-
Notifications
You must be signed in to change notification settings - Fork 2
Expand file tree
/
Copy pathruntime.py
More file actions
632 lines (541 loc) · 17.7 KB
/
runtime.py
File metadata and controls
632 lines (541 loc) · 17.7 KB
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
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
# -*- test-case-name: pymeta.test.test_runtime -*-
"""
Code needed to run a grammar after it has been compiled.
"""
import operator
# The public parse error
class ParseError(Exception):
pass
# The internal ParseError
class _MaybeParseError(Exception):
"""
?Redo from start
"""
@property
def position(self):
return self.args[0]
@property
def error(self):
return self.args[1]
def __init__(self, *a):
Exception.__init__(self, *a)
if len(a) > 2:
self.message = a[2]
def __eq__(self, other):
if other.__class__ == self.__class__:
return (self.position, self.error) == (other.position, other.error)
def formatReason(self):
if self.error is None:
return ''
if len(self.error) == 1:
if self.error[0][0] == 'message':
return self.error[0][1]
elif self.error[0][2] == None:
return 'expected a ' + self.error[0][1]
else:
return 'expected the %s %s' % (self.error[0][1], self.error[0][2])
else:
bits = []
for s in self.error:
if s[2] is None:
desc = "a " + s[1]
else:
desc = repr(s[2])
if s[1] is not None:
desc = "%s %s" % (s[1], desc)
bits.append(desc)
return "expected one of %s, or %s" % (', '.join(bits[:-1]), bits[-1])
def formatError(self, input):
"""
Return a pretty string containing error info about string parsing failure.
"""
reason = self.formatReason()
if not isinstance(input, basestring):
return ("Parse error at input %s: %s\n" % (input, reason))
lines = input.split('\n')
counter = 0
line_number = 1
column = 0
for line in lines:
new_counter = counter + len(line) + 1
if new_counter > self.position:
column = self.position - counter
break
else:
counter = new_counter
line_number += 1
return ('\n' + line + '\n' + (' ' * column + '^') +
"\nParse error at line %s, column %s: %s\n" % (line_number,
column,
reason))
class EOFError(_MaybeParseError):
def __init__(self, position):
_MaybeParseError.__init__(self, position, eof())
def expected(typ, val=None):
"""
Return an indication of expected input and the position where it was
expected and not encountered.
"""
return [("expected", typ, val)]
def eof():
"""
Return an indication that the end of the input was reached.
"""
return [("message", "end of input")]
def joinErrors(errors):
"""
Return the error from the branch that matched the most of the input.
"""
errors.sort(reverse=True, key=operator.itemgetter(0))
results = set()
pos = errors[0][0]
for err in errors:
if pos == err[0]:
e = err[1]
if e is not None:
for item in e:
results.add(item)
else:
break
return [pos, list(results)]
class character(str):
"""
Type to allow distinguishing characters from strings.
"""
def __iter__(self):
"""
Prevent string patterns and list patterns from matching single
characters.
"""
raise TypeError("Characters are not iterable")
class unicodeCharacter(unicode):
"""
Type to distinguish characters from Unicode strings.
"""
def __iter__(self):
"""
Prevent string patterns and list patterns from matching single
characters.
"""
raise TypeError("Characters are not iterable")
class InputStream(object):
"""
The basic input mechanism used by OMeta grammars.
"""
def fromIterable(cls, iterable):
"""
@param iterable: Any iterable Python object.
"""
if isinstance(iterable, str):
data = [character(c) for c in iterable]
elif isinstance(iterable, unicode):
data = [unicodeCharacter(c) for c in iterable]
else:
data = list(iterable)
return cls(data, 0)
fromIterable = classmethod(fromIterable)
def __init__(self, data, position):
self.data = data
self.position = position
self.memo = {}
self.tl = None
def head(self):
if self.position >= len(self.data):
raise EOFError(self.position)
return self.data[self.position], [self.position, None]
def nullError(self):
return _MaybeParseError(self.position, None)
def tail(self):
if self.tl is None:
self.tl = InputStream(self.data, self.position + 1)
return self.tl
def prev(self):
return InputStream(self.data, self.position - 1)
def getMemo(self, name):
"""
Returns the memo record for the named rule.
@param name: A rule name.
"""
return self.memo.get(name, None)
def setMemo(self, name, rec):
"""
Store a memo record for the given value and position for the given
rule.
@param name: A rule name.
@param rec: A memo record.
