P3 follow-up: log download (txt + ndjson) on the live job page

The diff job's full output streams to the standard live job log page,
which can be a lot of text the operator wants to grep through or paste
into a ticket. Add a Download button.

Source of truth is the persisted job_logs table — works any time
(running or finished) and doesn't need to pause the live WS stream.
The download is 'everything the server has up to right now'; if the
operator wants a fuller snapshot of a still-running job, they hit
Download again.

- New endpoint GET /api/jobs/{id}/log.{txt,ndjson} (chi {format}
  matcher constrained to the two known suffixes). Auth via session
  cookie. 404 on unknown job.
- internal/server/http/job_download.go writeLogsText emits a small
  header + 'HH:MM:SS.mmm  TAG  payload' rows mirroring what the live
  page shows. writeLogsNDJSON emits one self-contained {seq,ts,stream,
  payload} JSON object per line — appending stays valid (each line
  stands alone), and the whole file pipes cleanly into jq. NDJSON is
  newline-delimited JSON; not the same as a JSON array.
- web/templates/pages/job_detail.html grows two header buttons:
  'Download log' (txt) + '.ndjson' ghost variant for tooling.

Tests cover the txt format (header + per-row shape), the ndjson
format (each line round-trips through json.Unmarshal), unknown job
404, unauthenticated 401.
This commit is contained in:
2026-05-04 17:12:45 +01:00
parent 65a0134101
commit 727c610765
4 changed files with 326 additions and 0 deletions
+135
View File
@@ -0,0 +1,135 @@
package http
import (
"bufio"
"encoding/json"
"fmt"
stdhttp "net/http"
"strings"
"github.com/go-chi/chi/v5"
"gitea.dcglab.co.uk/steve/restic-manager/internal/store"
)
// handleJobLogDownload is GET /api/jobs/{id}/log{.txt,.ndjson}.
//
// Source of truth is the persisted job_logs table — works any time,
// regardless of whether the job is running or already finished. The
// download is "everything the server has up to right now"; the live
// stream is unaffected (no pause needed). If the operator wants a
// fuller snapshot of a still-running job, they hit Download again.
//
// Format is picked from the URL suffix (.txt | .ndjson) for a
// sensible filename in the browser, or the ?format= query param for
// REST callers. Default is txt.
func (s *Server) handleJobLogDownload(w stdhttp.ResponseWriter, r *stdhttp.Request) {
if _, ok := s.requireUser(r); !ok {
writeJSONError(w, stdhttp.StatusUnauthorized, "unauthorized", "")
return
}
jobID := chi.URLParam(r, "id")
if jobID == "" {
writeJSONError(w, stdhttp.StatusBadRequest, "missing_job_id", "")
return
}
job, err := s.deps.Store.GetJob(r.Context(), jobID)
if err != nil {
writeJSONError(w, stdhttp.StatusNotFound, "job_not_found", "")
return
}
format := r.URL.Query().Get("format")
if format == "" {
// Sniff the URL — chi routes both /log.txt and /log.ndjson here
// (or .log if a future route adds it) via the {format} matcher.
fmtParam := chi.URLParam(r, "format")
switch fmtParam {
case "ndjson":
format = "ndjson"
default:
format = "txt"
}
}
logs, err := s.deps.Store.ListJobLogs(r.Context(), jobID, 0, 0)
if err != nil {
writeJSONError(w, stdhttp.StatusInternalServerError, "internal", err.Error())
return
}
short := jobID
if len(short) > 8 {
short = short[:8]
}
filename := "job-" + job.Kind + "-" + short
switch format {
case "ndjson":
w.Header().Set("Content-Type", "application/x-ndjson; charset=utf-8")
w.Header().Set("Content-Disposition",
`attachment; filename="`+filename+`.ndjson"`)
writeLogsNDJSON(w, logs)
default:
w.Header().Set("Content-Type", "text/plain; charset=utf-8")
w.Header().Set("Content-Disposition",
`attachment; filename="`+filename+`.txt"`)
writeLogsText(w, job, logs)
}
}
// writeLogsText renders the logs in the same shape the live page shows:
// "HH:MM:SS.mmm TAG payload". Adds a small header so the file is
// useful as a standalone artifact (operator pastes it into a ticket).
func writeLogsText(w stdhttp.ResponseWriter, job *store.Job, logs []store.JobLogLine) {
bw := bufio.NewWriter(w)
defer func() { _ = bw.Flush() }()
_, _ = fmt.Fprintf(bw, "# job %s · kind %s · status %s\n",
job.ID, job.Kind, job.Status)
if job.StartedAt != nil {
_, _ = fmt.Fprintf(bw, "# started %s\n", job.StartedAt.UTC().Format("2006-01-02T15:04:05.000Z"))
}
if job.FinishedAt != nil {
_, _ = fmt.Fprintf(bw, "# finished %s\n", job.FinishedAt.UTC().Format("2006-01-02T15:04:05.000Z"))
}
_, _ = fmt.Fprintf(bw, "# %d log lines\n\n", len(logs))
for _, l := range logs {
tag := streamTag(l.Stream)
ts := l.TS.UTC().Format("15:04:05.000")
// Strip embedded newlines from payload — log lines should be
// single-line, but defensive: a stray '\n' in stderr would
// break grep -n.
