public
Last active

Showdown.as: An AS3 port of John Fraser's showdown.js

  • Download Gist
Showdown.as
ActionScript
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231
// UPDATE: For latest code, see https://github.com/cstrahan/Showdown.as
//
// Showdown.as -- An ActionScript port of showdown.js
//
// Copyright (c) 2010 Charles Strahan.
//
// Original Showdown Copyright (c) 2007 John Fraser.
// <http://attacklab.net/showdown/>
//
// Original Markdown Copyright (c) 2004-2005 John Gruber
// <http://daringfireball.net/projects/markdown/>
//
// Redistributable under a BSD-style open source license.
// See license.txt for more information.
//
// Usage:
//
// var text = "Markdown *rocks*.";
// var html = Showdown.makeHtml(text);
//
 
package {
 
public class Showdown
{
// Global hashes, used by various utility routines
private static var g_urls:Array;
private static var g_titles:Array;
private static var g_html_blocks:Array;
// Used to track when we're inside an ordered or unordered list
// (see _ProcessListItems() for details):
private static var g_list_level:Number = 0;
public static function makeHtml(text:String)
{
// Clear the global hashes. If we don't clear these, you get conflicts
// from other articles when generating a page which contains more than
// one article (e.g. an index page that shows the N most recent
// articles):
g_urls = new Array();
g_titles = new Array();
g_html_blocks = new Array();
// 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,"");
// 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,"~");
return text;
}
private static 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"
/*
var text = text.replace(/
^[ ]{0,3}\[(.+)\]: // id = $1 attacklab: g_tab_width - 1
[ \t]*
\n? // maybe *one* newline
[ \t]*
<?(\S+?)>? // url = $2
[ \t]*
\n? // maybe one newline
[ \t]*
(?:
(\n*) // any lines skipped = $3 attacklab: lookbehind removed
["(]
(.+?) // title = $4
[")]
[ \t]*
)? // title is optional
(?:\n+|$)
/gm,
function(){...});
*/
var text = text.replace(/^[ ]{0,3}\[(.+)\]:[ \t]*\n?[ \t]*<?(\S+?)>?[ \t]*\n?[ \t]*(?:(\n*)["(](.+?)[")][ \t]*)?(?:\n+|\Z)/gm,
function (wholeMatch,m1,m2,m3,m4) {
m1 = m1.toLowerCase();
g_urls[m1] = _EncodeAmpsAndAngles(m2); // Link IDs are case-insensitive
if (m3) {
// Oops, found blank lines, so it's not a title.
// Put back the parenthetical statement we stole.
return m3+m4;
} else if (m4) {
g_titles[m1] = m4.replace(/"/g,"&quot;");
}
// Completely remove the definition from the text
return "";
}
);
return text;
}
private static function _HashHTMLBlocks(text) {
// attacklab: Double up blank lines to reduce lookaround
text = text.replace(/\n/g,"\n\n");
// 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.
/*
var 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`
//
/*
var 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(/
( // save in $1
\n\n // Starting after a blank line
[ ]{0,3}
(<(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(/
( // save in $1
\n\n // Starting after a blank line
[ ]{0,3} // attacklab: g_tab_width - 1
<!
(--[^\r]*?--\s*)+
>
[ \t]*
(?=\n{2,}) // followed by a blank line
)
/g,hashElement);
*/
text = text.replace(/(\n\n[ ]{0,3}<!(--[^\r]*?--\s*)+>[ \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
(?:
<([?%]) // $2
[^\r]*?
\2>
)
[ \t]*
(?=\n{2,}) // followed by a blank line
)
/g,hashElement);
*/
