read failed", "repo", repoName, "path", storagePath, "error", err)
return
}
slug, version, _ := parseRelease(strings.TrimSuffix(path.Base(storagePath), ".tar.gz"))
if meta.Slug != slug || meta.Version != version {
slog.Error("puppet metadata: metadata.json does not match filename", "repo", repoName, "path", storagePath, "name", meta.Slug, "version", meta.Version)
return
}
meta.RepoName = repoName
meta.FilePath = storagePath
meta.ContentHash = contentHash
meta.Size = size
meta.MD5 = hex.EncodeToString(hash.Sum(nil))
store, ok := db.(provider.PuppetMetadataStore)
if !ok {
slog.Error("puppet metadata: store does not support puppet metadata", "repo", repoName)
return
}
if err := store.InsertPuppetMetadata(ctx, meta); err != nil {
slog.Error("puppet metadata: insert failed", "repo", repoName, "path", storagePath, "error", err)
return
}
slog.Info("puppet metadata: parsed", "repo", repoName, "module", meta.Slug, "version", meta.Version)
}
func (p *Provider) AfterDelete(ctx context.Context, repoName, storagePath string, db provider.MetadataDeleter) error {
deleter, ok := db.(provider.PuppetMetadataDeleter)
if !ok {
return nil
}
return deleter.DeletePuppetMetadata(ctx, repoName, storagePath)
}
const maxMetadataJSON = 1 << 20
var (
maxModuleTarball int64 = 100 << 20
maxModuleScan int64 = 200 << 20
)
// parseModule reads the top-level <dir>/metadata.json from a module tarball,
// scanning at most maxModuleScan decompressed bytes.
func parseModule(r io.Reader) (*provider.PuppetMetadata, error) {
zr, err := gzip.NewReader(r)
if err != nil {
return nil, err
}
scan := &io.LimitedReader{R: zr, N: maxModuleScan}
tr := tar.NewReader(scan)
for {
hdr, err := tr.Next()
if scan.N <= 0 {
return nil, errors.New("module tarball exceeds decompressed scan limit before metadata.json")
}
if err == io.EOF {
return nil, errors.New("no metadata.json in module tarball")
}
if err != nil {
return nil, err
}
dir, file := path.Split(strings.TrimPrefix(path.Clean(hdr.Name), "./"))
if hdr.Typeflag != tar.TypeReg || file != "metadata.json" || strings.Count(dir, "/") != 1 {
continue
}
body, err := io.ReadAll(io.LimitReader(tr, maxMetadataJSON))
if err != nil {
return nil, err
}
var md struct {
Name string `json:"name"`
Version string `json:"version"`
}
if err := json.Unmarshal(body, &md); err != nil {
return nil, fmt.Errorf("parse metadata.json: %w", err)
}
if md.Name == "" || md.Version == "" {
return nil, errors.New("metadata.json missing name or version")
}
return &provider.PuppetMetadata{Slug: normalizeSlug(md.Name), Version: md.Version, MetadataJSON: string(body)}, nil
}
}
func (p *Provider) ServeLocalIndex(w http.ResponseWriter, r *http.Request, files provider.FileStore, repoName, reqPath string) bool {
clean := strings.TrimPrefix(path.Clean("/"+reqPath), "/")
var list func(slug string) ([]provider.PuppetMetadata, error)
if reader, ok := files.(provider.PuppetMetadataReader); ok {
list = func(slug string) ([]provider.PuppetMetadata, error) {
metas, err := reader.ListPuppetMetadataEntries(r.Context(), repoName, slug)
sortReleases(metas)
return metas, err
}
} else {
list = func(string) ([]provider.PuppetMetadata, error) {
return nil, errors.New("puppet metadata not available")
}
}
switch {
case clean == "v3/releases":
serveReleaseList(w, r, list)
case strings.HasPrefix(clean, "v3/releases/"):
slug, version, ok := parseRelease(strings.TrimPrefix(clean, "v3/releases/"))
if !ok {
notFound(w)
return true
}
metas, err := list(slug)
if err != nil {
http.Error(w, err.Error(), http.StatusInternalServerError)
return true
}
for _, m := range metas {
if m.Version == version {
writeJSON(w, releaseObject(m))
return true
}
}
notFound(w)
case strings.HasPrefix(clean, "v3/modules/"):
slug := normalizeSlug(strings.TrimPrefix(clean, "v3/modules/"))
metas, err := list(slug)
if err != nil {
http.Error(w, err.Error(), http.StatusInternalServerError)
return true
}
if len(metas) == 0 {
notFound(w)
return true
}
writeJSON(w, moduleObject(metas))
default:
return false
}
return true
}
func (p *Provider) GenerateLocalIndex(ctx context.Context, files provider.FileStore, repoName, path string) ([]byte, error) {
return nil, fmt.Errorf("puppet local index generation for virtual repos not supported")
}
func serveReleaseList(w http.ResponseWriter, r *http.Request, list func(string) ([]provider.PuppetMetadata, error)) {
q := r.URL.Query()
slug := normalizeSlug(q.Get("module"))
limit, err := strconv.Atoi(q.Get("limit"))
if err != nil || limit <= 0 {
limit = 20
}
limit = min(limit, 100)
offset, err := strconv.Atoi(q.Get("offset"))
if err != nil || offset < 0 {
offset = 0
}
metas, err := list(slug)
if err != nil {
http.Error(w, err.Error(), http.StatusInternalServerError)
return
}
offset = min(offset, len(metas))
results := []map[string]any{}
for _, m := range metas[offset : offset+min(limit, len(metas)-offset)] {
results = append(results, releaseObject(m))
}
page := func(off int) any {
if off < 0 || off >= len(metas) && off != 0 {
return nil
}
v := url.Values{"limit": {strconv.Itoa(limit)}, "offset": {strconv.Itoa(off)}}
if slug != "" {
v.Set("module", slug)
}
return "/v3/releases?" + v.Encode()
}
var previous any
if offset > 0 {
previous = page(max(offset-limit, 0))
}
writeJSON(w, map[string]any{
"pagination": map[string]any{
"limit": limit,
"offset": offset,
"first": page(0),
"previous": previous,
"current": page(offset),
"next": page(offset + limit),
"total": len(metas),
},
"results": results,
})
}
func owner(slug string) map[string]any {
name, _, _ := strings.Cut(slug, "-")
return map[string]any{"uri": "/v3/users/" + name, "slug": name, "username": name}
}
func moduleRef(slug string) map[string]any {
_, name, _ := strings.Cut(slug, "-")
return map[string]any{"uri": "/v3/modules/" + slug, "slug": slug, "name": name, "deprecated_at": nil, "owner": owner(slug)}
}
const forgeTime = "2006-01-02 15:04:05 -0700"
func releaseObject(m provider.PuppetMetadata) map[string]any {
slug := m.Slug + "-" + m.Version
return map[string]any{
"uri": "/v3/releases/" + slug,
"slug": slug,
"module": moduleRef(m.Slug),
"version": m.Version,
"metadata": json.RawMessage(m.MetadataJSON),
"tags": []string{},
"supported": false,
"pdk": false,
"file_uri": "/" + m.FilePath,
"file_size": m.Size,
"file_md5": m.MD5,
"file_sha256": strings.TrimPrefix(m.ContentHash, "sha256:"),
"downloads": 0,
"readme": nil,
"changelog": nil,
"license": nil,
"created_at": m.CreatedAt.Format(forgeTime),
"updated_at": m.CreatedAt.Format(forgeTime),
"deleted_at": nil,
}
}
// moduleObject expects metas sorted newest version first.
