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

package parser

import (
	"bytes"
	"regexp"

	"github.com/yuin/goldmark/ast"
	"github.com/yuin/goldmark/text"
	"github.com/yuin/goldmark/util"
)

type rawHTMLParser struct {
}

var defaultRawHTMLParser = &rawHTMLParser{}

// NewRawHTMLParser return a new InlineParser that can parse
// inline htmls
func NewRawHTMLParser() InlineParser {
	return defaultRawHTMLParser
}

func (s *rawHTMLParser) Trigger() []byte {
	return []byte{'<'}
}

func (s *rawHTMLParser) Parse(parent ast.Node, block text.Reader, pc Context) ast.Node {
	line, _ := block.PeekLine()
	if len(line) > 1 && util.IsAlphaNumeric(line[1]) {
		return s.parseMultiLineRegexp(openTagRegexp, block, pc)
	}
	if len(line) > 2 && line[1] == '/' && util.IsAlphaNumeric(line[2]) {
		return s.parseMultiLineRegexp(closeTagRegexp, block, pc)
	}
	if bytes.HasPrefix(line, []byte("<!--")) {
		return s.parseMultiLineRegexp(commentRegexp, block, pc)
	}
	if bytes.HasPrefix(line, []byte("<?")) {
		return s.parseSingleLineRegexp(processingInstructionRegexp, block, pc)
	}
	if len(line) > 2 && line[1] == '!' && line[2] >= 'A' && line[2] <= 'Z' {
		return s.parseSingleLineRegexp(declRegexp, block, pc)
	}
	if bytes.HasPrefix(line, []byte("<![CDATA[")) {
		return s.parseMultiLineRegexp(cdataRegexp, block, pc)
	}
	return nil
}

var tagnamePattern = `([A-Za-z][A-Za-z0-9-]*)`
var attributePattern = `(?:\s+[a-zA-Z_:][a-zA-Z0-9:._-]*(?:\s*=\s*(?:[^\"'=<>` + "`" + `\x00-\x20]+|'[^']*'|"[^"]*"))?)`
var openTagRegexp = regexp.MustCompile("^<" + tagnamePattern + attributePattern + `*\s*/?>`)
var closeTagRegexp = regexp.MustCompile("^</" + tagnamePattern + `\s*>`)
var commentRegexp = regexp.MustCompile(`^<!---->|<!--(?:-?[^>-])(?:-?[^-])*-->`)
var processingInstructionRegexp = regexp.MustCompile(`^(?:<\?).*?(?:\?>)`)
var declRegexp = regexp.MustCompile(`^<![A-Z]+\s+[^>]*>`)
var cdataRegexp = regexp.MustCompile(`<!\[CDATA\[[\s\S]*?\]\]>`)

func (s *rawHTMLParser) parseSingleLineRegexp(reg *regexp.Regexp, block text.Reader, pc Context) ast.Node {
	line, segment := block.PeekLine()
	match := reg.FindSubmatchIndex(line)
	if match == nil {
		return nil
	}
	node := ast.NewRawHTML()
	node.Segments.Append(segment.WithStop(segment.Start + match[1]))
	block.Advance(match[1])
	return node
}

func (s *rawHTMLParser) parseMultiLineRegexp(reg *regexp.Regexp, block text.Reader, pc Context) ast.Node {
	sline, ssegment := block.Position()
	if block.Match(reg) {
		node := ast.NewRawHTML()
		eline, esegment := block.Position()
		block.SetPosition(sline, ssegment)
		for {
			line, segment := block.PeekLine()
			if line == nil {
				break
			}
			l, _ := block.Position()
			start := segment.Start
			if l == sline {
				start = ssegment.Start
			}
			end := segment.Stop
			if l == eline {
				end = esegment.Start
			}

			node.Segments.Append(text.NewSegment(start, end))
			if l == eline {
				block.Advance(end - start)
				break
			} else {
				block.AdvanceLine()
			}
		}
		return node
	}
	return nil
}