webhooker/internal/logfield/logfield_test.go

package logfield_test

import (
	"bytes"
	"log/slog"
	"strings"
	"testing"
	"unicode/utf8"

	"github.com/stretchr/testify/assert"
	"github.com/stretchr/testify/require"
	"sneak.berlin/go/webhooker/internal/logfield"
)

// encodedCost is what a whole string costs on a line, by the same
// accounting Truncate spends its budget with.
func encodedCost(s string) int {
	total := 0
	for _, r := range s {
		total += logfield.EncodedBytes(r)
	}

	return total
}

// TestTruncate_SpendsEncodedBytesNotRawBytes is the zero-headroom
// version of the line-length assertions elsewhere.
//
// A line ceiling has slack in it by construction, so a line-level
// assertion only catches a raw-byte budget for the fills with the
// widest multiplier. Here the budget is checked against exactly what
// it bought: a value built from a single rune must keep exactly
// MaxBytes/EncodedBytes(r) of them, for every rune, with nothing
// spare.
func TestTruncate_SpendsEncodedBytesNotRawBytes(t *testing.T) {
	t.Parallel()

	for name, r := range map[string]rune{
		"plain":                'x',
		"quote":                '"',
		"backslash":            '\\',
		"tab":                  '\t',
		"newline":              '\n',
		"carriage_return":      '\r',
		"c0_control":           '
',
		"del":                  '',
		"line_separator":       '
',
		"astral_nonprintable":  '\U0001000C',
		"multibyte_printable":  'é',
		"three_byte_printable": '€',
		"emoji_printable":      '\U0001F600',
	} {
		t.Run(name, func(t *testing.T) {
			t.Parallel()

			cost := logfield.EncodedBytes(r)
			want := logfield.MaxBytes / cost

			// Far past the budget under either accounting.
			in := strings.Repeat(string(r), logfield.MaxBytes*2)

			got := logfield.Truncate(in, logfield.MaxBytes)

			assert.True(
				t, strings.HasSuffix(got, "[truncated]"),
				"a value past the budget must be marked",
			)

			kept := strings.TrimSuffix(got, "[truncated]")

			assert.Equal(
				t, want, utf8.RuneCountInString(kept),
				"budget bought the wrong number of runes at "+
					"%d encoded bytes each", cost,
			)
			assert.LessOrEqual(
				t, encodedCost(kept), logfield.MaxBytes,
			)
		})
	}
}

// TestEncodedBytes_CoversWhatTheHandlersActuallyEmit measures the
// charge against what slog really writes rather than against a
// reading of its source, over both handlers internal/logger can
// install. An undercharged rune fails here rather than quietly
// falsifying every stated line ceiling.
func TestEncodedBytes_CoversWhatTheHandlersActuallyEmit(t *testing.T) {
	t.Parallel()

	emitted := func(h func(*bytes.Buffer) slog.Handler, r rune) int {
		var withValue, withoutValue bytes.Buffer

		slog.New(h(&withValue)).Info("m", "v", string(r))
		slog.New(h(&withoutValue)).Info("m", "v", "")

		return withValue.Len() - withoutValue.Len()
	}

	jsonHandler := func(b *bytes.Buffer) slog.Handler {
		return slog.NewJSONHandler(b, &slog.HandlerOptions{
			ReplaceAttr: dropTime,
		})
	}
	textHandler := func(b *bytes.Buffer) slog.Handler {
		return slog.NewTextHandler(b, &slog.HandlerOptions{
			ReplaceAttr: dropTime,
		})
	}

	// Every code point below U+0800 densely — which covers all of C0,
	// DEL, C1 and the two-byte range — plus the separators only the
	// JSON handler escapes, plus a stratified walk across the rest of
	// the assigned space and into the astral planes.
	var runes []rune

	for r := rune(1); r < 0x800; r++ {
		runes = append(runes, r)
	}

	runes = append(
		runes,
		'
',          // LINE SEPARATOR, escaped only by the JSON handler
		'
',          // PARAGRAPH SEPARATOR, likewise
		rune(0xFEFF), // ZERO WIDTH NO-BREAK SPACE
		rune(0xFFFD), // REPLACEMENT CHARACTER
	)

	for r := rune(0x800); r <= 0x10FFFF; r += 0x1D1 {
		runes = append(runes, r)
	}

	for _, r := range runes {
		if !utf8.ValidRune(r) {
			continue
		}

		charged := logfield.EncodedBytes(r)

		require.LessOrEqual(
			t, emitted(jsonHandler, r), charged,
			"json handler spends more than U+%04X is charged", r,
		)
		require.LessOrEqual(
			t, emitted(textHandler, r), charged,
			"text handler spends more than U+%04X is charged", r,
		)
	}
}

func dropTime(_ []string, a slog.Attr) slog.Attr {
	if a.Key == slog.TimeKey {
		return slog.Attr{}
	}

	return a
}

// TestTruncate_LeavesShortValuesAlone keeps the marker meaningful: a
// value that fits is returned untouched, so a reader can tell a short
// value from a cut one.
func TestTruncate_LeavesShortValuesAlone(t *testing.T) {
	t.Parallel()

	const in = "Mozilla/5.0 (X11; Linux x86_64)"

	assert.Equal(t, in, logfield.Truncate(in, logfield.MaxBytes))
}

// TestTruncate_DropsInvalidUTF8 covers a value that was never valid
// UTF-8 — a SQL parameter or a header can carry one. Replacing each
// bad byte would cost six encoded bytes apiece, so they are dropped.
func TestTruncate_DropsInvalidUTF8(t *testing.T) {
	t.Parallel()

	got := logfield.Truncate("a\xffb\xfec", logfield.MaxBytes)

	assert.Equal(t, "abc", got)
	assert.True(t, utf8.ValidString(got))
}

// TestTruncate_NeverSplitsARune covers a cut landing inside a
// multi-byte encoding.
func TestTruncate_NeverSplitsARune(t *testing.T) {
	t.Parallel()

	// A three-byte printable rune, so a small budget lands inside the
	// encoding rather than between two of them.
	in := strings.Repeat("€", logfield.MaxBytes)

	for budget := 1; budget <= 16; budget++ {
		got := strings.TrimSuffix(
			logfield.Truncate(in, budget), "[truncated]",
		)

		assert.True(
			t, utf8.ValidString(got),
			"budget %d produced invalid UTF-8", budget,
		)
		assert.LessOrEqual(t, encodedCost(got), budget)
	}
}