From d3933e0b6c6885a762ae2716f37bda595d4e9a33 Mon Sep 17 00:00:00 2001
From: Alex Dowad <alexinbeijing@gmail.com>
Date: Mon, 14 Nov 2022 11:02:21 +0200
Subject: [PATCH] Fix regression test for GH-9535 on PHP-8.2+

Some of the legacy text encodings which were used in this regression
test are deprecated in PHP-8.2+. The deprecation warnings break the
expected output. Since using these encodings in mbstring is now
deprecated, I think there is little point in keeping them in this test.
So they are now removed from it.

Further, in 219fff376b, I made a change to avoid a situation where the
legacy UTF7-IMAP conversion code gets stuck in a wrong state when its
attempt to emit a character fails. When a Base64-encoded section of
input ended with -, the previous code would FIRST emit a character if
necessary (using the CK or "check" macro, which causes the function to
return immediately if the downstream filter function returns an error
code), and THEN update its own state to indicate that it is now in
ASCII rather than Base64 mode.

If the downstream filter function returned an error code, the CK macro
would then cause the UTF7-IMAP filter function to return immediately
WITHOUT setting its own state to indicate that the Base64-encoded
section was done.

I fixed this by updating the filter state as needed BEFORE calling CK...
but I missed updating the filter state in the case where the Base64
section ends normally and there is no need to emit anything.

Again, in 6d525a425e, I modified the legacy conversion code for
ISO-2022-KR to try to comply more closely with the RFC for this
text encoding. The RFC states that before any occurrence of 'Shift In'
or 'Shift Out' codes in a ISO-2022-KR string, a special escape
sequence must appear at least ONCE, at the beginning of a line.
The previous code did not comply with this requirement. I made it
comply by always emitting this escape sequence at the beginning of
the first line.

Since mb_strcut (wrongly) determines when it has consumed enough of
the input string by looking at the length of its output in bytes, this
extra escape sequence makes mb_strcut consume 4 bytes less of an
ISO-2022-KR string than would otherwise be the case. When this
strange behavior of mb_strcut is fixed, this test will have to be
adjusted to restore the previous expected outputs for ISO-2022-KR.
---
 .../libmbfl/filters/mbfilter_utf7imap.c       |  3 +
 ext/mbstring/tests/gh9535.phpt                | 60 +++++++------------
 2 files changed, 24 insertions(+), 39 deletions(-)

diff --git a/ext/mbstring/libmbfl/filters/mbfilter_utf7imap.c b/ext/mbstring/libmbfl/filters/mbfilter_utf7imap.c
index 45722ce2c89..f3cbb87f2fd 100644
--- a/ext/mbstring/libmbfl/filters/mbfilter_utf7imap.c
+++ b/ext/mbstring/libmbfl/filters/mbfilter_utf7imap.c
@@ -147,6 +147,9 @@ int mbfl_filt_conv_utf7imap_wchar(int c, mbfl_convert_filter *filter)
 					 * or it could be that it ended on the first half of a surrogate pair */
 					filter->cache = filter->status = 0;
 					CK((*filter->output_function)(MBFL_BAD_INPUT, filter->data));
+				} else {
+					/* Base64-encoded section properly terminated by - */
+					filter->cache = filter->status = 0;
 				}
 			} else { /* illegal character */
 				filter->cache = filter->status = 0;
diff --git a/ext/mbstring/tests/gh9535.phpt b/ext/mbstring/tests/gh9535.phpt
index f22a473561a..9b491673731 100644
--- a/ext/mbstring/tests/gh9535.phpt
+++ b/ext/mbstring/tests/gh9535.phpt
@@ -5,9 +5,6 @@ mbstring
 --FILE--
 <?php
 $encodings = [
-	'BASE64',
-	'HTML-ENTITIES',
-	'Quoted-Printable',
     'UTF-16',
     'UTF-16BE',
     'UTF-16LE',
@@ -58,6 +55,8 @@ echo PHP_EOL;
 
 $input = 'AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA';
 $bytes_length = 10;
+// For ISO-2022-KR, the initial escape sequence 'ESC $ ) C' will occupy 4 bytes of the output;
+// this will make mb_strcut only pick out 6 'A' characters from the input string and not 10
 foreach($encodings as $encoding) {
     $converted_str = mb_convert_encoding($input, $encoding, mb_internal_encoding());
     $cut_str = mb_strcut($converted_str, 0, $bytes_length, $encoding);
@@ -69,24 +68,22 @@ echo PHP_EOL;
 
