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 the rows through one cursor on its own connection
inside a read-only transaction: one snapshot, and no write lock. A
download runs for as long as the client keeps reading, and one that
fails after it has started aborts the connection. 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

README.md

@@ -2029,6 +2029,29 @@ Because each `database` target has its own archive file, a target's
 webhook with different expiries keep two archives, each pruned on its
 own schedule.
 
+Each `database` target on the webhook page has a **Download** button,
+which returns its archive as one gzipped JSON file,
+`archive-{webhook_name}-{target_name}-{YYYYMMDDTHHMMSSZ}.json.gz`, the
+names made safe as above and the time in UTC. The file holds one
+object: `webhook` and `target`, each an `id` and a `name`;
+`exported_at`; and `archived_events`, one object per archived row with
+every column, keyed by column name. A body that is not valid UTF-8 is
+written in base64, with `"body_encoding": "base64"` beside it. An
+archive that does not exist yet, or was moved away, downloads with an
+empty `archived_events`; the download never creates the file.
+
+The download streams: each row is read and written out compressed
+before the next is read, so neither the archive nor the JSON is held in
+memory. It reads on a connection of its own, inside one read-only
+transaction, so the file holds the archive as it stood when the
+download started, and archive writes go on meanwhile, since under WAL a
+reader never blocks a writer. While it runs, the `-wal` cannot be
+checkpointed past what it reads, so a long download lets the `-wal`
+grow. It finds the file by the stored names under the lock that webhook
+edits, target edits and target creation hold, and lets go once the file
+is open: a rename during the download moves the file without affecting
+it.
+
 Deleting a webhook releases its archives: the delivery engine's cached
 archive writers are dropped and their file handles closed, so nothing
 lingers after the webhook is gone. The archive **files themselves are
@@ -2892,6 +2915,7 @@ returns to the page that was asked for.
 | `POST` | `/hook/{id}/targets`     | Add target to webhook |
 | `GET`  | `/hook/{id}/targets/{targetID}/edit` | Edit target form. The one page that renders a target's destination URL and header values in full, rather than masked |
 | `POST` | `/hook/{id}/targets/{targetID}/edit` | Edit target submission |
+| `GET`  | `/hook/{id}/targets/{targetID}/download` | Download a `database` target's archive as one gzipped JSON file. See [Database Architecture](#database-architecture) |
 | `POST` | `/hook/{id}/targets/{targetID}/delete` | Delete a target |
 | `POST` | `/hook/{id}/targets/{targetID}/toggle` | Enable or disable a target |
 
@@ -2972,6 +2996,7 @@ webhooker/
 │   │   ├── target_slack.go    # Slack/Mattermost incoming-webhook target
 │   │   ├── target_database.go # Database archive target
 │   │   ├── target_database_archive.go  # Archive file lifecycle and pruning
+│   │   ├── target_database_export.go   # Archive download as gzipped JSON
 │   │   ├── target_log.go      # Log target (stdout)
 │   │   ├── target_config_view.go  # Masked target config for templates
 │   │   ├── archive_sweeper.go # Periodic pruning of idle archives

internal/delivery/target_database.go

@@ -3,7 +3,6 @@ package delivery
 import (
 	"context"
 	"fmt"
-	"path/filepath"
 	"strings"
 	"sync"
 	"time"
@@ -277,10 +276,9 @@ func (t *databaseTarget) releaseSweepWriter(
 }
 
 // newWriter builds the writer for a database target's archive. The
-// file lives beside the webhook's event database in the data
-// directory and is named for the webhook and the target as the main
-// database has them now; from then on only rename changes the name
-// the writer uses. It does not touch the archive file.
+// file is the one ArchivePath gives for the webhook and the target as
+// the main database names them now; from then on only rename changes
+// the name the writer uses. It does not touch the archive file.
 func (t *databaseTarget) newWriter(
 	targetID string,
 ) (*archiveWriter, error) {
@@ -299,12 +297,10 @@ func (t *databaseTarget) newWriter(
 		)
 	}
 
-	dir := filepath.Dir(t.eng.dbManager.DBPath(target.WebhookID))
-	name := ArchiveFileName(
-		target.Webhook.Name, target.Name, target.ID,
+	w := newArchiveWriter(
+		ArchivePath(t.eng.dbManager, &target.Webhook, &target),
+		t.eng.log,
 	)
-
-	w := newArchiveWriter(filepath.Join(dir, name), t.eng.log)
 	w.webhookID = target.WebhookID
 