func moduleObject(metas []provider.PuppetMetadata) map[string]any {
obj := moduleRef(metas[0].Slug)
releases := make([]map[string]any, 0, len(metas))
for _, m := range metas {
slug := m.Slug + "-" + m.Version
releases = append(releases, map[string]any{
"uri": "/v3/releases/" + slug, "slug": slug, "version": m.Version,
"file_uri": "/" + m.FilePath, "file_size": m.Size, "supported": false,
"created_at": m.CreatedAt.Format(forgeTime), "deleted_at": nil,
})
}
obj["current_release"] = releaseObject(metas[0])
obj["releases"] = releases
obj["downloads"] = 0
obj["created_at"] = metas[len(metas)-1].CreatedAt.Format(forgeTime)
obj["updated_at"] = metas[0].CreatedAt.Format(forgeTime)
return obj
}
func writeJSON(w http.ResponseWriter, v any) {
w.Header().Set("Content-Type", "application/json")
w.WriteHeader(http.StatusOK)
enc := json.NewEncoder(w)
enc.SetEscapeHTML(false)
_ = enc.Encode(v)
}
func notFound(w http.ResponseWriter) {
w.Header().Set("Content-Type", "application/json")
w.WriteHeader(http.StatusNotFound)
_, _ = io.WriteString(w, `{"message":"404 Not Found","errors":["The requested resource could not be found"]}`)
}
// sortReleases orders by module slug, then newest semver first.
func sortReleases(metas []provider.PuppetMetadata) {
slices.SortStableFunc(metas, func(a, b provider.PuppetMetadata) int {
if c := strings.Compare(a.Slug, b.Slug); c != 0 {
return c
}
return compareSemver(b.Version, a.Version)
})
}
func compareSemver(a, b string) int {
a, _, _ = strings.Cut(a, "+")
b, _, _ = strings.Cut(b, "+")
aCore, aPre, aHasPre := strings.Cut(a, "-")
bCore, bPre, bHasPre := strings.Cut(b, "-")
if c := compareIdents(strings.Split(aCore, "."), strings.Split(bCore, ".")); c != 0 {
return c
}
switch {
case aHasPre && !bHasPre:
return -1
case !aHasPre && bHasPre:
return 1
}
return compareIdents(strings.Split(aPre, "."), strings.Split(bPre, "."))
}
func compareIdents(a, b []string) int {
for i := 0; i < len(a) && i < len(b); i++ {
an, aErr := strconv.Atoi(a[i])
bn, bErr := strconv.Atoi(b[i])
var c int
switch {
case aErr == nil && bErr == nil:
c = an - bn
case aErr == nil:
c = -1
case bErr == nil:
c = 1
default:
c = strings.Compare(a[i], b[i])
}
if c != 0 {
return c
}
}
return len(a) - len(b)
}
-301
View File
@@ -1,301 +0,0 @@
package puppet
import (
"archive/tar"
"bytes"
"compress/gzip"
"context"
"crypto/md5"
"encoding/hex"
"encoding/json"
"io"
"net/http"
"net/http/httptest"
"strings"
"testing"
"time"
"git.unkin.net/unkin/artifactapi/internal/provider"
)
func moduleTarball(t *testing.T, dir, metadata string) []byte {
t.Helper()
var buf bytes.Buffer
zw := gzip.NewWriter(&buf)
tw := tar.NewWriter(zw)
for name, body := range map[string]string{dir + "/metadata.json": metadata, dir + "/manifests/init.pp": "class hello {}\n"} {
if err := tw.WriteHeader(&tar.Header{Name: name, Mode: 0o644, Size: int64(len(body))}); err != nil {
t.Fatal(err)
}
_, _ = tw.Write([]byte(body))
}
_ = tw.Close()
_ = zw.Close()
return buf.Bytes()
}
const helloMetadata = `{"name":"unkin-hello","version":"0.1.0","dependencies":[{"name":"puppetlabs/stdlib","version_requirement":">= 4.0.0"}]}`
type fakeBlobs struct{ data []byte }
func (f fakeBlobs) Download(context.Context, string) (io.ReadCloser, int64, error) {
return io.NopCloser(bytes.NewReader(f.data)), int64(len(f.data)), nil
}
type fakeStore struct{ inserted *provider.PuppetMetadata }
func (f *fakeStore) InsertRPMMetadata(context.Context, *provider.RPMMetadata) error { return nil }
func (f *fakeStore) InsertDebMetadata(context.Context, *provider.DebMetadata) error { return nil }
func (f *fakeStore) InsertPuppetMetadata(_ context.Context, m *provider.PuppetMetadata) error {
f.inserted = m
return nil
}
type fakeReader struct{ metas []provider.PuppetMetadata }
func (f fakeReader) ListPuppetMetadataEntries(_ context.Context, _, slug string) ([]provider.PuppetMetadata, error) {
var out []provider.PuppetMetadata
for _, m := range f.metas {
if slug == "" || m.Slug == slug {
out = append(out, m)
}
}
return out, nil
}
func (fakeReader) ListFilesByPrefix(context.Context, string, string) ([]provider.FileEntry, error) {
return nil, nil
}
func (fakeReader) ListPackages(context.Context, string) ([]string, error) { return nil, nil }
func TestValidateUpload(t *testing.T) {
p := &Provider{}
sp, ct, err := p.ValidateUpload("some/dir/Unkin-hello-0.1.0.tar.gz")
if err != nil || sp != "v3/files/unkin-hello-0.1.0.tar.gz" || ct != "application/gzip" {
t.Errorf("sp=%q ct=%q err=%v", sp, ct, err)
}
for _, bad := range []string{"hello-0.1.0.tar.gz", "unkin-hello-0.1.tar.gz", "unkin-hello-0.1.0.zip", "unkin-Hello_x-0.1.0.tgz"} {
if _, _, err := p.ValidateUpload(bad); err == nil {
t.Errorf("%q accepted", bad)
}
}
}
func TestAfterUploadRecordsMetadata(t *testing.T) {
raw := moduleTarball(t, "unkin-hello-0.1.0", helloMetadata)
store := &fakeStore{}
(&Provider{}).AfterUpload(context.Background(), "forge", "v3/files/unkin-hello-0.1.0.tar.gz", "sha256:abc", fakeBlobs{raw}, store)
m := store.inserted
if m == nil {
t.Fatal("nothing inserted")
}
sum := md5.Sum(raw)
if m.Slug != "unkin-hello" || m.Version != "0.1.0" || m.MD5 != hex.EncodeToString(sum[:]) || m.Size != int64(len(raw)) || m.MetadataJSON != helloMetadata {
t.Errorf("got %+v", m)
}
}
func TestAfterUploadRejectsMismatchedFilename(t *testing.T) {
raw := moduleTarball(t, "unkin-hello-0.2.0", `{"name":"unkin-hello","version":"0.2.0"}`)
store := &fakeStore{}
(&Provider{}).AfterUpload(context.Background(), "forge", "v3/files/unkin-hello-0.1.0.tar.gz", "sha256:abc", fakeBlobs{raw}, store)
if store.inserted != nil {
t.Error("mismatched version indexed")
}
}
func TestParseModuleRequiresTopLevelMetadata(t *testing.T) {
if _, err := parseModule(bytes.NewReader(moduleTarball(t, "a/b", helloMetadata))); err == nil {
t.Error("nested metadata.json accepted")
}
if _, err := parseModule(bytes.NewReader(moduleTarball(t, "x", `{"name":"unkin-hello"}`))); err == nil {
t.Error("missing version accepted")
}
}
func tarballOf(t *testing.T, entries ...*tar.Header) []byte {
t.Helper()
var buf bytes.Buffer
zw := gzip.NewWriter(&buf)
tw := tar.NewWriter(zw)
for _, h := range entries {
if err := tw.WriteHeader(h); err != nil {
t.Fatal(err)
}
if h.Typeflag == tar.TypeReg {
body := helloMetadata
if !strings.HasSuffix(h.Name, "metadata.json") {
body = strings.Repeat("x", int(h.Size))
}
_, _ = tw.Write([]byte(body))
}
}
_ = tw.Close()
_ = zw.Close()
return buf.Bytes()
}
func TestParseModuleSkipsNonRegularMetadata(t *testing.T) {
raw := tarballOf(t,
&tar.Header{Name: "unkin-hello-0.1.0/metadata.json", Typeflag: tar.TypeSymlink, Linkname: "/etc/passwd"},
&tar.Header{Name: "unkin-hello-0.1.0/metadata.json/", Typeflag: tar.TypeDir, Mode: 0o755},
