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
|
// Package markdown is a package for parsing and processing markdown text.
// It translates plain text with simple formatting rules into HTML or XML.
package mmark
import (
"bytes"
"path"
"unicode/utf8"
)
const Version = "1.3.4"
var test = false
// These are the supported markdown parsing extensions.
// OR these values together to select multiple extensions.
const (
_ = 1 << iota
EXTENSION_ABBREVIATIONS // Render abbreviations `*[HTML]: Hyper Text Markup Language`
EXTENSION_AUTO_HEADER_IDS // Create the header ID from the text
EXTENSION_AUTOLINK // Detect embedded URLs that are not explicitly marked
EXTENSION_CITATION // Support citations via the link syntax
EXTENSION_EXAMPLE_LISTS // Render '(@tag) ' example lists
EXTENSION_FENCED_CODE // Render fenced code blocks
EXTENSION_FOOTNOTES // Pandoc-style footnotes
EXTENSION_HARD_LINE_BREAK // Translate newlines into line breaks
EXTENSION_HEADER_IDS // Specify header IDs with {#id}
EXTENSION_INCLUDE // Include file with {{ syntax
EXTENSION_INLINE_ATTR // Detect CommonMark's IAL syntax
EXTENSION_LAX_HTML_BLOCKS // Loosen up HTML block parsing rules
EXTENSION_MATH // Detect $$...$$ and parse as math
EXTENSION_MATTER // Use {frontmatter} {mainmatter} {backmatter} (TODO(miek): not actually used)
EXTENSION_NO_EMPTY_LINE_BEFORE_BLOCK // No need to insert an empty line to start a (code, quote, order list, unorder list)block
EXTENSION_PARTS // Detect part headers (-#)
EXTENSION_QUOTES // Allow A> as asides
EXTENSION_SHORT_REF // (#id) will be a cross reference
EXTENSION_SPACE_HEADERS // Be strict about prefix header rules
EXTENSION_TABLES // Render tables
EXTENSION_TITLEBLOCK_TOML // Titleblock in TOML
EXTENSION_UNIQUE_HEADER_IDS // When detecting identical anchors add a sequence number -1, -2 etc
EXTENSION_BACKSLASH_LINE_BREAK // Translate trailing backslashes into line breaks
EXTENSION_RFC7328 // Parse RFC 7328 markdown. Depends on FOOTNOTES extension.
EXTENSION_DEFINITION_LISTS // render definition lists
commonHtmlFlags = 0 |
HTML_USE_SMARTYPANTS |
HTML_SMARTYPANTS_FRACTIONS |
HTML_SMARTYPANTS_DASHES |
HTML_SMARTYPANTS_LATEX_DASHES
commonExtensions = 0 |
EXTENSION_TABLES |
EXTENSION_FENCED_CODE |
EXTENSION_AUTOLINK |
EXTENSION_SPACE_HEADERS |
EXTENSION_HEADER_IDS |
EXTENSION_ABBREVIATIONS |
EXTENSION_NO_EMPTY_LINE_BEFORE_BLOCK | // CommonMark
EXTENSION_BACKSLASH_LINE_BREAK | // CommonMark
EXTENSION_DEFINITION_LISTS
commonXmlExtensions = commonExtensions |
EXTENSION_UNIQUE_HEADER_IDS |
EXTENSION_AUTO_HEADER_IDS |
EXTENSION_INLINE_ATTR |
EXTENSION_QUOTES |
EXTENSION_MATTER |
EXTENSION_CITATION |
EXTENSION_EXAMPLE_LISTS |
EXTENSION_SHORT_REF |
EXTENSION_DEFINITION_LISTS
)
// 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_TYPE_ORDERED_ROMAN_UPPER
_LIST_TYPE_ORDERED_ROMAN_LOWER
_LIST_TYPE_ORDERED_ALPHA_UPPER
_LIST_TYPE_ORDERED_ALPHA_LOWER
_LIST_TYPE_ORDERED_GROUP
_LIST_TYPE_DEFINITION
_LIST_TYPE_TERM
_LIST_ITEM_CONTAINS_BLOCK
_LIST_ITEM_BEGINNING_OF_LIST
_LIST_ITEM_END_OF_LIST
_LIST_INSIDE_LIST
_INSIDE_FIGURE
)
// 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
const (
_DOC_FRONT_MATTER = iota + 1 // Different divisions of the document
_DOC_MAIN_MATTER
_DOC_BACK_MATTER
_ABSTRACT // Special headers, keep track if there are open
_NOTE // Special Note headers, keep track if there are open
_PREFACE
_COLOPHON
)
// blockTags is a set of tags that are recognized as HTML block tags.
