MFH: fixed #65045: mb_convert_encoding breaks well-formed character.

2 files changed, 38 insertions, 9 deletions

diff --git a/ext/mbstring/tests/bug65045.phpt b/ext/mbstring/tests/bug65045.phpt
new file mode 100644
index 0000000000..03a090ded2
--- /dev/null
+++ b/ext/mbstring/tests/bug65045.phpt
@@ -0,0 +1,29 @@
+--TEST--
+Bug #65045: mb_convert_encoding breaks well-formed character
+--SKIPIF--
+<?php extension_loaded('mbstring') or die('skip mbstring not available'); ?>
+--FILE--
+<?php
+
+//declare(encoding = 'UTF-8');
+mb_internal_encoding('UTF-8');
+
+$str = "\xF0\xA4\xAD".  "\xF0\xA4\xAD\xA2"."\xF0\xA4\xAD\xA2";
+$expected = "\xEF\xBF\xBD"."\xF0\xA4\xAD\xA2"."\xF0\xA4\xAD\xA2";
+
+$str2 = "\xF0\xA4\xAD\xA2"."\xF0\xA4\xAD\xA2"."\xF0\xA4\xAD";
+$expected2 = "\xF0\xA4\xAD\xA2"."\xF0\xA4\xAD\xA2"."\xEF\xBF\xBD";
+
+mb_substitute_character(0xFFFD);
+var_dump(
+    $expected === htmlspecialchars_decode(htmlspecialchars($str, ENT_SUBSTITUTE, 'UTF-8')),
+    $expected2 === htmlspecialchars_decode(htmlspecialchars($str2, ENT_SUBSTITUTE, 'UTF-8')), 
+    $expected === mb_convert_encoding($str, 'UTF-8', 'UTF-8'),
+    $expected2 === mb_convert_encoding($str2, 'UTF-8', 'UTF-8')
+);
+
+--EXPECT--
+bool(true)
+bool(true)
+bool(true)
+bool(true)
\ No newline at end of file
diff --git a/ext/mbstring/tests/illformed_utf_sequences.phpt b/ext/mbstring/tests/illformed_utf_sequences.phpt
index b5b9d94db8..378b956d68 100644
--- a/ext/mbstring/tests/illformed_utf_sequences.phpt
+++ b/ext/mbstring/tests/illformed_utf_sequences.phpt
@@ -25,28 +25,28 @@ var_dump(chk_enc("\x31\x32\x33", 0));
 var_dump(chk_enc("\x41\x42\x43", 0));
 var_dump(chk_enc("\xc0\xb1\xc0\xb2\xc0\xb3", 6));
 var_dump(chk_enc("\xc1\x81\xc1\x82\xc1\x83", 6));
-var_dump(chk_enc("\xe0\x80\xb1\xe0\x80\xb2\xe0\x80\xb3", 6));
-var_dump(chk_enc("\xe0\x81\x81\xe0\x81\x82\xe0\x81\x83", 6));
-var_dump(chk_enc("\xf0\x80\x80\xb1\xf0\x80\x80\xb2\xf0\x80\x80\xb3", 9));
-var_dump(chk_enc("\xf0\x80\x81\x81\xf0\x80\x81\x82\xf0\x81\x83", 8));
+var_dump(chk_enc("\xe0\x80\xb1\xe0\x80\xb2\xe0\x80\xb3", 9));
+var_dump(chk_enc("\xe0\x81\x81\xe0\x81\x82\xe0\x81\x83", 9));
+var_dump(chk_enc("\xf0\x80\x80\xb1\xf0\x80\x80\xb2\xf0\x80\x80\xb3", 12));
+var_dump(chk_enc("\xf0\x80\x81\x81\xf0\x80\x81\x82\xf0\x81\x83", 11));
 var_dump(chk_enc("\xf8\x80\x80\x80\xb1\xf8\x80\x80\x80\xb2\xf8\x80\x80\x80\xb3", 15));
 var_dump(chk_enc("\xf8\x80\x80\x81\x81\xf8\x80\x80\x81\x82\xf8\x80\x80\x81\x83", 15));
 var_dump(chk_enc("\xfc\x80\x80\x80\x80\xb1\xfc\x80\x80\x80\x80\xb2\xfc\x80\x80\x80\x80\xb3", 18));
 var_dump(chk_enc("\xfc\x80\x80\x80\x81\x81\xfc\x80\x80\x80\x81\x82\xfc\x80\x80\x80\x81\x83", 18));
 
 var_dump(chk_enc("\xc2\xa2\xc2\xa3\xc2\xa5", 0));
-var_dump(chk_enc("\xe0\x82\xa2\xe0\x82\xa3\xe0\x82\xa5", 6));
-var_dump(chk_enc("\xf0\x80\x82\xa2\xf0\x80\x82\xa3\xf0\x80\x82\xa5", 9));
+var_dump(chk_enc("\xe0\x82\xa2\xe0\x82\xa3\xe0\x82\xa5", 9));
+var_dump(chk_enc("\xf0\x80\x82\xa2\xf0\x80\x82\xa3\xf0\x80\x82\xa5", 12));
 var_dump(chk_enc("\xf8\x80\x80\x82\xa2\xf8\x80\x80\x82\xa3\xf8\x80\x80\x82\xa5", 15));
 var_dump(chk_enc("\xfc\x80\x80\x80\x82\xa2\xfc\x80\x80\x80\x82\xa3\xfc\x80\x80\x80\x82\xa5", 18));
 
 var_dump(chk_enc("\xc1\xbf", 2));
 var_dump(chk_enc("\xc2\x80", 0));
 var_dump(chk_enc("\xdf\xbf", 0));
-var_dump(chk_enc("\xe0\x9f\xff", 2));
+var_dump(chk_enc("\xe0\x9f\xff", 3));
 var_dump(chk_enc("\xe0\xa0\x80", 2));
 var_dump(chk_enc("\xef\xbf\xbf", 0));
-var_dump(chk_enc("\xf0\x8f\xbf\xbf", 3));
+var_dump(chk_enc("\xf0\x8f\xbf\xbf", 4));
 var_dump(chk_enc("\xf0\x90\x80\x80", 0));
 var_dump(chk_enc("\xf7\xbf\xbf\xbf", 4));
 var_dump(chk_enc("\xf8\x87\xbf\xbf\xbf", 5));
@@ -61,7 +61,7 @@ echo "UTF-8 and surrogates area\n";
 $out = '';
 $cnt = 0;
 for ($i = 0xd7ff; $i <= 0xe000; ++$i) {
-	$s = chk_enc(pack('C3', 0xe0 | ($i >> 12), 0x80 | ($i >> 6) & 0x3f, 0x80 | $i & 0x3f), 2);
+	$s = chk_enc(pack('C3', 0xe0 | ($i >> 12), 0x80 | ($i >> 6) & 0x3f, 0x80 | $i & 0x3f), 3);
 	if ($s === false) {
 		$cnt++;
 	} else {