&tar.Header{Name: "unkin-hello-0.1.0/metadata.json", Typeflag: tar.TypeReg, Mode: 0o644, Size: int64(len(helloMetadata))},
)
meta, err := parseModule(bytes.NewReader(raw))
if err != nil || meta.Slug != "unkin-hello" || meta.Version != "0.1.0" {
t.Fatalf("got %v, %v", meta, err)
}
}
func TestParseModuleCapsDecompressedScan(t *testing.T) {
defer func(n int64) { maxModuleScan = n }(maxModuleScan)
maxModuleScan = 64 << 10
raw := tarballOf(t,
&tar.Header{Name: "unkin-hello-0.1.0/big", Typeflag: tar.TypeReg, Mode: 0o644, Size: 1 << 20},
&tar.Header{Name: "unkin-hello-0.1.0/metadata.json", Typeflag: tar.TypeReg, Mode: 0o644, Size: int64(len(helloMetadata))},
)
if _, err := parseModule(bytes.NewReader(raw)); err == nil || !strings.Contains(err.Error(), "scan limit") {
t.Fatalf("expected scan limit error, got %v", err)
}
maxModuleScan = 2 << 20
if _, err := parseModule(bytes.NewReader(raw)); err != nil {
t.Fatalf("under cap: %v", err)
}
}
func TestAfterUploadCapsTarballSize(t *testing.T) {
defer func(n int64) { maxModuleTarball = n }(maxModuleTarball)
raw := moduleTarball(t, "unkin-hello-0.1.0", helloMetadata)
maxModuleTarball = int64(len(raw)) - 1
store := &fakeStore{}
(&Provider{}).AfterUpload(context.Background(), "forge", "v3/files/unkin-hello-0.1.0.tar.gz", "sha256:abc", fakeBlobs{raw}, store)
if store.inserted != nil {
t.Error("oversized tarball indexed")
}
maxModuleTarball = int64(len(raw))
(&Provider{}).AfterUpload(context.Background(), "forge", "v3/files/unkin-hello-0.1.0.tar.gz", "sha256:abc", fakeBlobs{raw}, store)
if store.inserted == nil {
t.Error("tarball at cap not indexed")
}
}
func TestReleaseListClampsPagination(t *testing.T) {
files := releases("0.1.0", "0.2.0", "0.3.0")
for _, q := range []string{"offset=9223372036854775807", "offset=9223372036854775807&limit=9223372036854775807", "offset=-5&limit=-5", "limit=9223372036854775807"} {
code, body := get(t, files, "v3/releases?module=unkin-hello&"+q)
if code != http.StatusOK {
t.Fatalf("%s: code %d", q, code)
}
pg := body["pagination"].(map[string]any)
if l := pg["limit"].(float64); l < 1 || l > 100 {
t.Errorf("%s: limit %v", q, l)
}
if o := pg["offset"].(float64); o < 0 || o > 3 {
t.Errorf("%s: offset %v", q, o)
}
}
_, body := get(t, files, "v3/releases?module=unkin-hello&offset=9223372036854775807")
if len(body["results"].([]any)) != 0 || body["pagination"].(map[string]any)["next"] != nil {
t.Errorf("past-end page: %v", body)
}
}
func get(t *testing.T, files provider.FileStore, target string) (int, map[string]any) {
t.Helper()
rec := httptest.NewRecorder()
req := httptest.NewRequest(http.MethodGet, "/x/"+target, nil)
path, _, _ := strings.Cut(target, "?")
if !(&Provider{}).ServeLocalIndex(rec, req, files, "forge", path) {
return 0, nil
}
var body map[string]any
_ = json.Unmarshal(rec.Body.Bytes(), &body)
return rec.Code, body
}
func releases(versions ...string) fakeReader {
var f fakeReader
for i, v := range versions {
f.metas = append(f.metas, provider.PuppetMetadata{
FilePath: "v3/files/unkin-hello-" + v + ".tar.gz", ContentHash: "sha256:feed", Slug: "unkin-hello",
Version: v, MetadataJSON: `{"name":"unkin-hello","version":"` + v + `"}`, MD5: "m" + v,
CreatedAt: time.Unix(int64(i), 0),
})
}
f.metas = append(f.metas, provider.PuppetMetadata{Slug: "other-mod", Version: "9.9.9", MetadataJSON: `{}`})
return f
}
func TestReleaseListPaginatesNewestFirst(t *testing.T) {
files := releases("0.1.0", "0.10.0", "0.2.0", "1.0.0-rc.1", "1.0.0")
code, body := get(t, files, "v3/releases?module=unkin/hello&limit=2")
if code != http.StatusOK {
t.Fatalf("code %d", code)
}
results := body["results"].([]any)
pg := body["pagination"].(map[string]any)
if len(results) != 2 || results[0].(map[string]any)["version"] != "1.0.0" || results[1].(map[string]any)["version"] != "1.0.0-rc.1" {
t.Fatalf("page 1: %v", results)
}
if pg["total"] != float64(5) || pg["next"] != "/v3/releases?limit=2&module=unkin-hello&offset=2" || pg["previous"] != nil {
t.Errorf("pagination: %v", pg)
}
_, body = get(t, files, "v3/releases?module=unkin-hello&limit=2&offset=4")
results = body["results"].([]any)
pg = body["pagination"].(map[string]any)
if len(results) != 1 || results[0].(map[string]any)["version"] != "0.1.0" || pg["next"] != nil || pg["previous"] != "/v3/releases?limit=2&module=unkin-hello&offset=2" {
t.Errorf("last page: %v %v", results, pg)
}
_, body = get(t, files, "v3/releases?module=nobody-none")
if len(body["results"].([]any)) != 0 {
t.Error("unknown module returned results")
}
}
func TestReleaseObject(t *testing.T) {
code, body := get(t, releases("0.1.0"), "v3/releases/unkin-hello-0.1.0")
if code != http.StatusOK {
t.Fatalf("code %d", code)
}
if body["file_uri"] != "/v3/files/unkin-hello-0.1.0.tar.gz" || body["file_md5"] != "m0.1.0" || body["file_sha256"] != "feed" {
t.Errorf("release: %v", body)
}
if body["metadata"].(map[string]any)["name"] != "unkin-hello" || body["module"].(map[string]any)["owner"].(map[string]any)["username"] != "unkin" {
t.Errorf("release refs: %v", body)
}
if code, _ := get(t, releases("0.1.0"), "v3/releases/unkin-hello-0.2.0"); code != http.StatusNotFound {
t.Errorf("missing version: %d", code)
}
}
func TestModuleObject(t *testing.T) {
code, body := get(t, releases("0.9.0", "0.10.0"), "v3/modules/unkin-hello")
if code != http.StatusOK {
t.Fatalf("code %d", code)
}
if body["slug"] != "unkin-hello" || body["name"] != "hello" || body["current_release"].(map[string]any)["version"] != "0.10.0" || len(body["releases"].([]any)) != 2 {
t.Errorf("module: %v", body)
}
if code, _ := get(t, releases(), "v3/modules/unkin-missing"); code != http.StatusNotFound {
t.Errorf("missing module: %d", code)
}
}
func TestFilesFallThrough(t *testing.T) {
if code, _ := get(t, releases(), "v3/files/unkin-hello-0.1.0.tar.gz"); code != 0 {
t.Error("file downloads must fall through to the stored file")
}
}
func TestCompareSemver(t *testing.T) {
ordered := []string{"0.1.0", "0.2.0", "0.10.0", "1.0.0-alpha", "1.0.0-alpha.1", "1.0.0-beta", "1.0.0-beta.2", "1.0.0-beta.11", "1.0.0", "1.0.1+build"}
for i := 1; i < len(ordered); i++ {
if compareSemver(ordered[i-1], ordered[i]) >= 0 || compareSemver(ordered[i], ordered[i-1]) <= 0 {
t.Errorf("%s should sort before %s", ordered[i-1], ordered[i])
}
}
if compareSemver("1.0.0+a", "1.0.0+b") != 0 {
t.Error("build metadata must not affect precedence")
}
}
+245
View File
@@ -0,0 +1,245 @@
package virtual
import (
"bytes"
"crypto/md5"
"encoding/hex"
"fmt"
"path"
"regexp"
"slices"
"strings"
"time"
)
// debIndexRe matches the binary Packages indexes a virtual merges: the flat
// repo's root Packages and a suite's <component>/binary-<arch>/Packages.