 	return w, nil

internal/delivery/target_database_export.go

@@ -0,0 +1,275 @@
+package delivery
+
+import (
+	"compress/gzip"
+	"context"
+	"database/sql"
+	"encoding/base64"
+	"encoding/json"
+	"fmt"
+	"io"
+	"log/slog"
+	"path/filepath"
+	"time"
+	"unicode/utf8"
+
+	"gorm.io/driver/sqlite"
+	"gorm.io/gorm"
+	"sneak.berlin/go/webhooker/internal/database"
+	"sneak.berlin/go/webhooker/internal/gormlog"
+)
+
+// archiveTableQuery counts the archive's table: 0 when the archive
+// writer has created the file but not yet the table in it.
+const archiveTableQuery = "SELECT count(*) FROM sqlite_master " +
+	"WHERE type = 'table' AND name = 'archived_events'"
+
+// ArchivePath returns where a database target's archive file is: in
+// the data directory, beside the webhook's event database, under the
+// name ArchiveFileName gives it.
+func ArchivePath(
+	dbMgr *database.WebhookDBManager,
+	webhook *database.Webhook,
+	target *database.Target,
+) string {
+	return filepath.Join(
+		filepath.Dir(dbMgr.DBPath(webhook.ID)),
+		ArchiveFileName(webhook.Name, target.Name, target.ID),
+	)
+}
+
+// ArchiveExportFileName returns the name a database target's archive
+// downloads under:
+// archive-WEBHOOKNAME-TARGETNAME-YYYYMMDDTHHMMSSZ.json.gz, the names
+// made safe as in ArchiveFileName and the time in UTC.
+func ArchiveExportFileName(
+	webhookName, targetName string, at time.Time,
+) string {
+	return "archive-" + archiveNamePart(webhookName) + "-" +
+		archiveNamePart(targetName) + "-" +
+		at.UTC().Format("20060102T150405Z") + ".json.gz"
+}
+
+// ArchiveExport is a database target's archive opened for download.
+// It reads the file on its own connection, inside one read-only
+// transaction, so it writes out the archive as it stood when
+// OpenArchiveExport returned.
+//
+// Archives are in WAL mode, where a reader works from a snapshot and
+// never blocks a writer: archive writes go on while an export is open,
+// and the export does not see them. SQLite cannot checkpoint the -wal
+// past an open snapshot, so the -wal grows until the export is closed.
+type ArchiveExport struct {
+	db *sql.DB
+	tx *gorm.DB
+
+	// empty is true when there is nothing to read: no file, or a file
+	// without the archive's table yet.
+	empty bool
+}
+
+// exportedName is how an export names its webhook and its target.
+type exportedName struct {
+	ID   string `json:"id"`
+	Name string `json:"name"`
+}
+
+// OpenArchiveExport opens the archive file at path for export and
+// takes the snapshot the export reads. It never creates the file: with
+// no file at path, the export has no rows.
+//
+// Once it has returned, the file is open, so a rename or a move of it
+// does not affect the export, which reads the same file under its new
+// name.
+//
+// The transaction lasts as long as ctx does, so ctx must last for the
+// whole export.
+func OpenArchiveExport(
+	ctx context.Context, path string, log *slog.Logger,
+) (*ArchiveExport, error) {
+	if !fileExists(path) {
+		return &ArchiveExport{empty: true}, nil
+	}
+
+	db, err := database.OpenSQLite(path, archiveModeExisting)
+	if err != nil {
+		return nil, fmt.Errorf("opening archive %s: %w", path, err)
+	}
+
+	gdb, err := gorm.Open(
+		sqlite.Dialector{Conn: db}, &gorm.Config{
+			// Never leave this at GORM's default. See
+			// internal/gormlog.
+			Logger: gormlog.New(log),
+		},
+	)
+	if err != nil {
+		_ = db.Close()
+
+		return nil, fmt.Errorf("opening archive %s: %w", path, err)
+	}
+
+	// ReadOnly makes the driver begin a deferred transaction in place
+	// of the BEGIN IMMEDIATE the connection string asks for, so the
+	// export never takes the archive's write lock.
+	tx := gdb.WithContext(ctx).Begin(&sql.TxOptions{ReadOnly: true})
+	if tx.Error != nil {
+		_ = db.Close()
+
+		return nil, fmt.Errorf("reading archive %s: %w", path, tx.Error)