// Any of these can be included in markdown text without special escaping.
var blockTags = map[string]struct{}{
"blockquote": {},
"del": {},
"div": {},
"dl": {},
"fieldset": {},
"form": {},
"h1": {},
"h2": {},
"h3": {},
"h4": {},
"h5": {},
"h6": {},
"iframe": {},
"ins": {},
"math": {},
"noscript": {},
"ol": {},
"pre": {},
"p": {},
"script": {},
"style": {},
"table": {},
"ul": {},
// HTML5
"article": {},
"aside": {},
"canvas": {},
"figcaption": {},
"figure": {},
"footer": {},
"header": {},
"hgroup": {},
"output": {},
"progress": {},
"section": {},
"video": {},
}
// 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, XML2RFC v3 and XML2RFC v2 implementations are provided.
type Renderer interface {
// block-level callbacks
BlockCode(out *bytes.Buffer, text []byte, lang string, caption []byte, subfigure bool, callouts bool)
BlockQuote(out *bytes.Buffer, text []byte, attribution []byte)
BlockHtml(out *bytes.Buffer, text []byte)
CommentHtml(out *bytes.Buffer, text []byte)
// SpecialHeader is used for Abstract and Preface. The what string contains abstract or preface.
SpecialHeader(out *bytes.Buffer, what []byte, text func() bool, id string)
// Note is use for typesetting notes.
Note(out *bytes.Buffer, text func() bool, id string)
Part(out *bytes.Buffer, text func() bool, id string)
Header(out *bytes.Buffer, text func() bool, level int, id string)
HRule(out *bytes.Buffer)
List(out *bytes.Buffer, text func() bool, flags, start int, group []byte)
ListItem(out *bytes.Buffer, text []byte, flags int)
Paragraph(out *bytes.Buffer, text func() bool, flags int)
Table(out *bytes.Buffer, header []byte, body []byte, footer []byte, columnData []int, caption []byte)
TableRow(out *bytes.Buffer, text []byte)
TableHeaderCell(out *bytes.Buffer, text []byte, flags, colspan int)
TableCell(out *bytes.Buffer, text []byte, flags, colspan int)
Footnotes(out *bytes.Buffer, text func() bool)
FootnoteItem(out *bytes.Buffer, name, text []byte, flags int)
TitleBlockTOML(out *bytes.Buffer, data *title)
Aside(out *bytes.Buffer, text []byte)
Figure(out *bytes.Buffer, text []byte, caption []byte)
// Span-level callbacks
AutoLink(out *bytes.Buffer, link []byte, kind int)
CodeSpan(out *bytes.Buffer, text []byte)
// CalloutText is called when a callout is seen in the text. Id is the text
// seen between < and > and ids references the callout counter(s) in the code.
CalloutText(out *bytes.Buffer, id string, ids []string)
// Called when a callout is seen in a code block. Index is the callout counter, id
// is the number seen between < and >.
CalloutCode(out *bytes.Buffer, index, id string)
DoubleEmphasis(out *bytes.Buffer, text []byte)
Emphasis(out *bytes.Buffer, text []byte)
Subscript(out *bytes.Buffer, text []byte)
Superscript(out *bytes.Buffer, text []byte)
Image(out *bytes.Buffer, link []byte, title []byte, alt []byte, subfigure bool)
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)
Index(out *bytes.Buffer, primary, secondary []byte, prim bool)
Citation(out *bytes.Buffer, link, title []byte)
Abbreviation(out *bytes.Buffer, abbr, title []byte)
Example(out *bytes.Buffer, index int)
Math(out *bytes.Buffer, text []byte, display bool)
// Low-level callbacks
Entity(out *bytes.Buffer, entity []byte)
NormalText(out *bytes.Buffer, text []byte)
// Header and footer
DocumentHeader(out *bytes.Buffer, start bool)
DocumentFooter(out *bytes.Buffer, start bool)
// Frontmatter, mainmatter or backmatter
DocumentMatter(out *bytes.Buffer, matter int)
References(out *bytes.Buffer, citations map[string]*citation)
// Helper functions
Flags() int
// Attr returns the inline attribute.
Attr() *inlineAttr
// SetAttr set the inline attribute.
SetAttr(*inlineAttr)
// AttrString return the string representation of this inline attribute.