var debIndexRe = regexp.MustCompile(`^([^/]+/binary-[^/]+/)?Packages(\.[a-z0-9]+)?$`)
// debByHashRe matches an index requested by its SHA256 (Acquire-By-Hash).
var debByHashRe = regexp.MustCompile(`^([^/]+/binary-[^/]+/)?by-hash/SHA256/[0-9a-f]{64}$`)
// debCompressions is the order a member's index variants are fetched in.
var debCompressions = []string{".xz", ".gz", ".zst", ".bz2", ""}
// DebMember is one member's Release plus its decompressed Packages indexes,
// keyed by index directory relative to the Release ("" for a flat repo).
type DebMember struct {
RemoteName string
Release []byte
Packages map[string][]byte
}
// DebRepo is a merged apt repo: Release plus the indexes it lists, keyed by
// their path relative to the Release.
type DebRepo struct {
Release []byte
Files map[string][]byte
}
type debRelease struct {
fields map[string]string
files []string
}
// parseDebRelease reads a Release file's single-line fields and the names
// listed in its checksum sections.
func parseDebRelease(body []byte) debRelease {
rel := debRelease{fields: map[string]string{}}
inSums := false
seen := map[string]bool{}
for line := range strings.SplitSeq(string(body), "\n") {
line = strings.TrimRight(line, "\r")
if line == "" {
continue
}
if line[0] == ' ' || line[0] == '\t' {
if f := strings.Fields(line); inSums && len(f) == 3 && !seen[f[2]] {
seen[f[2]] = true
rel.files = append(rel.files, f[2])
}
continue
}
k, v, _ := strings.Cut(line, ":")
v = strings.TrimSpace(v)
inSums = v == "" && (k == "MD5Sum" || strings.HasPrefix(k, "SHA"))
if _, ok := rel.fields[k]; !ok {
rel.fields[k] = v
}
}
return rel
}
// debIndexFiles returns, per index directory, the variant of its Packages file
// to fetch from a member's Release listing.
func debIndexFiles(rel debRelease) map[string]string {
listed := map[string]bool{}
for _, f := range rel.files {
listed[f] = true
}
out := map[string]string{}
for _, f := range rel.files {
m := debIndexRe.FindStringSubmatch(f)
if m == nil || out[m[1]] != "" {
continue
}
for _, c := range debCompressions {
if listed[m[1]+"Packages"+c] {
out[m[1]] = m[1] + "Packages" + c
break
}
}
}
return out
}
func splitStanzas(body []byte) []string {
var out []string
for s := range strings.SplitSeq(strings.ReplaceAll(string(body), "\r\n", "\n"), "\n\n") {
if s = strings.Trim(s, "\n"); s != "" {
out = append(out, s)
}
}
return out
}
func stanzaField(stanza, key string) string {
for line := range strings.SplitSeq(stanza, "\n") {
if k, v, ok := strings.Cut(line, ":"); ok && k == key {
return strings.TrimSpace(v)
}
}
return ""
}
func unionFields(dst []string, field string) []string {
for f := range strings.FieldsSeq(field) {
if !slices.Contains(dst, f) {
dst = append(dst, f)
}
}
return dst
}
func parseDebDate(s string) (time.Time, bool) {
for _, layout := range []string{time.RFC1123Z, time.RFC1123} {
if t, err := time.Parse(layout, s); err == nil {
return t, true
}
}
return time.Time{}, false
}
// MergeDeb merges members into one apt repo. Members are in priority order: the
// first member to carry a (Package, Version, Architecture) in an index wins;
// stanzas missing any of those are always kept. Filename is prefixed with the
// owning member's name so the virtual can route downloads back to it.
func MergeDeb(members []DebMember) *DebRepo {
var suite, codename string
var arches, comps, dirs []string
date := time.Unix(0, 0)
for _, m := range members {
rel := parseDebRelease(m.Release)
if suite == "" {
suite, codename = rel.fields["Suite"], rel.fields["Codename"]
}
arches = unionFields(arches, rel.fields["Architectures"])
comps = unionFields(comps, rel.fields["Components"])
if t, ok := parseDebDate(rel.fields["Date"]); ok && t.After(date) {
date = t
}
for d := range m.Packages {
if !slices.Contains(dirs, d) {
dirs = append(dirs, d)
}
}
}
slices.Sort(dirs)
repo := &DebRepo{Files: map[string][]byte{}}
for _, d := range dirs {
seen := map[string]bool{}
var b bytes.Buffer
for _, m := range members {
for _, s := range splitStanzas(m.Packages[d]) {
pkg, ver, arch := stanzaField(s, "Package"), stanzaField(s, "Version"), stanzaField(s, "Architecture")
if pkg != "" && ver != "" && arch != "" {
key := pkg + "\x00" + ver + "\x00" + arch
if seen[key] {
continue
}
seen[key] = true
}
if fn := stanzaField(s, "Filename"); fn != "" {
s = rewriteFilename(s, m.RemoteName+"/"+strings.TrimPrefix(path.Clean("/"+fn), "/"))
}
b.WriteString(s)
b.WriteString("\n\n")
}
}
gz := gzipDeterministic(b.Bytes())
repo.Files[d+"Packages"] = b.Bytes()
repo.Files[d+"Packages.gz"] = gz
repo.Files[d+"by-hash/SHA256/"+sha256Hex(b.Bytes())] = b.Bytes()
repo.Files[d+"by-hash/SHA256/"+sha256Hex(gz)] = gz
}
var r bytes.Buffer
if suite != "" {
fmt.Fprintf(&r, "Suite: %s\n", suite)
}
if codename != "" {
fmt.Fprintf(&r, "Codename: %s\n", codename)
}
fmt.Fprintf(&r, "Date: %s\n", date.UTC().Format(time.RFC1123Z))
fmt.Fprintf(&r, "Architectures: %s\n", strings.Join(arches, " "))
if len(comps) > 0 {
fmt.Fprintf(&r, "Components: %s\n", strings.Join(comps, " "))
}
r.WriteString("Acquire-By-Hash: yes\n")
for _, sec := range []struct {
name string
sum func([]byte) string
}{{"MD5Sum", md5Hex}, {"SHA256", sha256Hex}} {
r.WriteString(sec.name + ":\n")
for _, d := range dirs {
for _, n := range []string{d + "Packages", d + "Packages.gz"} {
fmt.Fprintf(&r, " %s %d %s\n", sec.sum(repo.Files[n]), len(repo.Files[n]), n)
}
}
}
repo.Release = r.Bytes()
return repo
}
func rewriteFilename(stanza, fn string) string {
lines := strings.Split(stanza, "\n")
for i, l := range lines {
if strings.HasPrefix(l, "Filename:") {
lines[i] = "Filename: " + fn
break
}
}
return strings.Join(lines, "\n")
}
// debIndexPath splits an index request into its Release directory and the file
// under it. ok is false for anything a deb virtual does not merge.