text = text.replace(/(?:\n\n)([ ]{0,3}(?:<([?%])[^\r]*?\2>)[ \t]*(?=\n{2,}))/g,hashElement);
// attacklab: Undo double lines (see comment at top of this function)
text = text.replace(/\n\n/g,"\n");
return text;
}
private static function hashElement(wholeMatch,m1) {
var blockText = m1;
// Undo double lines
blockText = blockText.replace(/\n\n/g,"\n");
blockText = blockText.replace(/^\n/,"");
// strip trailing blank lines
blockText = blockText.replace(/\n+$/g,"");
// Replace the element text with a marker ("~KxK" where x is its key)
blockText = "\n\n~K" + (g_html_blocks.push(blockText)-1) + "K\n\n";
return blockText;
};
private static function _RunBlockGamut(text) {
//
// These are all the transformations that form block-level
// tags like paragraphs, headers, and list items.
//
text = _DoHeaders(text);
// Do Horizontal Rules:
var key = hashBlock("<hr />");
text = text.replace(/^[ ]{0,2}([ ]?\*[ ]?){3,}[ \t]*$/gm,key);
text = text.replace(/^[ ]{0,2}([ ]?\-[ ]?){3,}[ \t]*$/gm,key);
text = text.replace(/^[ ]{0,2}([ ]?\_[ ]?){3,}[ \t]*$/gm,key);
text = _DoLists(text);
text = _DoCodeBlocks(text);
text = _DoBlockQuotes(text);
// We already ran _HashHTMLBlocks() before, in Markdown(), but that
// was to escape raw HTML in the original Markdown source. This time,
// we're escaping the markup we've just created, so that we don't wrap
// <p> tags around block-level tags.
text = _HashHTMLBlocks(text);
text = _FormParagraphs(text);
return text;
}
private static function _RunSpanGamut(text) {
//
// These are all the transformations that occur *within* block-level
// tags like paragraphs, headers, and list items.
//
text = _DoCodeSpans(text);
text = _EscapeSpecialCharsWithinTagAttributes(text);
text = _EncodeBackslashEscapes(text);
// Process anchor and image tags. Images must come first,
// because ![foo][f] looks like an anchor.
text = _DoImages(text);
text = _DoAnchors(text);
// Make links out of things like `<http://example.com/>`
// Must come after _DoAnchors(), because you can use < and >
// delimiters in inline links like [this](<url>).
text = _DoAutoLinks(text);
text = _EncodeAmpsAndAngles(text);
text = _DoItalicsAndBold(text);
// Do hard breaks:
text = text.replace(/ +\n/g," <br />\n");
return text;
}
private static function _EscapeSpecialCharsWithinTagAttributes(text) {
//
// Within tags -- meaning between < and > -- encode [\ ` * _] so they
// don't conflict with their use in Markdown for code, italics and strong.
//
// Build a regex to find HTML tags and comments. See Friedl's
// "Mastering Regular Expressions", 2nd Ed., pp. 200-201.
var regex = /(<[a-z\/!$]("[^"]*"|'[^']*'|[^'">])*>|<!(--.*?--\s*)+>)/gi;
text = text.replace(regex, function(wholeMatch) {
var tag = wholeMatch.replace(/(.)<\/?code>(?=.)/g,"$1`");
tag = escapeCharacters(tag,"\\`*_");
return tag;
});
return text;
}
private static function _DoAnchors(text) {
//
// Turn Markdown link shortcuts into XHTML <a> tags.
//
//
// First, handle reference-style links: [link text] [id]
//
/*
text = text.replace(/
( // wrap whole match in $1
\[
(
(?:
\[[^\]]*\] // allow brackets nested one level
|
[^\[] // or anything else
)*
)
\]
[ ]? // one optional space
(?:\n[ ]*)? // one optional newline followed by spaces
\[
(.*?) // id = $3
\]
)()()()() // pad remaining backreferences
/g,_DoAnchors_callback);
*/
text = text.replace(/(\[((?:\[[^\]]*\]|[^\[\]])*)\][ ]?(?:\n[ ]*)?\[(.*?)\])()()()()/g,writeAnchorTag);