AttrString(*inlineAttr) string
}
// 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
citations map[string]*citation
abbreviations map[string]*abbreviation
examples map[string]int
callouts map[string][]string
codeBlock int // count codeblock for callout ID generation
inlineCallback [256]inlineParser
flags int
nesting int
maxNesting int
insideLink bool
insideDefinitionList bool // when in def. list ... TODO(miek):doc
insideList int // list in list counter
insideFigure bool // when inside a F> paragraph
displayMath 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
appendix bool // have we seen a {backmatter}?
titleblock bool // have we seen a titleblock
headerLen int // if a header is written what is length
partCount int // TODO, keep track of part counts (-#)
chapterCount int // TODO, keep track of chapter count (#)
// Placeholder IAL that can be added to blocklevel elements.
ial *inlineAttr
// Prevent identical header anchors by appending -<sequence_number> starting
// with -1, this is the same thing that pandoc does.
anchors map[string]int
}
// Markdown is an io.Writer. Writing a buffer with markdown text will be converted to
// the output format the renderer outputs. Note that the conversion only takes place
// when String() or Bytes() is called.
type Markdown struct {
renderer Renderer
extensions int
in *bytes.Buffer
out *bytes.Buffer
renderedSinceLastWrite bool
}
func NewMarkdown(renderer Renderer, extensions int) *Markdown {
return &Markdown{renderer, extensions, &bytes.Buffer{}, &bytes.Buffer{}, false}
}
func (m *Markdown) Write(p []byte) (n int, err error) {
m.renderedSinceLastWrite = false
return m.in.Write(p)
}
func (m *Markdown) String() string { m.render(); return m.out.String() }
func (m *Markdown) Bytes() []byte { m.render(); return m.out.Bytes() }
func (m *Markdown) render() {
if m.renderer == nil {
// default to Html renderer
}
if m.renderedSinceLastWrite {
return
}
m.out = Parse(m.in.Bytes(), m.renderer, m.extensions)
m.renderedSinceLastWrite = true
}
// Parse 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 XML renderers, see HtmlRenderer, XmlRenderer and
// Xml2Renderer, respectively.
func Parse(input []byte, renderer Renderer, extensions int) *bytes.Buffer {
// 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.abbreviations = make(map[string]*abbreviation)
p.anchors = make(map[string]int)
p.examples = make(map[string]int)
// newly created in 'callouts'
p.maxNesting = 16
p.insideLink = false
// register inline parsers
p.inlineCallback['*'] = emphasis
p.inlineCallback['_'] = emphasis
p.inlineCallback['~'] = emphasis
p.inlineCallback['`'] = codeSpan
p.inlineCallback['\n'] = lineBreak
p.inlineCallback['['] = link
p.inlineCallback['<'] = leftAngle
p.inlineCallback['\\'] = escape
p.inlineCallback['&'] = entity
p.inlineCallback['{'] = leftBrace
p.inlineCallback['^'] = superscript // subscript is handled in emphasis
p.inlineCallback['('] = index // also find example list references and cross references
p.inlineCallback['$'] = math
if extensions&EXTENSION_AUTOLINK != 0 {
p.inlineCallback[':'] = autoLink
}
if extensions&EXTENSION_FOOTNOTES != 0 {
p.notes = make([]*reference, 0)
}
if extensions&EXTENSION_CITATION != 0 {
p.inlineCallback['@'] = citationReference // @ref, short form of citations
p.citations = make(map[string]*citation)
}
first := firstPass(p, input, 0)
second := secondPass(p, first.Bytes(), 0)
return second
}
// first pass:
// - extract references
// - extract abbreviations
// - expand tabs
// - normalize newlines
// - copy everything else
// - include includes
func firstPass(p *parser, input []byte, depth int) *bytes.Buffer {
var out bytes.Buffer
if depth > 8 {
printf(p, "nested includes depth > 8")
out.WriteByte('\n')
return &out
}
tabSize := _TAB_SIZE_DEFAULT
beg, end := 0, 0
lastFencedCodeBlockEnd := 0
for beg < len(input) { // iterate over lines
if beg >= lastFencedCodeBlockEnd { // don't parse inside fenced code blocks
if end = isReference(p, input[beg:], tabSize); end > 0 {
beg += end
continue
}
}
// skip to the next line
end = beg
for end < len(input) && input[end] != '\n' && input[end] != '\r' {
end++
}
if p.flags&EXTENSION_FENCED_CODE != 0 {
// track fenced code block boundaries to suppress tab expansion
// inside them:
if beg >= lastFencedCodeBlockEnd {
if i := p.fencedCode(&out, append(input[beg:], '\n'), false); i > 0 {
lastFencedCodeBlockEnd = beg + i
}
}
}
// add the line body if present
if end > beg {
if end < lastFencedCodeBlockEnd { // Do not expand tabs while inside fenced code blocks.