func debIndexPath(p string) (base, name string, ok bool) {
if rest, found := strings.CutPrefix(p, "dists/"); found {
suite, n, found := strings.Cut(rest, "/")
if !found || suite == "" {
return "", "", false
}
base, p = "dists/"+suite+"/", n
}
if p != "Release" && !debIndexRe.MatchString(p) && !debByHashRe.MatchString(p) {
return "", "", false
}
return base, p, true
}
func md5Hex(data []byte) string {
h := md5.Sum(data)
return hex.EncodeToString(h[:])
}
+179
View File
@@ -0,0 +1,179 @@
package virtual
import (
"bytes"
"crypto/md5"
"encoding/hex"
"fmt"
"maps"
"path"
"slices"
"strings"
"testing"
)
func debStanza(pkg, ver, arch, filename string) string {
return fmt.Sprintf("Package: %s\nVersion: %s\nArchitecture: %s\nDescription: test\n multi-line body\nFilename: %s\nSize: 1\n", pkg, ver, arch, filename)
}
func flatDebMember(name, date string, stanzas ...string) DebMember {
rel := "Date: " + date + "\nArchitectures: amd64\nAcquire-By-Hash: no\nSHA256:\n x 1 Packages\n x 1 Packages.gz\n"
return DebMember{RemoteName: name, Release: []byte(rel), Packages: map[string][]byte{"": []byte(strings.Join(stanzas, "\n"))}}
}
func TestMergeDebDedupesByMemberOrder(t *testing.T) {
repo := MergeDeb([]DebMember{
flatDebMember("a", "Mon, 05 Oct 2026 10:00:00 +0000",
debStanza("foo", "1.0", "amd64", "pool/foo_1.0_amd64.deb"),
debStanza("bar", "2.0", "amd64", "/pool/bar.deb"),
debStanza("dot", "1.0", "amd64", "./dot.deb"),
"Package: noversion\nFilename: nv1.deb\n",
"Package: noversion\nFilename: nv2.deb\n"),
flatDebMember("b", "Tue, 06 Oct 2026 10:00:00 UTC",
debStanza("foo", "1.0", "amd64", "pool/foo-from-b.deb"),
debStanza("foo", "1.0", "arm64", "pool/foo_arm64.deb"),
debStanza("foo", "1.1", "amd64", "o/r/releases/download/v1/foo.deb")),
})
pk := string(repo.Files["Packages"])
stanzas := splitStanzas(repo.Files["Packages"])
if len(stanzas) != 7 {
t.Fatalf("want 7 stanzas (one duplicate dropped), got %d:\n%s", len(stanzas), pk)
}
for _, want := range []string{
"Filename: a/pool/foo_1.0_amd64.deb",
"Filename: a/pool/bar.deb",
"Filename: a/dot.deb",
"Filename: a/nv1.deb",
"Filename: a/nv2.deb",
"Filename: b/pool/foo_arm64.deb",
"Filename: b/o/r/releases/download/v1/foo.deb",
" multi-line body",
} {
if !strings.Contains(pk, want) {
t.Errorf("merged Packages missing %q:\n%s", want, pk)
}
}
if strings.Contains(pk, "foo-from-b") {
t.Fatalf("second member's duplicate must lose:\n%s", pk)
}
if !bytes.Equal(gunzip(t, repo.Files["Packages.gz"]), repo.Files["Packages"]) {
t.Fatal("Packages.gz does not match Packages")
}
if !strings.Contains(string(repo.Release), "Date: Tue, 06 Oct 2026 10:00:00 +0000\n") {
t.Fatalf("Date should be the newest member date:\n%s", repo.Release)
}
}
func TestMergeDebReleaseHashesFiles(t *testing.T) {
repo := MergeDeb([]DebMember{flatDebMember("a", "", debStanza("foo", "1", "amd64", "pool/foo.deb"))})
rel := parseDebRelease(repo.Release)
if got := slices.Sorted(slices.Values(rel.files)); !slices.Equal(got, []string{"Packages", "Packages.gz"}) {
t.Fatalf("Release lists %v", got)
}
inSHA := false
checked := 0
for line := range strings.SplitSeq(string(repo.Release), "\n") {
if !strings.HasPrefix(line, " ") {
inSHA = line == "SHA256:"
continue
}
var sum, name string
var size int
if _, err := fmt.Sscan(line, &sum, &size, &name); err != nil {
t.Fatal(err)
}
body := repo.Files[name]
want := sha256Hex(body)
if !inSHA {
h := md5.Sum(body)
want = hex.EncodeToString(h[:])
}
if sum != want || size != len(body) {
t.Errorf("%s: Release has %s %d, file is %s %d", name, sum, size, want, len(body))
}
checked++
}
if checked != 4 {
t.Fatalf("checked %d Release entries, want 4:\n%s", checked, repo.Release)
}
if !bytes.Equal(MergeDeb([]DebMember{flatDebMember("a", "", debStanza("foo", "1", "amd64", "pool/foo.deb"))}).Release, repo.Release) {
t.Fatal("merge must be deterministic")
}
}
func TestMergeDebSuiteLayout(t *testing.T) {
rel := func(comps string) []byte {
return []byte("Suite: stable\nCodename: trixie\nArchitectures: amd64 arm64\nComponents: " + comps + "\nSHA256:\n x 1 main/binary-amd64/Packages.xz\n")
}
repo := MergeDeb([]DebMember{
{RemoteName: "deb1", Release: rel("main"), Packages: map[string][]byte{"main/binary-amd64/": []byte(debStanza("foo", "1", "amd64", "pool/main/f/foo.deb"))}},
{RemoteName: "deb2", Release: rel("main contrib"), Packages: map[string][]byte{
"main/binary-amd64/": []byte(debStanza("bar", "1", "amd64", "pool/main/b/bar.deb")),
"contrib/binary-amd64/": []byte(debStanza("baz", "1", "amd64", "pool/contrib/b/baz.deb")),
}},
})
for _, want := range []string{"Suite: stable\n", "Codename: trixie\n", "Components: main contrib\n", "Architectures: amd64 arm64\n"} {
if !strings.Contains(string(repo.Release), want) {
t.Errorf("Release missing %q:\n%s", want, repo.Release)
}
}
want := []string{"contrib/binary-amd64/Packages", "contrib/binary-amd64/Packages.gz", "main/binary-amd64/Packages", "main/binary-amd64/Packages.gz"}
if got := slices.Sorted(slices.Values(parseDebRelease(repo.Release).files)); !slices.Equal(got, want) {
t.Fatalf("Release lists %v, want %v", got, want)
}
if !strings.Contains(string(repo.Release), "Acquire-By-Hash: yes\n") {
t.Fatalf("Release must advertise by-hash:\n%s", repo.Release)
}
for _, n := range want {
byHash := path.Dir(n) + "/by-hash/SHA256/" + sha256Hex(repo.Files[n])
if !bytes.Equal(repo.Files[byHash], repo.Files[n]) {
t.Errorf("%s not served at %s", n, byHash)
}
}
if len(repo.Files) != 2*len(want) {
t.Fatalf("files %v, want each index plus its by-hash copy", slices.Sorted(maps.Keys(repo.Files)))
}
if n := len(splitStanzas(repo.Files["main/binary-amd64/Packages"])); n != 2 {
t.Fatalf("main/binary-amd64 should merge both members, got %d stanzas", n)
}
}
func TestDebIndexFiles(t *testing.T) {
rel := parseDebRelease([]byte("Origin: Debian\nMD5Sum:\n a 1 main/binary-amd64/Packages\n a 1 main/binary-amd64/Packages.gz\nSHA256:\n" +
" a 1 main/binary-amd64/Packages\n a 1 main/binary-amd64/Packages.xz\n a 1 main/binary-amd64/Packages.gz\n" +
" a 1 main/debian-installer/binary-amd64/Packages.xz\n a 1 main/i18n/Translation-en.xz\n a 1 contrib/binary-all/Packages\n"))
got := debIndexFiles(rel)
want := map[string]string{"main/binary-amd64/": "main/binary-amd64/Packages.xz", "contrib/binary-all/": "contrib/binary-all/Packages"}
if !maps.Equal(got, want) {
t.Fatalf("got %v, want %v", got, want)
}
if flat := debIndexFiles(parseDebRelease([]byte("SHA256:\n a 1 Packages\n a 1 Packages.gz\n"))); flat[""] != "Packages.gz" {
t.Fatalf("flat repo should fetch Packages.gz, got %v", flat)
}
}
func TestDebIndexPath(t *testing.T) {
for _, tc := range []struct {
in, base, name string
ok bool
}{
{"Release", "", "Release", true},
{"Packages.gz", "", "Packages.gz", true},
{"dists/trixie/Release", "dists/trixie/", "Release", true},
{"dists/trixie/main/binary-amd64/Packages", "dists/trixie/", "main/binary-amd64/Packages", true},
{"by-hash/SHA256/abababababababababababababababababababababababababababababababab", "", "by-hash/SHA256/abababababababababababababababababababababababababababababababab", true},
{"dists/trixie/main/binary-amd64/by-hash/SHA256/abababababababababababababababababababababababababababababababab", "dists/trixie/", "main/binary-amd64/by-hash/SHA256/abababababababababababababababababababababababababababababababab", true},
{"dists/trixie/main/binary-amd64/by-hash/MD5Sum/abababababababababababababababab", "", "", false},
{"InRelease", "", "", false},
{"Release.gpg", "", "", false},
{"dists/trixie/InRelease", "", "", false},
{"dists/trixie/main/i18n/Translation-en", "", "", false},
{"dists/Release", "", "", false},
{"pool/foo.deb", "", "", false},
} {
base, name, ok := debIndexPath(tc.in)
if base != tc.base || name != tc.name || ok != tc.ok {
t.Errorf("%s: got (%q, %q, %v), want (%q, %q, %v)", tc.in, base, name, ok, tc.base, tc.name, tc.ok)
}
}
}
+166 -43
View File
@@ -9,6 +9,7 @@ import (
"net/http"
"net/http/httptest"
"net/url"
"path"
"slices"
"strings"
"sync"
@@ -26,32 +27,51 @@ type Engine struct {
proxyEngine *proxy.Engine
getRemote func(context.Context, string) (*models.Remote, error)
rpmMember func(context.Context, string) (*RPMMember, error)
debMember func(ctx context.Context, name, base string) (*DebMember, error)
mergeTTL time.Duration
sf singleflight.Group
mu sync.Mutex
rpm map[string]*rpmGen
sf singleflight.Group
mu sync.Mutex
gens map[string]*repoGen
}
// rpmGen holds a virtual's current merge plus the previous one, so a client
// holding the previous repomd can still fetch its content-hashed data files.