+	}
+
+	// The transaction's first read is what takes the snapshot.
+	var tables int
+
+	err = tx.Raw(archiveTableQuery).Row().Scan(&tables)
+	if err != nil {
+		_ = tx.Rollback()
+		_ = db.Close()
+
+		return nil, fmt.Errorf("reading archive %s: %w", path, err)
+	}
+
+	return &ArchiveExport{db: db, tx: tx, empty: tables == 0}, nil
+}
+
+// WriteGzipJSON writes the export to w as one gzipped JSON object:
+// webhook and target, each an id and a name; exported_at; and
+// archived_events, one object per archived row, keyed by column name.
+// A body that is not valid UTF-8 cannot be a JSON string, so it is
+// written in base64, with "body_encoding": "base64" beside it.
+//
+// Each row is written out before the next is read, so neither the
+// archive nor its JSON is ever held in memory whole. After an error
+// the gzip stream is left unfinished, so what was written does not
+// decompress as a whole file.
+func (x *ArchiveExport) WriteGzipJSON(
+	ctx context.Context,
+	w io.Writer,
+	webhook *database.Webhook,
+	target *database.Target,
+	exportedAt time.Time,
+) error {
+	head, err := json.Marshal(map[string]any{
+		"webhook":     exportedName{ID: webhook.ID, Name: webhook.Name},
+		"target":      exportedName{ID: target.ID, Name: target.Name},
+		"exported_at": exportedAt.UTC(),
+	})
+	if err != nil {
+		return fmt.Errorf("encoding archive export: %w", err)
+	}
+
+	zw := gzip.NewWriter(w)
+
+	err = x.writeJSON(ctx, zw, head)
+	if err != nil {
+		return fmt.Errorf("writing archive export: %w", err)
+	}
+
+	return zw.Close()
+}
+
+// Close ends the export's transaction and closes its connection.
+func (x *ArchiveExport) Close() error {
+	if x.db == nil {
+		return nil
+	}
+
+	_ = x.tx.Rollback()
+
+	return x.db.Close()
+}
+
+// writeJSON writes head with archived_events added as its last key,
+// the rows going into it one at a time.
+func (x *ArchiveExport) writeJSON(
+	ctx context.Context, w io.Writer, head []byte,
+) error {
+	// head goes out without its closing brace, so that
+	// archived_events can follow it.
+	_, err := w.Write(head[:len(head)-1])
+	if err != nil {
+		return err
+	}
+
+	_, err = io.WriteString(w, `,"archived_events":[`)
+	if err != nil {
+		return err
+	}
+
+	err = x.writeRows(ctx, w)
+	if err != nil {
+		return err
+	}
+
+	_, err = io.WriteString(w, "\n]}\n")
+
+	return err
+}
+
+// writeRows writes each archived row to w, oldest first, one per line,
+// separated by commas.
+func (x *ArchiveExport) writeRows(ctx context.Context, w io.Writer) error {
+	if x.empty {
+		return nil
+	}
+
+	rows, err := x.tx.WithContext(ctx).
+		Model(&archivedEvent{}).Order("id").Rows()
+	if err != nil {
+		return err
+	}
+
+	defer func() { _ = rows.Close() }()
+
+	for sep := "\n"; rows.Next(); sep = ",\n" {
+		var ev archivedEvent
+
+		err = x.tx.ScanRows(rows, &ev)
+		if err != nil {
+			return err
+		}
+
+		_, err = io.WriteString(w, sep)
+		if err != nil {
+			return err
+		}
+
+		err = writeRow(w, &ev)
+		if err != nil {
+			return err
+		}
+	}
+
+	return rows.Err()
+}
+
+// writeRow writes an archived row to w as a JSON object keyed by
+// column name, its body in base64 when it is not valid UTF-8.
+func writeRow(w io.Writer, ev *archivedEvent) error {
+	row := map[string]any{
+		"id":            ev.ID,
+		"event_id":      ev.EventID,
+		"webhook_id":    ev.WebhookID,
+		"entrypoint_id": ev.EntrypointID,
+		"method":        ev.Method,
+		"headers":       ev.Headers,
+		"body":          ev.Body,
+		"content_type":  ev.ContentType,
+		"archived_at":   ev.ArchivedAt.UTC(),
+	}
+
+	if !utf8.ValidString(ev.Body) {
+		row["body"] = base64.StdEncoding.EncodeToString([]byte(ev.Body))
+		row["body_encoding"] = "base64"
+	}
+
+	line, err := json.Marshal(row)
+	if err != nil {
+		return err
+	}
+
+	_, err = w.Write(line)
+
+	return err
+}

