rgviz 0.2 → 0.3
Sign up to get free protection for your applications and to get access to all the features.
- data/lib/rgviz/lexer.rb +605 -0
- data/lib/rgviz/nodes.rb +437 -0
- data/lib/rgviz/parser.rb +403 -0
- data/lib/rgviz/token.rb +83 -0
- data/lib/rgviz/visitor.rb +18 -0
- metadata +8 -3
data/lib/rgviz/lexer.rb
ADDED
@@ -0,0 +1,605 @@
|
|
1
|
+
module Rgviz
|
2
|
+
class Lexer
|
3
|
+
def initialize(str)
|
4
|
+
@str = str.chars.to_a
|
5
|
+
@len = @str.length
|
6
|
+
@token = Token.new
|
7
|
+
@p = 0
|
8
|
+
end
|
9
|
+
|
10
|
+
def next_token
|
11
|
+
while true
|
12
|
+
@token.start = @p
|
13
|
+
@token.string = nil
|
14
|
+
|
15
|
+
case c
|
16
|
+
when nil
|
17
|
+
@token.value = Token::EOF
|
18
|
+
return @token
|
19
|
+
when ' ', "\n", "\r", "\t"
|
20
|
+
@p += 1
|
21
|
+
next
|
22
|
+
when '`', '"', "'"
|
23
|
+
ending = c
|
24
|
+
while c! != ending && c != nil
|
25
|
+
end
|
26
|
+
raise ParseException.new "Unmatched #{char}" if c != ending
|
27
|
+
@p += 1
|
28
|
+
@token.value = ending == '`' ? Token::ID : Token::STRING
|
29
|
+
@token.string = @str[@token.start + 1 ... @p - 1].join
|
30
|
+
return @token
|
31
|
+
when '0' .. '9'
|
32
|
+
found_dot = false
|
33
|
+
while true
|
34
|
+
case c!
|
35
|
+
when '0' .. '9'
|
36
|
+
next
|
37
|
+
when '.'
|
38
|
+
break if found_dot
|
39
|
+
found_dot = true
|
40
|
+
next
|
41
|
+
else
|
42
|
+
break
|
43
|
+
end
|
44
|
+
end
|
45
|
+
if found_dot
|
46
|
+
@token.value = Token::DECIMAL
|
47
|
+
@token.number = @str[@token.start ... @p].join.to_f
|
48
|
+
else
|
49
|
+
@token.value = Token::INTEGER
|
50
|
+
@token.number = @str[@token.start ... @p].join.to_i
|
51
|
+
end
|
52
|
+
return @token
|
53
|
+
when '.'
|
54
|
+
while true
|
55
|
+
case c!
|
56
|
+
when '0' .. '9'
|
57
|
+
next
|
58
|
+
else
|
59
|
+
break
|
60
|
+
end
|
61
|
+
end
|
62
|
+
@token.value = Token::DECIMAL
|
63
|
+
@token.number = @str[@token.start ... @p].join.to_f
|
64
|
+
return @token
|
65
|
+
when '+'; return keyword! Token::PLUS
|
66
|
+
when '-'; return keyword! Token::MINUS
|
67
|
+
when '*'; return keyword! Token::STAR
|
68
|
+
when '/'; return keyword! Token::SLASH
|
69
|
+
when ','; return keyword! Token::COMMA
|
70
|
+
when '('; return keyword! Token::LPAREN
|
71
|
+
when ')'; return keyword! Token::RPAREN
|
72
|
+
when '='; return keyword! Token::EQ
|
73
|
+
when '!';
|
74
|
+
raise ParseException.new "Unexpected character '!'" if c! != '='
|
75
|
+
return keyword! Token::NEQ
|
76
|
+
when '<';
|
77
|
+
case c!
|
78
|
+
when '='
|
79
|
+
@p += 1
|
80
|
+
@token.value = Token::LTE
|
81
|
+
return @token
|
82
|
+
when '>'
|
83
|
+
@p += 1
|
84
|
+
@token.value = Token::NEQ
|
85
|
+
return @token
|
86
|
+
else
|
87
|
+
@token.value = Token::LT
|
88
|
+
return @token
|
89
|
+
end
|
90
|
+
when '>';
|
91
|
+
if c! == '='
|
92
|
+
@p += 1
|
93
|
+
@token.value = Token::GTE
|
94
|
+
return @token
|
95
|
+
end
|
96
|
+
@token.value = Token::GT
|
97
|
+
return @token
|
98
|
+
when 'a', 'A'
|
99
|
+
case c!
