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
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
|
/*
Copyright 2012 Google Inc. All Rights Reserved.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
*/
package shlex
/*
Package shlex implements a simple lexer which splits input in to tokens using
shell-style rules for quoting and commenting.
*/
import (
"bufio"
"errors"
"fmt"
"io"
"strings"
)
/*
A TokenType is a top-level token; a word, space, comment, unknown.
*/
type TokenType int
/*
A RuneTokenType is the type of a UTF-8 character; a character, quote, space, escape.
*/
type RuneTokenType int
type lexerState int
type Token struct {
tokenType TokenType
value string
}
/*
Two tokens are equal if both their types and values are equal. A nil token can
never equal another token.
*/
func (a *Token) Equal(b *Token) bool {
if a == nil || b == nil {
return false
}
if a.tokenType != b.tokenType {
return false
}
return a.value == b.value
}
const (
RUNE_CHAR string = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789._-,/@$*()+=><:;&^%~|!?[]{}"
RUNE_SPACE string = " \t\r\n"
RUNE_ESCAPING_QUOTE string = "\""
RUNE_NONESCAPING_QUOTE string = "'"
RUNE_ESCAPE = "\\"
RUNE_COMMENT = "#"
RUNETOKEN_UNKNOWN RuneTokenType = 0
RUNETOKEN_CHAR RuneTokenType = 1
RUNETOKEN_SPACE RuneTokenType = 2
RUNETOKEN_ESCAPING_QUOTE RuneTokenType = 3
RUNETOKEN_NONESCAPING_QUOTE RuneTokenType = 4
RUNETOKEN_ESCAPE RuneTokenType = 5
RUNETOKEN_COMMENT RuneTokenType = 6
RUNETOKEN_EOF RuneTokenType = 7
TOKEN_UNKNOWN TokenType = 0
TOKEN_WORD TokenType = 1
TOKEN_SPACE TokenType = 2
TOKEN_COMMENT TokenType = 3
STATE_START lexerState = 0
STATE_INWORD lexerState = 1
STATE_ESCAPING lexerState = 2
STATE_ESCAPING_QUOTED lexerState = 3
STATE_QUOTED_ESCAPING lexerState = 4
STATE_QUOTED lexerState = 5
STATE_COMMENT lexerState = 6
INITIAL_TOKEN_CAPACITY int = 100
)
/*
A type for classifying characters. This allows for different sorts of
classifiers - those accepting extended non-ascii chars, or strict posix
compatibility, for example.
*/
type TokenClassifier struct {
typeMap map[int32]RuneTokenType
}
func addRuneClass(typeMap *map[int32]RuneTokenType, runes string, tokenType RuneTokenType) {
for _, rune := range runes {
(*typeMap)[int32(rune)] = tokenType
}
}
/*
Create a new classifier for basic ASCII characters.
*/
func NewDefaultClassifier() *TokenClassifier {
typeMap := map[int32]RuneTokenType{}
addRuneClass(&typeMap, RUNE_CHAR, RUNETOKEN_CHAR)
addRuneClass(&typeMap, RUNE_SPACE, RUNETOKEN_SPACE)
addRuneClass(&typeMap, RUNE_ESCAPING_QUOTE, RUNETOKEN_ESCAPING_QUOTE)
addRuneClass(&typeMap, RUNE_NONESCAPING_QUOTE, RUNETOKEN_NONESCAPING_QUOTE)
addRuneClass(&typeMap, RUNE_ESCAPE, RUNETOKEN_ESCAPE)
addRuneClass(&typeMap, RUNE_COMMENT, RUNETOKEN_COMMENT)
return &TokenClassifier{
typeMap: typeMap}
}
func (classifier *TokenClassifier) ClassifyRune(rune int32) RuneTokenType {
return classifier.typeMap[rune]
}
/*
A type for turning an input stream in to a sequence of strings. Whitespace and
comments are skipped.
*/
type Lexer struct {
tokenizer *Tokenizer
}
/*
Create a new lexer.
*/
func NewLexer(r io.Reader) (*Lexer, error) {
tokenizer, err := NewTokenizer(r)
if err != nil {
return nil, err
}
lexer := &Lexer{tokenizer: tokenizer}
return lexer, nil
}
/*
Return the next word, and an error value. If there are no more words, the error
will be io.EOF.
*/
func (l *Lexer) NextWord() (string, error) {
var token *Token
var err error
for {
token, err = l.tokenizer.NextToken()
if err != nil {
return "", err
}
switch token.tokenType {
case TOKEN_WORD:
{
return token.value, nil
}
case TOKEN_COMMENT:
{
// skip comments
}
default:
{
panic(fmt.Sprintf("Unknown token type: %v", token.tokenType))
}
}
}
return "", io.EOF
}
/*
A type for turning an input stream in to a sequence of typed tokens.
*/
type Tokenizer struct {
input *bufio.Reader
classifier *TokenClassifier
}
/*
Create a new tokenizer.
*/
func NewTokenizer(r io.Reader) (*Tokenizer, error) {
input := bufio.NewReader(r)
classifier := NewDefaultClassifier()
tokenizer := &Tokenizer{
input: input,
classifier: classifier}
return tokenizer, nil
}
/*
Scan the stream for the next token.
This uses an internal state machine. It will panic if it encounters a character
which it does not know how to handle.
*/
func (t *Tokenizer) scanStream() (*Token, error) {
state := STATE_START
var tokenType TokenType
value := make([]int32, 0, INITIAL_TOKEN_CAPACITY)
var (
nextRune int32
nextRuneType RuneTokenType
err error
)
SCAN:
for {
nextRune, _, err = t.input.ReadRune()
nextRuneType = t.classifier.ClassifyRune(nextRune)
if err != nil {
if err == io.EOF {
nextRuneType = RUNETOKEN_EOF
err = nil
} else {
return nil, err
}
}
switch state {
case STATE_START: // no runes read yet
{
switch nextRuneType {
case RUNETOKEN_EOF:
{
return nil, io.EOF
}
case RUNETOKEN_CHAR:
{
tokenType = TOKEN_WORD
value = append(value, nextRune)
state = STATE_INWORD
}
case RUNETOKEN_SPACE:
{
}
case RUNETOKEN_ESCAPING_QUOTE:
{
tokenType = TOKEN_WORD
state = STATE_QUOTED_ESCAPING
}
case RUNETOKEN_NONESCAPING_QUOTE:
{
tokenType = TOKEN_WORD
state = STATE_QUOTED
}
case RUNETOKEN_ESCAPE:
{
tokenType = TOKEN_WORD
state = STATE_ESCAPING
}
case RUNETOKEN_COMMENT:
|