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

// Package chardet ports character set detection from ICU.
package chardet

import (
	"errors"
	"sort"
)

// Result contains all the information that charset detector gives.
type Result struct {
	// IANA name of the detected charset.
	Charset string
	// IANA name of the detected language. It may be empty for some charsets.
	Language string
	// Confidence of the Result. Scale from 1 to 100. The bigger, the more confident.
	Confidence int
}

// Detector implements charset detection.
type Detector struct {
	recognizers []recognizer
	stripTag    bool
}

// List of charset recognizers
var recognizers = []recognizer{
	newRecognizer_utf8(),
	newRecognizer_utf16be(),
	newRecognizer_utf16le(),
	newRecognizer_utf32be(),
	newRecognizer_utf32le(),
	newRecognizer_8859_1_en(),
	newRecognizer_8859_1_da(),
	newRecognizer_8859_1_de(),
	newRecognizer_8859_1_es(),
	newRecognizer_8859_1_fr(),
	newRecognizer_8859_1_it(),
	newRecognizer_8859_1_nl(),
	newRecognizer_8859_1_no(),
	newRecognizer_8859_1_pt(),
	newRecognizer_8859_1_sv(),
	newRecognizer_8859_2_cs(),
	newRecognizer_8859_2_hu(),
	newRecognizer_8859_2_pl(),
	newRecognizer_8859_2_ro(),
	newRecognizer_8859_5_ru(),
	newRecognizer_8859_6_ar(),
	newRecognizer_8859_7_el(),
	newRecognizer_8859_8_I_he(),
	newRecognizer_8859_8_he(),
	newRecognizer_windows_1251(),
	newRecognizer_windows_1256(),
	newRecognizer_KOI8_R(),
	newRecognizer_8859_9_tr(),

	newRecognizer_sjis(),
	newRecognizer_gb_18030(),
	newRecognizer_euc_jp(),
	newRecognizer_euc_kr(),
	newRecognizer_big5(),

	newRecognizer_2022JP(),
	newRecognizer_2022KR(),
	newRecognizer_2022CN(),

	newRecognizer_IBM424_he_rtl(),
	newRecognizer_IBM424_he_ltr(),
	newRecognizer_IBM420_ar_rtl(),
	newRecognizer_IBM420_ar_ltr(),
}

// NewTextDetector creates a Detector for plain text.
func NewTextDetector() *Detector {
	return &Detector{recognizers, false}
}

// NewHtmlDetector creates a Detector for Html.
func NewHtmlDetector() *Detector {
	return &Detector{recognizers, true}
}

var (
	NotDetectedError = errors.New("Charset not detected.")
)

// DetectBest returns the Result with highest Confidence.
func (d *Detector) DetectBest(b []byte) (r *Result, err error) {
	var all []Result
	if all, err = d.DetectAll(b); err == nil {
		r = &all[0]
	}
	return
}

// DetectAll returns all Results which have non-zero Confidence. The Results are sorted by Confidence in descending order.
func (d *Detector) DetectAll(b []byte) ([]Result, error) {
	input := newRecognizerInput(b, d.stripTag)
	outputChan := make(chan recognizerOutput)
	for _, r := range d.recognizers {
		go matchHelper(r, input, outputChan)
	}
	outputs := make([]recognizerOutput, 0, len(d.recognizers))
	for i := 0; i < len(d.recognizers); i++ {
		o := <-outputChan
		if o.Confidence > 0 {
			outputs = append(outputs, o)
		}
	}
	if len(outputs) == 0 {
		return nil, NotDetectedError
	}

	sort.Sort(recognizerOutputs(outputs))
	dedupOutputs := make([]Result, 0, len(outputs))
	foundCharsets := make(map[string]struct{}, len(outputs))
	for _, o := range outputs {
		if _, found := foundCharsets[o.Charset]; !found {
			dedupOutputs = append(dedupOutputs, Result(o))
			foundCharsets[o.Charset] = struct{}{}
		}
	}
	if len(dedupOutputs) == 0 {
		return nil, NotDetectedError
	}
	return dedupOutputs, nil
}

func matchHelper(r recognizer, input *recognizerInput, outputChan chan<- recognizerOutput) {
	outputChan <- r.Match(input)
}

type recognizerOutputs []recognizerOutput

func (r recognizerOutputs) Len() int           { return len(r) }
func (r recognizerOutputs) Less(i, j int) bool { return r[i].Confidence > r[j].Confidence }
func (r recognizerOutputs) Swap(i, j int)      { r[i], r[j] = r[j], r[i] }