webhooker/internal/handlers/event_log_view_test.go

package handlers_test

import (
	"net/http"
	"net/http/httptest"
	"strconv"
	"strings"
	"testing"
	"unicode/utf8"

	"github.com/stretchr/testify/assert"
	"github.com/stretchr/testify/require"
	"gorm.io/gorm/clause"
	"sneak.berlin/go/webhooker/internal/database"
	"sneak.berlin/go/webhooker/internal/handlers"
	"sneak.berlin/go/webhooker/internal/session"
)

// bodyCap is the number of body bytes the lists of events are
// allowed to render for one event.
const bodyCap = handlers.MaxRenderedBodyBytesForTest

// snowman is a three-byte rune, so a body of them straddles the
// byte-wise cut: bodyCap is not a multiple of three.
const snowman = "☃"

// seedEventWithBody records one event with the given body in the
// webhook's own database and returns it, so a caller that needs
// the generated event id can have it.
func seedEventWithBody(
	t *testing.T,
	dbMgr *database.WebhookDBManager,
	webhookID string,
	body string,
) *database.Event {
	t.Helper()

	webhookDB, err := dbMgr.GetDB(webhookID)
	require.NoError(t, err)

	event := &database.Event{
		WebhookID:   webhookID,
		Method:      http.MethodPost,
		Body:        body,
		ContentType: "application/octet-stream",
	}

	require.NoError(t, webhookDB.Omit(
		clause.Associations,
	).Create(event).Error)

	return event
}

// seedAndProject stores one body and returns the projection the
// event log page would be handed for it.
func seedAndProject(
	t *testing.T,
	body string,
) handlers.EventLogView {
	t.Helper()

	var (
		h     *handlers.Handlers
		sess  *session.Session
		db    *database.Database
		dbMgr *database.WebhookDBManager
	)

	app := newTestApp(t, &h, &sess, &db, &dbMgr)
	app.RequireStart()

	t.Cleanup(app.RequireStop)

	wh := seedWebhook(t, db)
	seedEventWithBody(t, dbMgr, wh.ID, body)

	views := h.LoadEventLogViewsForTest(
		httptest.NewRecorder(), *wh, 1,
	)
	require.Len(t, views, 1)

	return views[0]
}

// TestHandleSourceLogs_BoundsOversizeBody proves the rendered
// page is bounded by the cap rather than by the stored payload:
// the body here is 16 times the cap, and the ingest path would
// accept twice as much again.
func TestHandleSourceLogs_BoundsOversizeBody(t *testing.T) {
	t.Parallel()

	var (
		h     *handlers.Handlers
		sess  *session.Session
		db    *database.Database
		dbMgr *database.WebhookDBManager
	)

	app := newTestApp(t, &h, &sess, &db, &dbMgr)
	app.RequireStart()

	t.Cleanup(app.RequireStop)

	const (
		sentinel    = "TAIL-SENTINEL-1f4a9c"
		storedBytes = 512 * 1024
	)

	wh := seedWebhook(t, db)
	seedEventWithBody(
		t, dbMgr, wh.ID,
		strings.Repeat("A", storedBytes-len(sentinel))+sentinel,
	)

	page := renderSourceLogsPage(t, h, sess, wh.ID)

	// Nothing past the cap reaches the page, and the whole page
	// stays far below the stored body it is reporting on.
	assert.NotContains(t, page, sentinel)
	assert.Less(t, len(page), 4*bodyCap)

	// The marker states the true stored size, not the cut one.
	assert.Contains(
		t, page,
		"Showing the first "+strconv.Itoa(bodyCap)+
			" of "+strconv.Itoa(storedBytes)+" bytes",
	)
}

// TestHandleSourceLogs_SmallBodyRendersWhole guards the other
// side of the cap: a body under it is shown in full and carries
// no truncation marker.
func TestHandleSourceLogs_SmallBodyRendersWhole(t *testing.T) {
	t.Parallel()

	var (
		h     *handlers.Handlers
		sess  *session.Session
		db    *database.Database
		dbMgr *database.WebhookDBManager
	)

	app := newTestApp(t, &h, &sess, &db, &dbMgr)
	app.RequireStart()

	t.Cleanup(app.RequireStop)

	wh := seedWebhook(t, db)
	seedEventWithBody(t, dbMgr, wh.ID, `{"kept":"whole"}`)

	page := renderSourceLogsPage(t, h, sess, wh.ID)

	assert.Contains(t, page, ""kept"")
	assert.NotContains(t, page, "Showing the first")
}