|
100
|
+
when 'n', 'N'
|
101
|
+
case c! when 'd', 'D'
|
102
|
+
return keyword Token::And if end_of_identifier!
|
103
|
+
end
|
104
|
+
when 's', 'S'
|
105
|
+
case c! when 'c', 'C'
|
106
|
+
return keyword Token::Asc if end_of_identifier!
|
107
|
+
end
|
108
|
+
when 'v', 'V'
|
109
|
+
case c! when 'g', 'G'
|
110
|
+
return keyword Token::Avg if end_of_identifier!
|
111
|
+
end
|
112
|
+
end
|
113
|
+
when 'b', 'B'
|
114
|
+
case c! when 'y', 'Y'
|
115
|
+
return keyword Token::By if end_of_identifier!
|
116
|
+
end
|
117
|
+
when 'c', 'C'
|
118
|
+
case c! when 'o', 'O'
|
119
|
+
case c!
|
120
|
+
when 'n', 'N'
|
121
|
+
case c! when 't', 'T'
|
122
|
+
case c! when 'a', 'A'
|
123
|
+
case c! when 'i', 'I'
|
124
|
+
case c! when 'n', 'N'
|
125
|
+
case c! when 's', 'S'
|
126
|
+
return keyword Token::Contains if end_of_identifier!
|
127
|
+
end
|
128
|
+
end
|
129
|
+
end
|
130
|
+
end
|
131
|
+
end
|
132
|
+
when 'u', 'U'
|
133
|
+
case c! when 'n', 'N'
|
134
|
+
case c! when 't', 'T'
|
135
|
+
return keyword Token::Count if end_of_identifier!
|
136
|
+
end
|
137
|
+
end
|
138
|
+
end
|
139
|
+
end
|
140
|
+
when 'd', 'D'
|
141
|
+
case c!
|
142
|
+
when 'a', 'A'
|
143
|
+
case c!
|
144
|
+
when 't', 'T'
|
145
|
+
case c! when 'e', 'E'
|
146
|
+
return keyword Token::Date if end_of_identifier!
|
147
|
+
case c
|
148
|
+
when 'd', 'D'
|
149
|
+
case c! when 'i', 'I'
|
150
|
+
case c! when 'f', 'F'
|
151
|
+
case c! when 'f', 'F'
|
152
|
+
return keyword Token::DateDiff if end_of_identifier!
|
153
|
+
end
|
154
|
+
end
|
155
|
+
end
|
156
|
+
when 't', 'T'
|
157
|
+
case c! when 'i', 'I'
|
158
|
+
case c! when 'm', 'M'
|
159
|
+
case c! when 'e', 'E'
|
160
|
+
return keyword Token::DateTime if end_of_identifier!
|
161
|
+
end
|
162
|
+
end
|
163
|
+
end
|
164
|
+
end
|
165
|
+
end
|
166
|
+
when 'y', 'Y'
|
167
|
+
return keyword Token::Day if end_of_identifier!
|
168
|
+
case c when 'o', 'O'
|
169
|
+
case c! when 'f', 'F'
|
170
|
+
case c! when 'w', 'W'
|
171
|
+
case c! when 'e', 'E'
|
172
|
+
case c! when 'e', 'E'
|
173
|
+
case c! when 'k', 'K'
|
174
|
+
return keyword Token::DayOfWeek if end_of_identifier!
|
175
|
+
end
|
176
|
+
end
|
177
|
+
end
|
178
|
+
end
|
179
|
+
end
|
180
|
+
end
|
181
|
+
end
|
182
|
+
when 'e', 'E'
|
183
|
+
case c! when 's', 'S'
|
184
|
+
case c! when 'c', 'C'
|
185
|
+
return keyword Token::Desc if end_of_identifier!
|
186
|
+
end
|
187
|
+
end
|
188
|
+
end
|
189
|
+
when 'e', 'E'
|
190
|
+
case c! when 'n', 'N'
|
191
|
+
case c! when 'd', 'D'
|
192
|
+
case c! when 's', 'S'
|
193
|
+
return keyword Token::Ends if end_of_identifier!
