markdown.go (view raw)
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 |
// // Blackfriday Markdown Processor // Available at http://github.com/russross/blackfriday // // Copyright © 2011 Russ Ross <russ@russross.com>. // Distributed under the Simplified BSD License. // See README.md for details. // // // // Markdown parsing and processing // // // Blackfriday markdown processor. // // Translates plain text with simple formatting rules into HTML or LaTeX. package blackfriday import ( "bytes" "unicode/utf8" ) const VERSION = "1.1" // These are the supported markdown parsing extensions. // OR these values together to select multiple extensions. const ( EXTENSION_NO_INTRA_EMPHASIS = 1 << iota // ignore emphasis markers inside words EXTENSION_TABLES // render tables EXTENSION_FENCED_CODE // render fenced code blocks EXTENSION_AUTOLINK // detect embedded URLs that are not explicitly marked EXTENSION_STRIKETHROUGH // strikethrough text using ~~test~~ EXTENSION_LAX_HTML_BLOCKS // loosen up HTML block parsing rules EXTENSION_SPACE_HEADERS // be strict about prefix header rules EXTENSION_HARD_LINE_BREAK // translate newlines into line breaks EXTENSION_TAB_SIZE_EIGHT // expand tabs to eight spaces instead of four EXTENSION_FOOTNOTES // Pandoc-style footnotes ) // These are the possible flag values for the link renderer. // Only a single one of these values will be used; they are not ORed together. // These are mostly of interest if you are writing a new output format. const ( LINK_TYPE_NOT_AUTOLINK = iota LINK_TYPE_NORMAL LINK_TYPE_EMAIL ) // These are the possible flag values for the ListItem renderer. // Multiple flag values may be ORed together. // These are mostly of interest if you are writing a new output format. const ( LIST_TYPE_ORDERED = 1 << iota LIST_ITEM_CONTAINS_BLOCK LIST_ITEM_BEGINNING_OF_LIST LIST_ITEM_END_OF_LIST ) // These are the possible flag values for the table cell renderer. // Only a single one of these values will be used; they are not ORed together. // These are mostly of interest if you are writing a new output format. const ( TABLE_ALIGNMENT_LEFT = 1 << iota TABLE_ALIGNMENT_RIGHT TABLE_ALIGNMENT_CENTER = (TABLE_ALIGNMENT_LEFT | TABLE_ALIGNMENT_RIGHT) ) // The size of a tab stop. const ( TAB_SIZE_DEFAULT = 4 TAB_SIZE_EIGHT = 8 ) // These are the tags that are recognized as HTML block tags. // Any of these can be included in markdown text without special escaping. var blockTags = map[string]bool{ "p": true, "dl": true, "h1": true, "h2": true, "h3": true, "h4": true, "h5": true, "h6": true, "ol": true, "ul": true, "del": true, "div": true, "ins": true, "pre": true, "form": true, "math": true, "table": true, "iframe": true, "script": true, "fieldset": true, "noscript": true, "blockquote": true, // HTML5 "video": true, "aside": true, "canvas": true, "figure": true, "footer": true, "header": true, "hgroup": true, "output": true, "article": true, "section": true, "progress": true, "figcaption": true, } // Renderer is the rendering interface. // This is mostly of interest if you are implementing a new rendering format. // // When a byte slice is provided, it contains the (rendered) contents of the // element. // // When a callback is provided instead, it will write the contents of the // respective element directly to the output buffer and return true on success. // If the callback returns false, the rendering function should reset the // output buffer as though it had never been called. // // Currently Html and Latex implementations are provided type Renderer interface { // block-level callbacks BlockCode(out *bytes.Buffer, text []byte, lang string) BlockQuote(out *bytes.Buffer, text []byte) BlockHtml(out *bytes.Buffer, text []byte) Header(out *bytes.Buffer, text