use strict;
my $str = '<abbr title="`first backtick!">SB</abbr>
<abbr title="`second backtick!">SB</abbr>
<table>
<tr><td markdown="block">test _emphasis_ (block)</td></tr>
</table>
## More complicated
<table>
<tr><td markdown="1">
* this is _not_ a list item</td></tr>
<tr><td markdown="span">
* this is _not_ a list item</td></tr>
<tr><td markdown="block">
* this _is_ a list item
</td></tr>
</table>
';
my $regex = qr/(?:(?<=\n)|(?<=\A)) # Necessarily at the begining of a new line or start of string
(?<leading_space>[ ]{0,3})
(?<tag_all>
(?:
(?<div_open>
<(?<tag_name>\S+)
(?<tag_attributes>(?&tag_attr))*
[^\>]*
>\n*
)
(?<content>.+?)
\n*
(?<div_close>
(?(<leading_space>) # If leading spaces were found
(?:
(?<=\n)\g{leading_space} # Either there is a symmetry in leading space for open and closing tag
|
(?:(?<=\S)[[:blank:]\h]*) # or the closing tag is on the same line with preceding data
)
|
(?=<\/\g{tag_name}>) # No leading space, so we don't expect anything before the closing tag other than what has already been caught in the 'content'
)
<\/\g{tag_name}>
)
[[:blank:]\h]*\n
)
|
(?:
<!--[[:blank:]\h\v]*(?<html_comment>.*?)[[:blank:]\h\v]*-->
)
|
(?:
<
[[:blank:]\h\v]*
(?<tag_name>[a-zA-Z0-9][\w\-]+)
(?<tag_attributes>(?&tag_attr))*
[[:blank:]\h\v]*
\/?
[[:blank:]\h\v]*
>
)
)
(?(DEFINE)
(?<tag_attr>
(?:
[[:blank:]\h]*
[\w\-]+
[[:blank:]\h]*
=
[^\"\'[:blank]\h]+
[[:blank:]\h]*
)
|
(?:
[[:blank:]\h]*
[\w\-]+
[[:blank:]\h]*
=
[[:blank:]\h]*
(?<quote>["'])
(.*?)
\g{quote}
[[:blank:]\h]*
)
)
)/xsmp;
if ( $str =~ /$regex/g ) {
print "Whole match is ${^MATCH} and its start/end positions can be obtained via \$-[0] and \$+[0]\n";
# print "Capture Group 1 is $1 and its start/end positions can be obtained via \$-[1] and \$+[1]\n";
# print "Capture Group 2 is $2 ... and so on\n";
}
# ${^POSTMATCH} and ${^PREMATCH} are also available with the use of '/p'
# Named capture groups can be called via $+{name}
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 Perl, please visit: http://perldoc.perl.org/perlre.html