gitea

Development moved to Codeberg

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5
  6. 6
  7. 7
  8. 8
  9. 9
  10. 10
  11. 11
  12. 12
  13. 13
  14. 14
  15. 15
  16. 16
  17. 17
  18. 18
  19. 19
  20. 20
  21. 21
  22. 22
  23. 23
  24. 24
  25. 25
  26. 26
  27. 27
  28. 28
  29. 29
  30. 30
  31. 31
  32. 32
  33. 33
  34. 34
  35. 35
  36. 36
  37. 37
  38. 38
  39. 39
  40. 40
  41. 41
  42. 42
  43. 43
  44. 44
  45. 45
  46. 46
  47. 47
  48. 48
  49. 49
  50. 50
  51. 51
  52. 52
  53. 53
  54. 54
  55. 55
  56. 56
  57. 57
  58. 58
  59. 59
  60. 60
  61. 61
  62. 62
  63. 63
  64. 64
  65. 65
  66. 66
  67. 67
  68. 68
  69. 69
  70. 70
  71. 71
  72. 72
  73. 73
  74. 74
  75. 75
  76. 76
  77. 77
  78. 78
  79. 79
  80. 80
  81. 81
  82. 82
  83. 83
  84. 84
  85. 85
  86. 86
  87. 87
  88. 88
  89. 89
  90. 90
  91. 91
  92. 92
  93. 93
  94. 94
  95. 95
  96. 96
  97. 97
  98. 98
  99. 99
  100. 100
  101. 101
  102. 102
  103. 103
  104. 104
  105. 105
  106. 106
  107. 107
  108. 108
  109. 109
  110. 110
  111. 111
  112. 112
  113. 113
  114. 114
  115. 115
  116. 116
  117. 117
  118. 118
  119. 119
  120. 120
  121. 121
  122. 122
  123. 123
  124. 124
  125. 125
  126. 126
  127. 127
  128. 128
  129. 129
  130. 130
  131. 131
  132. 132
  133. 133
  134. 134
  135. 135
  136. 136
  137. 137
  138. 138
  139. 139
  140. 140
  141. 141
  142. 142
  143. 143
  144. 144
  145. 145
  146. 146
  147. 147
  148. 148
  149. 149
  150. 150
  151. 151
  152. 152
  153. 153
  154. 154
  155. 155
  156. 156
  157. 157
  158. 158
  159. 159
  160. 160
  161. 161
  162. 162
  163. 163
  164. 164
  165. 165
  166. 166
  167. 167
  168. 168
  169. 169
  170. 170
  171. 171
  172. 172
  173. 173
  174. 174
  175. 175
  176. 176
  177. 177
  178. 178
  179. 179
  180. 180
  181. 181
  182. 182
  183. 183
  184. 184
  185. 185
  186. 186
  187. 187
  188. 188
  189. 189
  190. 190
  191. 191
  192. 192
  193. 193
  194. 194
  195. 195
  196. 196
  197. 197
  198. 198
  199. 199
  200. 200
  201. 201
  202. 202
  203. 203
  204. 204
  205. 205
  206. 206
  207. 207
  208. 208
  209. 209
  210. 210
  211. 211
  212. 212
  213. 213
  214. 214
  215. 215
  216. 216
  217. 217
  218. 218
  219. 219
  220. 220
  221. 221
  222. 222
  223. 223
  224. 224
  225. 225
  226. 226
  227. 227
  228. 228
  229. 229
  230. 230
  231. 231
  232. 232
  233. 233
  234. 234
  235. 235
  236. 236
  237. 237
  238. 238
  239. 239
  240. 240
  241. 241
  242. 242
  243. 243
  244. 244
  245. 245
  246. 246
  247. 247
  248. 248
  249. 249
  250. 250
  251. 251
  252. 252
  253. 253
  254. 254
  255. 255
  256. 256
  257. 257
  258. 258
  259. 259
  260. 260
  261. 261
  262. 262
  263. 263
  264. 264
  265. 265
  266. 266
  267. 267
  268. 268
  269. 269
  270. 270
  271. 271
  272. 272
  273. 273
  274. 274
  275. 275
  276. 276
  277. 277
  278. 278
  279. 279
  280. 280
  281. 281
  282. 282
  283. 283
  284. 284
  285. 285
  286. 286
  287. 287
  288. 288
  289. 289
  290. 290
  291. 291
  292. 292
  293. 293
  294. 294
  295. 295
  296. 296
  297. 297
  298. 298
  299. 299
  300. 300
  301. 301
  302. 302
  303. 303
  304. 304
  305. 305
  306. 306
  307. 307
  308. 308
  309. 309
  310. 310
  311. 311
  312. 312
  313. 313
  314. 314
  315. 315
  316. 316
  317. 317
  318. 318
  319. 319
  320. 320
  321. 321
  322. 322
  323. 323
  324. 324
  325. 325
  326. 326
  327. 327
  328. 328
