Ado

 view release on metacpan or  search on metacpan

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

        pluginHooks.addNoop("postConversion");

        //
        // Private state of the converter instance:
        //

        // Global hashes, used by various utility routines
        var g_urls;
        var g_titles;
        var g_html_blocks;

        // Used to track when we're inside an ordered or unordered list
        // (see _ProcessListItems() for details):
        var g_list_level;

        this.makeHtml = function (text) {

            //
            // Main function. The order in which other subs are called here is
            // essential. Link and image substitutions need to happen before
            // _EscapeSpecialCharsWithinTagAttributes(), so that any *'s or _'s in the <a>
            // and <img> tags get encoded.
            //

            // This will only happen if makeHtml on the same converter instance is called from a plugin hook.
            // Don't do that.
            if (g_urls)
                throw new Error("Recursive call to converter.makeHtml");
        
            // Create the private state objects.
            g_urls = new SaveHash();
            g_titles = new SaveHash();
            g_html_blocks = [];
            g_list_level = 0;

            text = pluginHooks.preConversion(text);

            // attacklab: Replace ~ with ~T
            // This lets us use tilde as an escape char to avoid md5 hashes
            // The choice of character is arbitray; anything that isn't
            // magic in Markdown will work.
            text = text.replace(/~/g, "~T");

            // attacklab: Replace $ with ~D
            // RegExp interprets $ as a special character
            // when it's in a replacement string
            text = text.replace(/\$/g, "~D");

            // Standardize line endings
            text = text.replace(/\r\n/g, "\n"); // DOS to Unix
            text = text.replace(/\r/g, "\n"); // Mac to Unix

            // Make sure text begins and ends with a couple of newlines:
            text = "\n\n" + text + "\n\n";

            // Convert all tabs to spaces.
            text = _Detab(text);

            // Strip any lines consisting only of spaces and tabs.
            // This makes subsequent regexen easier to write, because we can
            // match consecutive blank lines with /\n+/ instead of something
            // contorted like /[ \t]*\n+/ .
            text = text.replace(/^[ \t]+$/mg, "");
            
            text = pluginHooks.postNormalization(text);

            // Turn block-level HTML blocks into hash entries
            text = _HashHTMLBlocks(text);

            // Strip link definitions, store in hashes.
            text = _StripLinkDefinitions(text);

            text = _RunBlockGamut(text);

            text = _UnescapeSpecialChars(text);

            // attacklab: Restore dollar signs
            text = text.replace(/~D/g, "$$");

            // attacklab: Restore tildes
            text = text.replace(/~T/g, "~");

            text = pluginHooks.postConversion(text);

            g_html_blocks = g_titles = g_urls = null;

            return text;
        };

        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,

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

                    )
                )
            /g
            */
            var whole_list = /^(([ ]{0,3}([*+-]|\d+[.])[ \t]+)[^\r]+?(~0|\n{2,}(?=\S)(?![ \t]*(?:[*+-]|\d+[.])[ \t]+)))/gm;

            if (g_list_level) {
                text = text.replace(whole_list, function (wholeMatch, m1, m2) {
                    var list = m1;
                    var list_type = (m2.search(/[*+-]/g) > -1) ? "ul" : "ol";

                    var result = _ProcessListItems(list, list_type, isInsideParagraphlessListItem);

                    // Trim any trailing whitespace, to put the closing `</$list_type>`
                    // up on the preceding line, to get it past the current stupid
                    // HTML block parser. This is a hack to work around the terrible
                    // hack that is the HTML block parser.
                    result = result.replace(/\s+$/, "");
                    result = "<" + list_type + ">" + result + "</" + list_type + ">\n";
                    return result;
                });
            } else {
                whole_list = /(\n\n|^\n?)(([ ]{0,3}([*+-]|\d+[.])[ \t]+)[^\r]+?(~0|\n{2,}(?=\S)(?![ \t]*(?:[*+-]|\d+[.])[ \t]+)))/g;
                text = text.replace(whole_list, function (wholeMatch, m1, m2, m3) {
                    var runup = m1;
                    var list = m2;

                    var list_type = (m3.search(/[*+-]/g) > -1) ? "ul" : "ol";
                    var result = _ProcessListItems(list, list_type);
                    result = runup + "<" + list_type + ">\n" + result + "</" + list_type + ">\n";
                    return result;
                });
            }

            // attacklab: strip sentinel
            text = text.replace(/~0/, "");

            return text;
        }

        var _listItemMarkers = { ol: "\\d+[.]", ul: "[*+-]" };

        function _ProcessListItems(list_str, list_type, isInsideParagraphlessListItem) {
            //
            //  Process the contents of a single ordered or unordered list, splitting it
            //  into individual list items.
            //
            //  list_type is either "ul" or "ol".