// TestEventLogView_CutMidRune proves a multi-byte rune severed
// by the byte-wise cut is dropped rather than surfaced as a
// mojibake tail, which would also make the text look binary.
func TestEventLogView_CutMidRune(t *testing.T) {
	t.Parallel()

	body := strings.Repeat(snowman, bodyCap)
	view := seedAndProject(t, body)

	// bodyCap bytes hold bodyCap/3 whole snowmen and two bytes
	// of the next one; those two are dropped.
	whole := bodyCap / len(snowman)

	assert.True(t, view.Body.Cut)
	assert.False(t, view.Body.Binary)
	assert.Equal(t, int64(len(body)), view.Body.Size)
	assert.Equal(t, strings.Repeat(snowman, whole), view.Body.Text)
	assert.True(t, utf8.ValidString(view.Body.Text))
	assert.Equal(t, len(view.Body.Text), view.Body.ShownBytes)
	assert.LessOrEqual(t, view.Body.ShownBytes, bodyCap)
}

// TestEventLogView_BinaryBodyNotShown proves a body that is not
// text is left out rather than shown as replacement characters,
// whether it is cut or not.
func TestEventLogView_BinaryBodyNotShown(t *testing.T) {
	t.Parallel()

	raw := make([]byte, bodyCap+808)
	for i := range raw {
		// 0x80..0xBF: continuation bytes, never a rune start.
		raw[i] = 0x80 | byte(i%0x40)
	}

	for name, body := range map[string][]byte{
		"cut":   raw,
		"whole": raw[:2048],
		"NUL":   []byte("text\x00text"),
	} {
		t.Run(name, func(t *testing.T) {
			t.Parallel()

			view := seedAndProject(t, string(body))

			assert.True(t, view.Body.Binary)
			assert.Empty(t, view.Body.Text)
			assert.Equal(t, int64(len(body)), view.Body.Size)
		})
	}
}

// TestTrimPartialRune covers the distinction the cut repair
// turns on: an incomplete but valid sequence is dropped, while
// bytes that are merely invalid UTF-8 are left alone.
func TestTrimPartialRune(t *testing.T) {
	t.Parallel()

	cases := []struct {
		name string
		in   []byte
		want []byte
	}{{
		name: "complete ascii",
		in:   []byte("abc"),
		want: []byte("abc"),
	}, {
		name: "complete multibyte",
		in:   []byte("ab" + snowman),
		want: []byte("ab" + snowman),
	}, {
		name: "two byte rune cut",
		in:   []byte{'a', 0xC3},
		want: []byte{'a'},
	}, {
		name: "three byte rune cut after one",
		in:   []byte{'a', 0xE2},
		want: []byte{'a'},
	}, {
		name: "three byte rune cut after two",
		in:   []byte{'a', 0xE2, 0x98},
		want: []byte{'a'},
	}, {
		name: "four byte rune cut",
		in:   []byte{'a', 0xF0, 0x9F, 0x92}, // U+1F4A9 cut
		want: []byte{'a'},
	}, {
		name: "invalid start byte kept",
		in:   []byte{'a', 0xFF},
		want: []byte{'a', 0xFF},
	}, {
		name: "orphan continuation bytes kept",
		in:   []byte{0x80, 0x81, 0x82, 0x83, 0x84},
		want: []byte{0x80, 0x81, 0x82, 0x83, 0x84},
	}, {
		name: "truncated sequence followed by junk kept",
		in:   []byte{0xE2, 0x98, 0xFF},
		want: []byte{0xE2, 0x98, 0xFF},
	}, {
		name: "empty",
		in:   []byte{},
		want: []byte{},
	}}

	for _, tc := range cases {
		t.Run(tc.name, func(t *testing.T) {
			t.Parallel()

			assert.Equal(
				t, tc.want,
				handlers.TrimPartialRuneForTest(tc.in),
			)
		})
	}
}