|
194
|
+
end
|
195
|
+
end
|
196
|
+
end
|
197
|
+
when 'f', 'F'
|
198
|
+
case c!
|
199
|
+
when 'a', 'A'
|
200
|
+
case c! when 'l', 'L'
|
201
|
+
case c! when 's', 'S'
|
202
|
+
case c! when 'e', 'E'
|
203
|
+
return keyword Token::False if end_of_identifier!
|
204
|
+
end
|
205
|
+
end
|
206
|
+
end
|
207
|
+
when 'o', 'O'
|
208
|
+
case c! when 'r', 'R'
|
209
|
+
case c! when 'm', 'M'
|
210
|
+
case c! when 'a', 'A'
|
211
|
+
case c! when 't', 'T'
|
212
|
+
return keyword Token::Format if end_of_identifier!
|
213
|
+
end
|
214
|
+
end
|
215
|
+
end
|
216
|
+
end
|
217
|
+
end
|
218
|
+
when 'g', 'G'
|
219
|
+
case c! when 'r', 'R'
|
220
|
+
case c! when 'o', 'O'
|
221
|
+
case c! when 'u', 'U'
|
222
|
+
case c! when 'p', 'P'
|
223
|
+
return keyword Token::Group if end_of_identifier!
|
224
|
+
end
|
225
|
+
end
|
226
|
+
end
|
227
|
+
end
|
228
|
+
when 'h', 'H'
|
229
|
+
case c! when 'o', 'O'
|
230
|
+
case c! when 'u', 'U'
|
231
|
+
case c! when 'r', 'R'
|
232
|
+
return keyword Token::Hour if end_of_identifier!
|
233
|
+
end
|
234
|
+
end
|
235
|
+
end
|
236
|
+
when 'i', 'I'
|
237
|
+
case c! when 's', 'S'
|
238
|
+
return keyword Token::Is if end_of_identifier!
|
239
|
+
end
|
240
|
+
when 'l', 'L'
|
241
|
+
case c!
|
242
|
+
when 'a', 'A'
|
243
|
+
case c! when 'b', 'B'
|
244
|
+
case c! when 'e', 'E'
|
245
|
+
case c! when 'l', 'L'
|
246
|
+
return keyword Token::Label if end_of_identifier!
|
247
|
+
end
|
248
|
+
end
|
249
|
+
end
|
250
|
+
when 'i', 'I'
|
251
|
+
case c!
|
252
|
+
when 'k', 'K'
|
253
|
+
case c! when 'e', 'E'
|
254
|
+
return keyword Token::Like if end_of_identifier!
|
255
|
+
end
|
256
|
+
when 'm', 'M'
|
257
|
+
case c! when 'i', 'I'
|
258
|
+
case c! when 't', 'T'
|
259
|
+
return keyword Token::Limit if end_of_identifier!
|
260
|
+
end
|
261
|
+
end
|
262
|
+
end
|
263
|
+
when 'o', 'O'
|
264
|
+
case c! when 'w', 'W'
|
265
|
+
case c! when 'e', 'E'
|
266
|
+
case c! when 'r', 'R'
|
267
|
+
return keyword Token::Lower if end_of_identifier!
|
268
|
+
end
|
269
|
+
end
|
270
|
+
end
|
271
|
+
end
|
272
|
+
when 'm', 'M'
|
273
|
+
case c!
|
274
|
+
when 'a', 'A'
|
275
|
+
case c!
|
276
|
+
when 't', 'T'
|
277
|
+
case c! when 'c', 'C'
|
278
|
+
case c! when 'h', 'H'
|
279
|
+
case c! when 'e', 'E'
|
280
|
+
case c! when 's', 'S'
|
281
|
+
return keyword Token::Matches if end_of_identifier!
|
282
|
+
end
|
283
|
+
end
|
284
|
+
end
|
285
|
+
end
|
286
|
+
when 'x', 'X'
|
287
|
+
return keyword Token::Max if end_of_identifier!
