fix(text): avoid breaking UTF-8 during truncation

Use rune-aware truncation for user-facing text and log previews so multibyte content is not corrupted in memory context, Telegram messages, or diagnostics.

internal/textutil/truncate.go

@@ -0,0 +1,52 @@
+package textutil
+
+import "unicode/utf8"
+
+// TruncateRunes returns s truncated to at most maxRunes Unicode code points.
+func TruncateRunes(s string, maxRunes int) string {
+	if maxRunes <= 0 || s == "" {
+		return ""
+	}
+	cut, truncated := byteIndexAfterRunes(s, maxRunes)
+	if !truncated {
+		return s
+	}
+	return s[:cut]
+}
+
+// TruncateRunesWithSuffix returns s truncated to at most maxRunes Unicode code
+// points, appending suffix when truncation occurs.
+func TruncateRunesWithSuffix(s string, maxRunes int, suffix string) string {
+	if maxRunes <= 0 || s == "" {
+		return ""
+	}
+	if _, truncated := byteIndexAfterRunes(s, maxRunes); !truncated {
+		return s
+	}
+	if suffix == "" {
+		return TruncateRunes(s, maxRunes)
+	}
+	suffixRunes := utf8.RuneCountInString(suffix)
+	if suffixRunes >= maxRunes {
+		return TruncateRunes(s, maxRunes)
+	}
+	cut, truncated := byteIndexAfterRunes(s, maxRunes-suffixRunes)
+	if !truncated {
+		return s
+	}
+	return s[:cut] + suffix
+}
+
+func byteIndexAfterRunes(s string, maxRunes int) (int, bool) {
+	if maxRunes <= 0 || s == "" {
+		return 0, len(s) > 0
+	}
+	count := 0
+	for i := range s {
+		if count == maxRunes {
+			return i, true
+		}
+		count++
+	}
+	return len(s), false
+}

internal/textutil/truncate_test.go

@@ -0,0 +1,55 @@
+package textutil
+
+import (
+	"strings"
+	"testing"
+	"unicode/utf8"
+)
+
+func TestTruncateRunes(t *testing.T) {
+	t.Parallel()
+
+	text := "你好世界"
+	got := TruncateRunes(text, 3)
+	if got != "你好世" {
+		t.Fatalf("TruncateRunes() = %q, want %q", got, "你好世")
+	}
+	if !utf8.ValidString(got) {
+		t.Fatalf("TruncateRunes() returned invalid UTF-8: %q", got)
+	}
+}
+
+func TestTruncateRunesWithSuffix(t *testing.T) {
+	t.Parallel()
+
+	text := strings.Repeat("你", 10) + "abc"
+	got := TruncateRunesWithSuffix(text, 8, "...")
+	if utf8.RuneCountInString(got) != 8 {
+		t.Fatalf("TruncateRunesWithSuffix() rune count = %d, want 8", utf8.RuneCountInString(got))
+	}
+	if got != strings.Repeat("你", 5)+"..." {
+		t.Fatalf("TruncateRunesWithSuffix() = %q", got)
+	}
+	if !utf8.ValidString(got) {
+		t.Fatalf("TruncateRunesWithSuffix() returned invalid UTF-8: %q", got)
+	}
+}
+
+func TestTruncateRunesWithSuffixNoTruncation(t *testing.T) {
+	t.Parallel()
+
+	text := "你好世界"
+	if got := TruncateRunesWithSuffix(text, 8, "..."); got != text {
+		t.Fatalf("TruncateRunesWithSuffix() = %q, want %q", got, text)
+	}
+}
+
+func TestTruncateRunesWithSuffixKeepsInvalidUTF8Bytes(t *testing.T) {
+	t.Parallel()
+
+	text := "ab\xffcd"
+	got := TruncateRunesWithSuffix(text, 4, "...")
+	if got != "a..." {
+		t.Fatalf("TruncateRunesWithSuffix() = %q, want %q", got, "a...")
+	}
+}