 $input = '???';
 $bytes_length = 2;
+// ISO-2022-KR will be affected by the initial escape sequence as stated above
 foreach($encodings as $encoding) {
     $converted_str = mb_convert_encoding($input, $encoding, mb_internal_encoding());
     $cut_str = mb_strcut($converted_str, 0, $bytes_length, $encoding);
     $reconverted_str = mb_convert_encoding($cut_str, mb_internal_encoding(), $encoding);
-    echo $encoding.': '.$reconverted_str.PHP_EOL;
+    echo $encoding.trim(': '.$reconverted_str).PHP_EOL;
 }
 
 echo PHP_EOL;
 
 foreach($encodings as $encoding) {
-    var_dump(mb_strcut($input, 0, $bytes_length, $encoding));
+    echo $encoding.trim(': '.mb_strcut($input, 0, $bytes_length, $encoding)).PHP_EOL;
 }
 
 ?>
---EXPECTF--
-BASE64: 宛如繁
-HTML-ENTITIES: 宛&#22914
-Quoted-Printable: %s
+--EXPECT--
 UTF-16: 宛如繁星般宛如
 UTF-16BE: 宛如繁星般宛如
 UTF-16LE: 宛如繁星般宛如
@@ -101,9 +98,6 @@ CP50220: 宛如繁星
 CP50221: 宛如繁星
 CP50222: 宛如繁星
 
-BASE64: 星のように
-HTML-ENTITIES: 星の&#12
-Quoted-Printable: 星の
 UTF-16: 星のように月のように
 UTF-16BE: 星のように月のように
 UTF-16LE: 星のように月のように
@@ -118,9 +112,6 @@ CP50220: 星のように月の
 CP50221: 星のように月の
 CP50222: 星のように月の
 
-BASE64: %s
-HTML-ENTITIES: あa&
-Quoted-Printable: あa
 UTF-16: あaいb
 UTF-16BE: あaいb
 UTF-16LE: あaいb
@@ -135,9 +126,6 @@ CP50220: あa
 CP50221: あa
 CP50222: あa
 
-BASE64: AAAAAA
-HTML-ENTITIES: AAAAAAAAAA
-Quoted-Printable: AAAAAAAAAA
 UTF-16: AAAAA
 UTF-16BE: AAAAA
 UTF-16LE: AAAAA
@@ -146,15 +134,12 @@ UTF7-IMAP: AAAAAAAAAA
 ISO-2022-JP-MS: AAAAAAAAAA
 GB18030: AAAAAAAAAA
 HZ: AAAAAAAAAA
-ISO-2022-KR: AAAAAAAAAA
+ISO-2022-KR: AAAAAA
 ISO-2022-JP-MOBILE#KDDI: AAAAAAAAAA
 CP50220: AAAAAAAAAA
 CP50221: AAAAAAAAAA
 CP50222: AAAAAAAAAA
 
-BASE64:%s
-HTML-ENTITIES: ??
-Quoted-Printable: ??
 UTF-16: ?
 UTF-16BE: ?
 UTF-16LE: ?
@@ -163,25 +148,22 @@ UTF7-IMAP: ??
 ISO-2022-JP-MS: ??
 GB18030: ??
 HZ: ??
-ISO-2022-KR: ??
+ISO-2022-KR:
 ISO-2022-JP-MOBILE#KDDI: ??
 CP50220: ??
 CP50221: ??
 CP50222: ??
 
-string(0) ""
-string(2) "??"
-string(2) "??"
-string(2) "??"
-string(2) "??"
-string(2) "??"
-string(2) "??"
-string(2) "??"
-string(2) "??"
-string(2) "??"
-string(2) "??"
-string(2) "??"
-string(2) "??"
-string(2) "??"
-string(2) "??"
-string(2) "??"
+UTF-16: ??
+UTF-16BE: ??
+UTF-16LE: ??
+UTF-7: ??
+UTF7-IMAP: ??
+ISO-2022-JP-MS: ??
+GB18030: ??
+HZ: ??
+ISO-2022-KR:
+ISO-2022-JP-MOBILE#KDDI: ??
+CP50220: ??
+CP50221: ??
+CP50222: ??