|
288
|
+
end
|
289
|
+
when 'i', 'I'
|
290
|
+
case c! when 'l', 'L'
|
291
|
+
case c! when 'l', 'L'
|
292
|
+
case c! when 'i', 'I'
|
293
|
+
case c! when 's', 'S'
|
294
|
+
case c! when 'e', 'E'
|
295
|
+
case c! when 'c', 'C'
|
296
|
+
case c! when 'o', 'O'
|
297
|
+
case c! when 'n', 'N'
|
298
|
+
case c! when 'd', 'D'
|
299
|
+
return keyword Token::Millisecond if end_of_identifier!
|
300
|
+
end
|
301
|
+
end
|
302
|
+
end
|
303
|
+
end
|
304
|
+
end
|
305
|
+
end
|
306
|
+
end
|
307
|
+
end
|
308
|
+
when 'n', 'N'
|
309
|
+
return keyword Token::Min if end_of_identifier!
|
310
|
+
case c when 'u', 'U'
|
311
|
+
case c! when 't', 'T'
|
312
|
+
case c! when 'e', 'E'
|
313
|
+
return keyword Token::Minute if end_of_identifier!
|
314
|
+
end
|
315
|
+
end
|
316
|
+
end
|
317
|
+
end
|
318
|
+
when 'o', 'O'
|
319
|
+
case c! when 'n', 'N'
|
320
|
+
case c! when 't', 'T'
|
321
|
+
case c! when 'h', 'H'
|
322
|
+
return keyword Token::Month if end_of_identifier!
|
323
|
+
end
|
324
|
+
end
|
325
|
+
end
|
326
|
+
end
|
327
|
+
when 'n', 'N'
|
328
|
+
case c!
|
329
|
+
when 'o', 'O'
|
330
|
+
case c!
|
331
|
+
when 't', 'T'
|
332
|
+
return keyword Token::Not if end_of_identifier!
|
333
|
+
when 'w', 'W'
|
334
|
+
return keyword Token::Now if end_of_identifier!
|
335
|
+
when '_'
|
336
|
+
case c!
|
337
|
+
when 'f', 'F'
|
338
|
+
case c! when 'o', 'O'
|
339
|
+
case c! when 'r', 'R'
|
340
|
+
case c! when 'm', 'M'
|
341
|
+
case c! when 'a', 'A'
|
342
|
+
case c! when 't', 'T'
|
343
|
+
return keyword Token::NoFormat if end_of_identifier!
|
344
|
+
end
|
345
|
+
end
|
346
|
+
end
|
347
|
+
end
|
348
|
+
end
|
349
|
+
when 'v', 'V'
|
350
|
+
case c! when 'a', 'A'
|
351
|
+
case c! when 'l', 'L'
|
352
|
+
case c! when 'u', 'U'
|
353
|
+
case c! when 'e', 'E'
|
354
|
+
case c! when 's', 'S'
|
355
|
+
return keyword Token::NoValues if end_of_identifier!
|
356
|
+
end
|
357
|
+
end
|
358
|
+
end
|
359
|
+
end
|
360
|
+
end
|
361
|
+
end
|
362
|
+
end
|
363
|
+
when 'u', 'U'
|
364
|
+
case c! when 'l', 'L'
|
365
|
+
case c! when 'l', 'L'
|
366
|
+
return keyword Token::Null if end_of_identifier!
|
367
|
+
end
|
368
|
+
end
|
369
|
+
end
|
370
|
+
when 'o', 'O'
|
371
|
+
case c!
|
372
|
+
when 'f', 'F'
|
373
|
+
case c! when 'f', 'F'
|
374
|
+
case c! when 's', 'S'
|
375
|
+
case c! when 'e', 'E'
|
376
|
+
case c! when 't', 'T'
|
377
|
+
return keyword Token::Offset if end_of_identifier!
|
378
|
+
end
|
379
|
+
end
|
380
|
+
end
|
381
|
+
end
|
382
|
+
when 'p', 'P'
|
383
|
+
case c! when 't', 'T'
|
384
|
+
case c! when 'i', 'I'
|
385
|
+
case c! when 'o', 'O'
|
386
|
+
case c! when 'n', 'N'
|
387
|
+
case c! when 's', 'S'
|
388
|
+
return keyword Token::Options if end_of_identifier!