  329. 329
  330. 330
  331. 331
  332. 332
  333. 333
  334. 334
  335. 335
  336. 336
  337. 337
  338. 338
  339. 339
  340. 340
  341. 341
  342. 342
  343. 343
  344. 344
  345. 345
  346. 346
  347. 347
  348. 348
  349. 349
  350. 350
  351. 351
  352. 352
  353. 353
  354. 354
  355. 355
  356. 356
  357. 357
  358. 358
  359. 359
  360. 360
  361. 361
  362. 362
  363. 363
  364. 364
  365. 365
  366. 366
  367. 367
  368. 368
  369. 369
  370. 370
  371. 371
  372. 372
  373. 373
  374. 374
  375. 375
  376. 376
  377. 377
  378. 378
  379. 379
  380. 380
  381. 381
  382. 382
  383. 383
  384. 384
  385. 385
  386. 386
  387. 387
  388. 388
  389. 389
  390. 390
  391. 391
  392. 392
  393. 393
  394. 394
  395. 395
  396. 396
  397. 397
  398. 398
  399. 399
  400. 400
  401. 401
  402. 402
  403. 403
  404. 404
  405. 405
  406. 406
  407. 407
  408. 408
  409. 409
  410. 410
  411. 411
  412. 412
  413. 413
  414. 414
  415. 415
  416. 416
  417. 417
  418. 418
  419. 419
  420. 420
  421. 421
  422. 422
  423. 423
  424. 424
  425. 425
  426. 426
  427. 427
  428. 428
  429. 429
  430. 430
  431. 431
  432. 432
  433. 433
  434. 434
  435. 435
  436. 436
  437. 437
  438. 438
  439. 439
  440. 440
  441. 441
  442. 442
  443. 443
  444. 444
  445. 445
  446. 446
  447. 447
  448. 448
  449. 449
  450. 450
  451. 451
  452. 452
  453. 453
  454. 454
  455. 455
  456. 456
  457. 457
  458. 458
  459. 459
  460. 460
  461. 461
  462. 462
  463. 463
  464. 464
  465. 465
  466. 466
  467. 467
  468. 468
  469. 469
  470. 470
  471. 471
  472. 472
  473. 473
  474. 474
  475. 475
  476. 476
  477. 477
  478. 478
  479. 479
  480. 480
  481. 481
  482. 482
  483. 483
  484. 484
  485. 485
  486. 486
  487. 487
  488. 488
  489. 489
  490. 490
  491. 491
  492. 492
  493. 493
  494. 494
  495. 495
  496. 496
  497. 497
  498. 498
  499. 499
  500. 500
  501. 501
  502. 502
  503. 503
  504. 504
  505. 505
  506. 506
  507. 507
  508. 508
  509. 509
  510. 510
  511. 511
  512. 512
  513. 513
  514. 514
  515. 515
  516. 516
  517. 517
  518. 518
  519. 519
  520. 520
  521. 521
  522. 522
  523. 523
  524. 524
  525. 525
  526. 526
  527. 527
  528. 528
  529. 529
  530. 530
  531. 531
  532. 532
  533. 533
  534. 534
  535. 535
  536. 536
  537. 537
  538. 538
  539. 539
  540. 540
  541. 541
  542. 542
  543. 543
  544. 544
  545. 545
  546. 546
  547. 547
  548. 548
  549. 549
  550. 550
  551. 551
  552. 552
  553. 553
  554. 554
  555. 555
  556. 556
  557. 557
  558. 558
  559. 559
  560. 560
  561. 561
  562. 562
  563. 563
  564. 564
  565. 565
  566. 566
  567. 567
  568. 568
  569. 569
  570. 570
  571. 571
  572. 572
  573. 573
  574. 574
  575. 575
  576. 576
  577. 577
  578. 578
  579. 579
  580. 580
  581. 581
  582. 582
  583. 583
  584. 584
  585. 585
  586. 586
  587. 587
  588. 588
  589. 589
  590. 590
  591. 591
  592. 592
  593. 593
  594. 594
  595. 595
  596. 596
  597. 597
  598. 598
  599. 599
  600. 600
  601. 601
  602. 602
  603. 603
  604. 604
  605. 605
  606. 606
  607. 607
  608. 608
  609. 609
  610. 610
  611. 611
  612. 612
  613. 613
  614. 614
  615. 615
  616. 616
  617. 617
  618. 618
  619. 619
  620. 620
  621. 621
  622. 622
  623. 623
  624. 624
  625. 625
  626. 626
  627. 627
  628. 628
  629. 629
  630. 630
  631. 631
  632. 632
  633. 633
  634. 634
  635. 635
  636. 636
  637. 637
  638. 638
  639. 639
  640. 640
  641. 641
  642. 642
