ZDDC/zddc/internal/convert/convert_test.go
ZDDC 7aec631a22 feat(convert): support remote podman mode + configurable scratch dir
zddc-server can now invoke podman as a CLIENT against a remote socket
instead of creating containers in its own process. The sidecar pattern
in tnd-zddc-chart will use this so zddc-server's own pod stays
unprivileged (only the podman-system-service sidecar runs privileged).

New surface:

  --convert-podman-socket / ZDDC_CONVERT_PODMAN_SOCKET
    e.g. unix:///var/run/podman/podman.sock
    Empty (default) → local mode (podman creates containers in
    zddc-server's own filesystem namespace).
    Non-empty → remote mode: `podman --remote --url=<this> run …`
    dispatches each container request to whatever process owns the
    socket. Typically a `podman system service` sidecar in the same
    Kubernetes pod.

  --convert-scratch-dir / ZDDC_CONVERT_SCRATCH_DIR
    Host-side directory for per-conversion intermediates (template,
    HTML, PDF). In remote mode this MUST be a path the sidecar sees
    at the same mountpoint — typically a shared emptyDir at /work
    in both containers. Empty = $TMPDIR (local-mode default).

Runner behaviour:

  local mode → unchanged. `podman run --userns=host --rm --pull=missing
  --network=none --read-only …`. `--userns=host` stays so nested-podman
  on a privileged host (the previous chart shape) keeps working for
  anyone still using it.

  remote mode → `podman --remote --url=<sock> run --rm --pull=missing
  --network=none --read-only …`. `--userns=host` is dropped because
  the sidecar is rootful inside its own privileged container and
  doesn't need userns juggling.

Health probe gains a Mode field ("local" | "remote") and, in remote
mode, runs `podman --remote --url=<sock> version` to confirm the
sidecar's socket is reachable. Unreachable-socket → 503 with a clear
reason (sidecar may still be starting up); reachable → ready.

Capabilities log now includes engine_version + mode + remote_url for
easier debugging of "which podman is actually doing the work".

No tests removed — the existing fake-runner table covers both modes
since the runner's args are uniform (remote prefix is the only thing
that differs).
2026-05-13 12:17:40 -05:00