|
389
|
+
end
|
390
|
+
end
|
391
|
+
end
|
392
|
+
end
|
393
|
+
end
|
394
|
+
when 'r', 'R'
|
395
|
+
return keyword Token::Or if end_of_identifier!
|
396
|
+
case c when 'd', 'D'
|
397
|
+
case c! when 'e', 'E'
|
398
|
+
case c! when 'r', 'R'
|
399
|
+
return keyword Token::Order if end_of_identifier!
|
400
|
+
end
|
401
|
+
end
|
402
|
+
end
|
403
|
+
end
|
404
|
+
when 'p', 'P'
|
405
|
+
case c! when 'i', 'I'
|
406
|
+
case c! when 'v', 'V'
|
407
|
+
case c! when 'o', 'O'
|
408
|
+
case c! when 't', 'T'
|
409
|
+
return keyword Token::Pivot if end_of_identifier!
|
410
|
+
end
|
411
|
+
end
|
412
|
+
end
|
413
|
+
end
|
414
|
+
when 'q', 'Q'
|
415
|
+
case c! when 'u', 'U'
|
416
|
+
case c! when 'a', 'A'
|
417
|
+
case c! when 'r', 'R'
|
418
|
+
case c! when 't', 'T'
|
419
|
+
case c! when 'e', 'E'
|
420
|
+
case c! when 'r', 'R'
|
421
|
+
return keyword Token::Quarter if end_of_identifier!
|
422
|
+
end
|
423
|
+
end
|
424
|
+
end
|
425
|
+
end
|
426
|
+
end
|
427
|
+
end
|
428
|
+
when 's', 'S'
|
429
|
+
case c!
|
430
|
+
when 'e', 'E'
|
431
|
+
case c!
|
432
|
+
when 'c', 'C'
|
433
|
+
case c! when 'o', 'O'
|
434
|
+
case c! when 'n', 'N'
|
435
|
+
case c! when 'd', 'D'
|
436
|
+
return keyword Token::Second if end_of_identifier!
|
437
|
+
end
|
438
|
+
end
|
439
|
+
end
|
440
|
+
when 'l', 'L'
|
441
|
+
case c! when 'e', 'E'
|
442
|
+
case c! when 'c', 'C'
|
443
|
+
case c! when 't', 'T'
|
444
|
+
return keyword Token::Select if end_of_identifier!
|
445
|
+
end
|
446
|
+
end
|
447
|
+
end
|
448
|
+
end
|
449
|
+
when 't', 'T'
|
450
|
+
case c! when 'a', 'A'
|
451
|
+
case c! when 'r', 'R'
|
452
|
+
case c! when 't', 'T'
|
453
|
+
case c! when 's', 'S'
|
454
|
+
return keyword Token::Starts if end_of_identifier!
|
455
|
+
end
|
456
|
+
end
|
457
|
+
end
|
458
|
+
end
|
459
|
+
when 'u', 'U'
|
460
|
+
case c! when 'm', 'M'
|
461
|
+
return keyword Token::Sum if end_of_identifier!
|
462
|
+
end
|
463
|
+
end
|
464
|
+
when 't', 'T'
|
465
|
+
case c!
|
466
|
+
when 'i', 'I'
|
467
|
+
case c! when 'm', 'M'
|
468
|
+
case c! when 'e', 'E'
|
469
|
+
case c!
|
470
|
+
when 'o', 'O'
|
471
|
+
case c! when 'f', 'F'
|
472
|
+
case c! when 'd', 'D'
|
473
|
+
case c! when 'a', 'A'
|
474
|
+
case c! when 'y', 'Y'
|
475
|
+
return keyword Token::TimeOfDay if end_of_identifier!
|
476
|
+
end
|
477
|
+
end
|
478
|
+
end
|
479
|
+
end
|
480
|
+
when 's', 'S'
|
481
|
+
case c! when 't', 'T'
|
482
|
+
case c! when 'a', 'A'
|
483
|
+
case c! when 'm', 'M'
|
484
|
+
case c! when 'p', 'P'
|
485
|
+
return keyword Token::Timestamp if end_of_identifier!
|
486
|
+
end
|
487
|
+
end
|
488
|
+
end
|
489
|
+
end
|
490
|
+
end
|
491
|
+
end
|
492
|
+
end
|
493
|
+
when 'o', 'O'
|
494
|
+
case c! when 'd', 'D'
|
495
|
+
case c! when 'a', 'A'
|
496
|
+
case c! when 't', 'T'
|
497
|
+
case c! when 'e', 'E'
|
498
|
+
return keyword Token::ToDate if end_of_identifier!