func() bool, level int) HRule(out *bytes.Buffer) List(out *bytes.Buffer, text func() bool, flags int) ListItem(out *bytes.Buffer, text []byte, flags int) Paragraph(out *bytes.Buffer, text func() bool) Table(out *bytes.Buffer, header []byte, body []byte, columnData []int) TableRow(out *bytes.Buffer, text []byte) TableCell(out *bytes.Buffer, text []byte, flags int) Footnotes(out *bytes.Buffer, text func() bool) FootnoteItem(out *bytes.Buffer, name, text []byte, flags int) // Span-level callbacks AutoLink(out *bytes.Buffer, link []byte, kind int) CodeSpan(out *bytes.Buffer, text []byte) DoubleEmphasis(out *bytes.Buffer, text []byte) Emphasis(out *bytes.Buffer, text []byte) Image(out *bytes.Buffer, link []byte, title []byte, alt []byte) LineBreak(out *bytes.Buffer) Link(out *bytes.Buffer, link []byte, title []byte, content []byte) RawHtmlTag(out *bytes.Buffer, tag []byte) TripleEmphasis(out *bytes.Buffer, text []byte) StrikeThrough(out *bytes.Buffer, text []byte) FootnoteRef(out *bytes.Buffer, ref []byte, id int) // Low-level callbacks Entity(out *bytes.Buffer, entity []byte) NormalText(out *bytes.Buffer, text []byte) // Header and footer DocumentHeader(out *bytes.Buffer) DocumentFooter(out *bytes.Buffer) } // Callback functions for inline parsing. One such function is defined // for each character that triggers a response when parsing inline data. type inlineParser func(p *parser, out *bytes.Buffer, data []byte, offset int) int // Parser holds runtime state used by the parser. // This is constructed by the Markdown function. type parser struct { r Renderer refs map[string]*reference inlineCallback [256]inlineParser flags int nesting int maxNesting int insideLink bool // Footnotes need to be ordered as well as available to quickly check for // presence. If a ref is also a footnote, it's stored both in refs and here // in notes. Slice is nil if footnotes not enabled. notes []*reference } // // // Public interface // // // MarkdownBasic is a convenience function for simple rendering. // It processes markdown input with no extensions enabled. func MarkdownBasic(input []byte) []byte { // set up the HTML renderer htmlFlags := HTML_USE_XHTML renderer := HtmlRenderer(htmlFlags, "", "") // set up the parser extensions := 0 return Markdown(input, renderer, extensions) } // Call Markdown with most useful extensions enabled // MarkdownCommon is a convenience function for simple rendering. // It processes markdown input with common extensions enabled, including: // // * Smartypants processing with smart fractions and LaTeX dashes // // * Intra-word emphasis suppression // // * Tables // // * Fenced code blocks // // * Autolinking // // * Strikethrough support // // * Strict header parsing func MarkdownCommon(input []byte) []byte { // set up the HTML renderer htmlFlags := 0 htmlFlags |= HTML_USE_XHTML htmlFlags |= HTML_USE_SMARTYPANTS htmlFlags |= HTML_SMARTYPANTS_FRACTIONS htmlFlags |= HTML_SMARTYPANTS_LATEX_DASHES htmlFlags |= HTML_SKIP_SCRIPT renderer := HtmlRenderer(htmlFlags, "", "") // set up the parser extensions := 0 extensions |= EXTENSION_NO_INTRA_EMPHASIS extensions |= EXTENSION_TABLES extensions |= EXTENSION_FENCED_CODE extensions |= EXTENSION_AUTOLINK extensions |= EXTENSION_STRIKETHROUGH extensions |= EXTENSION_SPACE_HEADERS return Markdown(input, renderer, extensions) } // Markdown is the main rendering function. // It parses and renders a block of markdown-encoded text. // The supplied Renderer is used to format the output, and extensions dictates // which non-standard extensions are enabled. // // To use the supplied Html or LaTeX renderers, see HtmlRenderer and // LatexRenderer, respectively. func Markdown(input []byte, renderer Renderer, extensions int) []byte { // no point in parsing if we can't