  643. 643
  644. 644
  645. 645
  646. 646
  647. 647
  648. 648
  649. 649
  650. 650
  651. 651
  652. 652
  653. 653
  654. 654
  655. 655
  656. 656
  657. 657
  658. 658
  659. 659
  660. 660
  661. 661
  662. 662
  663. 663
  664. 664
  665. 665
  666. 666
  667. 667
  668. 668
  669. 669
  670. 670
  671. 671
  672. 672
  673. 673
  674. 674
  675. 675
  676. 676
  677. 677
  678. 678
  679. 679
  680. 680
  681. 681
  682. 682
  683. 683
  684. 684
  685. 685
  686. 686
  687. 687
  688. 688
  689. 689
  690. 690
  691. 691
  692. 692
  693. 693
  694. 694
  695. 695
  696. 696
  697. 697
  698. 698
  699. 699
  700. 700
  701. 701
  702. 702
  703. 703
  704. 704
  705. 705
  706. 706
  707. 707
  708. 708
  709. 709
  710. 710
  711. 711
  712. 712
  713. 713
  714. 714
  715. 715
  716. 716
  717. 717
  718. 718
  719. 719
  720. 720
  721. 721
  722. 722
  723. 723
  724. 724
  725. 725
  726. 726
  727. 727
  728. 728
  729. 729
  730. 730
  731. 731
  732. 732
  733. 733
  734. 734
  735. 735
  736. 736
  737. 737
  738. 738
  739. 739
  740. 740
  741. 741
  742. 742
  743. 743
  744. 744
  745. 745
  746. 746
  747. 747
  748. 748
  749. 749
  750. 750
  751. 751
  752. 752
  753. 753
  754. 754
  755. 755
  756. 756
  757. 757
  758. 758
  759. 759
  760. 760
  761. 761
  762. 762
  763. 763
  764. 764
  765. 765
  766. 766
  767. 767
  768. 768
  769. 769
  770. 770
  771. 771
  772. 772
  773. 773
  774. 774
  775. 775
  776. 776
  777. 777
  778. 778
  779. 779
  780. 780
  781. 781
  782. 782
  783. 783
  784. 784
  785. 785
  786. 786
  787. 787
  788. 788
  789. 789
  790. 790
  791. 791
  792. 792
  793. 793
  794. 794
  795. 795
  796. 796
  797. 797
  798. 798
  799. 799
  800. 800
  801. 801
  802. 802
  803. 803
  804. 804
  805. 805
  806. 806
  807. 807
  808. 808
  809. 809
  810. 810
  811. 811
  812. 812
  813. 813
  814. 814
  815. 815
  816. 816
  817. 817
  818. 818
  819. 819
  820. 820
  821. 821
  822. 822
  823. 823
  824. 824
  825. 825
  826. 826
  827. 827
  828. 828
  829. 829
  830. 830
  831. 831
  832. 832
  833. 833
  834. 834
  835. 835
  836. 836
  837. 837
  838. 838
  839. 839
  840. 840
  841. 841
  842. 842
  843. 843
  844. 844
  845. 845
  846. 846
  847. 847
  848. 848
  849. 849
  850. 850
  851. 851
  852. 852
  853. 853
  854. 854
  855. 855
  856. 856
  857. 857
  858. 858
  859. 859
  860. 860
  861. 861
  862. 862
  863. 863
  864. 864
  865. 865
  866. 866
  867. 867
  868. 868
  869. 869
  870. 870
  871. 871
  872. 872
  873. 873
  874. 874
  875. 875
  876. 876
  877. 877
  878. 878
  879. 879
  880. 880
  881. 881
  882. 882
  883. 883
  884. 884
  885. 885
  886. 886
  887. 887
  888. 888
  889. 889
  890. 890
  891. 891
  892. 892
  893. 893
  894. 894
  895. 895
  896. 896
  897. 897
  898. 898
  899. 899
  900. 900
  901. 901
  902. 902
  903. 903
  904. 904
  905. 905
  906. 906
  907. 907
  908. 908
  909. 909
  910. 910
  911. 911
  912. 912
  913. 913
  914. 914
  915. 915
  916. 916
  917. 917
  918. 918
  919. 919
  920. 920
  921. 921
  922. 922
  923. 923
  924. 924
  925. 925
  926. 926
  927. 927
  928. 928
  929. 929
  930. 930
  931. 931
  932. 932
  933. 933
  934. 934
  935. 935
  936. 936
  937. 937
  938. 938
  939. 939
  940. 940
  941. 941
  942. 942
  943. 943
  944. 944
  945. 945
  946. 946
  947. 947
  948. 948
  949. 949
  950. 950
// 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.

