perf(parse): cut allocations and validate UTF-8 in the scan

decode_test.go

@@ -24,19 +24,38 @@ func TestSyntaxErrorMessage(t *testing.T) {
 }
 
 func TestParseRejectsInvalidUTF8(t *testing.T) {
-	_, err := ParseMap([]byte("v = \"\xff\"\n"))
-	if err == nil {
-		t.Fatal("expected a UTF-8 validation error")
+	// The scan validates UTF-8 where it meets the byte, so the reported line
+	// is the invalid byte's own, wherever in the document it sits.
+	cases := []struct {
+		name string
+		doc  string
+		line int
+	}{
+		{"in a basic string", "v = \"\xff\"\n", 1},
+		{"in a literal string", "v = '\xff'\n", 1},
+		{"in a multiline string", "v = \"\"\"\n\xff\"\"\"\n", 2},
+		{"in a comment", "v = 1\n# caf\xe9\xff\n", 2},
+		{"in a bare key", "va\xfflue = 1\n", 1},
+		{"as a statement", "\xff = 1\n", 1},
+		{"in a bare value", "v = \xff1\n", 1},
+		{"after a value", "v = 1 \xff\n", 1},
+		{"after the first line", "a = 1\nb = \"\xff\"\n", 2},
 	}
-	se, ok := err.(*SyntaxError)
-	if !ok {
-		t.Fatalf("err is %T, want *SyntaxError", err)
-	}
-	if !strings.Contains(se.Msg, "UTF-8") {
-		t.Errorf("Msg = %q, want it to mention UTF-8", se.Msg)
-	}
-	if se.Line != 1 {
-		t.Errorf("Line = %d, want 1", se.Line)
+	for _, c := range cases {
+		_, err := ParseMap([]byte(c.doc))
+		if err == nil {
+			t.Fatalf("%s: expected a UTF-8 validation error", c.name)
+		}
+		se, ok := err.(*SyntaxError)
+		if !ok {
+			t.Fatalf("%s: err is %T, want *SyntaxError", c.name, err)
+		}
+		if !strings.Contains(se.Msg, "UTF-8") {
+			t.Errorf("%s: Msg = %q, want it to mention UTF-8", c.name, se.Msg)
+		}
+		if se.Line != c.line {
+			t.Errorf("%s: Line = %d, want %d", c.name, se.Line, c.line)
+		}
 	}
 }