internal/delivery/target_database_export_test.go

@@ -0,0 +1,388 @@
+package delivery_test
+
+import (
+	"bytes"
+	"compress/gzip"
+	"crypto/rand"
+	"encoding/base64"
+	"encoding/json"
+	"fmt"
+	"io"
+	"os"
+	"path/filepath"
+	"runtime"
+	"runtime/debug"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/webhooker/internal/database"
+	"sneak.berlin/go/webhooker/internal/delivery"
+)
+
+// The webhook and the target the export tests' archives belong to.
+const (
+	exportWebhookID   = "wh-export"
+	exportWebhookName = "Orders (EU)"
+	exportTargetID    = "tgt-export"
+	exportTargetName  = "Long-term archive"
+)
+
+const (
+	// binaryBody is a body that is not valid UTF-8.
+	binaryBody = "\xff\xfe\x00\x01binary\x80"
+
+	// openedEventID is the event the snapshot tests archive before
+	// they open the export.
+	openedEventID = "opened"
+)
+
+// writeExportTo writes export to w as the archive of the export tests'
+// webhook and target, exported at 2026-10-02T12:03:04Z.
+func writeExportTo(
+	t *testing.T, export *delivery.ArchiveExport, w io.Writer,
+) error {
+	t.Helper()
+
+	return export.WriteGzipJSON(
+		t.Context(), w,
+		&database.Webhook{
+			BaseModel: database.BaseModel{ID: exportWebhookID},
+			Name:      exportWebhookName,
+		},
+		&database.Target{
+			BaseModel: database.BaseModel{ID: exportTargetID},
+			Name:      exportTargetName,
+		},
+		time.Date(2026, 10, 2, 12, 3, 4, 0, time.UTC),
+	)
+}
+
+// exportArchive runs a whole export of the archive at path and returns
+// its JSON, decompressed and parsed.
+func exportArchive(t *testing.T, path string) map[string]any {
+	t.Helper()
+
+	export, err := delivery.OpenArchiveExport(
+		t.Context(), path, archiveTestLogger(),
+	)
+	require.NoError(t, err)
+
+	defer func() { require.NoError(t, export.Close()) }()
+
+	return writeExport(t, export)
+}
+
+// writeExport writes an opened export and returns its JSON,
+// decompressed and parsed. Reading to the end makes the gzip reader
+// check that the stream was finished.
+func writeExport(
+	t *testing.T, export *delivery.ArchiveExport,
+) map[string]any {
+	t.Helper()
+
+	var buf bytes.Buffer
+
+	require.NoError(t, writeExportTo(t, export, &buf))
+
+	zr, err := gzip.NewReader(&buf)
+	require.NoError(t, err)
+
+	raw, err := io.ReadAll(zr)
+	require.NoError(t, err)
+
+	var got map[string]any
+
+	require.NoError(t, json.Unmarshal(raw, &got))
+
+	return got
+}
+
+// exportedEvents returns an export's archived_events.
+func exportedEvents(t *testing.T, got map[string]any) []map[string]any {
+	t.Helper()
+
+	list, ok := got["archived_events"].([]any)
+	require.True(t, ok, "archived_events must be an array: %v", got)
+
+	events := make([]map[string]any, len(list))
+
+	for i, v := range list {
+		events[i], ok = v.(map[string]any)
+		require.True(t, ok, "an archived event must be an object: %v", v)
+	}
+
+	return events
+}
+
+// exportedEventIDs returns the event_id of each of an export's
+// archived_events.
+func exportedEventIDs(t *testing.T, got map[string]any) []string {
+	t.Helper()
+
+	events := exportedEvents(t, got)
+	ids := make([]string, 0, len(events))
+
+	for _, ev := range events {
+		ids = append(ids, fmt.Sprint(ev["event_id"]))
+	}
+
+	return ids
+}
+
+// TestArchiveExport_MatchesStoredRows proves an export holds the
+// webhook, the target, the time, and every column of every stored
+// row: a body that is valid UTF-8 as a string, and one that is not in
+// base64, marked as such.
+func TestArchiveExport_MatchesStoredRows(t *testing.T) {
+	t.Parallel()
+
+	path := filepath.Join(t.TempDir(), "archive.db")
+	w := delivery.NewExportArchiveWriter(path, archiveTestLogger(), 0)
+	bodies := []string{`{"order":1}`, "plain text", "", binaryBody}
+
+	for i, body := range bodies {
+		require.NoError(t, w.Write(delivery.ExportArchivedEvent{
+			EventID:      fmt.Sprintf("ev-%d", i),
+			WebhookID:    exportWebhookID,
+			EntrypointID: "ep-1",
+			Method:       "POST",
+			Headers:      `{"X-Test":["yes"]}`,
+			Body:         body,
+			ContentType:  testContentType,
+		}, 0))
+	}
+
+	var stored []delivery.ExportArchivedEvent
+
+	require.NoError(t, openArchiveDBForRead(t, path).
+		Order("id").Find(&stored).Error)
+
+	got := exportArchive(t, path)
+
+	assert.Equal(t,
+		map[string]any{"id": exportWebhookID, "name": exportWebhookName},
+		got["webhook"],
+	)
+	assert.Equal(t,
+		map[string]any{"id": exportTargetID, "name": exportTargetName},
+		got["target"],
+	)
+	assert.Equal(t, "2026-10-02T12:03:04Z", got["exported_at"])
+
+	events := exportedEvents(t, got)
+	require.Len(t, events, len(bodies))
+
+	for i, row := range stored {
+		assertExportedRow(t, row, events[i])
+	}
+}
+
+// assertExportedRow checks that ev, from an export, holds every column
+// of the stored row.
+func assertExportedRow(
+	t *testing.T, row delivery.ExportArchivedEvent, ev map[string]any,
+) {
+	t.Helper()
+
+	archivedAt, err := time.Parse(
+		time.RFC3339Nano, fmt.Sprint(ev["archived_at"]),
+	)
+	require.NoError(t, err)
+	assert.True(t, archivedAt.Equal(row.ArchivedAt))
+
+	assert.EqualValues(t, row.ID, ev["id"])
+	assert.Equal(t, row.EventID, ev["event_id"])
+	assert.Equal(t, row.WebhookID, ev["webhook_id"])
+	assert.Equal(t, row.EntrypointID, ev["entrypoint_id"])
+	assert.Equal(t, row.Method, ev["method"])
+	assert.Equal(t, row.Headers, ev["headers"])
+	assert.Equal(t, row.ContentType, ev["content_type"])
+
+	if row.Body != binaryBody {
+		assert.Equal(t, row.Body, ev["body"])
+		assert.Len(t, ev, 9, "the nine columns and nothing else: %v", ev)
+
+		return
+	}
+
+	body, err := base64.StdEncoding.DecodeString(fmt.Sprint(ev["body"]))