//
// Next, inline-style links: [link text](url "optional title")
//
/*
text = text.replace(/
( // wrap whole match in $1
\[
(
(?:
\[[^\]]*\] // allow brackets nested one level
|
[^\[\]] // or anything else
)
)
\]
\( // literal paren
[ \t]*
() // no id, so leave $3 empty
<?(.*?)>? // href = $4
[ \t]*
( // $5
(['"]) // quote char = $6
(.*?) // Title = $7
\6 // matching quote
[ \t]* // ignore any spaces/tabs between closing quote and )
)? // title is optional
\)
)
/g,writeAnchorTag);
*/
text = text.replace(/(\[((?:\[[^\]]*\]|[^\[\]])*)\]\([ \t]*()<?(.*?)>?[ \t]*((['"])(.*?)\6[ \t]*)?\))/g,writeAnchorTag);
//
// Last, handle reference-style shortcuts: [link text]
// These must come last in case you've also got [link test][1]
// or [link test](/foo)
//
/*
text = text.replace(/
( // wrap whole match in $1
\[
([^\[\]]+) // link text = $2; can't contain '[' or ']'
\]
)()()()()() // pad rest of backreferences
/g, writeAnchorTag);
*/
text = text.replace(/(\[([^\[\]]+)\])()()()()()/g, writeAnchorTag);
return text;
}
private static function writeAnchorTag(wholeMatch,m1,m2,m3,m4,m5,m6,m7) {
if (m7 == undefined) m7 = "";
var whole_match = m1;
var link_text = m2;
var link_id = m3.toLowerCase();
var url = m4;
var title = m7;
if (url == "") {
if (link_id == "") {
// lower-case and turn embedded newlines into spaces
link_id = link_text.toLowerCase().replace(/ ?\n/g," ");
}
url = "#"+link_id;
if (g_urls[link_id] != undefined) {
url = g_urls[link_id];
if (g_titles[link_id] != undefined) {
title = g_titles[link_id];
}
}
else {
if (whole_match.search(/\(\s*\)$/m)>-1) {
// Special case for explicit empty url
url = "";
} else {
return whole_match;
}
}
}
url = escapeCharacters(url,"*_");
var result = "<a href=\"" + url + "\"";
if (title != "") {
title = title.replace(/"/g,"&quot;");
title = escapeCharacters(title,"*_");
result += " title=\"" + title + "\"";
}
result += ">" + link_text + "</a>";
return result;
}
private static function _DoImages(text) {
//
// Turn Markdown image shortcuts into <img> tags.
//
//
// First, handle reference-style labeled images: ![alt text][id]
//
/*
text = text.replace(/
( // wrap whole match in $1
!\[
(.*?) // alt text = $2
\]
[ ]? // one optional space
(?:\n[ ]*)? // one optional newline followed by spaces
\[
(.*?) // id = $3
\]
)()()()() // pad rest of backreferences
/g,writeImageTag);
*/
text = text.replace(/(!\[(.*?)\][ ]?(?:\n[ ]*)?\[(.*?)\])()()()()/g,writeImageTag);
//
// Next, handle inline images: ![alt text](url "optional title")
// Don't forget: encode * and _
/*
text = text.replace(/
( // wrap whole match in $1
!\[
(.*?) // alt text = $2
\]
\s? // One optional whitespace character
\( // literal paren
[ \t]*
() // no id, so leave $3 empty
<?(\S+?)>? // src url = $4
[ \t]*
( // $5
(['"]) // quote char = $6
(.*?) // title = $7
\6 // matching quote
[ \t]*
)? // title is optional
\)
)
/g,writeImageTag);
*/
text = text.replace(/(!\[(.*?)\]\s?\([ \t]*()<?(\S+?)>?[ \t]*((['"])(.*?)\6[ \t]*)?\))/g,writeImageTag);
return text;
}
private static function writeImageTag(wholeMatch,m1,m2,m3,m4,m5,m6,m7) {
var whole_match = m1;
var alt_text = m2;
var link_id = m3.toLowerCase();
var url = m4;
var title = m7;
if (!title) title = "";
if (url == "") {
if (link_id == "") {
// lower-case and turn embedded newlines into spaces
link_id = alt_text.toLowerCase().replace(/ ?\n/g," ");
