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

package chroma

import (
	"bytes"
)

type delegatingLexer struct {
	root     Lexer
	language Lexer
}

// DelegatingLexer combines two lexers to handle the common case of a language embedded inside another, such as PHP
// inside HTML or PHP inside plain text.
//
// It takes two lexer as arguments: a root lexer and a language lexer.  First everything is scanned using the language
// lexer, which must return "Other" for unrecognised tokens. Then all "Other" tokens are lexed using the root lexer.
// Finally, these two sets of tokens are merged.
//
// The lexers from the template lexer package use this base lexer.
func DelegatingLexer(root Lexer, language Lexer) Lexer {
	return &delegatingLexer{
		root:     root,
		language: language,
	}
}

func (d *delegatingLexer) Config() *Config {
	return d.language.Config()
}

// An insertion is the character range where language tokens should be inserted.
type insertion struct {
	start, end int
	tokens     []Token
}

func (d *delegatingLexer) Tokenise(options *TokeniseOptions, text string) (Iterator, error) { // nolint: gocognit
	tokens, err := Tokenise(Coalesce(d.language), options, text)
	if err != nil {
		return nil, err
	}
	// Compute insertions and gather "Other" tokens.
	others := &bytes.Buffer{}
	insertions := []*insertion{}
	var insert *insertion
	offset := 0
	var last Token
	for _, t := range tokens {
		if t.Type == Other {
			if last != EOF && insert != nil && last.Type != Other {
				insert.end = offset
			}
			others.WriteString(t.Value)
		} else {
			if last == EOF || last.Type == Other {
				insert = &insertion{start: offset}
				insertions = append(insertions, insert)
			}
			insert.tokens = append(insert.tokens, t)
		}
		last = t
		offset += len(t.Value)
	}

	if len(insertions) == 0 {
		return d.root.Tokenise(options, text)
	}

	// Lex the other tokens.
	rootTokens, err := Tokenise(Coalesce(d.root), options, others.String())
	if err != nil {
		return nil, err
	}

	// Interleave the two sets of tokens.
	var out []Token
	offset = 0 // Offset into text.
	tokenIndex := 0
	nextToken := func() Token {
		if tokenIndex >= len(rootTokens) {
			return EOF
		}
		t := rootTokens[tokenIndex]
		tokenIndex++
		return t
	}
	insertionIndex := 0
	nextInsertion := func() *insertion {
		if insertionIndex >= len(insertions) {
			return nil
		}
		i := insertions[insertionIndex]
		insertionIndex++
		return i
	}
	t := nextToken()
	i := nextInsertion()
	for t != EOF || i != nil {
		// fmt.Printf("%d->%d:%q   %d->%d:%q\n", offset, offset+len(t.Value), t.Value, i.start, i.end, Stringify(i.tokens...))
		if t == EOF || (i != nil && i.start < offset+len(t.Value)) {
			var l Token
			l, t = splitToken(t, i.start-offset)
			if l != EOF {
				out = append(out, l)
				offset += len(l.Value)
			}
			out = append(out, i.tokens...)
			offset += i.end - i.start
			if t == EOF {
				t = nextToken()
			}
			i = nextInsertion()
		} else {
			out = append(out, t)
			offset += len(t.Value)
			t = nextToken()
		}
	}
	return Literator(out...), nil
}

func splitToken(t Token, offset int) (l Token, r Token) {
	if t == EOF {
		return EOF, EOF
	}
	if offset == 0 {
		return EOF, t
	}
	if offset == len(t.Value) {
		return t, EOF
	}
	l = t.Clone()
	r = t.Clone()
	l.Value = l.Value[:offset]
	r.Value = r.Value[offset:]
	return
}