+	require.NoError(t, err)
+	assert.Equal(t, binaryBody, string(body))
+	assert.Equal(t, "base64", ev["body_encoding"])
+	assert.Len(t, ev, 10, "the nine columns and body_encoding: %v", ev)
+}
+
+// TestArchiveExport_Empty proves an archive with nothing in it exports
+// as an empty archived_events: no file, which the export must not
+// create; a file the archive writer has not yet put its table in; and
+// a table with no rows.
+func TestArchiveExport_Empty(t *testing.T) {
+	t.Parallel()
+
+	dir := t.TempDir()
+	missing := filepath.Join(dir, "missing.db")
+	noTable := filepath.Join(dir, "no-table.db")
+	noRows := filepath.Join(dir, "no-rows.db")
+
+	require.NoError(t, os.WriteFile(noTable, nil, 0o600))
+	require.NoError(t,
+		delivery.NewExportArchiveWriter(noRows, archiveTestLogger(), 0).
+			Open(0),
+	)
+
+	for _, path := range []string{missing, noTable, noRows} {
+		assert.Empty(t, exportedEvents(t, exportArchive(t, path)), path)
+	}
+
+	for _, suffix := range archiveFileSuffixes() {
+		assert.NoFileExists(t, missing+suffix)
+	}
+}
+
+// TestArchiveExport_ReadsOneSnapshot proves an export writes the
+// archive as it was when it was opened, and holds up no archive
+// write: a row written while the export is open is stored, and is not
+// in the export. A write held up for the whole busy timeout would
+// fail.
+func TestArchiveExport_ReadsOneSnapshot(t *testing.T) {
+	t.Parallel()
+
+	path := filepath.Join(t.TempDir(), "archive.db")
+	w := delivery.NewExportArchiveWriter(path, archiveTestLogger(), 0)
+
+	require.NoError(t, w.Write(delivery.ExportArchivedEvent{EventID: openedEventID}, 0))
+
+	export, err := delivery.OpenArchiveExport(
+		t.Context(), path, archiveTestLogger(),
+	)
+	require.NoError(t, err)
+
+	defer func() { require.NoError(t, export.Close()) }()
+
+	require.NoError(t, w.Write(delivery.ExportArchivedEvent{EventID: "during"}, 0))
+
+	assert.Equal(t,
+		[]string{openedEventID}, exportedEventIDs(t, writeExport(t, export)),
+	)
+
+	var stored int64
+
+	require.NoError(t, openArchiveDBForRead(t, path).
+		Model(&delivery.ExportArchivedEvent{}).Count(&stored).Error)
+	assert.Equal(t, int64(2), stored)
+}
+
+// TestArchiveExport_SurvivesRename proves that renaming the archive
+// while an export of it is open, as renaming its webhook or target
+// does, leaves the export reading the same file.
+func TestArchiveExport_SurvivesRename(t *testing.T) {
+	t.Parallel()
+
+	path := filepath.Join(t.TempDir(), "archive-old.db")
+	w := delivery.NewExportArchiveWriter(path, archiveTestLogger(), 0)
+
+	require.NoError(t, w.Write(delivery.ExportArchivedEvent{EventID: openedEventID}, 0))
+
+	export, err := delivery.OpenArchiveExport(
+		t.Context(), path, archiveTestLogger(),
+	)
+	require.NoError(t, err)
+
+	defer func() { require.NoError(t, export.Close()) }()
+
+	require.NoError(t, w.Rename("archive-new.db"))
+	require.NoError(t, w.Write(delivery.ExportArchivedEvent{EventID: "after"}, 0))
+	require.NoFileExists(t, path)
+
+	assert.Equal(t,
+		[]string{openedEventID}, exportedEventIDs(t, writeExport(t, export)),
+	)
+}
+
+// heapPeak is an io.Writer that discards what it is given and records
+// the largest heap it saw at a write.
+type heapPeak struct {
+	max uint64
+}
+
+func (p *heapPeak) Write(b []byte) (int, error) {
+	var m runtime.MemStats
+
+	runtime.ReadMemStats(&m)
+	p.max = max(p.max, m.HeapAlloc)
+
+	return len(b), nil
+}
+
+// TestArchiveExport_Streams proves an export holds neither the archive
+// nor its output in memory whole: exporting a 16 MiB archive grows the
+// heap by less than half of that. The bodies are random bytes in
+// base64, which gzip shrinks by only a quarter, so an export that read
+// every row before writing, or built the JSON or the gzipped file
+// before writing it, would hold at least 12 MiB at a write.
+//
+//nolint:paralleltest // It measures the heap, which tests share.
+func TestArchiveExport_Streams(t *testing.T) {
+	const (
+		rows     = 64
+		bodySize = 256 << 10
+		limit    = rows * bodySize / 2
+	)
+
+	path := filepath.Join(t.TempDir(), "archive.db")
+	w := delivery.NewExportArchiveWriter(path, archiveTestLogger(), 0)
+
+	// Base64 makes four characters of every three bytes.
+	random := make([]byte, bodySize/4*3)
+
+	for range rows {
+		_, _ = rand.Read(random)
+
+		require.NoError(t, w.Write(delivery.ExportArchivedEvent{
+			Body: base64.StdEncoding.EncodeToString(random),
+		}, 0))
+	}
+
+	export, err := delivery.OpenArchiveExport(
+		t.Context(), path, archiveTestLogger(),
+	)
+	require.NoError(t, err)
+
+	defer func() { require.NoError(t, export.Close()) }()
+
+	// A low GC target collects garbage soon after it is made, so the
+	// heap at each write is close to what the export is holding.
+	defer debug.SetGCPercent(debug.SetGCPercent(10))
+
+	runtime.GC()
+
+	var start runtime.MemStats
+
+	runtime.ReadMemStats(&start)
+
+	peak := &heapPeak{}
+
+	require.NoError(t, writeExportTo(t, export, peak))
+	assert.Less(t, peak.max, start.HeapAlloc+limit,
+		"heap at the start %d, at its peak %d", start.HeapAlloc, peak.max,
+	)
+}
+
+// TestArchiveExportFileName proves the download is named for the
+// webhook and the target, with the names made safe as for the archive
+// file, and the export time in UTC.
+func TestArchiveExportFileName(t *testing.T) {
+	t.Parallel()
+
+	cest := time.FixedZone("CEST", int((2 * time.Hour).Seconds()))
+
+	assert.Equal(t,
+		"archive-orders-eu-long-term-archive-20261002T120304Z.json.gz",
+		delivery.ArchiveExportFileName(
+			exportWebhookName, exportTargetName,
+			time.Date(2026, 10, 2, 14, 3, 4, 0, cest),
+		),
+	)
+}

