view release on metacpan or  search on metacpan

public/vendor/pagedown/Markdown.Converter.js  view on Meta::CPAN

        function _StripLinkDefinitions(text) {
            //
            // Strips link definitions from text, stores the URLs and titles in
            // hash references.
            //

            // Link defs are in the form: ^[id]: url "optional title"

            /*
            text = text.replace(/
                ^[ ]{0,3}\[(.+)\]:  // id = $1  attacklab: g_tab_width - 1
                [ \t]*
                \n?                 // maybe *one* newline
                [ \t]*
                <?(\S+?)>?          // url = $2
                (?=\s|$)            // lookahead for whitespace instead of the lookbehind removed below
                [ \t]*
                \n?                 // maybe one newline
                [ \t]*
                (                   // (potential) title = $3
                    (\n*)           // any lines skipped = $4 attacklab: lookbehind removed
                    [ \t]+
                    ["(]
                    (.+?)           // title = $5
                    [")]
                    [ \t]*
                )?                  // title is optional
                (?:\n+|$)
            /gm, function(){...});
            */

            text = text.replace(/^[ ]{0,3}\[(.+)\]:[ \t]*\n?[ \t]*<?(\S+?)>?(?=\s|$)[ \t]*\n?[ \t]*((\n*)["(](.+?)[")][ \t]*)?(?:\n+)/gm,
                function (wholeMatch, m1, m2, m3, m4, m5) {
                    m1 = m1.toLowerCase();
                    g_urls.set(m1, _EncodeAmpsAndAngles(m2));  // Link IDs are case-insensitive
                    if (m4) {
                        // Oops, found blank lines, so it's not a title.
                        // Put back the parenthetical statement we stole.
                        return m3;
                    } else if (m5) {
                        g_titles.set(m1, m5.replace(/"/g, "&quot;"));
                    }

                    // Completely remove the definition from the text
                    return "";
                }
            );

            return text;
        }

        function _HashHTMLBlocks(text) {

            // Hashify HTML blocks:
            // We only want to do this for block-level HTML tags, such as headers,
            // lists, and tables. That's because we still want to wrap <p>s around
            // "paragraphs" that are wrapped in non-block-level tags, such as anchors,
            // phrase emphasis, and spans. The list of tags we're looking for is
            // hard-coded:
            var block_tags_a = "p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math|ins|del"
            var block_tags_b = "p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math"

            // First, look for nested blocks, e.g.:
            //   <div>
            //     <div>
            //     tags for inner block must be indented.
            //     </div>
            //   </div>
            //
            // The outermost tags must start at the left margin for this to match, and
            // the inner nested divs must be indented.
            // We need to do this before the next, more liberal match, because the next
            // match will start at the first `<div>` and stop at the first `</div>`.

            // attacklab: This regex can be expensive when it fails.

            /*
            text = text.replace(/
                (                       // save in $1
                    ^                   // start of line  (with /m)
                    <($block_tags_a)    // start tag = $2
                    \b                  // word break
                                        // attacklab: hack around khtml/pcre bug...
                    [^\r]*?\n           // any number of lines, minimally matching
                    </\2>               // the matching end tag
                    [ \t]*              // trailing spaces/tabs
                    (?=\n+)             // followed by a newline
                )                       // attacklab: there are sentinel newlines at end of document
            /gm,function(){...}};
            */
            text = text.replace(/^(<(p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math|ins|del)\b[^\r]*?\n<\/\2>[ \t]*(?=\n+))/gm, hashElement);

            //
            // Now match more liberally, simply from `\n<tag>` to `</tag>\n`
            //

            /*
            text = text.replace(/
                (                       // save in $1
                    ^                   // start of line  (with /m)
                    <($block_tags_b)    // start tag = $2
                    \b                  // word break
                                        // attacklab: hack around khtml/pcre bug...
                    [^\r]*?             // any number of lines, minimally matching
                    .*</\2>             // the matching end tag
                    [ \t]*              // trailing spaces/tabs
                    (?=\n+)             // followed by a newline
                )                       // attacklab: there are sentinel newlines at end of document
            /gm,function(){...}};
            */
            text = text.replace(/^(<(p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math)\b[^\r]*?.*<\/\2>[ \t]*(?=\n+)\n)/gm, hashElement);

            // Special case just for <hr />. It was easier to make a special case than
            // to make the other regex more complicated.  

            /*
            text = text.replace(/
                \n                  // Starting after a blank line
                [ ]{0,3}
                (                   // save in $1
                    (<(hr)          // start tag = $2
                        \b          // word break
                        ([^<>])*?
                    \/?>)           // the matching end tag
                    [ \t]*
                    (?=\n{2,})      // followed by a blank line
                )
            /g,hashElement);
            */
            text = text.replace(/\n[ ]{0,3}((<(hr)\b([^<>])*?\/?>)[ \t]*(?=\n{2,}))/g, hashElement);

            // Special case for standalone HTML comments:

            /*
            text = text.replace(/
                \n\n                                            // Starting after a blank line
                [ ]{0,3}                                        // attacklab: g_tab_width - 1
                (                                               // save in $1
                    <!
                    (--(?:|(?:[^>-]|-[^>])(?:[^-]|-[^-])*)--)   // see http://www.w3.org/TR/html-markup/syntax.html#comments and http://meta.stackoverflow.com/q/95256
                    >
                    [ \t]*
                    (?=\n{2,})                                  // followed by a blank line
                )
            /g,hashElement);
            */
            text = text.replace(/\n\n[ ]{0,3}(<!(--(?:|(?:[^>-]|-[^>])(?:[^-]|-[^-])*)--)>[ \t]*(?=\n{2,}))/g, hashElement);

            // PHP and ASP-style processor instructions (<?...?> and <%...%>)

            /*
            text = text.replace(/
                (?:
                    \n\n            // Starting after a blank line
                )
                (                   // save in $1
                    [ ]{0,3}        // attacklab: g_tab_width - 1
                    (?:
                        <([?%])     // $2
                        [^\r]*?
                        \2>
                    )
                    [ \t]*
                    (?=\n{2,})      // followed by a blank line
                )
            /g,hashElement);
            */
            text = text.replace(/(?:\n\n)([ ]{0,3}(?:<([?%])[^\r]*?\2>)[ \t]*(?=\n{2,}))/g, hashElement);

            return text;
        }