package blackfriday

import (
	"bytes"
	"fmt"
	"io"
	"strings"
	"unicode/utf8"
)

//
// Markdown parsing and processing
//

// Version string of the package. Appears in the rendered document when
// CompletePage flag is on.
const Version = "2.0"

// Extensions is a bitwise or'ed collection of enabled Blackfriday's
// extensions.
type Extensions int

// These are the supported markdown parsing extensions.
// OR these values together to select multiple extensions.
const (
	NoExtensions           Extensions = 0
	NoIntraEmphasis        Extensions = 1 << iota // Ignore emphasis markers inside words
	Tables                                        // Render tables
	FencedCode                                    // Render fenced code blocks
	Autolink                                      // Detect embedded URLs that are not explicitly marked
	Strikethrough                                 // Strikethrough text using ~~test~~
	LaxHTMLBlocks                                 // Loosen up HTML block parsing rules
	SpaceHeadings                                 // Be strict about prefix heading rules
	HardLineBreak                                 // Translate newlines into line breaks
	TabSizeEight                                  // Expand tabs to eight spaces instead of four
	Footnotes                                     // Pandoc-style footnotes
	NoEmptyLineBeforeBlock                        // No need to insert an empty line to start a (code, quote, ordered list, unordered list) block
	HeadingIDs                                    // specify heading IDs  with {#id}
	Titleblock                                    // Titleblock ala pandoc
	AutoHeadingIDs                                // Create the heading ID from the text
	BackslashLineBreak                            // Translate trailing backslashes into line breaks
	DefinitionLists                               // Render definition lists

	CommonHTMLFlags HTMLFlags = UseXHTML | Smartypants |
		SmartypantsFractions | SmartypantsDashes | SmartypantsLatexDashes

	CommonExtensions Extensions = NoIntraEmphasis | Tables | FencedCode |
		Autolink | Strikethrough | SpaceHeadings | HeadingIDs |
		BackslashLineBreak | DefinitionLists
)

// ListType contains bitwise or'ed flags for list and list item objects.
type ListType int

// 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 (
	ListTypeOrdered ListType = 1 << iota
	ListTypeDefinition
	ListTypeTerm

	ListItemContainsBlock
	ListItemBeginningOfList // TODO: figure out if this is of any use now
	ListItemEndOfList
)

// CellAlignFlags holds a type of alignment in a table cell.
type CellAlignFlags int

// 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 (
	TableAlignmentLeft CellAlignFlags = 1 << iota
	TableAlignmentRight
	TableAlignmentCenter = (TableAlignmentLeft | TableAlignmentRight)
)

// The size of a tab stop.
const (
	TabSizeDefault = 4
	TabSizeDouble  = 8
)

// 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
	"address":    {},
	"article":    {},
	"aside":      {},
	"canvas":     {},
	"figcaption": {},
	"figure":     {},
	"footer":     {},
	"header":     {},
	"hgroup":     {},
	"main":       {},
	"nav":        {},
	"output":     {},
	"progress":   {},
	"section":    {},
	"video":      {},
}

