Add a Download button that exports a database target's archive as gzipped JSON (closes #374)

Each database target on the webhook page links to
/hook/ID/targets/TARGETID/download, which streams the target's archive
as archive-WEBHOOK-TARGET-YYYYMMDDTHHMMSSZ.json.gz: the webhook, the
target, exported_at, and archived_events, one object per row keyed by
column, a body that is not valid UTF-8 in base64 with body_encoding.
The export reads one row at a time on its own connection inside a
read-only transaction: one snapshot, and no write lock. The handler
holds the rename lock only while it reads the names and opens the file.
A missing archive exports empty and is not created.

Model: opus-5-5

internal/handlers/handlers.go

@@ -97,7 +97,8 @@ type Handlers struct {
 	// names through the archive rename, the save and any move back.
 	// Interleaved, one could rename an archive between another's
 	// rename and save, leaving the file named for one edit and the
-	// stored names from the other.
+	// stored names from the other. An archive download holds it while
+	// it reads the stored names and opens the file they give.
 	renameMu sync.Mutex
 
 	// dummyVerifications counts the equivalent-cost verifications

internal/handlers/target_download.go

@@ -0,0 +1,82 @@
+package handlers
+
+import (
+	"net/http"
+	"time"
+
+	"sneak.berlin/go/webhooker/internal/database"
+	"sneak.berlin/go/webhooker/internal/delivery"
+)
+
+// HandleTargetDownload serves a database target's archive as one
+// gzipped JSON file, named for the webhook, the target and the time;
+// see delivery.ArchiveExport.WriteGzipJSON for what it holds. Other
+// target types have no archive and are a 404.
+func (h *Handlers) HandleTargetDownload() http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		webhook, target, export, ok := h.openTargetArchive(w, r)
+		if !ok {
+			return
+		}
+
+		defer func() { _ = export.Close() }()
+
+		now := time.Now()
+
+		w.Header().Set("Content-Type", "application/gzip")
+		w.Header().Set(
+			"Content-Disposition",
+			`attachment; filename="`+delivery.ArchiveExportFileName(
+				webhook.Name, target.Name, now,
+			)+`"`,
+		)
+
+		err := export.WriteGzipJSON(r.Context(), w, &webhook, target, now)
+		if err != nil {
+			// The 200 has gone out. The client is left with a file
+			// that does not decompress; the log is the record.
+			h.log.Error(
+				"failed to export archive",
+				"target_id", target.ID,
+				"error", err,
+			)
+		}
+	}
+}
+
+// openTargetArchive opens the archive of the request's database target
+// for export. It reports false once it has written the response.
+//
+// It holds renameMu, which every archive rename runs under, while it
+// reads the stored names and opens the file, so the file it opens is
+// the one those names give. It lets go before the export is streamed:
+// once the file is open, a rename does not affect the export.
+func (h *Handlers) openTargetArchive(
+	w http.ResponseWriter,
+	r *http.Request,
+) (database.Webhook, *database.Target, *delivery.ArchiveExport, bool) {
+	h.renameMu.Lock()
+	defer h.renameMu.Unlock()
+
+	webhook, target, ok := h.ownedTarget(w, r)
+	if !ok {
+		return database.Webhook{}, nil, nil, false
+	}
+
+	if target.Type != database.TargetTypeDatabase {
+		h.renderError(w, r, http.StatusNotFound)
+
+		return database.Webhook{}, nil, nil, false
+	}
+
+	export, err := delivery.OpenArchiveExport(
+		r.Context(), delivery.ArchivePath(h.dbMgr, &webhook, target),
+	)
+	if err != nil {
+		h.serverError(w, r, "failed to open archive for export", err)
+
+		return database.Webhook{}, nil, nil, false
+	}
+
+	return webhook, target, export, true
+}