}
url = "#"+link_id;
if (g_urls[link_id] != undefined) {
url = g_urls[link_id];
if (g_titles[link_id] != undefined) {
title = g_titles[link_id];
}
}
else {
return whole_match;
}
}
alt_text = alt_text.replace(/"/g,"&quot;");
url = escapeCharacters(url,"*_");
var result = "<img src=\"" + url + "\" alt=\"" + alt_text + "\"";
// attacklab: Markdown.pl adds empty title attributes to images.
// Replicate this bug.
//if (title != "") {
title = title.replace(/"/g,"&quot;");
title = escapeCharacters(title,"*_");
result += " title=\"" + title + "\"";
//}
result += " />";
return result;
}
private static function _DoHeaders(text:String) {
// Setext-style headers:
// Header 1
// ========
//
// Header 2
// --------
//
text = text.replace(/^(.+)[ \t]*\n=+[ \t]*\n+/gm,
function(wholeMatch,m1){return hashBlock("<h1>" + _RunSpanGamut(m1) + "</h1>");});
text = text.replace(/^(.+)[ \t]*\n-+[ \t]*\n+/gm,
function(matchFound,m1){return hashBlock("<h2>" + _RunSpanGamut(m1) + "</h2>");});
// atx-style headers:
// # Header 1
// ## Header 2
// ## Header 2 with closing hashes ##
// ...
// ###### Header 6
//
/*
text = text.replace(/
^(\#{1,6}) // $1 = string of #'s
[ \t]*
(.+?) // $2 = Header text
[ \t]*
\#* // optional closing #'s (not counted)
\n+
/gm, function() {...});
*/
text = text.replace(/^(\#{1,6})[ \t]*(.+?)[ \t]*\#*\n+/gm,
function(wholeMatch,m1,m2) {
var h_level = m1.length;
return hashBlock("<h" + h_level + ">" + _RunSpanGamut(m2) + "</h" + h_level + ">");
});
return text;
}
private static function _DoLists(text) {
//
// Form HTML ordered (numbered) and unordered (bulleted) lists.
//
// attacklab: add sentinel to hack around khtml/safari bug:
// http://bugs.webkit.org/show_bug.cgi?id=11231
text += "~0";
// Re-usable pattern to match any entirel ul or ol list:
/*
var whole_list = /
( // $1 = whole list
( // $2
[ ]{0,3} // attacklab: g_tab_width - 1
([*+-]|\d+[.]) // $3 = first list item marker
[ \t]+
)
[^\r]+?
( // $4
~0 // sentinel for workaround; should be $
|
\n{2,}
(?=\S)
(?! // Negative lookahead for another list item marker
[ \t]*
(?:[*+-]|\d+[.])[ \t]+
)
)
)/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";
// Turn double returns into triple returns, so that we can make a
// paragraph for the last item in a list, if necessary:
list = list.replace(/\n{2,}/g,"\n\n\n");;
var result = _ProcessListItems(list);
// 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";
// Turn double returns into triple returns, so that we can make a
// paragraph for the last item in a list, if necessary:
var list = list.replace(/\n{2,}/g,"\n\n\n");;
var result = _ProcessListItems(list);
result = runup + "<"+list_type+">\n" + result + "</"+list_type+">\n";
return result;
});
}
// attacklab: strip sentinel
text = text.replace(/~0/,"");
return text;
}
private static function _ProcessListItems(list_str) {
//
// Process the contents of a single ordered or unordered list, splitting it
// into individual list items.
//
// 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";
/*
list_str = list_str.replace(/
(\n)? // leading line = $1
(^[ \t]*) // leading whitespace = $2
([*+-]|\d+[.]) [ \t]+ // list marker = $3
([^\r]+? // list item text = $4
(\n{1,2}))
(?= \n* (~0 | \2 ([*+-]|\d+[.]) [ \t]+))
/gm, function(){...});
*/
list_str = list_str.replace(/(\n)?(^[ \t]*)([*+-]|\d+[.])[ \t]+([^\r]+?(\n{1,2}))(?=\n*(~0|\2([*+-]|\d+[.])[ \t]+))/gm,
