[ruby/prism] Fix multibyte non-alphanumeric chars for bare percent string literals

Earlopain · matzbot · commit 29764156f6e0 · 2026-06-10T12:20:27.000Z
Alphanumerics are correctly handled in the check below by simply discarding the `%`. The same was not true for the other types, which caused some assumption to no longer hold. ruby/prism@69a9a36a6a
diff --git a/prism/prism.c b/prism/prism.c
@@ -11094,6 +11094,7 @@ parser_lex(pm_parser_t *parser) {
                         if (!parser->encoding->alnum_char(parser->current.end, parser->end - parser->current.end)) {
                             if (*parser->current.end >= 0x80) {
                                 pm_parser_err_current(parser, PM_ERR_INVALID_PERCENT);
+                                goto lex_next_token;
                             }
 
                             const uint8_t delimiter = pm_lex_percent_delimiter(parser);
diff --git a/test/prism/errors/alnum_delimiters_10.txt b/test/prism/errors/alnum_delimiters_10.txt
@@ -0,0 +1,4 @@
+%â
+^ unknown type of %string
+â
+
diff --git a/test/prism/errors/alnum_delimiters_11.txt b/test/prism/errors/alnum_delimiters_11.txt
@@ -0,0 +1,4 @@
+%💎
+^ unknown type of %string
+💎
+

Original file line number	Diff line number	Diff line change
`@@ -11094,6 +11094,7 @@ parser_lex(pm_parser_t *parser) {`
`11094`	`11094`	`if (!parser->encoding->alnum_char(parser->current.end, parser->end - parser->current.end)) {`
`11095`	`11095`	`if (*parser->current.end >= 0x80) {`
`11096`	`11096`	`pm_parser_err_current(parser, PM_ERR_INVALID_PERCENT);`
	`11097`	`+ goto lex_next_token;`
`11097`	`11098`	`}`
`11098`	`11099`
`11099`	`11100`	`const uint8_t delimiter = pm_lex_percent_delimiter(parser);`
-Original file line number
+Diff line change
@@ @@ -0,0 +1,4 @@ @@
 +%â
 +^ unknown type of %string
 +â
++