// include the latest version of the regex crate in your Cargo.toml
extern crate regex;
use regex::Regex;
fn main() {
let regex = Regex::new(r#"(?xsm)(?:(?<=\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]*
)
)
)"#).unwrap();
let string = "<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>
";
// result will be an iterator over tuples containing the start and end indices for each match in the string
let result = regex.captures_iter(string);
for mat in result {
println!("{:?}", mat);
}
}
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 Rust, please visit: https://docs.rs/regex/latest/regex/