fix(util): rune-safe truncation across formatters

firstLineOf (query) and truncateString (edit) sliced strings at a raw byte
offset, splitting a multibyte UTF-8 character into invalid bytes in
LLM-facing output (ast_query compact format and edit not-found errors are
hot paths). Extract the rune-boundary backoff already used by search's
truncateLine into util.RuneBoundary and route all three sites through it.

Adds table-driven tests for the primitive and a multibyte case for firstLineOf.
This commit is contained in:
2026-06-20 00:44:38 +01:00
parent 549ec2a177
commit 3195e353e2
6 changed files with 64 additions and 8 deletions
+3
View File
@@ -186,6 +186,9 @@ func TestFirstLineOf(t *testing.T) {
{"line1\nline2", 20, "line1"},
{"\n\nfoo", 20, "foo"},
{"abcdefghij", 5, "abcd…"},
// Multibyte: "ααα" is 6 bytes (each α = 2). maxLen-1 = 3 lands inside the
// 2nd α; must back off to a rune boundary, never split into invalid UTF-8.
{"ααα", 4, "α…"},
}
for _, c := range cases {
got := firstLineOf(c.input, c.maxLen)
+1 -1
View File
@@ -583,7 +583,7 @@ func firstLineOf(s string, maxLen int) string {
continue
}
if len(line) > maxLen {
return line[:maxLen-1] + "…"
return line[:util.RuneBoundary(line, maxLen-1)] + "…"
}
return line
}