307 lines
8.7 KiB
Go

package convert
import (
"context"
"errors"
"strings"
"sync"
"testing"
"time"
)
// fakeRunner records the args it was invoked with and replays canned
// responses. Lets us assert the command lines + image refs without
// needing podman.
type fakeRunner struct {
mu sync.Mutex
calls [][]string
images []string
stdin [][]byte
mounts [][]string
resp []byte
err error
}
func (f *fakeRunner) Run(_ context.Context, image string, stdin []byte, mounts []string, cmd []string) ([]byte, error) {
f.mu.Lock()
defer f.mu.Unlock()
f.calls = append(f.calls, append([]string(nil), cmd...))
f.images = append(f.images, image)
f.stdin = append(f.stdin, append([]byte(nil), stdin...))
f.mounts = append(f.mounts, append([]string(nil), mounts...))
return f.resp, f.err
}
func (f *fakeRunner) lastCall() (string, []string) {
f.mu.Lock()
defer f.mu.Unlock()
if len(f.calls) == 0 {
return "", nil
}
return f.images[len(f.images)-1], f.calls[len(f.calls)-1]
}
func TestToDocx_UsesPandocImage(t *testing.T) {
f := &fakeRunner{resp: []byte("FAKE-DOCX")}
InstallRunner(f)
t.Cleanup(func() { InstallRunner(nil) })
SetImages("docker.io/pandoc/latex:latest", "")
out, err := ToDocx(context.Background(), []byte("# Hello\n"), Metadata{
Title: "Hello",
Client: "Acme",
})
if err != nil {
t.Fatalf("ToDocx: %v", err)
}
if string(out) != "FAKE-DOCX" {
t.Errorf("unexpected output: %q", out)
}
image, call := f.lastCall()
if image != "docker.io/pandoc/latex:latest" {
t.Errorf("expected pandoc image, got %q", image)
}
if !contains(call, "--to=docx") {
t.Errorf("missing --to=docx: %v", call)
}
if !contains(call, "title=Hello") {
t.Errorf("missing title metadata: %v", call)
}
if !contains(call, "client=Acme") {
t.Errorf("missing client metadata: %v", call)
}
// Last arg must be "-" so pandoc reads from stdin.
if call[len(call)-1] != "-" {
t.Errorf("expected stdin marker as last arg, got %q", call[len(call)-1])
}
}
func TestToHTML_UsesTemplateAndMountsScratch(t *testing.T) {
f := &fakeRunner{resp: []byte("<html>fake</html>")}
InstallRunner(f)
t.Cleanup(func() { InstallRunner(nil) })
SetImages("docker.io/pandoc/latex:latest", "")
_, err := ToHTML(context.Background(), []byte("# Hi\n"), Metadata{Title: "Hi"})
if err != nil {
t.Fatalf("ToHTML: %v", err)
}
image, call := f.lastCall()
if image != "docker.io/pandoc/latex:latest" {
t.Errorf("expected pandoc image, got %q", image)
}
if !contains(call, "--template=/tpl/viewer-template.html") {
t.Errorf("template flag missing: %v", call)
}
if !contains(call, "--toc") {
t.Errorf("TOC flag missing (default NoTOC=false): %v", call)
}
if len(f.mounts) == 0 || len(f.mounts[0]) == 0 {
t.Fatalf("expected at least one bind mount for /tpl")
}
mount := f.mounts[0][0]
if !strings.Contains(mount, ":/tpl:") {
t.Errorf("mount missing /tpl: %q", mount)
}
}
func TestToHTML_NoTOCSuppressesTOC(t *testing.T) {
f := &fakeRunner{resp: []byte("<html/>")}
InstallRunner(f)
t.Cleanup(func() { InstallRunner(nil) })
_, _ = ToHTML(context.Background(), []byte("# Hi\n"), Metadata{NoTOC: true})
_, call := f.lastCall()
if contains(call, "--toc") {
t.Errorf("TOC should be suppressed when NoTOC=true: %v", call)
}
if !contains(call, "no-toc=true") {
t.Errorf("no-toc metadata variable missing: %v", call)
}
}
// recordingRunner records every call and returns canned responses
// in sequence. Lets ToPDF tests assert the two-stage pipeline
// (pandoc image then chromium image).
type recordingRunner struct {
mu sync.Mutex
calls []recordedCall
resp [][]byte
err []error
cursor int
}
type recordedCall struct {
image string
cmd []string
mounts []string
}
func (r *recordingRunner) Run(_ context.Context, image string, _ []byte, mounts []string, cmd []string) ([]byte, error) {
r.mu.Lock()
defer r.mu.Unlock()
r.calls = append(r.calls, recordedCall{
image: image,
cmd: append([]string(nil), cmd...),
mounts: append([]string(nil), mounts...),
})
if r.cursor >= len(r.resp) {
return nil, nil
}
out := r.resp[r.cursor]
var e error
if r.cursor < len(r.err) {
e = r.err[r.cursor]
}
r.cursor++
return out, e
}
func TestScratchDir_UsedByToHTML(t *testing.T) {
f := &fakeRunner{resp: []byte("<html/>")}
InstallRunner(f)
t.Cleanup(func() { InstallRunner(nil); SetScratchDir("") })