function(wholeMatch,m1,m2,m3,m4){
var item = m4;
var leading_line = m1;
var leading_space = m2;
if (leading_line || (item.search(/\n{2,}/)>-1)) {
item = _RunBlockGamut(_Outdent(item));
}
else {
// Recursion for sub-lists:
item = _DoLists(_Outdent(item));
item = item.replace(/\n$/,""); // chomp(item)
item = _RunSpanGamut(item);
}
return "<li>" + item + "</li>\n";
}
);
// attacklab: strip sentinel
list_str = list_str.replace(/~0/g,"");
g_list_level--;
return list_str;
}
private static function _DoCodeBlocks(text:String) {
//
// Process Markdown `<pre><code>` blocks.
//
/*
text = text.replace(text,
/(?:\n\n|^)
( // $1 = the code block -- one or more lines, starting with a space/tab
(?:
(?:[ ]{4}|\t) // Lines must start with a tab or a tab-width of spaces - attacklab: g_tab_width
.*\n+
)+
)
(\n*[ ]{0,3}[^ \t\n]|(?=~0)) // attacklab: g_tab_width
/g,function(){...});
*/
// attacklab: sentinel workarounds for lack of \A and \Z, safari\khtml bug
text += "~0";
text = text.replace(/(?:\n\n|^)((?:(?:[ ]{4}|\t).*\n+)+)(\n*[ ]{0,3}[^ \t\n]|(?=~0))/g,
function(wholeMatch,m1,m2) {
var codeblock = m1;
var nextChar = m2;
codeblock = _EncodeCode( _Outdent(codeblock));
codeblock = _Detab(codeblock);
codeblock = codeblock.replace(/^\n+/g,""); // trim leading newlines
codeblock = codeblock.replace(/\n+$/g,""); // trim trailing whitespace
codeblock = "<pre><code>" + codeblock + "\n</code></pre>";
return hashBlock(codeblock) + nextChar;
}
);
// attacklab: strip sentinel
text = text.replace(/~0/,"");
return text;
}
private static function hashBlock(text) {
text = text.replace(/(^\n+|\n+$)/g,"");
return "\n\n~K" + (g_html_blocks.push(text)-1) + "K\n\n";
}
private static function _DoCodeSpans(text:String) {
//
// * 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);
return m1+"<code>"+c+"</code>";
});
return text;
}
private static function _EncodeCode(text:String) {
//
// 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;
}
private static function _DoItalicsAndBold(text:String) {
// <strong> must go first:
text = text.replace(/(\*\*|__)(?=\S)([^\r]*?\S[*_]*)\1/g,
"<strong>$2</strong>");
text = text.replace(/(\*|_)(?=\S)([^\r]*?\S)\1/g,
"<em>$2</em>");
return text;
}
private static function _DoBlockQuotes(text:String) {
/*
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;
}
private static function _FormParagraphs(text:String) {
//
// 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:Array = text.split(/\n{2,}/g);
var grafsOut:Array = new Array();
//
// Wrap <p> tags.
//
var end = grafs.length;
for (var i=0; i<end; i++) {
var str:String = grafs[i];
// if this is an HTML marker, copy it
if (str.search(/~K(\d+)K/g) >= 0) {
grafsOut.push(str);
}
else if (str.search(/\S/) >= 0) {
str = _RunSpanGamut(str);
str = str.replace(/^([ \t]*)/g,"<p>");
str += "</p>"
grafsOut.push(str);
}
}
//
// Unhashify HTML blocks
//
end = grafsOut.length;
for (var i=0; i<end; i++) {
// if this is a marker for an html block...
while (grafsOut[i].search(/~K(\d+)K/) >= 0) {
var firstGroup:String = (/~K(\d+)K/).exec(grafsOut[i])[1];
var blockText = g_html_blocks[firstGroup];
blockText = blockText.replace(/\$/g,"$$$$"); // Escape any dollar signs
grafsOut[i] = grafsOut[i].replace(/~K\d+K/,blockText);
}
}
return grafsOut.join("\n\n");
}
private static function _EncodeAmpsAndAngles(text:String) {