render if renderer == nil { return nil } // fill in the render structure p := new(parser) p.r = renderer p.flags = extensions p.refs = make(map[string]*reference) p.maxNesting = 16 p.insideLink = false // register inline parsers p.inlineCallback['*'] = emphasis p.inlineCallback['_'] = emphasis if extensions&EXTENSION_STRIKETHROUGH != 0 { p.inlineCallback['~'] = emphasis } p.inlineCallback['`'] = codeSpan p.inlineCallback['\n'] = lineBreak p.inlineCallback['['] = link p.inlineCallback['<'] = leftAngle p.inlineCallback['\\'] = escape p.inlineCallback['&'] = entity if extensions&EXTENSION_AUTOLINK != 0 { p.inlineCallback[':'] = autoLink } if extensions&EXTENSION_FOOTNOTES != 0 { p.notes = make([]*reference, 0) } first := firstPass(p, input) second := secondPass(p, first) return second } // first pass: // - extract references // - expand tabs // - normalize newlines // - copy everything else func firstPass(p *parser, input []byte) []byte { var out bytes.Buffer tabSize := TAB_SIZE_DEFAULT if p.flags&EXTENSION_TAB_SIZE_EIGHT != 0 { tabSize = TAB_SIZE_EIGHT } beg, end := 0, 0 for beg < len(input) { // iterate over lines if end = isReference(p, input[beg:], tabSize); end > 0 { beg += end } else { // skip to the next line end = beg for end < len(input) && input[end] != '\n' && input[end] != '\r' { end++ } // add the line body if present if end > beg { expandTabs(&out, input[beg:end], tabSize) } out.WriteByte('\n') if end < len(input) && input[end] == '\r' { end++ } if end < len(input) && input[end] == '\n' { end++ } beg = end } } // empty input? if out.Len() == 0 { out.WriteByte('\n') } return out.Bytes() } // second pass: actual rendering func secondPass(p *parser, input []byte) []byte { var output bytes.Buffer p.r.DocumentHeader(&output) p.block(&output, input) if p.flags&EXTENSION_FOOTNOTES != 0 && len(p.notes) > 0 { p.r.Footnotes(&output, func() bool { flags := LIST_ITEM_BEGINNING_OF_LIST for _, ref := range p.notes { var buf bytes.Buffer if ref.hasBlock { flags |= LIST_ITEM_CONTAINS_BLOCK p.block(&buf, ref.title) } else { p.inline(&buf, ref.title) } p.r.FootnoteItem(&output, ref.link, buf.Bytes(), flags) flags &^= LIST_ITEM_BEGINNING_OF_LIST | LIST_ITEM_CONTAINS_BLOCK } return true }) } p.r.DocumentFooter(&output) if p.nesting != 0 { panic("Nesting level did not end at zero") } return output.Bytes() } // // Link references // // This section implements support for references that (usually) appear // as footnotes in a document, and can be referenced anywhere in the document. // The basic format is: // // [1]: http://www.google.com/ "Google" // [2]: http://www.github.com/ "Github" // // Anywhere in the document, the reference can be linked by referring to its // label, i.e., 1 and 2 in this example, as in: // // This library is hosted on [Github][2], a git hosting site. // // Actual footnotes as specified in Pandoc and supported by some other Markdown // libraries such as php-markdown are also taken care of. They look like this: // // This sentence needs a bit of further explanation.[^note] // // [^note]: This is the explanation. // // Footnotes should be placed at the end of the document in an ordered list. // Inline footnotes such as: // // Inline footnotes^[Not supported.] also exist. // // are not yet supported. // References are parsed and stored in this struct. type reference struct { link []byte title []byte noteId int // 0 if not a footnote ref hasBlock bool } // Check whether or not data starts with a reference link. // If so, it is parsed and stored in the list of references // (in the render struct). // Returns the number of bytes to skip to move past it, // or zero if the first line is not a reference. func isReference(p *parser, data []byte, tabSize int) int { if len(data) >= 5 { } // up to 3 optional leading spaces if len(data) < 4 { return 0 } i := 0 for i < 3 && data[i] == ' ' { i++ } noteId := 0 // id part: anything but a newline between brackets if data[i] != '[' { return 0 } i++ if p.flags&EXTENSION_FOOTNOTES != 0 { if data[i] == '^' { noteId = len(p.notes) + 1 i++ } } idOffset := i for i < len(data) && data[i] != '\n' && data[i] != '\r' && data[i] != ']' { i++ } if i >= len(data) || data[i] != ']' { return 0 } idEnd := i // spacer: colon (space | tab)* newline? (space | tab)* i++ if i >= len(data) || data[i] != ':' { return 0 } i++ for i < len(data) && (data[i] == ' ' || data[i] == '\t') { i++ } if i < len(data) && (data[i] == '\n' || data[i] == '\r') { i++ if i < len(data) && data[i] == '\n' && data[i-1] == '\r' { i++ } } for i < len(data) && (data[i] == ' ' || data[i] == '\t') { i++ } if i >= len(data) { return 0 } var ( linkOffset, linkEnd int titleOffset, titleEnd int lineEnd int raw []byte hasBlock bool ) if p.flags&EXTENSION_FOOTNOTES != 0 && noteId > 0 { linkOffset, linkEnd, raw, hasBlock = scanFootnote(p, data, i, tabSize) lineEnd = linkEnd } else { linkOffset, linkEnd, titleOffset, titleEnd, lineEnd = scanLinkRef(p, data, i) } if lineEnd == 0 { return 0 } // a valid ref has been found ref := &reference{ noteId: noteId, hasBlock: hasBlock, } if noteId > 0 { // reusing the link field for the id since footnotes don't have links ref.link = data[idOffset:idEnd] // if footnote, it's not really a title, it's the contained text ref.title = raw p.notes = append(p.notes, ref) } else { ref.link = data[linkOffset:linkEnd] ref.title = data[titleOffset:titleEnd] } // id matches are case-insensitive id := string(bytes.ToLower(data[idOffset:idEnd])) p.refs[id] = ref return lineEnd } func scanLinkRef(p *parser, data []byte, i int) (linkOffset, linkEnd, titleOffset, titleEnd, lineEnd int) { // link: whitespace-free sequence, optionally between angle brackets if data[i] == '<' { i++ } linkOffset = i for i < len(data) && data[i] != ' ' && data[i] != '\t' && data[i] != '\n' && data[i] != '\r' { i++ } linkEnd = i if data[linkOffset] == '<' && data[linkEnd-1] == '>' { linkOffset++ linkEnd-- } // optional spacer: (space | tab)* (newline | '\'' | '"' | '(' ) for i < len(data) && (data[i] == ' ' || data[i] == '\t') { i++ } if i < len(data) && data[i] != '\n' && data[i] != '\r' && data[i] != '\'' && data[i] != '"' && data[i] != '(' { return } // compute end-of-line if i >= len(data) || data[i] == '\r' || data[i] == '\n' { lineEnd = i } if i+1 < len(data) && data[i] == '\r' && data[i+1] == '\n' { lineEnd++ } // optional (space|tab)* spacer after a newline if lineEnd > 0 { i = lineEnd + 1 for i < len(data) && (data[i] == ' ' || data[i] == '\t') { i++ } } // optional title: any non-newline sequence enclosed in '"() alone on its line if i+1 < len(data) && (data[i] == '\'' || data[i] == '"' || data[i] == '(') { i++ titleOffset = i // look for EOL for i < len(data) && data[i] != '\n' && data[i] != '\r' { i++ } if i+1 < len(data) && data[i] == '\n' && data[i+1] == '\r' { titleEnd = i + 1 } else { titleEnd = i } // step back i-- for i > titleOffset && (data[i] == ' ' || data[i] == '\t') { i-- } if i > titleOffset && (data[i] == '\'' || data[i] == '"' || data[i] == ')') { lineEnd = titleEnd titleEnd = i } } return } // The first bit of this logic is the same as (*parser).listItem, but the rest // is much simpler. This function simply finds the entire block and shifts it // over by one tab if it is indeed a block (just returns the line if it's not). // blockEnd is the end of the section in the input buffer, and contents is the // extracted text that was shifted over one tab. It will need to be rendered at // the end of the document. func scanFootnote(p *parser, data []byte, i, indentSize