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
191. 191
192. 192
193. 193

// Package shlex provides a simple lexical analysis like Unix shell.
package shlex

import (
	"bufio"
	"errors"
	"io"
	"strings"
	"unicode"
)

var (
	ErrNoClosing = errors.New("No closing quotation")
	ErrNoEscaped = errors.New("No escaped character")
)

// Tokenizer is the interface that classifies a token according to
// words, whitespaces, quotations, escapes and escaped quotations.
type Tokenizer interface {
	IsWord(rune) bool
	IsWhitespace(rune) bool
	IsQuote(rune) bool
	IsEscape(rune) bool
	IsEscapedQuote(rune) bool
}

// DefaultTokenizer implements a simple tokenizer like Unix shell.
type DefaultTokenizer struct{}

func (t *DefaultTokenizer) IsWord(r rune) bool {
	return r == '_' || unicode.IsLetter(r) || unicode.IsNumber(r)
}
func (t *DefaultTokenizer) IsQuote(r rune) bool {
	switch r {
	case '\'', '"':
		return true
	default:
		return false
	}
}
func (t *DefaultTokenizer) IsWhitespace(r rune) bool {
	return unicode.IsSpace(r)
}
func (t *DefaultTokenizer) IsEscape(r rune) bool {
	return r == '\\'
}
func (t *DefaultTokenizer) IsEscapedQuote(r rune) bool {
	return r == '"'
}

// Lexer represents a lexical analyzer.
type Lexer struct {
	reader          *bufio.Reader
	tokenizer       Tokenizer
	posix           bool
	whitespacesplit bool
}

// NewLexer creates a new Lexer reading from io.Reader.  This Lexer
// has a DefaultTokenizer according to posix and whitespacesplit
// rules.
func NewLexer(r io.Reader, posix, whitespacesplit bool) *Lexer {
	return &Lexer{
		reader:          bufio.NewReader(r),
		tokenizer:       &DefaultTokenizer{},
		posix:           posix,
		whitespacesplit: whitespacesplit,
	}
}

// NewLexerString creates a new Lexer reading from a string.  This
// Lexer has a DefaultTokenizer according to posix and whitespacesplit
// rules.
func NewLexerString(s string, posix, whitespacesplit bool) *Lexer {
	return NewLexer(strings.NewReader(s), posix, whitespacesplit)
}

// Split splits a string according to posix or non-posix rules.
func Split(s string, posix bool) ([]string, error) {
	return NewLexerString(s, posix, true).Split()
}

// SetTokenizer sets a Tokenizer.
func (l *Lexer) SetTokenizer(t Tokenizer) {
	l.tokenizer = t
}

func (l *Lexer) Split() ([]string, error) {
	result := make([]string, 0)
	for {
		token, err := l.readToken()
		if token != "" {
			result = append(result, token)
		}

		if err == io.EOF {
			break
		} else if err != nil {
			return result, err
		}
	}
	return result, nil
}

func (l *Lexer) readToken() (string, error) {
	t := l.tokenizer
	token := ""
	quoted := false
	state := ' '
	escapedstate := ' '
scanning:
	for {
		next, _, err := l.reader.ReadRune()
		if err != nil {
			if t.IsQuote(state) {
				return token, ErrNoClosing
			} else if t.IsEscape(state) {
				return token, ErrNoEscaped
			}
			return token, err
		}

		switch {
		case t.IsWhitespace(state):
			switch {
			case t.IsWhitespace(next):
				break scanning
			case l.posix && t.IsEscape(next):
				escapedstate = 'a'
				state = next
			case t.IsWord(next):
				token += string(next)
				state = 'a'
			case t.IsQuote(next):
				if !l.posix {
					token += string(next)
				}
				state = next
			default:
				token = string(next)
				if l.whitespacesplit {
					state = 'a'
				} else if token != "" || (l.posix && quoted) {
					break scanning
				}
			}
		case t.IsQuote(state):
			quoted = true
			switch {
			case next == state:
				if !l.posix {
					token += string(next)
					break scanning
				} else {
					state = 'a'
				}
			case l.posix && t.IsEscape(next) && t.IsEscapedQuote(state):
				escapedstate = state
				state = next
			default:
				token += string(next)
			}
		case t.IsEscape(state):
			if t.IsQuote(escapedstate) && next != state && next != escapedstate {
				token += string(state)
			}
			token += string(next)
			state = escapedstate
		case t.IsWord(state):
			switch {
			case t.IsWhitespace(next):
				if token != "" || (l.posix && quoted) {
					break scanning
				}
			case l.posix && t.IsQuote(next):
				state = next
			case l.posix && t.IsEscape(next):
				escapedstate = 'a'
				state = next
			case t.IsWord(next) || t.IsQuote(next):
				token += string(next)
			default:
				if l.whitespacesplit {
					token += string(next)
				} else if token != "" {
					l.reader.UnreadRune()
					break scanning
				}
			}
		}
	}
	return token, nil
}