// Renderer is the rendering interface. This is mostly of interest if you are
// implementing a new rendering format.
//
// Only an HTML implementation is provided in this repository, see the README
// for external implementations.
type Renderer interface {
	// RenderNode is the main rendering method. It will be called once for
	// every leaf node and twice for every non-leaf node (first with
	// entering=true, then with entering=false). The method should write its
	// rendition of the node to the supplied writer w.
	RenderNode(w io.Writer, node *Node, entering bool) WalkStatus

	// RenderHeader is a method that allows the renderer to produce some
	// content preceding the main body of the output document. The header is
	// understood in the broad sense here. For example, the default HTML
	// renderer will write not only the HTML document preamble, but also the
	// table of contents if it was requested.
	//
	// The method will be passed an entire document tree, in case a particular
	// implementation needs to inspect it to produce output.
	//
	// The output should be written to the supplied writer w. If your
	// implementation has no header to write, supply an empty implementation.
	RenderHeader(w io.Writer, ast *Node)

	// RenderFooter is a symmetric counterpart of RenderHeader.
	RenderFooter(w io.Writer, ast *Node)
}

// 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 *Markdown, data []byte, offset int) (int, *Node)

// Markdown is a type that holds extensions and the runtime state used by
// Parse, and the renderer. You can not use it directly, construct it with New.
type Markdown struct {
	renderer          Renderer
	referenceOverride ReferenceOverrideFunc
	refs              map[string]*reference
	inlineCallback    [256]inlineParser
	extensions        Extensions
	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

	doc                  *Node
	tip                  *Node // = doc
	oldTip               *Node
	lastMatchedContainer *Node // = doc
	allClosed            bool
}

func (p *Markdown) getRef(refid string) (ref *reference, found bool) {
	if p.referenceOverride != nil {
		r, overridden := p.referenceOverride(refid)
		if overridden {
			if r == nil {
				return nil, false
			}
			return &reference{
				link:     []byte(r.Link),
				title:    []byte(r.Title),
				noteID:   0,
				hasBlock: false,
				text:     []byte(r.Text)}, true
		}
	}
	// refs are case insensitive
	ref, found = p.refs[strings.ToLower(refid)]
	return ref, found
}

func (p *Markdown) finalize(block *Node) {
	above := block.Parent
	block.open = false
	p.tip = above
}

func (p *Markdown) addChild(node NodeType, offset uint32) *Node {
	return p.addExistingChild(NewNode(node), offset)
}

func (p *Markdown) addExistingChild(node *Node, offset uint32) *Node {
	for !p.tip.canContain(node.Type) {
		p.finalize(p.tip)
	}
	p.tip.AppendChild(node)
	p.tip = node
	return node
}

func (p *Markdown) closeUnmatchedBlocks() {
	if !p.allClosed {
		for p.oldTip != p.lastMatchedContainer {
			parent := p.oldTip.Parent
			p.finalize(p.oldTip)
			p.oldTip = parent
		}
		p.allClosed = true
	}
}

//
//
// Public interface
//
//

// Reference represents the details of a link.
// See the documentation in Options for more details on use-case.
type Reference struct {
	// Link is usually the URL the reference points to.
	Link string
	// Title is the alternate text describing the link in more detail.
	Title string
	// Text is the optional text to override the ref with if the syntax used was
	// [refid][]
	Text string
}

// ReferenceOverrideFunc is expected to be called with a reference string and
// return either a valid Reference type that the reference string maps to or
// nil. If overridden is false, the default reference logic will be executed.
// See the documentation in Options for more details on use-case.
type ReferenceOverrideFunc func(reference string) (ref *Reference, overridden bool)