type rpmGen struct {
cur, prev *RPMRepo
at time.Time
// mergedRepo is a merged index document plus the files it references.
type mergedRepo interface {
index() []byte
files() map[string][]byte
}
func (r *RPMRepo) index() []byte { return r.Repomd }
func (r *RPMRepo) files() map[string][]byte { return r.Files }
func (r *DebRepo) index() []byte { return r.Release }
func (r *DebRepo) files() map[string][]byte { return r.Files }
// repoGen holds a virtual's current merge plus the previous one, so a client
// holding the previous index can still fetch the files it references.
type repoGen struct {
cur, prev mergedRepo
at, used time.Time
}
const rpmMergeTTL = 60 * time.Second
// maxDebSuites bounds the client-chosen suites cached per deb virtual.
const maxDebSuites = 32
func NewEngine(db *database.DB, proxyEngine *proxy.Engine) *Engine {
e := &Engine{db: db, proxyEngine: proxyEngine, getRemote: db.GetRemote, mergeTTL: rpmMergeTTL}
e.rpmMember = e.fetchRPMMember
e.debMember = e.fetchDebMember
return e
}
func (e *Engine) Fetch(ctx context.Context, virt models.Virtual, path string, proxyBaseURL string) ([]byte, string, error) {
if virt.PackageType == models.PackageRPM {
switch virt.PackageType {
case models.PackageRPM:
return e.fetchRPM(ctx, virt, path)
case models.PackageDeb:
return e.fetchDeb(ctx, virt, path)
}
merger, err := GetMerger(virt.PackageType)
@@ -170,11 +190,22 @@ var (
ErrBadPath = errors.New("invalid path")
)
// MemberRedirect maps an rpm virtual package path (<member>/<href>, as written
// by MergeRPM) to the owning member's route. ok is false for any other path;
// ErrBadPath means the path is absolute or escapes the member.
// MemberRedirect maps an rpm or deb virtual package path (<member>/<href>, as
// written by MergeRPM/MergeDeb) to the owning member's route. ok is false for
// any other path; ErrBadPath means the path is absolute or escapes the member.
func (e *Engine) MemberRedirect(ctx context.Context, virt models.Virtual, path, rawQuery, proxyBaseURL string) (string, bool, error) {
if virt.PackageType != models.PackageRPM || strings.HasPrefix(path, "repodata/") {
switch virt.PackageType {
case models.PackageRPM:
if strings.HasPrefix(path, "repodata/") {
return "", false, nil
}
case models.PackageDeb:
// apt requests a flat repo's files under its "./" dist verbatim.
path = strings.TrimPrefix(path, "./")
if strings.HasPrefix(path, "dists/") {
return "", false, nil
}
default:
return "", false, nil
}
name, rest, found := strings.Cut(path, "/")
@@ -217,76 +248,93 @@ func (e *Engine) fetchRPM(ctx context.Context, virt models.Virtual, path string)
if !strings.HasPrefix(path, "repodata/") {
return nil, "", ErrNotFound
}
key := "rpm\x00" + virt.Name
if path != "repodata/repomd.xml" {
if body, ok := e.cachedRPMFile(virt.Name, path); ok {
if body, ok := e.cachedFile(key, path); ok {
return body, "application/gzip", nil
}
}
repo, err := e.mergedRPM(ctx, virt)
repo, err := e.merged(ctx, key, func(ctx context.Context) (mergedRepo, error) {
return e.mergeRPM(ctx, virt)
})
if err != nil {
return nil, "", err
}
if path == "repodata/repomd.xml" {
return repo.Repomd, "application/xml", nil
return repo.index(), "application/xml", nil
}
if body, ok := repo.Files[path]; ok {
if body, ok := repo.files()[path]; ok {
return body, "application/gzip", nil
}
return nil, "", ErrNotFound
}
// mergedRPM returns the virtual's merge, reusing it for mergeTTL and
// collapsing concurrent merges of the same virtual into one.
// merged returns the merge cached under key, reusing it for mergeTTL and
// collapsing concurrent merges of the same key into one.
// ponytail: per-replica cache; behind a non-sticky LB a data request landing on
// another replica re-merges and 404s if a member changed in between. Move to the
// shared redis cache if that shows up.
func (e *Engine) mergedRPM(ctx context.Context, virt models.Virtual) (*RPMRepo, error) {
func (e *Engine) merged(ctx context.Context, key string, merge func(context.Context) (mergedRepo, error)) (mergedRepo, error) {
e.mu.Lock()
g := e.rpm[virt.Name]
g := e.gens[key]
if g != nil && time.Since(g.at) < e.mergeTTL {
g.used = time.Now()
e.mu.Unlock()
return g.cur, nil
}
e.mu.Unlock()
v, err, _ := e.sf.Do(virt.Name, func() (any, error) {
repo, err := e.mergeRPM(context.WithoutCancel(ctx), virt)
v, err, _ := e.sf.Do(key, func() (any, error) {
repo, err := merge(context.WithoutCancel(ctx))
if err != nil {
return nil, err
}
e.mu.Lock()
defer e.mu.Unlock()
if e.rpm == nil {
e.rpm = map[string]*rpmGen{}
if e.gens == nil {
e.gens = map[string]*repoGen{}
}
g := e.rpm[virt.Name]
g := e.gens[key]
switch {
case g == nil:
e.rpm[virt.Name] = &rpmGen{cur: repo, at: time.Now()}
case string(g.cur.Repomd) == string(repo.Repomd):
g.at = time.Now()
e.gens[key] = &repoGen{cur: repo, at: time.Now(), used: time.Now()}
case string(g.cur.index()) == string(repo.index()):
g.at, g.used = time.Now(), time.Now()
repo = g.cur
default:
g.prev, g.cur, g.at = g.cur, repo, time.Now()
g.prev, g.cur, g.at, g.used = g.cur, repo, time.Now(), time.Now()
}
return repo, nil
})
if err != nil {
return nil, err
}
return v.(*RPMRepo), nil
return v.(mergedRepo), nil
}
func (e *Engine) mergeRPM(ctx context.Context, virt models.Virtual) (*RPMRepo, error) {
members := make([]RPMMember, len(virt.Members))
members, err := fetchMembers(virt, func(name string) (*RPMMember, error) { return e.rpmMember(ctx, name) })
if err != nil {
return nil, err
}
repo, err := MergeRPM(members)
if err != nil {
return nil, fmt.Errorf("merge rpm repodata: %w", err)
}
return repo, nil
}
// fetchMembers reads every member in parallel, failing if any member fails.