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/source_management_test.go

@@ -191,6 +191,7 @@ func storedRetentionDays(
 type sourceTestEnv struct {
 	handlers *handlers.Handlers
 	db       *database.Database
+	dbMgr    *database.WebhookDBManager
 	archives *recordingArchives
 	cookies  []*http.Cookie
 }
@@ -204,9 +205,11 @@ func setupSourceTest(t *testing.T) *sourceTestEnv {
 
 	var db *database.Database
 
+	var dbMgr *database.WebhookDBManager
+
 	var archives *recordingArchives
 
-	app := newTestApp(t, &h, &sess, &db, &archives)
+	app := newTestApp(t, &h, &sess, &db, &dbMgr, &archives)
 	app.RequireStart()
 
 	t.Cleanup(app.RequireStop)
@@ -214,6 +217,7 @@ func setupSourceTest(t *testing.T) *sourceTestEnv {
 	return &sourceTestEnv{
 		handlers: h,
 		db:       db,
+		dbMgr:    dbMgr,
 		archives: archives,
 		cookies: authenticatedCookies(
 			t, sess, sourceTestUserID, "sourceuser",

internal/handlers/target_download.go

@@ -0,0 +1,121 @@
+package handlers
+
+import (
+	"context"
+	"errors"
+	"net/http"
+	"time"
+
+	"sneak.berlin/go/webhooker/internal/database"
+	"sneak.berlin/go/webhooker/internal/delivery"
+)
+
+// downloadWriteTimeout is how long one write of a download may wait
+// for a client that has stopped reading.
+const downloadWriteTimeout = 60 * time.Second
+
+// 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.
+//
+// A download runs for as long as the client keeps reading: it reads
+// under a context the request limit does not cancel, and gives each
+// write its own deadline in place of the server's write timeout. It
+// stops when a write fails.
+func (h *Handlers) HandleTargetDownload() http.HandlerFunc {
+	return func(w http.ResponseWriter, r *http.Request) {
+		ctx := context.WithoutCancel(r.Context())
+
+		webhook, target, export, ok := h.openTargetArchive(ctx, 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(
+			ctx,
+			downloadWriter{w: w, rc: http.NewResponseController(w)},
+			&webhook, target, now,
+		)
+		if err != nil {
+			h.log.Error(
+				"failed to export archive",
+				"target_id", target.ID,
+				"error", err,
+			)
+
+			// The 200 has gone out. Aborting the connection is what
+			// tells the client the file is incomplete.
+			panic(http.ErrAbortHandler)
+		}
+	}
+}
+
+// downloadWriter writes a download to the client, giving each write
+// downloadWriteTimeout to finish.
+type downloadWriter struct {
+	w  http.ResponseWriter
+	rc *http.ResponseController
+}
+
+func (d downloadWriter) Write(b []byte) (int, error) {
+	// A writer that has no write deadline, such as a test's recorder,
+	// answers http.ErrNotSupported and needs none extended.
+	err := d.rc.SetWriteDeadline(time.Now().Add(downloadWriteTimeout))
+	if err != nil && !errors.Is(err, http.ErrNotSupported) {
+		return 0, err
+	}
+
+	return d.w.Write(b)
+}
+
+// openTargetArchive opens the archive of the request's database target
+// for export, with its reads under ctx. 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(
+	ctx context.Context,
+	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(
+		ctx, delivery.ArchivePath(h.dbMgr, &webhook, target), h.log,
+	)
+	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 +1,328 @@
+package handlers_test
+
+import (
+	"compress/gzip"
+	"crypto/rand"
+	"encoding/json"
+	"errors"
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"net/url"
+	"sync"
+	"testing"
+	"time"
+
+	chimw "github.com/go-chi/chi/middleware"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"sneak.berlin/go/webhooker/internal/database"
+	"sneak.berlin/go/webhooker/internal/delivery"
+)
+
+// errClientGone is the write failure of a client that has gone away.
+var errClientGone = errors.New("client gone")
+
+// 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)
+}
+
+// seedArchive writes rows to the archive file at path, each with a
+// body of bodySize random bytes, which do not compress. Its table has
+// only the columns the test fills; an export writes the others empty.
+func seedArchive(t *testing.T, path string, rows, bodySize int) {
+	t.Helper()
+
+	db, err := database.OpenSQLite(path, database.SQLiteModeCreate)
+	require.NoError(t, err)
+
+	defer func() { require.NoError(t, db.Close()) }()
+
+	_, err = db.ExecContext(t.Context(),
+		"CREATE TABLE archived_events (id INTEGER PRIMARY KEY, body TEXT)",
+	)
+	require.NoError(t, err)
+
+	body := make([]byte, bodySize)
+
+	for range rows {
+		_, _ = rand.Read(body)
+
+		_, err = db.ExecContext(t.Context(),
+			"INSERT INTO archived_events (body) VALUES (?)", string(body),
+		)
+		require.NoError(t, err)
+	}
+}
+
+// TestHandleTargetDownload_OutlastsTheRequestLimit proves a download
+// runs for as long as the client keeps reading. Behind a request limit
+// and a server write timeout of a tenth of a second, the client stops
+// reading once the response has started, waits three times as long,
+// and still gets the whole file. The archive is larger than a
+// connection holds, so the download is still being written while the
+// client waits.
+func TestHandleTargetDownload_OutlastsTheRequestLimit(t *testing.T) {
+	t.Parallel()
+
+	const (
+		limit    = 100 * time.Millisecond
+		rows     = 12
+		bodySize = 1 << 20
+	)
+
+	env := setupSourceTest(t)
+	wh := seedWebhookWithRetention(t, env.db, 7)
+	archive := seedTarget(t, env.db, wh.ID, database.TargetTypeDatabase)
+	seedArchive(
+		t, delivery.ArchivePath(env.dbMgr, &wh, archive), rows, bodySize,
+	)
+
+	srv := httptest.NewUnstartedServer(
+		chimw.Timeout(limit)(targetRouter(env)),
+	)
+	srv.Config.WriteTimeout = limit
+	srv.Start()
+	t.Cleanup(srv.Close)
+
+	req, err := http.NewRequestWithContext(
+		t.Context(), http.MethodGet,
+		srv.URL+downloadPath(wh.ID, archive.ID), nil,
+	)
+	require.NoError(t, err)
+
+	for _, c := range env.cookies {
+		req.AddCookie(c)
+	}
+
+	resp, err := srv.Client().Do(req)
+	require.NoError(t, err)
+
+	defer func() { _ = resp.Body.Close() }()
+
+	require.Equal(t, http.StatusOK, resp.StatusCode)
+
+	time.Sleep(3 * limit)
+
+	zr, err := gzip.NewReader(resp.Body)
+	require.NoError(t, err)
+
+	var (
+		got    map[string]json.RawMessage
+		events []json.RawMessage
+	)
+
+	require.NoError(t, json.NewDecoder(zr).Decode(&got))
+	require.NoError(t, json.Unmarshal(got["archived_events"], &events))
+	assert.Len(t, events, rows)
+
+	// Reading to the end makes the gzip reader check that the file was
+	// finished.
+	_, err = io.ReadAll(zr)
+	require.NoError(t, err)
+}
+
+// brokenWriter is a response writer whose writes fail once the
+// response has started, as they do when the client goes away.
+type brokenWriter struct {
+	*httptest.ResponseRecorder
+}
+
+func (b brokenWriter) Write(p []byte) (int, error) {
+	if b.Body.Len() > 0 {
+		return 0, errClientGone
+	}
+
+	return b.ResponseRecorder.Write(p)
+}
+
+// TestHandleTargetDownload_AbortsWhenItFails proves a download that
+// fails after its response has started aborts the connection, so the
+// client sees a failed download rather than a file that looks
+// complete and does not decompress.
+func TestHandleTargetDownload_AbortsWhenItFails(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)
+	}
+
+	w := brokenWriter{ResponseRecorder: httptest.NewRecorder()}
+
+	assert.PanicsWithValue(t, http.ErrAbortHandler, func() {
+		targetRouter(env).ServeHTTP(w, req)
+	})
+	assert.Equal(t, http.StatusOK, w.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(),

