$re = '/(?<sub_all>
(?:
(?<!\\\\)\~
(?<sub_text>
(?>\\\\[\~[:blank:]\h]|[^\~[:blank:]\h\v])*+
)
(?<!\\\\)\~
)
|
(?: # or the Microsoft way. Beurk
\<sub\>
(?<sub_text>
((?!\v).)+
)
\<\/sub\>
)
)/Jx';
$str = 'log~10~100 is 2.
Space is not allowed:
P~a cat~
But it\'s ok if it is escaped
P~a\\ cat~
Line break is a no-no, even escaped
P~a\\
cat~
Hmm <sub>This is a Microsoft subscript!</sub>
H~2~0
text~a\\ superscript~
';
preg_match_all($re, $str, $matches, PREG_SET_ORDER, 0);
// Print the entire match result
var_dump($matches);
Please keep in mind that these code samples are automatically generated and are not guaranteed to work. If you find any syntax errors, feel free to submit a bug report. For a full regex reference for PHP, please visit: http://php.net/manual/en/ref.pcre.php