|
499
|
+
end
|
500
|
+
end
|
501
|
+
end
|
502
|
+
end
|
503
|
+
when 'r', 'R'
|
504
|
+
case c! when 'u', 'U'
|
505
|
+
case c! when 'e', 'E'
|
506
|
+
return keyword Token::True if end_of_identifier!
|
507
|
+
end
|
508
|
+
end
|
509
|
+
end
|
510
|
+
when 'u', 'U'
|
511
|
+
case c! when 'p', 'P'
|
512
|
+
case c! when 'p', 'P'
|
513
|
+
case c! when 'e', 'E'
|
514
|
+
case c! when 'r', 'R'
|
515
|
+
return keyword Token::Upper if end_of_identifier!
|
516
|
+
end
|
517
|
+
end
|
518
|
+
end
|
519
|
+
end
|
520
|
+
when 'w', 'W'
|
521
|
+
case c!
|
522
|
+
when 'h', 'H'
|
523
|
+
case c! when 'e', 'E'
|
524
|
+
case c! when 'r', 'R'
|
525
|
+
case c! when 'e', 'E'
|
526
|
+
return keyword Token::Where if end_of_identifier!
|
527
|
+
end
|
528
|
+
end
|
529
|
+
end
|
530
|
+
when 'i', 'I'
|
531
|
+
case c! when 't', 'T'
|
532
|
+
case c! when 'h', 'H'
|
533
|
+
return keyword Token::With if end_of_identifier!
|
534
|
+
end
|
535
|
+
end
|
536
|
+
end
|
537
|
+
when 'y', 'Y'
|
538
|
+
case c! when 'e', 'E'
|
539
|
+
case c! when 'a', 'A'
|
540
|
+
case c! when 'r', 'R'
|
541
|
+
return keyword Token::Year if end_of_identifier!
|
542
|
+
end
|
543
|
+
end
|
544
|
+
end
|
545
|
+
end
|
546
|
+
|
547
|
+
if @token.start == @p
|
548
|
+
case c
|
549
|
+
when 'a' .. 'z', 'A' .. 'Z', '_'
|
550
|
+
@p += 1
|
551
|
+
else
|
552
|
+
raise ParseException.new "Unexpected character #{c}"
|
553
|
+
end
|
554
|
+
end
|
555
|
+
|
556
|
+
while true
|
557
|
+
case c
|
558
|
+
when 'a' .. 'z', 'A' .. 'Z', '0' .. '9', '_'
|
559
|
+
@p += 1
|
560
|
+
else
|
561
|
+
break
|
562
|
+
end
|
563
|
+
end
|
564
|
+
|
565
|
+
@token.value = Token::ID
|
566
|
+
@token.string = @str[@token.start ... @p].join
|
567
|
+
return @token
|
568
|
+
end
|
569
|
+
end
|
570
|
+
|
571
|
+
def c
|
572
|
+
@str[@p]
|
573
|
+
end
|
574
|
+
|
575
|
+
def c!
|
576
|
+
@p += 1
|
577
|
+
c
|
578
|
+
end
|
579
|
+
|
580
|
+
def end_of_identifier?
|
581
|
+
case c
|
582
|
+
when ' ', "\n", "\r", "\t", '(', ')', '+', '-', '*', '/', '<', '=', '>', '`', '"', "'", ',', nil
|
583
|
+
true
|
584
|
+
else
|
585
|
+
false
|
586
|
+
end
|
587
|
+
end
|
588
|
+
|
589
|
+
def end_of_identifier!
|
590
|
+
@p += 1
|
591
|
+
end_of_identifier?
|
592
|
+
end
|
593
|
+
|
594
|
+
def keyword(value)
|
595
|
+
@token.value = value
|
596
|
+
@token
|
597
|
+
end
|
598
|
+
|
599
|
+
def keyword!(value)
|
600
|
+
@p += 1
|
601
|
+
@token.value = value
|
602
|
+
@token
|
603
|
+
end
|
604
|
+
end
|
605
|
+
end
|