            // The $g_list_level global keeps track of when we're inside a list.
            // Each time we enter a list, we increment it; when we leave a list,
            // we decrement. If it's zero, we're not in a list anymore.
            //
            // We do this because when we're not inside a list, we want to treat
            // something like this:
            //
            //    I recommend upgrading to version
            //    8. Oops, now this line is treated
            //    as a sub-list.
            //
            // As a single paragraph, despite the fact that the second line starts
            // with a digit-period-space sequence.
            //
            // Whereas when we're inside a list (or sub-list), that line will be
            // treated as the start of a sub-list. What a kludge, huh? This is
            // an aspect of Markdown's syntax that's hard to parse perfectly
            // without resorting to mind-reading. Perhaps the solution is to
            // change the syntax rules such that sub-lists must start with a
            // starting cardinal number; e.g. "1." or "a.".

            g_list_level++;

            // trim trailing blank lines:
            list_str = list_str.replace(/\n{2,}$/, "\n");

            // attacklab: add sentinel to emulate \z
            list_str += "~0";

            // In the original attacklab showdown, list_type was not given to this function, and anything
            // that matched /[*+-]|\d+[.]/ would just create the next <li>, causing this mismatch:
            //
            //  Markdown          rendered by WMD        rendered by MarkdownSharp
            //  ------------------------------------------------------------------
            //  1. first          1. first               1. first
            //  2. second         2. second              2. second
            //  - third           3. third                   * third
            //
            // We changed this to behave identical to MarkdownSharp. This is the constructed RegEx,
            // with {MARKER} being one of \d+[.] or [*+-], depending on list_type:
        
            /*
            list_str = list_str.replace(/
                (^[ \t]*)                       // leading whitespace = $1
                ({MARKER}) [ \t]+               // list marker = $2
                ([^\r]+?                        // list item text   = $3
                    (\n+)
                )
                (?=
                    (~0 | \2 ({MARKER}) [ \t]+)
                )
            /gm, function(){...});
            */

            var marker = _listItemMarkers[list_type];
            var re = new RegExp("(^[ \\t]*)(" + marker + ")[ \\t]+([^\\r]+?(\\n+))(?=(~0|\\1(" + marker + ")[ \\t]+))", "gm");
            var last_item_had_a_double_newline = false;
            list_str = list_str.replace(re,
                function (wholeMatch, m1, m2, m3) {
                    var item = m3;
                    var leading_space = m1;
                    var ends_with_double_newline = /\n\n$/.test(item);
                    var contains_double_newline = ends_with_double_newline || item.search(/\n{2,}/) > -1;

                    if (contains_double_newline || last_item_had_a_double_newline) {
                        item = _RunBlockGamut(_Outdent(item), /* doNotUnhash = */true);
                    }
                    else {
                        // Recursion for sub-lists:
                        item = _DoLists(_Outdent(item), /* isInsideParagraphlessListItem= */ true);
                        item = item.replace(/\n$/, ""); // chomp(item)
                        if (!isInsideParagraphlessListItem) // only the outer-most item should run this, otherwise it's run multiple times for the inner ones
                            item = _RunSpanGamut(item);
                    }
                    last_item_had_a_double_newline = ends_with_double_newline;
                    return "<li>" + item + "</li>\n";
                }
            );

            // attacklab: strip sentinel
            list_str = list_str.replace(/~0/g, "");

            g_list_level--;
            return list_str;
        }

        function _DoCodeBlocks(text) {
            //
            //  Process Markdown `<pre><code>` blocks.
            //  

            /*
            text = text.replace(/
                (?:\n\n|^)
                (                               // $1 = the code block -- one or more lines, starting with a space/tab
                    (?:
                        (?:[ ]{4}|\t)           // Lines must start with a tab or a tab-width of spaces - attacklab: g_tab_width
                        .*\n+
                    )+
                )
                (\n*[ ]{0,3}[^ \t\n]|(?=~0))    // attacklab: g_tab_width
            /g ,function(){...});
            */

            // attacklab: sentinel workarounds for lack of \A and \Z, safari\khtml bug
            text += "~0";

            text = text.replace(/(?:\n\n|^\n?)((?:(?:[ ]{4}|\t).*\n+)+)(\n*[ ]{0,3}[^ \t\n]|(?=~0))/g,
                function (wholeMatch, m1, m2) {
                    var codeblock = m1;
                    var nextChar = m2;

                    codeblock = _EncodeCode(_Outdent(codeblock));
                    codeblock = _Detab(codeblock);
                    codeblock = codeblock.replace(/^\n+/g, ""); // trim leading newlines
                    codeblock = codeblock.replace(/\n+$/g, ""); // trim trailing whitespace

                    codeblock = "<pre><code>" + codeblock + "\n</code></pre>";

                    return "\n\n" + codeblock + "\n\n" + nextChar;
                }
            );