// New constructs a Markdown processor. You can use the same With* functions as
// for Run() to customize parser's behavior and the renderer.
func New(opts ...Option) *Markdown {
	var p Markdown
	for _, opt := range opts {
		opt(&p)
	}
	p.refs = make(map[string]*reference)
	p.maxNesting = 16
	p.insideLink = false
	docNode := NewNode(Document)
	p.doc = docNode
	p.tip = docNode
	p.oldTip = docNode
	p.lastMatchedContainer = docNode
	p.allClosed = true
	// register inline parsers
	p.inlineCallback[' '] = maybeLineBreak
	p.inlineCallback['*'] = emphasis
	p.inlineCallback['_'] = emphasis
	if p.extensions&Strikethrough != 0 {
		p.inlineCallback['~'] = emphasis
	}
	p.inlineCallback['`'] = codeSpan
	p.inlineCallback['\n'] = lineBreak
	p.inlineCallback['['] = link
	p.inlineCallback['<'] = leftAngle
	p.inlineCallback['\\'] = escape
	p.inlineCallback['&'] = entity
	p.inlineCallback['!'] = maybeImage
	p.inlineCallback['^'] = maybeInlineFootnote
	if p.extensions&Autolink != 0 {
		p.inlineCallback['h'] = maybeAutoLink
		p.inlineCallback['m'] = maybeAutoLink
		p.inlineCallback['f'] = maybeAutoLink
		p.inlineCallback['H'] = maybeAutoLink
		p.inlineCallback['M'] = maybeAutoLink
		p.inlineCallback['F'] = maybeAutoLink
	}
	if p.extensions&Footnotes != 0 {
		p.notes = make([]*reference, 0)
	}
	return &p
}

// Option customizes the Markdown processor's default behavior.
type Option func(*Markdown)

// WithRenderer allows you to override the default renderer.
func WithRenderer(r Renderer) Option {
	return func(p *Markdown) {
		p.renderer = r
	}
}

// WithExtensions allows you to pick some of the many extensions provided by
// Blackfriday. You can bitwise OR them.
func WithExtensions(e Extensions) Option {
	return func(p *Markdown) {
		p.extensions = e
	}
}

// WithNoExtensions turns off all extensions and custom behavior.
func WithNoExtensions() Option {
	return func(p *Markdown) {
		p.extensions = NoExtensions
		p.renderer = NewHTMLRenderer(HTMLRendererParameters{
			Flags: HTMLFlagsNone,
		})
	}
}

// WithRefOverride sets an optional function callback that is called every
// time a reference is resolved.
//
// In Markdown, the link reference syntax can be made to resolve a link to
// a reference instead of an inline URL, in one of the following ways:
//
//  * [link text][refid]
//  * [refid][]
//
// Usually, the refid is defined at the bottom of the Markdown document. If
// this override function is provided, the refid is passed to the override
// function first, before consulting the defined refids at the bottom. If
// the override function indicates an override did not occur, the refids at
// the bottom will be used to fill in the link details.
func WithRefOverride(o ReferenceOverrideFunc) Option {
	return func(p *Markdown) {
		p.referenceOverride = o
	}
}

// Run is the main entry point to Blackfriday. It parses and renders a
// block of markdown-encoded text.
//
// The simplest invocation of Run takes one argument, input:
//     output := Run(input)
// This will parse the input with CommonExtensions enabled and render it with
// the default HTMLRenderer (with CommonHTMLFlags).
//
// Variadic arguments opts can customize the default behavior. Since Markdown
// type does not contain exported fields, you can not use it directly. Instead,
// use the With* functions. For example, this will call the most basic
// functionality, with no extensions:
//     output := Run(input, WithNoExtensions())
//
// You can use any number of With* arguments, even contradicting ones. They
// will be applied in order of appearance and the latter will override the
// former:
//     output := Run(input, WithNoExtensions(), WithExtensions(exts),
//         WithRenderer(yourRenderer))
func Run(input []byte, opts ...Option) []byte {
	r := NewHTMLRenderer(HTMLRendererParameters{
		Flags: CommonHTMLFlags,
	})
	optList := []Option{WithRenderer(r), WithExtensions(CommonExtensions)}
	optList = append(optList, opts...)
	parser := New(optList...)
	ast := parser.Parse(input)
	var buf bytes.Buffer
	parser.renderer.RenderHeader(&buf, ast)
	ast.Walk(func(node *Node, entering bool) WalkStatus {
		return parser.renderer.RenderNode(&buf, node, entering)
	})
	parser.renderer.RenderFooter(&buf, ast)
	return buf.Bytes()
}