int) (blockStart, blockEnd int, contents []byte, hasBlock bool) { if i == 0 { return } // skip leading whitespace on first line for data[i] == ' ' { i++ } blockStart = i // find the end of the line blockEnd = i for i < len(data) && data[i-1] != '\n' { i++ } // get working buffer var raw bytes.Buffer // put the first line into the working buffer raw.Write(data[blockEnd:i]) blockEnd = i // process the following lines containsBlankLine := false gatherLines: for blockEnd < len(data) { i++ // find the end of this line for i < len(data) && data[i-1] != '\n' { i++ } // if it is an empty line, guess that it is part of this item // and move on to the next line if p.isEmpty(data[blockEnd:i]) > 0 { containsBlankLine = true blockEnd = i continue } n := 0 if n = isIndented(data[blockEnd:i], indentSize); n == 0 { // this is the end of the block. // we don't want to include this last line in the index. break gatherLines } // if there were blank lines before this one, insert a new one now if containsBlankLine { raw.WriteByte('\n') containsBlankLine = false } // get rid of that first tab, write to buffer raw.Write(data[blockEnd+n : i]) hasBlock = true blockEnd = i } if data[blockEnd-1] != '\n' { raw.WriteByte('\n') } contents = raw.Bytes() return } // // // Miscellaneous helper functions // // // Test if a character is a punctuation symbol. // Taken from a private function in regexp in the stdlib. func ispunct(c byte) bool { for _, r := range []byte("!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~") { if c == r { return true } } return false } // Test if a character is a whitespace character. func isspace(c byte) bool { return c == ' ' || c == '\t' || c == '\n' || c == '\r' || c == '\f' || c == '\v' } // Test if a character is a letter or a digit. // TODO: check when this is looking for ASCII alnum and when it should use unicode func isalnum(c byte) bool { return (c >= '0' && c <= '9') || (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') } // Replace tab characters with spaces, aligning to the next TAB_SIZE column. // always ends output with a newline func expandTabs(out *bytes.Buffer, line []byte, tabSize int) { // first, check for common cases: no tabs, or only tabs at beginning of line i, prefix := 0, 0 slowcase := false for i = 0; i < len(line); i++ { if line[i] == '\t' { if prefix == i { prefix++ } else { slowcase = true break } } } // no need to decode runes if all tabs are at the beginning of the line if !slowcase { for i = 0; i < prefix*tabSize; i++ { out.WriteByte(' ') } out.Write(line[prefix:]) return } // the slow case: we need to count runes to figure out how // many spaces to insert for each tab column := 0 i = 0 for i < len(line) { start := i for i < len(line) && line[i] != '\t' { _, size := utf8.DecodeRune(line[i:]) i += size column++ } if i > start { out.Write(line[start:i]) } if i >= len(line) { break } for { out.WriteByte(' ') column++ if column%tabSize == 0 { break } } i++ } } // Find if a line counts as indented or not. // Returns number of characters the indent is (0 = not indented). func isIndented(data []byte, indentSize int) int { if len(data) == 0 { return 0 } if data[0] == '\t' { return 1 } if len(data) < indentSize { return 0 } for i := 0; i < indentSize; i++ { if data[i] != ' ' { return 0 } } return indentSize } // Create a url-safe slug for fragments func slugify(in []byte) []byte { if len(in) == 0 { return in } out := make([]byte, 0, len(in)) sym := false for _, ch := range in { if isalnum(ch) { sym = false out = append(out, ch) } else if sym { continue } else { out = append(out, '-') sym = true } } var a, b int var ch byte for a, ch = range out { if ch != '-' { break } } for b = len(out) - 1; b > 0; b-- { if out[b] != '-' { break } } return out[a : b+1] } |