/
tokenize.go
512 lines (407 loc) · 8.4 KB
/
tokenize.go
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
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
package arithmetic
import (
"bufio"
"errors"
"fmt"
"strconv"
"strings"
"unicode"
)
// tokenize takes an input and returns an infix slice of tokens.
// note: spaces are not mandatory.
//
// The algorithm is inspired by this:
// https://www.youtube.com/watch?v=HxaD_trXwRE
func tokenize(input string) ([]interface{}, error) {
t := &tokenizer{
reader: bufio.NewReader(strings.NewReader(input)),
}
for state := startState; state != nil; {
state = state(t)
}
if t.err != nil {
return nil, t.err
}
return t.output, nil
}
// stateFunc describes a function that returns another stateFunc.
// A stateFunc uses its tokenizer to define its output or payload given
// the current or last read rune.
type stateFunc func(t *tokenizer) stateFunc
// tokenizer s a structure that handles a reader and tokenizes it.
type tokenizer struct {
reader *bufio.Reader
payload string
prev interface{}
output []interface{}
err error
}
// push a token to the output.
func (t *tokenizer) push(token interface{}) {
t.prev = token
t.output = append(t.output, token)
}
// read the next rune from the reader.
func (t *tokenizer) read() (rune, bool) {
r, _, err := t.reader.ReadRune()
if err != nil {
return 0, false
}
return r, true
}
// unread the last read rune of the reader.
func (t *tokenizer) unread() {
t.reader.UnreadRune()
}
// startState is the default state: it is the state used at the beginning of the input, or after
// a token has been identified.
func startState(t *tokenizer) stateFunc {
// reset the payload before starting.
t.payload = ""
// get the next rune.
r, ok := t.read()
if !ok {
return nil
}
// Choose a state given the rune.
switch {
case isSpace(r):
return startState
case isPlus(r):
return plusState
case isMinus(r):
return minusState
case isDivide(r):
return divideState
case isMultiply(r):
return multiplyState
case isModulo(r):
return moduloState
case isExponant(r):
return exponantState
case isleftParenthesis(r):
return leftParenthesisState
case isrightParenthesis(r):
return rightParenthesisState
case isComma(r):
return commaState
case isEqual(r):
return equalState
case isGreater(r):
return greaterState
case isDoubleQuote(r):
return doubleQuoteState
case isLower(r):
return lowerState
case isAmpersand(r):
return ampersandState
case isPipe(r):
return pipeState
case isExclamation(r):
return exclamationState
case isAlphaNum(r):
t.payload += string(r)
return alphaNumState
default:
t.err = fmt.Errorf("unrecognized token: \"%s\"", string(r))
return nil
}
}
func plusState(t *tokenizer) stateFunc {
switch t.prev.(type) {
case rightParenthesis:
t.push(plus{})
case float64:
t.push(plus{})
case variable:
t.push(plus{})
default:
t.push(unaryPlus{})
}
return startState
}
func minusState(t *tokenizer) stateFunc {
switch t.prev.(type) {
case rightParenthesis:
t.push(minus{})
case float64:
t.push(minus{})
default:
t.push(unaryMinus{})
}
return startState
}
func multiplyState(t *tokenizer) stateFunc {
t.push(multiply{})
return startState
}
func exponantState(t *tokenizer) stateFunc {
t.push(exponant{})
return startState
}
func divideState(t *tokenizer) stateFunc {
t.push(divide{})
return startState
}
func moduloState(t *tokenizer) stateFunc {
t.push(modulo{})
return startState
}
func leftParenthesisState(t *tokenizer) stateFunc {
t.push(leftParenthesis{})
return startState
}
func rightParenthesisState(t *tokenizer) stateFunc {
t.push(rightParenthesis{})
return startState
}
func commaState(t *tokenizer) stateFunc {
t.push(comma{})
return startState
}
func equalState(t *tokenizer) stateFunc {
r, ok := t.read()
if !ok {
t.err = errors.New("unrecognized token \"=\"")
return nil
}
if !isEqual(r) {
t.err = fmt.Errorf("unrecognized token \"=%s\"", string(r))
return nil
}
t.push(equal{})
return startState
}
func greaterState(t *tokenizer) stateFunc {
r, ok := t.read()
if !ok {
t.err = errors.New("unrecognized token \">\"")
return nil
}
if isEqual(r) {
t.push(greaterEqual{})
return startState
}
t.unread()
t.push(greater{})