payload := strings.ReplaceAll(l.Payload, "\n", " ")
_, _ = fmt.Fprintf(bw, "%s %s %s\n", ts, tag, payload)
}
}
// writeLogsNDJSON emits one JSON object per line. Each object stands
// alone — appending to the file remains valid NDJSON.
func writeLogsNDJSON(w stdhttp.ResponseWriter, logs []store.JobLogLine) {
enc := json.NewEncoder(w)
for _, l := range logs {
_ = enc.Encode(struct {
Seq int64 `json:"seq"`
TS string `json:"ts"`
Stream string `json:"stream"`
Payload string `json:"payload"`
}{
Seq: l.Seq,
TS: l.TS.UTC().Format("2006-01-02T15:04:05.000Z"),
Stream: l.Stream,
Payload: l.Payload,
})
}
}
func streamTag(s string) string {
switch s {
case "stdout":
return "OUT"
case "stderr":
return "ERR"
case "event":
return "EVENT"
}
return strings.ToUpper(s)
}
+181
View File
@@ -0,0 +1,181 @@
// job_download_test.go — covers GET /api/jobs/{id}/log.{txt,ndjson}.
package http
import (
"context"
"encoding/json"
stdhttp "net/http"
"strings"
"testing"
"time"
"github.com/oklog/ulid/v2"
"gitea.dcglab.co.uk/steve/restic-manager/internal/store"
)
// seedJobWithLogs creates a job + a few log lines for it. Returns the
// job ID. Caller is responsible for the test server + auth.
func seedJobWithLogs(t *testing.T, st *store.Store, hostID string, lineCount int) string {
t.Helper()
jobID := ulid.Make().String()
now := time.Now().UTC()
if err := st.CreateJob(context.Background(), store.Job{
ID: jobID, HostID: hostID, Kind: "diff",
ActorKind: "user", CreatedAt: now,
}); err != nil {
t.Fatalf("create job: %v", err)
}
if err := st.MarkJobStarted(context.Background(), jobID, now); err != nil {
t.Fatalf("mark started: %v", err)
}
for i := 0; i < lineCount; i++ {
stream := "stdout"
if i%5 == 0 {
stream = "stderr"
}
payload := `{"message_type":"change","path":"/etc/file` +
ulid.Make().String()[:6] + `","modifier":"M"}`
if err := st.AppendJobLog(context.Background(), jobID, int64(i+1),
now.Add(time.Duration(i)*time.Millisecond),
stream, payload); err != nil {
t.Fatalf("append log: %v", err)
}
}
if err := st.MarkJobFinished(context.Background(), jobID, "succeeded", 0, nil, "", now); err != nil {
t.Fatalf("mark finished: %v", err)
}
return jobID
}
// TestJobLogDownloadTxt: plain-text format includes a header + one
// line per log row in the expected shape.
func TestJobLogDownloadTxt(t *testing.T) {
t.Parallel()
srv, ts, st := rawTestServer(t)
hostID, _ := enrolHostForWS(t, srv, st, "dl-txt-host")
jobID := seedJobWithLogs(t, st, hostID, 12)
cookie := loginAsAdmin(t, st)
req, _ := stdhttp.NewRequest("GET",
ts.URL+"/api/jobs/"+jobID+"/log.txt", nil)
req.AddCookie(cookie)
res, err := stdhttp.DefaultClient.Do(req)
if err != nil {
t.Fatalf("do: %v", err)
}
defer res.Body.Close()
if res.StatusCode != stdhttp.StatusOK {
t.Fatalf("status: got %d, want 200", res.StatusCode)
}
if ct := res.Header.Get("Content-Type"); !strings.HasPrefix(ct, "text/plain") {
t.Errorf("content-type: got %q", ct)
}
if cd := res.Header.Get("Content-Disposition"); !strings.Contains(cd, ".txt") {
t.Errorf("content-disposition: got %q", cd)
}
body := readBody(t, res.Body)
// Header lines.
if !strings.HasPrefix(body, "# job ") {
t.Errorf("expected '# job ...' header line; got %q", short(body))
}
if !strings.Contains(body, "12 log lines") {
t.Errorf("expected '12 log lines'; got %q", short(body))
}
// One body line per log row — count non-comment, non-empty lines.