out.Write(input[beg:end])
} else {
if p.flags&EXTENSION_INCLUDE != 0 && beg+1 < len(input) && input[beg] == '{' && input[beg+1] == '{' {
if beg == 0 || (beg > 0 && input[beg-1] == '\n') {
if j := p.include(&out, input[beg:end], depth); j > 0 {
beg += j
}
}
}
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
}
// second pass: actual rendering
func secondPass(p *parser, input []byte, depth int) *bytes.Buffer {
var output bytes.Buffer
p.r.DocumentHeader(&output, depth == 0)
p.headerLen = output.Len()
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 i := 0; i < len(p.notes); i += 1 {
var buf bytes.Buffer
ref := p.notes[i]
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
})
}
if !p.appendix {
if len(p.citations) > 0 {
// appendix not started in doc, start it now and output references
p.r.DocumentMatter(&output, _DOC_BACK_MATTER)
p.r.References(&output, p.citations)
}
p.appendix = true
}
p.r.DocumentFooter(&output, depth == 0)
if p.nesting != 0 {
panic("Nesting level did not end at zero")
}
return &output
}
//
// 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
}
// abbreviations are parsed and stored in this struct.
type abbreviation struct {
title []byte
}
// citations are parsed and stored in this struct.
type citation struct {
link []byte
title []byte
xml []byte // raw include of reference XML
typ byte // 'i' for informal, 'n' normative (default = 'i')
seq int // sequence number for I-Ds
}
// 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 {
// up to 3 optional leading spaces
if len(data) < 4 {
return 0
}
i := 0
for i < 3 && data[i] == ' ' {
i++
}
noteId := 0
abbrId := ""
// id part: anything but a newline between brackets
// abbreviations start with *[
if data[i] != '[' && data[i] != '*' {
return 0
}
if data[i] == '*' && (i < len(data)-1 && data[i+1] != '[') {
return 0
}
if data[i] == '*' && p.flags&EXTENSION_ABBREVIATIONS != 0 {
abbrId = "yes" // any non empty
}
i++
if p.flags&EXTENSION_FOOTNOTES != 0 {
if data[i] == '^' {
// we can set it to anything here because the proper noteIds will
// be assigned later during the second pass. It just has to be != 0
noteId = 1
i++
}
}
idOffset := i
for i < len(data) && data[i] != '\n' && data[i] != '\r' && data[i] != ']' {
if data[i] == '\\' {
i++
}
i++
}
if i >= len(data) || data[i] != ']' {
return 0
}
idEnd := i
if abbrId != "" {
abbrId = string(data[idOffset+1 : idEnd])
}
// 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 if abbrId != "" {
titleOffset, titleEnd, lineEnd = scanAbbreviation(p, data, idEnd)
p.abbreviations[abbrId] = &abbreviation{title: data[titleOffset:titleEnd]}
return lineEnd
} 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
} else {
ref.link = data[linkOffset:linkEnd]
ref.title = data[titleOffset:titleEnd]
}
// id matches are case-insensitive
id := string(bytes.ToLower(data[idOffset:idEnd]))
// CommonMark don't overwrite newly found references
if _, ok := p.refs[id]; !ok {
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
if i == len(data) {
return
}
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 || len(data) == 0 {
return
}
// skip leading whitespace on first line
for i < len(data) && 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
}
func scanAbbreviation(p *parser, data []byte, i int) (titleOffset, titleEnd, lineEnd int) {
lineEnd = i
for lineEnd < len(data) && data[lineEnd] != '\n' {
lineEnd++
}
if len(data[i+2:lineEnd]) == 0 || p.isEmpty(data[i+2:lineEnd]) > 0 {
return i + 2, i + 2, lineEnd
}
titleOffset = i + 2
for data[titleOffset] == ' ' {
titleOffset++
}
titleEnd = lineEnd
for data[titleEnd-1] == ' ' {
titleEnd--
}
return
}
// Miscellaneous helper functions
// 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'
}
func ispunct(c byte) bool {
for _, r := range []byte("!\"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~") {
if c == r {
return true
}
}
return false
}
func isupper(c byte) bool { return (c >= 'A' && c <= 'Z') }
func isletter(c byte) bool { return (c >= 'a' && c <= 'z') || (c >= 'A' && c <= 'Z') }
// 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') || isletter(c) }
func isnum(c byte) bool { return (c >= '0' && c <= '9') }
// check if the string only contains, i, v, x, c and l. If uppercase is true, check uppercase version.
