Skip to content

fix: replace invalid utf-8 sequences in agent logs #13436

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jun 10, 2024
Merged

fix: replace invalid utf-8 sequences in agent logs #13436

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4328983
fix: replace invalid utf-8 sequences in agent logs
kylecarbs Jun 3, 2024
91aff2a
fix: replace invalid UTF-8 with ❌, add regression
spikecurtis Jun 7, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion codersdk/agentsdk/convert.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -348,7 +348,7 @@ func ProtoFromLog(log Log) (*proto.Log, error) {
}
return &proto.Log{
CreatedAt: timestamppb.New(log.CreatedAt),
Output: log.Output,
Output: strings.ToValidUTF8(log.Output, "❌"),
Level: proto.Log_Level(lvl),
}, nil
}
Expand Down
45 changes: 45 additions & 0 deletions codersdk/agentsdk/logs_internal_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -231,6 +231,51 @@ func TestLogSender_SkipHugeLog(t *testing.T) {
require.ErrorIs(t, err, context.Canceled)
}

func TestLogSender_InvalidUTF8(t *testing.T) {
t.Parallel()
testCtx := testutil.Context(t, testutil.WaitShort)
ctx, cancel := context.WithCancel(testCtx)
logger := slogtest.Make(t, nil).Leveled(slog.LevelDebug)
fDest := newFakeLogDest()
uut := NewLogSender(logger)

t0 := dbtime.Now()
ls1 := uuid.UUID{0x11}

uut.Enqueue(ls1,
Log{
CreatedAt: t0,
Output: "test log 0, src 1\xc3\x28",
Level: codersdk.LogLevelInfo,
},
Log{
CreatedAt: t0,
Output: "test log 1, src 1",
Level: codersdk.LogLevelInfo,
})

loopErr := make(chan error, 1)
go func() {
err := uut.SendLoop(ctx, fDest)
loopErr <- err
}()

req := testutil.RequireRecvCtx(ctx, t, fDest.reqs)
require.NotNil(t, req)
require.Len(t, req.Logs, 2, "it should sanitize invalid UTF-8, but still send")
// the 0xc3, 0x28 is an invalid 2-byte sequence in UTF-8. The sanitizer replaces 0xc3 with ❌, and then
// interprets 0x28 as a 1-byte sequence "("
require.Equal(t, "test log 0, src 1❌(", req.Logs[0].GetOutput())
require.Equal(t, proto.Log_INFO, req.Logs[0].GetLevel())
require.Equal(t, "test log 1, src 1", req.Logs[1].GetOutput())
require.Equal(t, proto.Log_INFO, req.Logs[1].GetLevel())
testutil.RequireSendCtx(ctx, t, fDest.resps, &proto.BatchCreateLogsResponse{})

cancel()
err := testutil.RequireRecvCtx(testCtx, t, loopErr)
require.ErrorIs(t, err, context.Canceled)
}

func TestLogSender_Batch(t *testing.T) {
t.Parallel()
testCtx := testutil.Context(t, testutil.WaitShort)
Expand Down
Loading