return startState
}
func lowerState(t *tokenizer) stateFunc {
r, ok := t.read()
if !ok {
t.err = errors.New("unrecognized token \"<\"")
return nil
}
if isEqual(r) {
t.push(lowerEqual{})
return startState
}
t.unread()
t.push(lower{})
return startState
}
func exclamationState(t *tokenizer) stateFunc {
r, ok := t.read()
if !ok {
t.err = errors.New("unrecognized token \"!\"")
return nil
}
if isEqual(r) {
t.push(different{})
return startState
}
t.unread()
t.push(not{})
return startState
}
func doubleQuoteState(t *tokenizer) stateFunc {
for {
r, ok := t.read()
if !ok {
t.err = fmt.Errorf("expecting \" at end of string: %s", t.payload)
return nil
}
if isDoubleQuote(r) {
t.push(t.payload)
return startState
}
t.payload += string(r)
}
}
func ampersandState(t *tokenizer) stateFunc {
r, ok := t.read()
if !ok {
t.err = errors.New("unrecognized token \"&\"")
return nil
}
if isAmpersand(r) {
t.push(and{})
return startState
}
t.unread()
t.err = fmt.Errorf("unrecognized tocken \"&%s\"", rune(r))
return nil
}
func pipeState(t *tokenizer) stateFunc {
r, ok := t.read()
if !ok {
t.err = errors.New("unrecognized token \"|\"")
return nil
}
if isPipe(r) {
t.push(or{})
return startState
}
t.unread()
t.err = fmt.Errorf("unrecognized tocken \"|%s\"", rune(r))
return nil
}
func alphaNumState(t *tokenizer) stateFunc {
r, ok := t.read()
if !ok {
token, err := t.parse()
if err != nil {
t.err = err
return nil
}
t.push(token)
return startState
}
switch {
case isSpace(r):
fallthrough
case isComma(r):
fallthrough
case isPlus(r):
fallthrough
case isMultiply(r):
fallthrough
case isDivide(r):
fallthrough
case isModulo(r):
fallthrough
case isExponant(r):
fallthrough
case isEqual(r):
fallthrough
case isGreater(r):
fallthrough
case isLower(r):
fallthrough
case isExclamation(r):
fallthrough
case isDoubleQuote(r):
fallthrough
case isAmpersand(r):
fallthrough
case isPipe(r):
fallthrough
case isrightParenthesis(r):
fallthrough
case isleftParenthesis(r):
fallthrough
case isMinus(r):
t.unread()
token, err := t.parse()
if err != nil {
t.err = err
return nil
}
t.push(token)
return startState
case isAlphaNum(r):
t.payload += string(r)
return alphaNumState
default:
t.err = fmt.Errorf("unrecognized token: \"%s\"", string(r))
return nil
}
}
func isAlphaNum(r rune) bool {
return unicode.IsDigit(r) || unicode.IsLetter(r) || r == '_' || r == '.'
}
func isleftParenthesis(r rune) bool {
return r == '('
}
func isrightParenthesis(r rune) bool {
return r == ')'
}
func isComma(r rune) bool {
return r == ','
}
func isEqual(r rune) bool {
return r == '='
}
func isGreater(r rune) bool {
return r == '>'
}
func isLower(r rune) bool {
return r == '<'
}
func isExclamation(r rune) bool {
return r == '!'
}
func isPlus(r rune) bool {
return r == '+'
}
func isMinus(r rune) bool {
return r == '-'
}
func isMultiply(r rune) bool {
return r == '*'
}
func isDivide(r rune) bool {
return r == '/'
}
func isModulo(r rune) bool {
return r == '%'
}
func isExponant(r rune) bool {
return r == '^'
}
func isDoubleQuote(r rune) bool {
return r == '"'
}
func isAmpersand(r rune) bool {
return r == '&'
}
func isPipe(r rune) bool {
return r == '|'
}
func isSpace(r rune) bool {
return unicode.IsSpace(r)
}
// parse the current payload value to tokenize it.
func (t *tokenizer) parse() (interface{}, error) {
// make input non-case sensitive.
input := strings.ToLower(t.payload)
// If the input matches a variable, return it.
v, ok := variables[input]
if ok {
return v, nil
}
// If the input matches a function, return it.
function, ok := functions[input]
if ok {
return function, nil
}
// If the input matches an alias, return the aliased value.
a, ok := aliases[input]
if ok {
return a, nil
}
// If the input can be translated by an expression, return a variable
// with the input as label, and the expressions output as value.
for _, exp := range expressions {
op, ok := exp(input)
if ok {
return variable{t.payload, op}, nil
}
}
// If the input can be converted in float, return the numeric value.
n, err := strconv.ParseFloat(input, 64)
if err == nil {
return n, nil
}
return nil, fmt.Errorf("unrecognized variable, function or expression: %s", input)
}