func isroman(digit byte, uppercase bool) bool {
if !uppercase {
if digit == 'i' || digit == 'v' || digit == 'x' || digit == 'c' || digit == 'l' {
return true
}
return false
}
if digit == 'I' || digit == 'V' || digit == 'X' || digit == 'C' || digit == 'L' {
return true
}
return false
}
// replace {{file.md}} with the contents of the file.
func (p *parser) include(out *bytes.Buffer, data []byte, depth int) int {
i := 0
if len(data) < 3 {
return 0
}
if data[i] != '{' && data[i+1] != '{' {
return 0
}
// find the end delimiter
end, j := 0, 0
for end = i; end < len(data) && j < 2; end++ {
if data[end] == '}' {
j++
} else {
j = 0
}
}
if j < 2 && end >= len(data) {
return 0
}
filename := data[i+2 : end-2]
// Now a possible address in blockquotes
var address []byte
if end < len(data) && data[end] == '[' {
j = end
for j < len(data) && data[j] != ']' {
j++
}
if j == len(data) {
// assuming no address
address = nil
} else {
address = data[end+1 : j]
end = j + 1
}
}
input := parseAddress(address, filename)
if input == nil {
return end
}
if input[len(input)-1] != '\n' {
input = append(input, '\n')
}
first := firstPass(p, input, depth+1)
out.Write(first.Bytes())
return end
}
// replace <{{file.go}}[address] with the contents of the file. Pay attention to the indentation of the
// include and prefix the code with that number of spaces + 4, it returns the new bytes and a boolean
// indicating we've detected a code include.
func (p *parser) codeInclude(out *bytes.Buffer, data []byte) int {
// TODO: this is not an inline element
i := 0
l := len(data)
if l < 3 {
return 0
}
if data[i] != '<' && data[i+1] != '{' && data[i+2] != '{' {
return 0
}
// find the end delimiter
end, j := 0, 0
for end = i; end < l && j < 2; end++ {
if data[end] == '}' {
j++
} else {
j = 0
}
}
if j < 2 && end >= l {
return 0
}
lang := ""
// found <{{filename}}
// this could be the end, or we could have an option [address] -block attached
filename := data[i+3 : end-2]
// get the extension of the filename, if it is a member of a predefined set a
// language we use it as the lang (and we will emit <sourcecode>)
if x := path.Ext(string(filename)); x != "" {
// x includes the dot
if _, ok := SourceCodeTypes[x[1:]]; ok {
lang = x[1:]
}
}
// Now a possible address in blockquotes
var address []byte
if end < l && data[end] == '[' {
j = end
for j < l && data[j] != ']' {
j++
}
if j == l {
// assuming no address
address = nil
end = l
} else {
address = data[end+1 : j]
end = j + 1
}
}
code := parseAddress(address, filename)
if len(code) == 0 {
code = []byte{'\n'}
}
if code[len(code)-1] != '\n' {
code = append(code, '\n')
}
// if the next line starts with Figure: we consider that a caption
var caption bytes.Buffer
if end < l-1 && bytes.HasPrefix(data[end+1:], []byte("Figure: ")) {
line := end + 1
j := end + 1
for line < l {
j++
// find the end of this line
for j <= l && data[j-1] != '\n' {
j++
}
if p.isEmpty(data[line:j]) > 0 {
break
}
line = j
}
p.inline(&caption, data[end+1+8:j-1]) // +8 for 'Figure: '
end = j - 1
}
co := ""
if p.ial != nil {
co = p.ial.Value("callout")
p.ial.DropAttr("callout")
}
p.r.SetAttr(p.ial)
p.ial = nil
if co != "" {
var callout bytes.Buffer
callouts(p, &callout, code, 0, co)
p.r.BlockCode(out, callout.Bytes(), lang, caption.Bytes(), p.insideFigure, true)
} else {
p.callouts = nil
p.r.BlockCode(out, code, lang, caption.Bytes(), p.insideFigure, false)
}
p.r.SetAttr(nil) // reset it again. TODO(miek): double check
return end
}
// 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]
}
|