internal/handlers/target_download_test.go

@@ -0,0 +1,185 @@
+package handlers_test
+
+import (
+	"compress/gzip"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"net/url"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/webhooker/internal/database"
+)
+
+// downloadPath is the archive download route of a target.
+func downloadPath(webhookID, targetID string) string {
+	return "/hook/" + webhookID + "/targets/" + targetID + "/download"
+}
+
+// renameTarget submits the edit form renaming a target to Renamed.
+func renameTarget(
+	env *sourceTestEnv, webhookID, targetID string,
+) *httptest.ResponseRecorder {
+	form := url.Values{}
+	form.Set("name", "Renamed")
+
+	return submitTargetEdit(env, webhookID, targetID, form)
+}
+
+// TestHandleTargetDownload proves a database target's archive
+// downloads as a gzipped JSON attachment named for the webhook, the
+// target and the time, here with no archive file yet, so with no
+// rows; and that a target of another type has no download.
+func TestHandleTargetDownload(t *testing.T) {
+	t.Parallel()
+
+	env := setupSourceTest(t)
+	wh := seedWebhookWithRetention(t, env.db, 7)
+	archive := seedTarget(t, env.db, wh.ID, database.TargetTypeDatabase)
+	logTarget := seedTarget(t, env.db, wh.ID, database.TargetTypeLog)
+
+	w := serveTarget(
+		env, http.MethodGet, downloadPath(wh.ID, archive.ID), nil,
+	)
+	require.Equal(t, http.StatusOK, w.Code, w.Body.String())
+	assert.Equal(t, "application/gzip", w.Header().Get("Content-Type"))
+	assert.Regexp(t,
+		`^attachment; filename="archive-seeded-t-database-`+
+			`\d{8}T\d{6}Z\.json\.gz"$`,
+		w.Header().Get("Content-Disposition"),
+	)
+
+	zr, err := gzip.NewReader(w.Body)
+	require.NoError(t, err)
+
+	var got map[string]json.RawMessage
+
+	require.NoError(t, json.NewDecoder(zr).Decode(&got))
+	assert.JSONEq(t,
+		`{"id":"`+archive.ID+`","name":"t-database"}`,
+		string(got["target"]),
+	)
+	assert.JSONEq(t, `[]`, string(got["archived_events"]))
+
+	w = serveTarget(
+		env, http.MethodGet, downloadPath(wh.ID, logTarget.ID), nil,
+	)
+	assert.Equal(t, http.StatusNotFound, w.Code)
+}
+
+// TestHandleTargetDownload_WaitsForRename proves a download reads the
+// target's names and opens its archive under the lock a rename holds:
+// started while an edit is renaming the archive, it waits, and is
+// named for the target's new name.
+func TestHandleTargetDownload_WaitsForRename(t *testing.T) {
+	t.Parallel()
+
+	env := setupSourceTest(t)
+	wh := seedWebhookWithRetention(t, env.db, 7)
+	archive := seedTarget(t, env.db, wh.ID, database.TargetTypeDatabase)
+
+	renaming, release := env.archives.BlockNextRename()
+	edited := make(chan *httptest.ResponseRecorder, 1)
+
+	go func() {
+		edited <- renameTarget(env, wh.ID, archive.ID)
+	}()
+
+	<-renaming
+
+	downloaded := make(chan *httptest.ResponseRecorder, 1)
+
+	go func() {
+		downloaded <- serveTarget(
+			env, http.MethodGet, downloadPath(wh.ID, archive.ID), nil,
+		)
+	}()
+
+	select {
+	case <-downloaded:
+		release()
+		t.Fatal("the download did not wait for the rename")
+	case <-time.After(100 * time.Millisecond):
+	}
+
+	release()
+	require.Equal(t, http.StatusSeeOther, (<-edited).Code)
+
+	w := <-downloaded
+	require.Equal(t, http.StatusOK, w.Code)
+	assert.Contains(t,
+		w.Header().Get("Content-Disposition"), "archive-seeded-renamed-",
+	)
+}
+
+// stalledWriter is a response writer whose first write waits until
+// resume is closed, closing writing when it starts to wait.
+type stalledWriter struct {
+	*httptest.ResponseRecorder
+
+	once    sync.Once
+	writing chan struct{}
+	resume  chan struct{}
+}
+
+func (s *stalledWriter) Write(b []byte) (int, error) {
+	s.once.Do(func() {
+		close(s.writing)
+		<-s.resume
+	})
+
+	return s.ResponseRecorder.Write(b)
+}
+
+// TestHandleTargetDownload_StreamsWithoutTheLock proves a download
+// lets go of the rename lock once its archive is open: while the
+// download is stalled writing, an edit can still rename the target.
+func TestHandleTargetDownload_StreamsWithoutTheLock(t *testing.T) {
+	t.Parallel()
+
+	env := setupSourceTest(t)
+	wh := seedWebhookWithRetention(t, env.db, 7)
+	archive := seedTarget(t, env.db, wh.ID, database.TargetTypeDatabase)
+
+	req := httptest.NewRequestWithContext(
+		t.Context(), http.MethodGet, downloadPath(wh.ID, archive.ID), nil,
+	)
+	for _, c := range env.cookies {
+		req.AddCookie(c)
+	}
+
+	sw := &stalledWriter{
+		ResponseRecorder: httptest.NewRecorder(),
+		writing:          make(chan struct{}),
+		resume:           make(chan struct{}),
+	}
+	downloaded := make(chan struct{})
+
+	go func() {
+		targetRouter(env).ServeHTTP(sw, req)
+		close(downloaded)
+	}()
+
+	<-sw.writing
+
+	edited := make(chan *httptest.ResponseRecorder, 1)
+
+	go func() {
+		edited <- renameTarget(env, wh.ID, archive.ID)
+	}()
+
+	select {
+	case w := <-edited:
+		assert.Equal(t, http.StatusSeeOther, w.Code)
+	case <-time.After(10 * time.Second):
+		t.Error("the rename waited for the download")
+	}
+
+	close(sw.resume)
+	<-downloaded
+	assert.Equal(t, http.StatusOK, sw.Code)
+}

internal/handlers/target_edit_test.go

@@ -37,14 +37,18 @@ const (
 	editAuthHeader   = "Authorization: Bearer " + editBearerSecret
 )
 
-// targetRouter mounts the target create and edit routes on a chi
-// router so the handlers see the URL parameters they read.
+// targetRouter mounts the target create, edit and download routes on
+// a chi router so the handlers see the URL parameters they read.
 func targetRouter(env *sourceTestEnv) *chi.Mux {
 	router := chi.NewRouter()
 	router.Post(
 		"/hook/{sourceID}/targets",
 		env.handlers.HandleTargetCreate(),
 	)
+	router.Get(
+		"/hook/{sourceID}/targets/{targetID}/download",
+		env.handlers.HandleTargetDownload(),
+	)
 	router.Get(
 		"/hook/{sourceID}/targets/{targetID}/edit",
 		env.handlers.HandleTargetEdit(),