// Smart processing for ampersands and angle brackets that need to be encoded.
// Ampersand-encoding based entirely on Nat Irons's Amputator MT plugin:
// http://bumppo.net/projects/amputator/
text = text.replace(/&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)/g,"&amp;");
// Encode naked <'s
text = text.replace(/<(?![a-z\/?\$!])/gi,"&lt;");
return text;
}
private static function _EncodeBackslashEscapes(text:String) {
//
// Parameter: String.
// Returns: The string, with after processing the following backslash
// escape sequences.
//
// attacklab: The polite way to do this is with the new
// escapeCharacters() function:
//
// text = escapeCharacters(text,"\\",true);
// text = escapeCharacters(text,"`*_{}[]()>#+-.!",true);
//
// ...but we're sidestepping its use of the (slow) RegExp constructor
// as an optimization for Firefox. This function gets called a LOT.
text = text.replace(/\\(\\)/g,escapeCharacters_callback);
text = text.replace(/\\([`*_{}\[\]()>#+-.!])/g,escapeCharacters_callback);
return text;
}
private static function _DoAutoLinks(text:String) {
text = text.replace(/<((https?|ftp|dict):[^'">\s]+)>/gi,"<a href=\"$1\">$1</a>");
// Email addresses: <address@domain.foo>
/*
text = text.replace(/
<
(?:mailto:)?
(
[-.\w]+
\@
[-a-z0-9]+(\.[-a-z0-9]+)*\.[a-z]+
)
>
/gi, _DoAutoLinks_callback());
*/
text = text.replace(/<(?:mailto:)?([-.\w]+\@[-a-z0-9]+(\.[-a-z0-9]+)*\.[a-z]+)>/gi,
function(wholeMatch,m1) {
return _EncodeEmailAddress( _UnescapeSpecialChars(m1) );
}
);
return text;
}
private static function _EncodeEmailAddress(addr:String) {
//
// Input: an email address, e.g. "foo@example.com"
//
// Output: the email address as a mailto link, with each character
// of the address encoded as either a decimal or hex entity, in
// the hopes of foiling most address harvesting spam bots. E.g.:
//
// <a href="&#x6D;&#97;&#105;&#108;&#x74;&#111;:&#102;&#111;&#111;&#64;&#101;
// x&#x61;&#109;&#x70;&#108;&#x65;&#x2E;&#99;&#111;&#109;">&#102;&#111;&#111;
// &#64;&#101;x&#x61;&#109;&#x70;&#108;&#x65;&#x2E;&#99;&#111;&#109;</a>
//
// Based on a filter by Matthew Wickline, posted to the BBEdit-Talk
// mailing list: <http://tinyurl.com/yu7ue>
//
// attacklab: why can't javascript speak hex?
function char2hex(ch:String) {
var hexDigits = '0123456789ABCDEF';
var dec = ch.charCodeAt(0);
return(hexDigits.charAt(dec>>4) + hexDigits.charAt(dec&15));
}
var encode = [
function(ch){return "&#"+ch.charCodeAt(0)+";";},
function(ch){return "&#x"+char2hex(ch)+";";},
function(ch){return ch;}
];
addr = "mailto:" + addr;
addr = addr.replace(/./g, function(ch) {
if (ch == "@") {
// this *must* be encoded. I insist.
ch = encode[Math.floor(Math.random()*2)](ch);
} else if (ch !=":") {
// leave ':' alone (to spot mailto: later)
var r = Math.random();
// roughly 10% raw, 45% hex, 45% dec
ch = (
r > .9 ? encode[2](ch) :
r > .45 ? encode[1](ch) :
encode[0](ch)
);
}
return ch;
});
addr = "<a href=\"" + addr + "\">" + addr + "</a>";
addr = addr.replace(/">.+:/g,"\">"); // strip the mailto: from the visible part
return addr;
}
private static function _UnescapeSpecialChars(text:String) {
//
// Swap back in all the special characters we've hidden.
//
text = text.replace(/~E(\d+)E/g,
function(wholeMatch,m1) {
var charCodeToReplace = parseInt(m1);
return String.fromCharCode(charCodeToReplace);
}
);
return text;
}
private static function _Outdent(text:String) {
