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

package chroma

import (
	"fmt"
	"strings"
)

var (
	defaultOptions = &TokeniseOptions{
		State:    "root",
		EnsureLF: true,
	}
)

// Config for a lexer.
type Config struct {
	// Name of the lexer.
	Name string

	// Shortcuts for the lexer
	Aliases []string

	// File name globs
	Filenames []string

	// Secondary file name globs
	AliasFilenames []string

	// MIME types
	MimeTypes []string

	// Regex matching is case-insensitive.
	CaseInsensitive bool

	// Regex matches all characters.
	DotAll bool

	// Regex does not match across lines ($ matches EOL).
	//
	// Defaults to multiline.
	NotMultiline bool

	// Don't strip leading and trailing newlines from the input.
	// DontStripNL bool

	// Strip all leading and trailing whitespace from the input
	// StripAll bool

	// Make sure that the input ends with a newline. This
	// is required for some lexers that consume input linewise.
	EnsureNL bool

	// If given and greater than 0, expand tabs in the input.
	// TabSize int

	// Priority of lexer.
	//
	// If this is 0 it will be treated as a default of 1.
	Priority float32
}

// Token output to formatter.
type Token struct {
	Type  TokenType `json:"type"`
	Value string    `json:"value"`
}

func (t *Token) String() string   { return t.Value }
func (t *Token) GoString() string { return fmt.Sprintf("&Token{%s, %q}", t.Type, t.Value) }

// Clone returns a clone of the Token.
func (t *Token) Clone() Token {
	return *t
}

// EOF is returned by lexers at the end of input.
var EOF Token

// TokeniseOptions contains options for tokenisers.
type TokeniseOptions struct {
	// State to start tokenisation in. Defaults to "root".
	State string
	// Nested tokenisation.
	Nested bool

	// If true, all EOLs are converted into LF
	// by replacing CRLF and CR
	EnsureLF bool
}

// A Lexer for tokenising source code.
type Lexer interface {
	// Config describing the features of the Lexer.
	Config() *Config
	// Tokenise returns an Iterator over tokens in text.
	Tokenise(options *TokeniseOptions, text string) (Iterator, error)
}

// Lexers is a slice of lexers sortable by name.
type Lexers []Lexer

func (l Lexers) Len() int      { return len(l) }
func (l Lexers) Swap(i, j int) { l[i], l[j] = l[j], l[i] }
func (l Lexers) Less(i, j int) bool {
	return strings.ToLower(l[i].Config().Name) < strings.ToLower(l[j].Config().Name)
}

// PrioritisedLexers is a slice of lexers sortable by priority.
type PrioritisedLexers []Lexer

func (l PrioritisedLexers) Len() int      { return len(l) }
func (l PrioritisedLexers) Swap(i, j int) { l[i], l[j] = l[j], l[i] }
func (l PrioritisedLexers) Less(i, j int) bool {
	ip := l[i].Config().Priority
	if ip == 0 {
		ip = 1
	}
	jp := l[j].Config().Priority
	if jp == 0 {
		jp = 1
	}
	return ip > jp
}

// Analyser determines how appropriate this lexer is for the given text.
type Analyser interface {
	AnalyseText(text string) float32
}