Make sure match is one character long

nikic · Apr 25, 2021 · ce91d13 · ce91d13
1 parent 33d7c8d
commit ce91d13
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 3 deletions.
diff --git a/lib/PhpParser/PrettyPrinter/Standard.php b/lib/PhpParser/PrettyPrinter/Standard.php
@@ -999,13 +999,13 @@ protected function escapeString($string, $quote) {
         }
 
         // Escape control characters and non-UTF-8 characters.
-        // Regex taken from https://stackoverflow.com/a/11709412/385378.
+        // Regex based on https://stackoverflow.com/a/11709412/385378.
         $regex = '/(
               [\x00-\x08\x0E-\x1F] # Control characters
             | [\xC0-\xC1] # Invalid UTF-8 Bytes
             | [\xF5-\xFF] # Invalid UTF-8 Bytes
-            | \xE0[\x80-\x9F] # Overlong encoding of prior code point
-            | \xF0[\x80-\x8F] # Overlong encoding of prior code point
+            | \xE0(?=[\x80-\x9F]) # Overlong encoding of prior code point
+            | \xF0(?=[\x80-\x8F]) # Overlong encoding of prior code point
             | [\xC2-\xDF](?![\x80-\xBF]) # Invalid UTF-8 Sequence Start
             | [\xE0-\xEF](?![\x80-\xBF]{2}) # Invalid UTF-8 Sequence Start
             | [\xF0-\xF4](?![\x80-\xBF]{3}) # Invalid UTF-8 Sequence Start
@@ -1016,6 +1016,7 @@ protected function escapeString($string, $quote) {
             | (?<=[\xF0-\xF4][\x80-\xBF])[\x80-\xBF](?![\x80-\xBF]) # Short 4 byte sequence (2)
         )/x';
         return preg_replace_callback($regex, function ($matches) {
+            assert(strlen($matches[0]) === 1);
             $hex = dechex(ord($matches[0]));;
             return '\\x' . str_pad($hex, 2, '0', \STR_PAD_LEFT);
         }, $escaped);

diff --git a/test/code/prettyPrinter/expr/stringEscaping.test b/test/code/prettyPrinter/expr/stringEscaping.test
@@ -7,6 +7,7 @@ Escape sequences in double-quoted strings
 "äöü";
 "\xc0\x80";
 "\xd0\x01";
+"\xf0\x80\x80";
 
 <<<DOC
 \n\r\t\f\v\$\"\\
@@ -22,6 +23,7 @@ DOC;
 "äöü";
 "\xc0\x80";
 "\xd0\x01";
+"\xf0\x80\x80";
 <<<DOC
 @@{ "\n\r" }@@\t\f\v\$\\"\\
 \x00\x01\x02\x03\x04\x05\x06\x07\x08\t@@{ "\n" }@@\v\f@@{ "\r" }@@\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f