//
// Remove one level of line-leading tabs or spaces
//
// attacklab: hack around Konqueror 3.5.4 bug:
// "----------bug".replace(/^-/g,"") == "bug"
text = text.replace(/^(\t|[ ]{1,4})/gm,"~0"); // attacklab: g_tab_width
// attacklab: clean up hack
text = text.replace(/~0/g,"")
return text;
}
private static function _Detab(text:String) {
// attacklab: Detab's completely rewritten for speed.
// In perl we could fix it by anchoring the regexp with \G.
// In javascript we're less fortunate.
// expand first n-1 tabs
text = text.replace(/\t(?=\t)/g," "); // attacklab: g_tab_width
// replace the nth with two sentinels
text = text.replace(/\t/g,"~A~B");
// use the sentinel to anchor our regex so it doesn't explode
text = text.replace(/~B(.+?)~A/g,
function(wholeMatch,m1,m2) {
var leadingText = m1;
var numSpaces = 4 - leadingText.length % 4; // attacklab: g_tab_width
// there *must* be a better way to do this:
for (var i=0; i<numSpaces; i++) leadingText+=" ";
return leadingText;
}
);
// clean up sentinels
text = text.replace(/~A/g," "); // attacklab: g_tab_width
text = text.replace(/~B/g,"");
return text;
}
//
// attacklab: Utility functions
//
private static function escapeCharacters(text:String, charsToEscape, afterBackslash = false):String {
// First we have to escape the escape characters so that
// we can build a character class out of them
var regexString = "([" + charsToEscape.replace(/([\[\]\\])/g,"\\$1") + "])";
if (afterBackslash) {
regexString = "\\\\" + regexString;
}
var regex = new RegExp(regexString,"g");
text = text.replace(regex,escapeCharacters_callback);
return text;
}
private static function escapeCharacters_callback(wholeMatch,m1) {
var charCodeToEscape = m1.charCodeAt(0);
return "~E"+charCodeToEscape+"E";
}
}// end of Showdown.converter
}
license.txt
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38
Copyright (c) 2010, Charles Strahan
<http://www.charlesstrahan.com/>
All rights reserved.
 
Original Showdown Copyright (c) 2007, John Fraser
<http://www.attacklab.net/>
All rights reserved.
 
Original Markdown copyright (c) 2004, John Gruber
<http://daringfireball.net/>
All rights reserved.
 
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are
met:
 
* Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
 
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
 
* Neither the name "Markdown" nor the names of its contributors may
be used to endorse or promote products derived from this software
without specific prior written permission.
 
This software is provided by the copyright holders and contributors "as
is" and any express or implied warranties, including, but not limited
to, the implied warranties of merchantability and fitness for a
particular purpose are disclaimed. In no event shall the copyright owner
or contributors be liable for any direct, indirect, incidental, special,
exemplary, or consequential damages (including, but not limited to,
procurement of substitute goods or services; loss of use, data, or
profits; or business interruption) however caused and on any theory of
liability, whether in contract, strict liability, or tort (including
negligence or otherwise) arising in any way out of the use of this
software, even if advised of the possibility of such damage.

Please sign in to comment on this gist.

Something went wrong with that request. Please try again.