"""
self.memo[name] = rec
return rec
class ArgInput(object):
def __init__(self, arg, parent):
self.arg = arg
self.parent = parent
self.memo = {}
self.err = parent.nullError()
def head(self):
return self.arg, self.err
def tail(self):
return self.parent
def nullError(self):
return self.parent.nullError()
def getMemo(self, name):
"""
Returns the memo record for the named rule.
@param name: A rule name.
"""
return self.memo.get(name, None)
def setMemo(self, name, rec):
"""
Store a memo record for the given value and position for the given
rule.
@param name: A rule name.
@param rec: A memo record.
"""
self.memo[name] = rec
return rec
class LeftRecursion(object):
"""
Marker for left recursion in a grammar rule.
"""
detected = False
class OMetaBase(object):
"""
Base class providing implementations of the fundamental OMeta
operations. Built-in rules are defined here.
"""
globals = None
def __init__(self, string, globals=None):
"""
@param string: The string to be parsed.
@param globals: A dictionary of names to objects, for use in evaluating
embedded Python expressions.
"""
self.input = InputStream.fromIterable(string)
self.locals = {}
if self.globals is None:
if globals is None:
self.globals = {}
else:
self.globals = globals
self.currentError = self.input.nullError()
@classmethod
def parse(cls, source):
if isinstance(source, str):
source = source.decode('utf8')
try:
parser = cls(source)
return parser.apply('grammar')[0]
except _MaybeParseError:
raise ParseError(parser.currentError.formatError(source))
def considerError(self, error):
if isinstance(error, _MaybeParseError):
error = error.args
if error and error[1] and error[0] > self.currentError[0]:
self.currentError = _MaybeParseError(*error)
def superApply(self, ruleName, *args):
"""
Apply the named rule as defined on this object's superclass.
@param ruleName: A rule name.
"""
r = getattr(super(self.__class__, self), "rule_" + ruleName, None)
if r is not None:
self.input.setMemo(ruleName, None)
return self._apply(r, ruleName, args)
else:
raise NameError("No rule named '%s'" % (ruleName,))
def apply(self, ruleName, *args):
"""
Apply the named rule, optionally with some arguments.
@param ruleName: A rule name.
"""
r = getattr(self, "rule_" + ruleName, None)
if r is not None:
val, err = self._apply(r, ruleName, args)
return val, _MaybeParseError(*err)
else:
raise NameError("No rule named '%s'" % (ruleName,))
rule_apply = apply
def _apply(self, rule, ruleName, args):
"""
Apply a rule method to some args.
@param rule: A method of this object.
@param ruleName: The name of the rule invoked.
@param args: A sequence of arguments to it.
"""
if args:
if rule.func_code.co_argcount - 1 != len(args):
for arg in args[::-1]:
self.input = ArgInput(arg, self.input)
return rule()
else:
return rule(*args)
memoRec = self.input.getMemo(ruleName)
if memoRec is None:
oldPosition = self.input
lr = LeftRecursion()
memoRec = self.input.setMemo(ruleName, lr)
#print "Calling", rule
try:
memoRec = self.input.setMemo(ruleName,
[rule(), self.input])
except _MaybeParseError:
#print "Failed", rule
raise
#print "Success", rule
if lr.detected:
sentinel = self.input
while True:
try:
self.input = oldPosition
ans = rule()
if (self.input == sentinel):
break
memoRec = oldPosition.setMemo(ruleName,
[ans, self.input])
except _MaybeParseError:
break
self.input = oldPosition
elif isinstance(memoRec, LeftRecursion):
memoRec.detected = True
raise _MaybeParseError(None, None)
self.input = memoRec[1]
return memoRec[0]
def rule_anything(self):
"""
Match a single item from the input of any kind.
"""
h, p = self.input.head()
self.input = self.input.tail()
return h, p
def exactly(self, wanted):
"""
Match a single item from the input equal to the given specimen.
@param wanted: What to match.
"""
i = self.input
val, p = self.input.head()
self.input = self.input.tail()
if wanted == val:
return val, p
else:
self.input = i
raise _MaybeParseError(p[0], expected(None, wanted))
rule_exactly = exactly
def many(self, fn, *initial):
"""
Call C{fn} until it fails to match the input. Collect the resulting
values into a list.
@param fn: A callable of no arguments.
@param initial: Initial values to populate the returned list with.
"""
ans = []
for x, e in initial:
ans.append(x)
while True:
try:
m = self.input
v, _ = fn()
ans.append(v)
except _MaybeParseError as e:
self.input = m
break
return ans, e
def manyn(self, fn, value):
"""
Call C{fn} <value> times. Collect the resulting values into a list.
@param fn: A callable of no arguments.