internal/logfield/logfield_test.go

@@ -5,7 +5,6 @@ import (
 	"io"
 	"log/slog"
 	"strings"
-	"sync"
 	"testing"
 	"unicode/utf8"
 
@@ -19,11 +18,15 @@ import (
 // width.
 const budget = 64
 
-// batchRunes is how many consecutive code points the charge test logs
-// in one value from U+1000 up. Logging each of those on its own line
-// is too slow for the suite under the race detector; 4,096 at a time
-// is 271 batches, each logged on two lines, so 542 lines per handler.
-const batchRunes = 4096
+// sampleRunes is how many runes wide the values in the charge test
+// are. The handlers add a constant per field — a pair of quotes when
+// the value needs quoting — so the per-rune charge is only visible
+// once it is amortised over a run of them.
+const sampleRunes = 64
+
+// quotingSlack is that constant: the pair of quotes a handler adds to
+// a value that needs them and omits from one that does not.
+const quotingSlack = 2
 
 // newHandlers are the two handlers internal/logger can install. Time
 // is dropped so a line's width is a function of its value alone —
@@ -63,43 +66,46 @@ func renderedWidth(
 	return buf.Len()
 }
 
-// emittedBytes is what a handler writes for the runes of s alone: the
-// width of a line carrying s twice, less that of a line carrying it
-// once. Both values hold the same runes, so the text handler quotes
-// both or neither, and the quotes cancel along with everything else on
-// the line.
-func emittedBytes(
-	newHandler func(io.Writer) slog.Handler,
-	s string,
-) int {
-	return renderedWidth(newHandler, s+s) - renderedWidth(newHandler, s)
-}
+// chargeTestRunes is the set of code points the charge test measures:
+// every rune in the first two planes' worth of the BMP that the
+// handlers are most likely to treat specially, the separators that
+// only slog's JSON handler escapes, and a stratified sample across
+// the rest of Unicode so the astral charge is exercised on more than
+// one hand-picked rune.
+func chargeTestRunes() []rune {
+	const (
+		denseCeiling = 0x800
+		stride       = 1021
+		surrogateLo  = 0xD800
+		surrogateHi  = 0xDFFF
+	)
 
-// firstUndercharged returns the first rune in s that the handler
-// writes in more bytes than EncodedBytes charges for it, and how many
-// runes in s are undercharged that way. It measures one rune per line,
-// so the charge test calls it on the code points below U+1000, and from
-// there up only on a batch that has already failed, to name the code
-// points rather than just their range.
-func firstUndercharged(
-	newHandler func(io.Writer) slog.Handler,
-	s string,
-) (rune, int) {
-	first, count := rune(-1), 0
+	var runes []rune
 
-	for _, r := range s {
-		if emittedBytes(newHandler, string(r)) <= logfield.EncodedBytes(r) {
-			continue
+	keep := func(r rune) {
+		if r >= surrogateLo && r <= surrogateHi {
+			return
 		}
 
-		if count == 0 {
-			first = r
-		}
-
-		count++
+		runes = append(runes, r)
 	}
 
-	return first, count
+	for r := range rune(denseCeiling) {
+		keep(r)
+	}
+
+	for _, r := range []rune{
+		0x2028, 0x2029, 0x200B, 0x4E00, 0xE000, 0xFFFD,
+		0x1000C, 0x1F600, 0xE0001, 0x10FFFF,
+	} {
+		keep(r)
+	}
+
+	for r := rune(denseCeiling); r <= utf8.MaxRune; r += stride {
+		keep(r)
+	}
+
+	return runes
 }
 
 // TestEncodedBytes_ChargesAtLeastWhatTheHandlersEmit is the property
@@ -108,90 +114,33 @@ func firstUndercharged(
 // how a stated ceiling becomes false without any test noticing, so
 // the charge is measured against what the handlers actually write
 // rather than against the escaping rules as read.
-//
-// Every code point below U+1000 is checked on its own, for both
-// handlers. That range holds the quote, the backslash and the control
-// characters the handlers escape, next to code points each handler
-// writes in fewer bytes than their charge, which in a sum would cover
-// a neighbour charged too little.
-//
-// From U+1000 up the text handler writes every code point in exactly
-// its charge, so the rest of Unicode is checked batchRunes at a time:
-// each batch's summed charge must cover what the handler writes for
-// the whole batch. The sums there can miss the JSON handler alone
-// writing one code point in more bytes than its charge, when it writes
-// others in the same batch in fewer.
 func TestEncodedBytes_ChargesAtLeastWhatTheHandlersEmit(t *testing.T) {
 	t.Parallel()
 
