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
138. 138
139. 139
140. 140
141. 141
142. 142
143. 143
144. 144
145. 145
146. 146
147. 147
148. 148
149. 149
150. 150
151. 151
152. 152
153. 153
154. 154
155. 155
156. 156
157. 157
158. 158
159. 159
160. 160
161. 161
162. 162
163. 163
164. 164
165. 165
166. 166
167. 167
168. 168
169. 169
170. 170
171. 171
172. 172
173. 173
174. 174
175. 175
176. 176
177. 177
178. 178
179. 179
180. 180
181. 181
182. 182
183. 183
184. 184
185. 185
186. 186
187. 187
188. 188
189. 189
190. 190

// Copyright 2018 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.

package text

// parseNumberValue parses a number from the input and returns a Token object.
func (d *Decoder) parseNumberValue() (Token, bool) {
	in := d.in
	num := parseNumber(in)
	if num.size == 0 {
		return Token{}, false
	}
	numAttrs := num.kind
	if num.neg {
		numAttrs |= isNegative
	}
	strSize := num.size
	last := num.size - 1
	if num.kind == numFloat && (d.in[last] == 'f' || d.in[last] == 'F') {
		strSize = last
	}
	tok := Token{
		kind:     Scalar,
		attrs:    numberValue,
		pos:      len(d.orig) - len(d.in),
		raw:      d.in[:num.size],
		str:      string(d.in[:strSize]),
		numAttrs: numAttrs,
	}
	d.consume(num.size)
	return tok, true
}

const (
	numDec uint8 = (1 << iota) / 2
	numHex
	numOct
	numFloat
)

// number is the result of parsing out a valid number from parseNumber. It
// contains data for doing float or integer conversion via the strconv package
// in conjunction with the input bytes.
type number struct {
	kind uint8
	neg  bool
	size int
}

// parseNumber constructs a number object from given input. It allows for the
// following patterns:
//   integer: ^-?([1-9][0-9]*|0[xX][0-9a-fA-F]+|0[0-7]*)
//   float: ^-?((0|[1-9][0-9]*)?([.][0-9]*)?([eE][+-]?[0-9]+)?[fF]?)
// It also returns the number of parsed bytes for the given number, 0 if it is
// not a number.
func parseNumber(input []byte) number {
	kind := numDec
	var size int
	var neg bool

	s := input
	if len(s) == 0 {
		return number{}
	}

	// Optional -
	if s[0] == '-' {
		neg = true
		s = s[1:]
		size++
		if len(s) == 0 {
			return number{}
		}
	}

	// C++ allows for whitespace and comments in between the negative sign and
	// the rest of the number. This logic currently does not but is consistent
	// with v1.

	switch {
	case s[0] == '0':
		if len(s) > 1 {
			switch {
			case s[1] == 'x' || s[1] == 'X':
				// Parse as hex number.
				kind = numHex
				n := 2
				s = s[2:]
				for len(s) > 0 && (('0' <= s[0] && s[0] <= '9') ||
					('a' <= s[0] && s[0] <= 'f') ||
					('A' <= s[0] && s[0] <= 'F')) {
					s = s[1:]
					n++
				}
				if n == 2 {
					return number{}
				}
				size += n

			case '0' <= s[1] && s[1] <= '7':
				// Parse as octal number.
				kind = numOct
				n := 2
				s = s[2:]
				for len(s) > 0 && '0' <= s[0] && s[0] <= '7' {
					s = s[1:]
					n++
				}
				size += n
			}

			if kind&(numHex|numOct) > 0 {
				if len(s) > 0 && !isDelim(s[0]) {
					return number{}
				}
				return number{kind: kind, neg: neg, size: size}
			}
		}
		s = s[1:]
		size++

	case '1' <= s[0] && s[0] <= '9':
		n := 1
		s = s[1:]
		for len(s) > 0 && '0' <= s[0] && s[0] <= '9' {
			s = s[1:]
			n++
		}
		size += n

	case s[0] == '.':
		// Set kind to numFloat to signify the intent to parse as float. And
		// that it needs to have other digits after '.'.
		kind = numFloat

	default:
		return number{}
	}

	// . followed by 0 or more digits.
	if len(s) > 0 && s[0] == '.' {
		n := 1
		s = s[1:]
		// If decimal point was before any digits, it should be followed by
		// other digits.
		if len(s) == 0 && kind == numFloat {
			return number{}
		}
		for len(s) > 0 && '0' <= s[0] && s[0] <= '9' {
			s = s[1:]
			n++
		}
		size += n
		kind = numFloat
	}

	// e or E followed by an optional - or + and 1 or more digits.
	if len(s) >= 2 && (s[0] == 'e' || s[0] == 'E') {
		kind = numFloat
		s = s[1:]
		n := 1
		if s[0] == '+' || s[0] == '-' {
			s = s[1:]
			n++
			if len(s) == 0 {
				return number{}
			}
		}
		for len(s) > 0 && '0' <= s[0] && s[0] <= '9' {
			s = s[1:]
			n++
		}
		size += n
	}

	// Optional suffix f or F for floats.
	if len(s) > 0 && (s[0] == 'f' || s[0] == 'F') {
		kind = numFloat
		s = s[1:]
		size++
	}

	// Check that next byte is a delimiter or it is at the end.
	if len(s) > 0 && !isDelim(s[0]) {
		return number{}
	}

	return number{kind: kind, neg: neg, size: size}
}