File: lex.go

package info (click to toggle)
aptly 1.6.2-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 49,928 kB
  • sloc: python: 10,398; sh: 252; makefile: 184
file content (239 lines) | stat: -rw-r--r-- 4,547 bytes parent folder | download | duplicates (5)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
package query

import (
	"fmt"
	"strings"
	"unicode"
	"unicode/utf8"
)

// itemType identifies the type of lex items.
type itemType int

const eof = -1

const (
	itemNull  itemType = iota
	itemError          // error occurred;
	// value is text of error
	itemEOF
	itemLeftParen  // (
	itemRightParen // )
	itemOr         // |
	itemAnd        // ,
	itemNot        // !
	itemLt         // <<
	itemLtEq       // <=, <
	itemGt         // >>
	itemGtEq       // >=, >
	itemEq         // =
	itemPatMatch   // %
	itemRegexp     // ~
	itemLeftCurly  // {
	itemRightCurly // }
	itemString
)

// item represents a token returned from the scanner.
type item struct {
	typ itemType // Type, such as itemNumber.
	val string   // Value, such as "23.2".
}

func (i item) String() string {
	if i.typ == itemString {
		return fmt.Sprintf("%#v", i.val)
	}
	if i.typ == itemEOF {
		return "<EOL>"
	}
	if i.typ == itemError {
		return fmt.Sprintf("error: %s", i.val)
	}
	if i.typ == itemNull {
		return "<NULL>"
	}
	return i.val
}

// stateFn represents the state of the scanner
// as a function that returns the next state.
type stateFn func(*lexer) stateFn

// lexer holds the state of the scanner.
type lexer struct {
	name  string    // used only for error reports.
	input string    // the string being scanned.
	start int       // start position of this item.
	pos   int       // current position in the input.
	width int       // width of last rune read from input.
	items chan item // channel of scanned items.
	last  item
}

func lex(name, input string) (*lexer, chan item) {
	l := &lexer{
		name:  name,
		input: input,
		items: make(chan item),
	}
	go l.run() // Concurrently run state machine.
	return l, l.items
}

// emit passes an item back to the client.
func (l *lexer) emit(t itemType) {
	l.items <- item{t, l.input[l.start:l.pos]}
	l.start = l.pos
}

// run lexes the input by executing state functions until
// the state is nil.
func (l *lexer) run() {
	for state := lexMain; state != nil; {
		state = state(l)
	}
	close(l.items) // No more tokens will be delivered.
}

// next returns the next rune in the input.
func (l *lexer) next() (r rune) {
	if l.pos >= len(l.input) {
		l.width = 0
		return eof
	}
	r, l.width =
		utf8.DecodeRuneInString(l.input[l.pos:])
	l.pos += l.width
	return r
}

// ignore skips over the pending input before this point.
func (l *lexer) ignore() {
	l.start = l.pos
}

// backup steps back one rune.
// Can be called only once per call of next.
func (l *lexer) backup() {
	l.pos -= l.width
}

func (l *lexer) Current() item {
	if l.last.typ == 0 {
		l.last = <-l.items
	}

	return l.last
}

func (l *lexer) Consume() {
	l.last = <-l.items
}

// error returns an error token and terminates the scan
// by passing back a nil pointer that will be the next
// state, terminating l.run.
func (l *lexer) errorf(format string, args ...interface{}) stateFn {
	l.items <- item{
		itemError,
		fmt.Sprintf(format, args...),
	}
	return nil
}

func lexMain(l *lexer) stateFn {
	switch r := l.next(); {
	case r == eof:
		l.emit(itemEOF)
		return nil
	case unicode.IsSpace(r):
		l.ignore()
	case r == '(':
		l.emit(itemLeftParen)
	case r == ')':
		l.emit(itemRightParen)
	case r == '{':
		l.emit(itemLeftCurly)
	case r == '}':
		l.emit(itemRightCurly)
	case r == '|':
		l.emit(itemOr)
	case r == ',':
		l.emit(itemAnd)
	case r == '!':
		l.emit(itemNot)
	case r == '<':
		r2 := l.next()
		if r2 == '<' {
			l.emit(itemLt)
		} else if r2 == '=' {
			l.emit(itemLtEq)
		} else {
			l.backup()
			l.emit(itemLtEq)
		}
	case r == '>':
		r2 := l.next()
		if r2 == '>' {
			l.emit(itemGt)
		} else if r2 == '=' {
			l.emit(itemGtEq)
		} else {
			l.backup()
			l.emit(itemGtEq)
		}
	case r == '=':
		l.emit(itemEq)
	case r == '%':
		l.emit(itemPatMatch)
	case r == '~':
		l.emit(itemRegexp)
	default:
		l.backup()
		return lexString
	}

	return lexMain
}

func lexString(l *lexer) stateFn {
	r := l.next()
	// quoted string
	if r == '"' || r == '\'' {
		quote := r
		result := ""
		l.ignore()
		for {
			r = l.next()
			if r == quote {
				l.ignore()
				l.items <- item{itemString, result}
				return lexMain
			}
			if r == '\\' {
				r = l.next()
			}
			if r == eof {
				return l.errorf("unexpected eof in quoted string")
			}
			result = result + string(r)
		}
	} else {
		// unquoted string
		for {
			if unicode.IsSpace(r) || strings.IndexRune("()|,!{}", r) > 0 {
				l.backup()
				l.emit(itemString)
				return lexMain
			}

			if r == eof {
				l.emit(itemString)
				l.emit(itemEOF)
				return nil
			}
			r = l.next()
		}
	}
}