@param value: Number of times to call the function.
"""
ans = [fn()[0] for x in xrange(value)]
return ans, self.input.nullError() # Is this the correct return value?
def _or(self, fns):
"""
Call each of a list of functions in sequence until one succeeds,
rewinding the input between each.
@param fns: A list of no-argument callables.
"""
errors = []
for f in fns:
try:
m = self.input
ret, err = f()
errors.append(err)
return ret, joinErrors(errors)
except _MaybeParseError as e:
errors.append(e)
self.input = m
raise _MaybeParseError(*joinErrors(errors))
def _not(self, fn):
"""
Call the given function. Raise _MaybeParseError iff it does not.
@param fn: A callable of no arguments.
"""
m = self.input
try:
fn()
except _MaybeParseError:
self.input = m
return True, self.input.nullError()
else:
raise _MaybeParseError(*self.input.nullError())
def eatWhitespace(self):
"""
Consume input until a non-whitespace character is reached.
"""
while True:
try:
c, e = self.input.head()
except EOFError as e:
break
t = self.input.tail()
if c.isspace():
self.input = t
else:
break
return True, e
rule_spaces = eatWhitespace
def pred(self, expr):
"""
Call the given function, raising _MaybeParseError if it returns false.
@param expr: A callable of no arguments.
"""
val, e = expr()
if not val:
raise _MaybeParseError(*e)
else:
return True, e
def listpattern(self, expr):
"""
Call the given function, treating the next object on the stack as an
iterable to be used for input.
@param expr: A callable of no arguments.
"""
v, e = self.rule_anything()
oldInput = self.input
try:
self.input = InputStream.fromIterable(v)
except TypeError:
raise _MaybeParseError(e[0], expected("an iterable"))
expr()
self.end()
self.input = oldInput
return v, e
def end(self):
"""
Match the end of the stream.
"""
return self._not(self.rule_anything)
rule_end = end
def lookahead(self, f):
"""
Execute the given callable, rewinding the stream no matter whether it
returns successfully or not.
@param f: A callable of no arguments.
"""
try:
m = self.input
x = f()
return x
finally:
self.input = m
def match_string(self, tok):
"""
Match and return the given string.
"""
m = self.input
try:
for c in tok:
v, e = self.exactly(c)
return tok, e
except _MaybeParseError as e:
self.input = m
raise _MaybeParseError(e[0], expected("string", tok))
rule_match_string = match_string
def token(self, tok):
"""
Match and return the given string, consuming any preceding whitespace.
"""
m = self.input
try:
self.eatWhitespace()
for c in tok:
v, e = self.exactly(c)
return tok, e
except _MaybeParseError as e:
self.input = m
raise _MaybeParseError(e[0], expected("token", tok))
rule_token = token
def letter(self):
"""
Match a single letter.
"""
x, e = self.rule_anything()
if x.isalpha():
return x, e
else:
e[1] = expected("letter")
raise _MaybeParseError(*e)
rule_letter = letter
def letterOrDigit(self):
"""
Match a single alphanumeric character.
"""
x, e = self.rule_anything()
if x.isalnum() or x == '_':
return x, e
else:
e[1] = expected("letter or digit")
raise _MaybeParseError(*e)
rule_letterOrDigit = letterOrDigit
def digit(self):
"""
Match a single digit.
"""
x, e = self.rule_anything()
if x.isdigit():
return x, e
else:
e[1] = expected("digit")
raise _MaybeParseError(*e)
rule_digit = digit
def pythonExpr(self, endChars="\r\n"):
"""
Extract a Python expression from the input and return it.
@arg endChars: A set of characters delimiting the end of the expression.
"""
delimiters = {"(": ")", "[": "]", "{": "}"}
stack = []
expr = []
endchar = None
while True:
try:
c, e = self.rule_anything()
except _MaybeParseError as e:
endchar = None
break
if c in endChars and len(stack) == 0:
endchar = c
break
else:
expr.append(c)
if c in delimiters:
stack.append(delimiters[c])
elif len(stack) > 0 and c == stack[-1]:
stack.pop()
elif c in delimiters.values():
raise _MaybeParseError(self.input.position,
expected("Python expression"))
elif c in "\"'":
while True:
strc, stre = self.rule_anything()
expr.append(strc)
slashcount = 0
while strc == '\\':
strc, stre = self.rule_anything()
expr.append(strc)
slashcount += 1
if strc == c and slashcount % 2 == 0:
break
if len(stack) > 0:
raise _MaybeParseError(self.input.position, expected("Python expression"))
return (''.join(expr).strip(), endchar), e