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

// Copyright 2015 Huan Du. All rights reserved.
// Licensed under the MIT license that can be found in the LICENSE file.

package xstrings

import (
	"unicode"
	"unicode/utf8"
)

// Len returns str's utf8 rune length.
func Len(str string) int {
	return utf8.RuneCountInString(str)
}

// WordCount returns number of words in a string.
//
// Word is defined as a locale dependent string containing alphabetic characters,
// which may also contain but not start with `'` and `-` characters.
func WordCount(str string) int {
	var r rune
	var size, n int

	inWord := false

	for len(str) > 0 {
		r, size = utf8.DecodeRuneInString(str)

		switch {
		case isAlphabet(r):
			if !inWord {
				inWord = true
				n++
			}

		case inWord && (r == '\'' || r == '-'):
			// Still in word.

		default:
			inWord = false
		}

		str = str[size:]
	}

	return n
}

const minCJKCharacter = '\u3400'

// Checks r is a letter but not CJK character.
func isAlphabet(r rune) bool {
	if !unicode.IsLetter(r) {
		return false
	}

	switch {
	// Quick check for non-CJK character.
	case r < minCJKCharacter:
		return true

	// Common CJK characters.
	case r >= '\u4E00' && r <= '\u9FCC':
		return false

	// Rare CJK characters.
	case r >= '\u3400' && r <= '\u4D85':
		return false

	// Rare and historic CJK characters.
	case r >= '\U00020000' && r <= '\U0002B81D':
		return false
	}

	return true
}

// Width returns string width in monotype font.
// Multi-byte characters are usually twice the width of single byte characters.
//
// Algorithm comes from `mb_strwidth` in PHP.
// http://php.net/manual/en/function.mb-strwidth.php
func Width(str string) int {
	var r rune
	var size, n int

	for len(str) > 0 {
		r, size = utf8.DecodeRuneInString(str)
		n += RuneWidth(r)
		str = str[size:]
	}

	return n
}

// RuneWidth returns character width in monotype font.
// Multi-byte characters are usually twice the width of single byte characters.
//
// Algorithm comes from `mb_strwidth` in PHP.
// http://php.net/manual/en/function.mb-strwidth.php
func RuneWidth(r rune) int {
	switch {
	case r == utf8.RuneError || r < '\x20':
		return 0

	case '\x20' <= r && r < '\u2000':
		return 1

	case '\u2000' <= r && r < '\uFF61':
		return 2

	case '\uFF61' <= r && r < '\uFFA0':
		return 1

	case '\uFFA0' <= r:
		return 2
	}

	return 0
}