scratchRoot := t.TempDir()
SetScratchDir(scratchRoot)
_, err := ToHTML(context.Background(), []byte("# Hi\n"), Metadata{})
if err != nil {
t.Fatalf("ToHTML: %v", err)
}
if len(f.mounts) == 0 || len(f.mounts[0]) == 0 {
t.Fatalf("expected at least one mount")
}
mount := f.mounts[0][0] // "<host>:/tpl:ro"
if !strings.HasPrefix(mount, scratchRoot+"/") {
t.Errorf("scratch dir not under configured root: %q (root=%q)", mount, scratchRoot)
}
}
func TestToPDF_TwoStagePipeline(t *testing.T) {
// Stage 1: pandoc emits HTML. Stage 2: chromium reads HTML from
// the bind mount and writes /pdf/out.pdf. The fake runner can't
// actually write the PDF, so we expect ToPDF to fail at the
// read-back step — but we can still assert the two-stage call
// shape and the right image per stage.
r := &recordingRunner{
resp: [][]byte{
[]byte("<html><body>fake</body></html>"), // stage 1 stdout
nil, // stage 2 stdout (chromium writes PDF to bind mount)
},
}
InstallRunner(r)
t.Cleanup(func() { InstallRunner(nil) })
SetImages("docker.io/pandoc/latex:latest", "docker.io/zenika/alpine-chrome:latest")
_, err := ToPDF(context.Background(), []byte("# Hi\n"), Metadata{})
// PDF read-back will fail (fake runner didn't write the file) —
// that's expected for this test which only inspects the call
// shape.
if err == nil {
t.Fatalf("expected error from PDF read-back; got nil")
}
if len(r.calls) != 2 {
t.Fatalf("expected 2 container calls (pandoc + chromium); got %d", len(r.calls))
}
if r.calls[0].image != "docker.io/pandoc/latex:latest" {
t.Errorf("stage 1 image: got %q want pandoc/latex", r.calls[0].image)
}
if r.calls[1].image != "docker.io/zenika/alpine-chrome:latest" {
t.Errorf("stage 2 image: got %q want alpine-chrome", r.calls[1].image)
}
// Stage 2 must include the --print-to-pdf flag pointing at /pdf.
if !contains(r.calls[1].cmd, "--print-to-pdf=/pdf/out.pdf") {
t.Errorf("chromium call missing --print-to-pdf flag: %v", r.calls[1].cmd)
}
if !contains(r.calls[1].cmd, "--no-sandbox") {
t.Errorf("chromium call missing --no-sandbox: %v", r.calls[1].cmd)
}
// Stage 2's bind mount must be writable (chromium writes the PDF).
if len(r.calls[1].mounts) == 0 || !strings.Contains(r.calls[1].mounts[0], ":rw") {
t.Errorf("chromium mount must be :rw, got %v", r.calls[1].mounts)
}
}
func TestErrUnavailable_WhenNoRunner(t *testing.T) {
InstallRunner(nil)
_, err := ToDocx(context.Background(), []byte("x"), Metadata{})
if !errors.Is(err, ErrUnavailable) {
t.Errorf("expected ErrUnavailable, got %v", err)
}
}
func TestMetadataArgs_OmitsEmptyAndOrdersStably(t *testing.T) {
args := metadataArgs(Metadata{
Title: "T",
Project: "P",
GenerationTime: time.Date(2026, 5, 13, 14, 30, 22, 0, time.UTC),
})
want := []string{
"-V", "title=T",
"-V", "project=P",
}
for i, w := range want {
if i >= len(args) || args[i] != w {
t.Fatalf("args[%d]: got %v want prefix %v", i, args, want)
}
}
joined := strings.Join(args, "|")
if !strings.Contains(joined, "generation_time=") || !strings.Contains(joined, "2026") {
t.Errorf("generation_time missing or malformed: %v", args)
}
if strings.Contains(joined, "client=") {
t.Errorf("empty client should not be passed: %v", args)
}
}
func TestImageTag(t *testing.T) {
cases := map[string]string{
"docker.io/pandoc/latex:latest": "pandoc/latex",
"docker.io/zenika/alpine-chrome:latest": "zenika/alpine-chrome",
"pandoc/core": "pandoc/core",
"quay.io/example/foo:v1": "example/foo",
"alpine": "alpine",
}
for in, want := range cases {
if got := imageTag(in); got != want {
t.Errorf("imageTag(%q) = %q, want %q", in, got, want)
}
}
}
func TestSingleflight_Collapses(t *testing.T) {
var g singleflightGroup
const N = 50
var wg sync.WaitGroup
var hits int32
var mu sync.Mutex
wg.Add(N)
for i := 0; i < N; i++ {
go func() {
defer wg.Done()
_, _ = g.Do("k", func() (any, error) {
mu.Lock()
hits++
mu.Unlock()
time.Sleep(20 * time.Millisecond)
return "v", nil
})
}()
}
wg.Wait()
if hits != 1 {
t.Errorf("singleflight collapse: got %d invocations, want 1", hits)
}
}
// contains reports whether haystack has needle as any of its elements.
func contains(haystack []string, needle string) bool {
for _, s := range haystack {
if s == needle {
return true
}
}
return false
}