func fetchMembers[T any](virt models.Virtual, fetch func(name string) (*T, error)) ([]T, error) {
members := make([]T, len(virt.Members))
errs := make([]error, len(virt.Members))
var wg sync.WaitGroup
for i, name := range virt.Members {
wg.Add(1)
go func() {
defer wg.Done()
m, err := e.rpmMember(ctx, name)
m, err := fetch(name)
if err != nil {
errs[i] = fmt.Errorf("member %q: %w", name, err)
return
@@ -299,26 +347,101 @@ func (e *Engine) mergeRPM(ctx context.Context, virt models.Virtual) (*RPMRepo, e
if err := errors.Join(errs...); err != nil {
return nil, fmt.Errorf("virtual %q: %v", virt.Name, err)
}
repo, err := MergeRPM(members)
if err != nil {
return nil, fmt.Errorf("merge rpm repodata: %w", err)
}
return repo, nil
return members, nil
}
func (e *Engine) cachedRPMFile(virt, path string) ([]byte, bool) {
func (e *Engine) fetchDeb(ctx context.Context, virt models.Virtual, reqPath string) ([]byte, string, error) {
base, name, ok := debIndexPath(strings.TrimPrefix(path.Clean("/"+reqPath), "/"))
if !ok {
return nil, "", ErrNotFound
}
key := "deb\x00" + virt.Name + "\x00" + base
if name != "Release" {
if body, ok := e.cachedFile(key, name); ok {
return body, debContentType(name), nil
}
}
repo, err := e.merged(ctx, key, func(ctx context.Context) (mergedRepo, error) {
members, err := fetchMembers(virt, func(name string) (*DebMember, error) { return e.debMember(ctx, name, base) })
if err != nil {
return nil, err
}
return MergeDeb(members), nil
})
if err != nil {
return nil, "", err
}
e.evictLRU("deb\x00"+virt.Name+"\x00", maxDebSuites)
if name == "Release" {
return repo.index(), "text/plain", nil
}
if body, ok := repo.files()[name]; ok {
return body, debContentType(name), nil
}
return nil, "", ErrNotFound
}
func debContentType(name string) string {
if strings.HasSuffix(name, ".gz") {
return "application/gzip"
}
return "text/plain"
}
// fetchDebMember reads a member's Release under base and each binary Packages
// index it lists.
func (e *Engine) fetchDebMember(ctx context.Context, name, base string) (*DebMember, error) {
remote, err := e.getRemote(ctx, name)
if err != nil {
return nil, fmt.Errorf("remote %q: %w", name, err)
}
rel, err := e.fetchMemberPath(ctx, *remote, base+"Release")
if err != nil {
return nil, err
}
m := &DebMember{RemoteName: name, Release: rel, Packages: map[string][]byte{}}
for dir, file := range debIndexFiles(parseDebRelease(rel)) {
raw, err := e.fetchMemberPath(ctx, *remote, base+file)
if err != nil {
return nil, err
}
if m.Packages[dir], err = decompress(file, raw); err != nil {
return nil, fmt.Errorf("decompress %s: %w", file, err)
}
}
return m, nil
}
// evictLRU drops the least recently used merges under prefix beyond keep.
func (e *Engine) evictLRU(prefix string, keep int) {
e.mu.Lock()
defer e.mu.Unlock()
g := e.rpm[virt]
var keys []string
for k := range e.gens {
if strings.HasPrefix(k, prefix) {
keys = append(keys, k)
}
}
slices.SortFunc(keys, func(a, b string) int { return e.gens[b].used.Compare(e.gens[a].used) })
for _, k := range keys[min(len(keys), keep):] {
delete(e.gens, k)
}
}
func (e *Engine) cachedFile(key, path string) ([]byte, bool) {
e.mu.Lock()
defer e.mu.Unlock()
g := e.gens[key]
if g == nil {
return nil, false
}
for _, r := range []*RPMRepo{g.cur, g.prev} {
for _, r := range []mergedRepo{g.cur, g.prev} {
if r == nil {
continue
}
if body, ok := r.Files[path]; ok {
if body, ok := r.files()[path]; ok {
g.used = time.Now()
return body, true
}
}
+211
View File
@@ -5,6 +5,7 @@ import (
"errors"
"fmt"
"regexp"
"strings"
"sync"
"sync/atomic"
"testing"
@@ -156,3 +157,213 @@ func TestMemberRedirect(t *testing.T) {
}
}
}
func debEngine(members map[string]*DebMember) *Engine {
e := fakeEngine(nil)
e.debMember = func(_ context.Context, name, base string) (*DebMember, error) {
if m := members[name]; m != nil && base == "" {
return m, nil
}
return nil, errors.New("upstream down")
}
return e
}
func debVirt(members ...string) models.Virtual {
return models.Virtual{Name: "v", PackageType: models.PackageDeb, Members: members}
}
func TestFetchDebFailsClosed(t *testing.T) {
a := flatDebMember("a", "", debStanza("foo", "1", "amd64", "pool/foo.deb"))
e := debEngine(map[string]*DebMember{"a": &a})
for _, p := range []string{"Release", "./Packages.gz", "dists/trixie/Release"} {
if _, _, err := e.Fetch(context.Background(), debVirt("a", "b"), p, ""); err == nil || errors.Is(err, ErrNotFound) {
t.Errorf("%s: want upstream error with a member down, got %v", p, err)
}
}
for _, p := range []string{"InRelease", "./Release.gpg", "Packages.xz"} {
if _, _, err := e.Fetch(context.Background(), debVirt("a"), p, ""); !errors.Is(err, ErrNotFound) {
t.Errorf("%s: want not found, got %v", p, err)
}
}
}
func TestFetchDebRemergesAfterTTL(t *testing.T) {
a := flatDebMember("a", "", debStanza("foo", "1", "amd64", "pool/foo_1.deb"))
e := debEngine(map[string]*DebMember{"a": &a})
virt := debVirt("a")
rel, _, err := e.Fetch(context.Background(), virt, "./Release", "")
if err != nil {
t.Fatal(err)
}
a.Packages[""] = []byte(debStanza("foo", "2", "amd64", "pool/foo_2.deb"))
e.mergeTTL = 0
newRel, _, err := e.Fetch(context.Background(), virt, "Release", "")
if err != nil || string(newRel) == string(rel) {
t.Fatalf("Release should reflect the member change (err %v)", err)
}
pk, ct, err := e.Fetch(context.Background(), virt, "./Packages", "")
if err != nil || ct != "text/plain" || !strings.Contains(string(pk), "Version: 2") {
t.Fatalf("Packages should be the current merge (ct %q, err %v):\n%s", ct, err, pk)
}
}
func TestFetchDebMergeIsSharedPerSuite(t *testing.T) {
var calls atomic.Int32
e := fakeEngine(nil)
e.mergeTTL = time.Minute
e.debMember = func(_ context.Context, name, base string) (*DebMember, error) {
calls.Add(1)
m := flatDebMember(name, "", debStanza("foo", "1", "amd64", "pool/foo.deb"))
return &m, nil
}
for _, p := range []string{"Release", "Packages", "Packages.gz", "./Release", "dists/a/Release", "dists/b/Release"} {
if _, _, err := e.Fetch(context.Background(), debVirt("a"), p, ""); err != nil && !errors.Is(err, ErrNotFound) {
t.Fatal(err)
}
}
if n := calls.Load(); n != 3 {
t.Fatalf("member fetched %d times, want once per Release dir (3)", n)
}
}
func TestMemberRedirectDeb(t *testing.T) {
e := fakeEngine(nil)
virt := debVirt("gh", "loc")
for _, tc := range []struct {
path, want string
ok bool
err error
}{
{path: "gh/o/r/releases/download/v1/foo_1.0_amd64.deb", ok: true, want: "http://h/api/v1/remote/gh/o/r/releases/download/v1/foo_1.0_amd64.deb"},
{path: "./gh/pool/a+b.deb", ok: true, want: "http://h/api/v1/remote/gh/pool/a+b.deb"},
{path: "gh/../loc/x.deb", err: ErrBadPath},
{path: "dists/trixie/Release"},
{path: "Packages"},
} {
got, ok, err := e.MemberRedirect(context.Background(), virt, tc.path, "", "http://h/")
if got != tc.want || ok != tc.ok || !errors.Is(err, tc.err) {
