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

package org

import (
	"regexp"
	"strings"
	"unicode"
)

type Block struct {
	Name       string
	Parameters []string
	Children   []Node
	Result     Node
}

type Result struct {
	Node Node
}

type Example struct {
	Children []Node
}

var exampleLineRegexp = regexp.MustCompile(`^(\s*):(\s(.*)|\s*$)`)
var beginBlockRegexp = regexp.MustCompile(`(?i)^(\s*)#\+BEGIN_(\w+)(.*)`)
var endBlockRegexp = regexp.MustCompile(`(?i)^(\s*)#\+END_(\w+)`)
var resultRegexp = regexp.MustCompile(`(?i)^(\s*)#\+RESULTS:`)
var exampleBlockEscapeRegexp = regexp.MustCompile(`(^|\n)([ \t]*),([ \t]*)(\*|,\*|#\+|,#\+)`)

func lexBlock(line string) (token, bool) {
	if m := beginBlockRegexp.FindStringSubmatch(line); m != nil {
		return token{"beginBlock", len(m[1]), strings.ToUpper(m[2]), m}, true
	} else if m := endBlockRegexp.FindStringSubmatch(line); m != nil {
		return token{"endBlock", len(m[1]), strings.ToUpper(m[2]), m}, true
	}
	return nilToken, false
}

func lexResult(line string) (token, bool) {
	if m := resultRegexp.FindStringSubmatch(line); m != nil {
		return token{"result", len(m[1]), "", m}, true
	}
	return nilToken, false
}

func lexExample(line string) (token, bool) {
	if m := exampleLineRegexp.FindStringSubmatch(line); m != nil {
		return token{"example", len(m[1]), m[3], m}, true
	}
	return nilToken, false
}

func isRawTextBlock(name string) bool { return name == "SRC" || name == "EXAMPLE" || name == "EXPORT" }

func (d *Document) parseBlock(i int, parentStop stopFn) (int, Node) {
	t, start := d.tokens[i], i
	name, parameters := t.content, splitParameters(t.matches[3])
	trim := trimIndentUpTo(d.tokens[i].lvl)
	stop := func(d *Document, i int) bool {
		return i >= len(d.tokens) || (d.tokens[i].kind == "endBlock" && d.tokens[i].content == name)
	}
	block, i := Block{name, parameters, nil, nil}, i+1
	if isRawTextBlock(name) {
		rawText := ""
		for ; !stop(d, i); i++ {
			rawText += trim(d.tokens[i].matches[0]) + "\n"
		}
		if name == "EXAMPLE" || (name == "SRC" && len(parameters) >= 1 && parameters[0] == "org") {
			rawText = exampleBlockEscapeRegexp.ReplaceAllString(rawText, "$1$2$3$4")
		}
		block.Children = d.parseRawInline(rawText)
	} else {
		consumed, nodes := d.parseMany(i, stop)
		block.Children = nodes
		i += consumed
	}
	if i >= len(d.tokens) || d.tokens[i].kind != "endBlock" || d.tokens[i].content != name {
		return 0, nil
	}
	if name == "SRC" {
		consumed, result := d.parseSrcBlockResult(i+1, parentStop)
		block.Result = result
		i += consumed
	}
	return i + 1 - start, block
}

func (d *Document) parseSrcBlockResult(i int, parentStop stopFn) (int, Node) {
	start := i
	for ; !parentStop(d, i) && d.tokens[i].kind == "text" && d.tokens[i].content == ""; i++ {
	}
	if parentStop(d, i) || d.tokens[i].kind != "result" {
		return 0, nil
	}
	consumed, result := d.parseResult(i, parentStop)
	return (i - start) + consumed, result
}

func (d *Document) parseExample(i int, parentStop stopFn) (int, Node) {
	example, start := Example{}, i
	for ; !parentStop(d, i) && d.tokens[i].kind == "example"; i++ {
		example.Children = append(example.Children, Text{d.tokens[i].content, true})
	}
	return i - start, example
}

func (d *Document) parseResult(i int, parentStop stopFn) (int, Node) {
	if i+1 >= len(d.tokens) {
		return 0, nil
	}
	consumed, node := d.parseOne(i+1, parentStop)
	return consumed + 1, Result{node}
}

func trimIndentUpTo(max int) func(string) string {
	return func(line string) string {
		i := 0
		for ; i < len(line) && i < max && unicode.IsSpace(rune(line[i])); i++ {
		}
		return line[i:]
	}
}

func splitParameters(s string) []string {
	parameters, parts := []string{}, strings.Split(s, " :")
	lang, rest := strings.TrimSpace(parts[0]), parts[1:]
	if lang != "" {
		parameters = append(parameters, lang)
	}
	for _, p := range rest {
		kv := strings.SplitN(p+" ", " ", 2)
		parameters = append(parameters, ":"+kv[0], strings.TrimSpace(kv[1]))
	}
	return parameters
}

func (b Block) ParameterMap() map[string]string {
	if len(b.Parameters) == 0 {
		return nil
	}
	m := map[string]string{":lang": b.Parameters[0]}
	for i := 1; i+1 < len(b.Parameters); i += 2 {
		m[b.Parameters[i]] = b.Parameters[i+1]
	}
	return m
}

func (n Example) String() string { return orgWriter.WriteNodesAsString(n) }
func (n Block) String() string   { return orgWriter.WriteNodesAsString(n) }
func (n Result) String() string  { return orgWriter.WriteNodesAsString(n) }