-	var below strings.Builder
-	for r := range rune(0x1000) {
-		below.WriteRune(r)
-	}
-
-	var batches []string
-
-	for lo := rune(0x1000); lo <= utf8.MaxRune; lo += batchRunes {
-		var batch strings.Builder
-
-		for r := lo; r < lo+batchRunes; r++ {
-			// Surrogate halves are not runes a string can carry.
-			if utf8.ValidRune(r) {
-				batch.WriteRune(r)
-			}
-		}
-
-		batches = append(batches, batch.String())
-	}
-
-	// What EncodedBytes charges for each batch. Under -race -cover this
-	// takes longer than logging the batches, so it is worked out once,
-	// by whichever handler finishes logging first, while the other is
-	// still logging.
-	charged := sync.OnceValue(func() []int {
-		costs := make([]int, len(batches))
-
-		for i, batch := range batches {
-			for _, r := range batch {
-				costs[i] += logfield.EncodedBytes(r)
-			}
-		}
-
-		return costs
-	})
-
 	for name, newHandler := range newHandlers() {
 		t.Run(name, func(t *testing.T) {
 			t.Parallel()
 
-			if first, count := firstUndercharged(newHandler, below.String()); count > 0 {
-				t.Errorf(
-					"%d code points below U+1000 cost more than "+
-						"EncodedBytes charges, the first U+%04X",
-					count, first,
+			// 'a' is a printable ASCII rune, charged exactly one
+			// byte, so it is the zero point the other runes are
+			// measured against.
+			base := renderedWidth(
+				newHandler, strings.Repeat("a", sampleRunes),
+			)
+
+			for _, r := range chargeTestRunes() {
+				got := renderedWidth(
+					newHandler,
+					strings.Repeat(string(r), sampleRunes),
 				)
-			}
+				charged := sampleRunes *
+					(logfield.EncodedBytes(r) - 1)
 
-			emitted := make([]int, len(batches))
-			for i, batch := range batches {
-				emitted[i] = emittedBytes(newHandler, batch)
-			}
-
-			for i, cost := range charged() {
-				if emitted[i] <= cost {
-					continue
-				}
-
-				lo := rune(0x1000 + i*batchRunes)
-				first, count := firstUndercharged(
-					newHandler, batches[i],
-				)
-				t.Errorf(
-					"U+%04X to U+%04X emit %d bytes but are "+
-						"charged %d; %d of them cost more than "+
-						"EncodedBytes charges, the first U+%04X",
-					lo, lo+batchRunes-1, emitted[i], cost,
-					count, first,
+				require.LessOrEqual(
+					t, got-base, charged+quotingSlack,
+					"U+%04X costs more on the line than "+
+						"EncodedBytes charges for it",
+					r,
 				)
 			}
 		})

internal/server/archive_download_test.go

@@ -0,0 +1,69 @@
+package server_test
+
+import (
+	"compress/gzip"
+	"encoding/json"
+	"net/http"
+	"regexp"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"gorm.io/gorm/clause"
+	"sneak.berlin/go/webhooker/internal/database"
+)
+
+// TestHook_DownloadArchive follows the Download link the webhook page
+// shows for a database target, and only for it, and gets the archive
+// as a gzipped JSON file. Signed out, the link leads to the login page.
+func TestHook_DownloadArchive(t *testing.T) {
+	t.Parallel()
+
+	env := newTestEnv(t)
+
+	userID, _ := env.seedUser(t, "archivist", "somepassword")
+	cookies := env.authCookies(t, userID, "archivist")
+	wh := env.seedWebhook(t, userID)
+	env.seedTarget(t, wh.ID)
+
+	archive := &database.Target{
+		WebhookID: wh.ID,
+		Name:      "kept",
+		Type:      database.TargetTypeDatabase,
+		Active:    true,
+	}
+	require.NoError(t,
+		env.db.DB().Omit(clause.Associations).Create(archive).Error,
+	)
+
+	page := env.get("/hook/"+wh.ID, cookies)
+	require.Equal(t, http.StatusOK, page.Code)
+
+	links := regexp.MustCompile(
+		`href="(/hook/[^/"]+/targets/[^/"]+/download)"`,
+	).FindAllStringSubmatch(page.Body.String(), -1)
+	require.Len(t, links, 1, "only the database target has a Download")
+
+	link := links[0][1]
+	assert.Equal(t,
+		"/hook/"+wh.ID+"/targets/"+archive.ID+"/download", link,
+	)
+
+	w := env.get(link, cookies)
+	require.Equal(t, http.StatusOK, w.Code)
+	assert.Equal(t, "application/gzip", w.Header().Get("Content-Type"))
+
+	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":"`+wh.ID+`","name":"routed"}`, string(got["webhook"]),
+	)
+
+	w = env.get(link, nil)
+	assert.Equal(t, http.StatusSeeOther, w.Code)
+	assert.Contains(t, w.Header().Get("Location"), "/pages/login")
+}

internal/server/routes.go

@@ -312,6 +312,10 @@ func (s *Server) setupSourceRoutes() {
 			"/targets/{targetID}/edit",
 			s.h.HandleTargetEditSubmit(),
 		)
+		r.Get(
+			"/targets/{targetID}/download",
+			s.h.HandleTargetDownload(),
+		)
 		r.Post(
 			"/targets/{targetID}/delete",
 			s.h.HandleTargetDelete(),

templates/source_detail.html

@@ -157,6 +157,9 @@
                             {{else}}
                             <span class="badge-error">Inactive</span>
                             {{end}}
+                            {{if eq .Type "database"}}
+                            <a href="/hook/{{$.Webhook.ID}}/targets/{{.ID}}/download" class="text-xs text-gray-500 hover:text-primary-600" title="Download the archive as gzipped JSON">Download</a>
+                            {{end}}
                             <a href="/hook/{{$.Webhook.ID}}/targets/{{.ID}}/edit" class="text-xs text-gray-500 hover:text-primary-600" title="Edit">Edit</a>
                             <form method="POST" action="/hook/{{$.Webhook.ID}}/targets/{{.ID}}/toggle" class="inline">
                                 <input type="hidden" name="csrf_token" value="{{$.CSRFToken}}">