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

package chardet

import (
	"bytes"
)

var utf8Bom = []byte{0xEF, 0xBB, 0xBF}

type recognizerUtf8 struct {
}

func newRecognizer_utf8() *recognizerUtf8 {
	return &recognizerUtf8{}
}

func (*recognizerUtf8) Match(input *recognizerInput) (output recognizerOutput) {
	output = recognizerOutput{
		Charset: "UTF-8",
	}
	hasBom := bytes.HasPrefix(input.raw, utf8Bom)
	inputLen := len(input.raw)
	var numValid, numInvalid uint32
	var trailBytes uint8
	for i := 0; i < inputLen; i++ {
		c := input.raw[i]
		if c&0x80 == 0 {
			continue
		}
		if c&0xE0 == 0xC0 {
			trailBytes = 1
		} else if c&0xF0 == 0xE0 {
			trailBytes = 2
		} else if c&0xF8 == 0xF0 {
			trailBytes = 3
		} else {
			numInvalid++
			if numInvalid > 5 {
				break
			}
			trailBytes = 0
		}

		for i++; i < inputLen; i++ {
			c = input.raw[i]
			if c&0xC0 != 0x80 {
				numInvalid++
				break
			}
			if trailBytes--; trailBytes == 0 {
				numValid++
				break
			}
		}
	}

	if hasBom && numInvalid == 0 {
		output.Confidence = 100
	} else if hasBom && numValid > numInvalid*10 {
		output.Confidence = 80
	} else if numValid > 3 && numInvalid == 0 {
		output.Confidence = 100
	} else if numValid > 0 && numInvalid == 0 {
		output.Confidence = 80
	} else if numValid == 0 && numInvalid == 0 {
		// Plain ASCII
		output.Confidence = 10
	} else if numValid > numInvalid*10 {
		output.Confidence = 25
	}
	return
}