var rows int
for _, line := range strings.Split(body, "\n") {
l := strings.TrimSpace(line)
if l == "" || strings.HasPrefix(l, "#") {
continue
}
rows++
}
if rows != 12 {
t.Errorf("expected 12 body rows, got %d", rows)
}
// Tag check: at least one ERR row (every 5th was stderr).
if !strings.Contains(body, " ERR ") {
t.Errorf("expected at least one ERR row")
}
}
// TestJobLogDownloadNDJSON: each line is a self-contained JSON object.
func TestJobLogDownloadNDJSON(t *testing.T) {
t.Parallel()
srv, ts, st := rawTestServer(t)
hostID, _ := enrolHostForWS(t, srv, st, "dl-ndjson-host")
jobID := seedJobWithLogs(t, st, hostID, 5)
cookie := loginAsAdmin(t, st)
req, _ := stdhttp.NewRequest("GET",
ts.URL+"/api/jobs/"+jobID+"/log.ndjson", nil)
req.AddCookie(cookie)
res, err := stdhttp.DefaultClient.Do(req)
if err != nil {
t.Fatalf("do: %v", err)
}
defer res.Body.Close()
if res.StatusCode != stdhttp.StatusOK {
t.Fatalf("status: got %d, want 200", res.StatusCode)
}
if ct := res.Header.Get("Content-Type"); !strings.HasPrefix(ct, "application/x-ndjson") {
t.Errorf("content-type: got %q", ct)
}
body := readBody(t, res.Body)
// Each non-empty line should parse as an object with seq/ts/stream/payload.
var seen int
for _, line := range strings.Split(body, "\n") {
if strings.TrimSpace(line) == "" {
continue
}
var obj struct {
Seq int64 `json:"seq"`
TS string `json:"ts"`
Stream string `json:"stream"`
Payload string `json:"payload"`
}
if err := json.Unmarshal([]byte(line), &obj); err != nil {
t.Fatalf("parse line %q: %v", line, err)
}
if obj.Seq == 0 || obj.TS == "" || obj.Stream == "" || obj.Payload == "" {
t.Errorf("incomplete object: %+v", obj)
}
seen++
}
if seen != 5 {
t.Errorf("parsed %d objects, want 5", seen)
}
}
// TestJobLogDownloadNotFound: 404 for an unknown job id.
func TestJobLogDownloadNotFound(t *testing.T) {
t.Parallel()
_, ts, st := rawTestServer(t)
cookie := loginAsAdmin(t, st)
req, _ := stdhttp.NewRequest("GET",
ts.URL+"/api/jobs/"+ulid.Make().String()+"/log.txt", nil)
req.AddCookie(cookie)
res, err := stdhttp.DefaultClient.Do(req)
if err != nil {
t.Fatalf("do: %v", err)
}
defer res.Body.Close()
if res.StatusCode != stdhttp.StatusNotFound {
t.Fatalf("status: got %d, want 404", res.StatusCode)
}
}
// TestJobLogDownloadUnauthenticated: without a session cookie, 401.
func TestJobLogDownloadUnauthenticated(t *testing.T) {
t.Parallel()
_, ts, _ := rawTestServer(t)
res, err := stdhttp.Get(ts.URL + "/api/jobs/x/log.txt")
if err != nil {
t.Fatalf("do: %v", err)
}
defer res.Body.Close()
if res.StatusCode != stdhttp.StatusUnauthorized {
t.Fatalf("status: got %d, want 401", res.StatusCode)
}
}
+5
View File
@@ -304,6 +304,11 @@ func (s *Server) routes(r chi.Router) {
if s.deps.JobHub != nil { if s.deps.JobHub != nil {
r.Get("/api/jobs/{id}/stream", s.handleJobStream) r.Get("/api/jobs/{id}/stream", s.handleJobStream)
} }
// Job log download (txt + ndjson). Source of truth is the
// persisted job_logs table; safe to call any time, no pause
// needed against the live stream.
r.Get("/api/jobs/{id}/log.{format:txt|ndjson}", s.handleJobLogDownload)
} }
// Start begins listening. Blocks until ListenAndServe returns // Start begins listening. Blocks until ListenAndServe returns
+5
View File
@@ -63,6 +63,11 @@
</div> </div>
</div> </div>
<div class="flex items-center gap-2"> <div class="flex items-center gap-2">
<a href="/api/jobs/{{$job.ID}}/log.txt" class="btn"
title="Download the full log up to this moment (works while running too).">
Download log
</a>
<a href="/api/jobs/{{$job.ID}}/log.ndjson" class="btn btn-ghost" title="Same log as NDJSON for jq / tooling">.ndjson</a>
{{if $page.IsActive}} {{if $page.IsActive}}
<button class="btn btn-danger" id="cancel-btn" <button class="btn btn-danger" id="cancel-btn"
hx-post="/api/jobs/{{$job.ID}}/cancel" hx-post="/api/jobs/{{$job.ID}}/cancel"