// Parse is an entry point to the parsing part of Blackfriday. It takes an
// input markdown document and produces a syntax tree for its contents. This
// tree can then be rendered with a default or custom renderer, or
// analyzed/transformed by the caller to whatever non-standard needs they have.
// The return value is the root node of the syntax tree.
func (p *Markdown) Parse(input []byte) *Node {
	p.block(input)
	// Walk the tree and finish up some of unfinished blocks
	for p.tip != nil {
		p.finalize(p.tip)
	}
	// Walk the tree again and process inline markdown in each block
	p.doc.Walk(func(node *Node, entering bool) WalkStatus {
		if node.Type == Paragraph || node.Type == Heading || node.Type == TableCell {
			p.inline(node, node.content)
			node.content = nil
		}
		return GoToNext
	})
	p.parseRefsToAST()
	return p.doc
}

func (p *Markdown) parseRefsToAST() {
	if p.extensions&Footnotes == 0 || len(p.notes) == 0 {
		return
	}
	p.tip = p.doc
	block := p.addBlock(List, nil)
	block.IsFootnotesList = true
	block.ListFlags = ListTypeOrdered
	flags := ListItemBeginningOfList
	// Note: this loop is intentionally explicit, not range-form. This is
	// because the body of the loop will append nested footnotes to p.notes and
	// we need to process those late additions. Range form would only walk over
	// the fixed initial set.
	for i := 0; i < len(p.notes); i++ {
		ref := p.notes[i]
		p.addExistingChild(ref.footnote, 0)
		block := ref.footnote
		block.ListFlags = flags | ListTypeOrdered
		block.RefLink = ref.link
		if ref.hasBlock {
			flags |= ListItemContainsBlock
			p.block(ref.title)
		} else {
			p.inline(block, ref.title)
		}
		flags &^= ListItemBeginningOfList | ListItemContainsBlock
	}
	above := block.Parent
	finalizeList(block)
	p.tip = above
	block.Walk(func(node *Node, entering bool) WalkStatus {
		if node.Type == Paragraph || node.Type == Heading {
			p.inline(node, node.content)
			node.content = nil
		}
		return GoToNext
	})
}

//
// 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.
// Finally, there are inline footnotes such as:
//
//    Inline footnotes^[Also supported.] provide a quick inline explanation,
//    but are rendered at the bottom of the document.
//

// reference holds all information necessary for a reference-style links or
// footnotes.
//
// Consider this markdown with reference-style links:
//
//     [link][ref]
//
//     [ref]: /url/ "tooltip title"
//
// It will be ultimately converted to this HTML:
//
//     <p><a href=\"/url/\" title=\"title\">link</a></p>
//
// And a reference structure will be populated as follows:
//
//     p.refs["ref"] = &reference{
//         link: "/url/",
//         title: "tooltip title",
//     }
//
// Alternatively, reference can contain information about a footnote. Consider
// this markdown:
//
//     Text needing a footnote.[^a]
//
//     [^a]: This is the note
//
// A reference structure will be populated as follows:
//
//     p.refs["a"] = &reference{
//         link: "a",
//         title: "This is the note",
//         noteID: <some positive int>,
//     }
//
// TODO: As you can see, it begs for splitting into two dedicated structures
// for refs and for footnotes.
type reference struct {
	link     []byte
	title    []byte
	noteID   int // 0 if not a footnote ref
	hasBlock bool
	footnote *Node // a link to the Item node within a list of footnotes

	text []byte // only gets populated by refOverride feature with Reference.Text
}

func (r *reference) String() string {
	return fmt.Sprintf("{link: %q, title: %q, text: %q, noteID: %d, hasBlock: %v}",
		r.link, r.title, r.text, r.noteID, r.hasBlock)
}

// 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 *Markdown, 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

	// id part: anything but a newline between brackets
	if data[i] != '[' {
		return 0
	}
	i++
	if p.extensions&Footnotes != 0 {
		if i < len(data) && 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] != ']' {
		i++
	}
	if i >= len(data) || data[i] != ']' {
		return 0
	}
	idEnd := i
	// footnotes can have empty ID, like this: [^], but a reference can not be
	// empty like this: []. Break early if it's not a footnote and there's no ID
	if noteID == 0 && idOffset == idEnd {
		return 0
	}
	// 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.extensions&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
	} 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 *Markdown, 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 *Markdown, 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
}

//
//
// 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 ishorizontalspace(c) || isverticalspace(c)
}

// Test if a character is a horizontal whitespace character.
func ishorizontalspace(c byte) bool {
	return c == ' ' || c == '\t'
}

// Test if a character is a vertical character.
func isverticalspace(c byte) bool {
	return c == '\n' || c == '\r' || c == '\f' || c == '\v'
}

// Test if a character is letter.
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)
}

// 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]
}