t.Errorf("%s: got (%q, %v, %v), want (%q, %v, %v)", tc.path, got, ok, err, tc.want, tc.ok, tc.err)
}
}
}
type fakeRepo struct {
idx string
fs map[string][]byte
}
func (r *fakeRepo) index() []byte { return []byte(r.idx) }
func (r *fakeRepo) files() map[string][]byte { return r.fs }
func genRepo(gen string) func(context.Context) (mergedRepo, error) {
return func(context.Context) (mergedRepo, error) {
return &fakeRepo{idx: gen, fs: map[string][]byte{gen + ".gz": []byte(gen), "fixed": []byte(gen)}}, nil
}
}
func TestMergedRetainsPreviousGeneration(t *testing.T) {
e := fakeEngine(nil)
for _, gen := range []string{"g1", "g2", "g3"} {
if _, err := e.merged(context.Background(), "k", genRepo(gen)); err != nil {
t.Fatal(err)
}
}
for path, want := range map[string]string{"g3.gz": "g3", "g2.gz": "g2", "fixed": "g3"} {
if body, ok := e.cachedFile("k", path); !ok || string(body) != want {
t.Errorf("%s: got (%q, %v), want %q", path, body, ok, want)
}
}
if _, ok := e.cachedFile("k", "g1.gz"); ok {
t.Error("generation two merges back must be dropped")
}
}
func TestMergedReusesWithinTTLAndIsolatesKeys(t *testing.T) {
e := fakeEngine(nil)
e.mergeTTL = time.Minute
for _, step := range []struct{ key, gen, want string }{
{"a", "a1", "a1"}, {"b", "b1", "b1"}, {"a", "a2", "a1"},
} {
repo, err := e.merged(context.Background(), step.key, genRepo(step.gen))
if err != nil || string(repo.index()) != step.want {
t.Fatalf("%s: got %v (err %v), want %s", step.key, repo, err, step.want)
}
}
if _, ok := e.cachedFile("b", "a1.gz"); ok {
t.Error("key b served key a's file")
}
if _, ok := e.cachedFile("c", "a1.gz"); ok {
t.Error("unknown key served a file")
}
}
func suiteDebMember(name, version string) *DebMember {
return &DebMember{RemoteName: name, Release: []byte("Suite: s\nSHA256:\n x 1 main/binary-amd64/Packages.gz\n"),
Packages: map[string][]byte{"main/binary-amd64/": []byte(debStanza("foo", version, "amd64", "pool/foo_"+version+".deb"))}}
}
func TestFetchDebByHashSurvivesRemerge(t *testing.T) {
version := "1"
e := fakeEngine(nil)
e.debMember = func(_ context.Context, name, _ string) (*DebMember, error) { return suiteDebMember(name, version), nil }
virt := debVirt("a")
fetch := func(p string) []byte {
body, _, err := e.Fetch(context.Background(), virt, p, "")
if err != nil {
t.Fatalf("%s: %v", p, err)
}
return body
}
byHash := func(rel []byte) string {
m := regexp.MustCompile(`(?m)^SHA256:\n(?: .*\n)*? ([0-9a-f]{64}) \d+ main/binary-amd64/Packages.gz$`).FindSubmatch(rel)
if m == nil {
t.Fatalf("no Packages.gz SHA256 in Release:\n%s", rel)
}
return "dists/trixie/main/binary-amd64/by-hash/SHA256/" + string(m[1])
}
oldRel := fetch("dists/trixie/Release")
version, e.mergeTTL = "2", 0
if newRel := fetch("dists/trixie/Release"); string(newRel) == string(oldRel) {
t.Fatal("Release should reflect the member change")
}
if got := string(gunzip(t, fetch(byHash(oldRel)))); !strings.Contains(got, "Version: 1\n") {
t.Fatalf("by-hash from the previous Release served the wrong index:\n%s", got)
}
if got := string(fetch("dists/trixie/main/binary-amd64/Packages")); !strings.Contains(got, "Version: 2\n") {
t.Fatalf("fixed-name Packages should be the current merge:\n%s", got)
}
}
func TestFetchDebBoundsSuitesPerVirtual(t *testing.T) {
e := fakeEngine(nil)
e.mergeTTL = time.Minute
e.debMember = func(_ context.Context, name, _ string) (*DebMember, error) { return suiteDebMember(name, "1"), nil }
other := models.Virtual{Name: "other", PackageType: models.PackageDeb, Members: []string{"a"}}
if _, _, err := e.Fetch(context.Background(), other, "dists/keep/Release", ""); err != nil {
t.Fatal(err)
}
for i := range maxDebSuites + 5 {
if _, _, err := e.Fetch(context.Background(), debVirt("a"), fmt.Sprintf("dists/s%d/Release", i), ""); err != nil {
t.Fatal(err)
}
time.Sleep(time.Microsecond)
}
n := 0
for k := range e.gens {
if strings.HasPrefix(k, "deb\x00v\x00") {
n++
}
}
if n != maxDebSuites {
t.Fatalf("virtual v caches %d suites, want %d", n, maxDebSuites)
}
if e.gens["deb\x00v\x00dists/s0/"] != nil || e.gens["deb\x00v\x00dists/s4/"] != nil {
t.Fatal("least recently used suites should be evicted first")
}
if e.gens["deb\x00other\x00dists/keep/"] == nil {
t.Fatal("another virtual's suites must not be evicted")
}
}
-15
View File
@@ -1,15 +0,0 @@
CREATE TABLE IF NOT EXISTS puppet_metadata (
id BIGSERIAL PRIMARY KEY,
repo_name TEXT NOT NULL,
file_path TEXT NOT NULL,
content_hash TEXT NOT NULL,
slug TEXT NOT NULL,
version TEXT NOT NULL,
metadata_json TEXT NOT NULL,
file_size BIGINT NOT NULL DEFAULT 0,
file_md5 TEXT NOT NULL,
created_at TIMESTAMPTZ DEFAULT NOW(),
UNIQUE(repo_name, file_path)
);
CREATE INDEX IF NOT EXISTS idx_puppet_metadata_repo_slug ON puppet_metadata(repo_name, slug);
+10 -43
View File
@@ -218,38 +218,15 @@ sudo apk add --allow-untrusted <package>`,
];
case 'goproxy':
return isLocal
? [
{
title: 'Fetch private modules from this proxy',
language: 'bash',
code: `export GOPROXY=${url}/api/v1/local/${name},https://proxy.golang.org,direct
export GONOSUMDB=example.unkin.net
go get example.unkin.net/hello@latest`,
note: 'Set GONOSUMDB (or GOPRIVATE) to your module prefix: private modules are not in sum.golang.org.',
},
{
title: 'Publish a module version',
language: 'bash',
code: `# build the zip with golang.org/x/mod/zip (CreateFromDir), or reuse
# the .zip/.mod/.info from $(go env GOMODCACHE)/cache/download after go mod download
MOD=example.unkin.net/hello VER=v0.1.0
for ext in zip mod info; do
curl -fsSL --upload-file $VER.$ext \\
${url}/api/v2/remotes/${name}/files/$MOD/@v/$VER.$ext
done`,
note: 'Paths use the case-encoded module path (uppercase as !lower). Zips must hold every file under module@version/ and are rejected otherwise; .info is optional.',
},
]
: [
{
title: 'Point the Go module proxy here',
language: 'bash',
code: `export GOPROXY=${proxy}
return [
{
title: 'Point the Go module proxy here',
language: 'bash',
code: `export GOPROXY=${proxy}
go mod download`,
note: 'Append ,direct to fall back to VCS for modules this proxy does not cover.',
},
];
note: 'Append ,direct to fall back to VCS for modules this proxy does not cover.',
},
];
case 'cargo':
return [
@@ -285,21 +262,11 @@ index = "sparse+${proxy}/"`,
case 'puppet':
return [
{
title: isLocal ? 'Install a module from this forge' : 'Install a module from the Forge proxy',
title: 'Install a module from the Forge proxy',
language: 'bash',
code: `puppet module install <author>-<module> \\
--module_repository ${isLocal ? `${url}/api/v1/local/${name}` : proxy}`,
--module_repository ${proxy}`,
},
...(isLocal
? [
{
title: 'Publish a module (versions are immutable)',
language: 'bash',
code: `puppet module build && curl -fsSL --upload-file pkg/<author>-<module>-<version>.tar.gz \\
${url}/api/v2/remotes/${name}/files/<author>-<module>-<version>.tar.gz`,
},
]
: []),
];
case 'deb':