            // attacklab: strip sentinel
            text = text.replace(/~0/, "");

            return text;
        }

        function hashBlock(text) {
            text = text.replace(/(^\n+|\n+$)/g, "");
            return "\n\n~K" + (g_html_blocks.push(text) - 1) + "K\n\n";
        }

        function _DoCodeSpans(text) {
            //
            // * Backtick quotes are used for <code></code> spans.
            // 
            // * You can use multiple backticks as the delimiters if you want to
            //   include literal backticks in the code span. So, this input:
            //     
            //      Just type ``foo `bar` baz`` at the prompt.
            //     
            //   Will translate to:
            //     
            //      <p>Just type <code>foo `bar` baz</code> at the prompt.</p>
            //     
            //   There's no arbitrary limit to the number of backticks you
            //   can use as delimters. If you need three consecutive backticks
            //   in your code, use four for delimiters, etc.
            //
            // * You can use spaces to get literal backticks at the edges:
            //     
            //      ... type `` `bar` `` ...
            //     
            //   Turns to:
            //     
            //      ... type <code>`bar`</code> ...
            //

            /*
            text = text.replace(/
                (^|[^\\])       // Character before opening ` can't be a backslash
                (`+)            // $2 = Opening run of `
                (               // $3 = The code block
                    [^\r]*?
                    [^`]        // attacklab: work around lack of lookbehind
                )
                \2              // Matching closer
                (?!`)
            /gm, function(){...});
            */

            text = text.replace(/(^|[^\\])(`+)([^\r]*?[^`])\2(?!`)/gm,
                function (wholeMatch, m1, m2, m3, m4) {
                    var c = m3;
                    c = c.replace(/^([ \t]*)/g, ""); // leading whitespace
                    c = c.replace(/[ \t]*$/g, ""); // trailing whitespace
                    c = _EncodeCode(c);
                    c = c.replace(/:\/\//g, "~P"); // to prevent auto-linking. Not necessary in code *blocks*, but in code spans. Will be converted back after the auto-linker runs.
                    return m1 + "<code>" + c + "</code>";
                }
            );

            return text;
        }

        function _EncodeCode(text) {
            //
            // Encode/escape certain characters inside Markdown code runs.
            // The point is that in code, these characters are literals,
            // and lose their special Markdown meanings.
            //
            // Encode all ampersands; HTML entities are not
            // entities within a Markdown code span.
            text = text.replace(/&/g, "&amp;");

            // Do the angle bracket song and dance:
            text = text.replace(/</g, "&lt;");
            text = text.replace(/>/g, "&gt;");

            // Now, escape characters that are magic in Markdown:
            text = escapeCharacters(text, "\*_{}[]\\", false);

            // jj the line above breaks this:
            //---

            //* Item

            //   1. Subitem

            //            special char: *
            //---

            return text;
        }

        function _DoItalicsAndBold(text) {

            // <strong> must go first:
            text = text.replace(/([\W_]|^)(\*\*|__)(?=\S)([^\r]*?\S[\*_]*)\2([\W_]|$)/g,
            "$1<strong>$3</strong>$4");

            text = text.replace(/([\W_]|^)(\*|_)(?=\S)([^\r\*_]*?\S)\2([\W_]|$)/g,
            "$1<em>$3</em>$4");

            return text;
        }

        function _DoBlockQuotes(text) {

            /*
            text = text.replace(/
                (                           // Wrap whole match in $1
                    (
                        ^[ \t]*>[ \t]?      // '>' at the start of a line
                        .+\n                // rest of the first line
                        (.+\n)*             // subsequent consecutive lines
                        \n*                 // blanks
                    )+
                )
            /gm, function(){...});
            */

            text = text.replace(/((^[ \t]*>[ \t]?.+\n(.+\n)*\n*)+)/gm,
                function (wholeMatch, m1) {
                    var bq = m1;

                    // attacklab: hack around Konqueror 3.5.4 bug:
                    // "----------bug".replace(/^-/g,"") == "bug"

                    bq = bq.replace(/^[ \t]*>[ \t]?/gm, "~0"); // trim one level of quoting

                    // attacklab: clean up hack
                    bq = bq.replace(/~0/g, "");

                    bq = bq.replace(/^[ \t]+$/gm, "");     // trim whitespace-only lines
                    bq = _RunBlockGamut(bq);             // recurse

                    bq = bq.replace(/(^|\n)/g, "$1  ");
                    // These leading spaces screw with <pre> content, so we need to fix that:
                    bq = bq.replace(
                            /(\s*<pre>[^\r]+?<\/pre>)/gm,
                        function (wholeMatch, m1) {
                            var pre = m1;
                            // attacklab: hack around Konqueror 3.5.4 bug:
                            pre = pre.replace(/^  /mg, "~0");
                            pre = pre.replace(/~0/g, "");
                            return pre;
                        });

                    return hashBlock("<blockquote>\n" + bq + "\n</blockquote>");
                }
            );
            return text;
        }

        function _FormParagraphs(text, doNotUnhash) {
            //
            //  Params:
            //    $text - string to process with html <p> tags
            //

            // Strip leading and trailing lines:
            text = text.replace(/^\n+/g, "");
            text = text.replace(/\n+$/g, "");

            var grafs = text.split(/\n{2,}/g);
            var grafsOut = [];
            
            var markerRe = /~K(\d+)K/;

            //
            // Wrap <p> tags.
            //
            var end = grafs.length;
            for (var i = 0; i < end; i++) {
                var str = grafs[i];



( run in 0.547 second using v1.01-cache-2.11-cpan-6aa56a78535 )