My favorites | Sign in
Project Home Downloads Wiki Issues Source
Repository:
Checkout   Browse   Changes   Clones  
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
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736

# The contents of this file are subject to the Mozilla Public License
# (MPL) Version 1.1 (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.mozilla.org/MPL/
#
# Software distributed under the License is distributed on an "AS IS"
# basis, WITHOUT WARRANTY OF ANY KIND, either express or implied. See
# the License for the specific language governing rights and
# limitations under the License.
#
# The Original Code is LEPL (http://www.acooke.org/lepl)
# The Initial Developer of the Original Code is Andrew Cooke.
# Portions created by the Initial Developer are Copyright (C) 2009-2010
# Andrew Cooke (andrew@acooke.org). All Rights Reserved.
#
# Alternatively, the contents of this file may be used under the terms
# of the LGPL license (the GNU Lesser General Public License,
# http://www.gnu.org/licenses/lgpl.html), in which case the provisions
# of the LGPL License are applicable instead of those above.
#
# If you wish to allow use of your version of this file only under the
# terms of the LGPL License and not to allow others to use your version
# of this file under the MPL, indicate your decision by deleting the
# provisions above and replace them with the notice and other provisions
# required by the LGPL License. If you do not delete the provisions
# above, a recipient may use your version of this file under either the
# MPL or the LGPL License.

'''
Support for operator syntactic sugar (and operator redefinition).
'''

from re import compile as compile_

from lepl.matchers.matcher import Matcher
from lepl.support.context import Namespace, NamespaceMixin, Scope
from lepl.support.lib import open_stop, fmt, basestring


DIGITS = compile_('^(-?\d+)(.*)')

def RepeatWrapper(matcher, start, stop, step, separator, add, reduce):
'''Parse `step` if it is a string.'''
# Handle circular dependencies
from lepl.matchers.derived import Repeat
if (isinstance(step, int)):
limit = step
algorithm = DEPTH_FIRST
elif (isinstance(step, basestring)):
limit = None
algorithm = None
while step:
match = DIGITS.match(step)
if match:
if limit is None:
limit = int(match.group(1))
step = match.group(2)
else:
raise TypeError(fmt('Cannot parse limit/algorithm for []: {}',
step))
else:
if algorithm is None:
algorithm = step[0]
step = step[1:]
else:
raise TypeError('The step of [...] must be an integer limit, or a '
'string to select the algorithm, or both as a string '
'like "d1" for a single value, depth first')
return Repeat(matcher, start=start, stop=stop, limit=limit,
algorithm=algorithm, separator=separator, add_=add,
reduce=reduce)

class OperatorNamespace(Namespace):
'''
Define the default operators.
'''

def __init__(self):
# Handle circular dependencies
from lepl.matchers.error import raise_error
from lepl.matchers.derived import Space, Add, Apply, KApply, Drop, Map
from lepl.matchers.combine import And, Or, First
super(OperatorNamespace, self).__init__({
SPACE_OPT: lambda a, b: And(a, Space()[0:,...], b),
SPACE_REQ: lambda a, b: And(a, Space()[1:,...], b),
ADD: lambda a, b: Add(And(a, b)),
AND: And,
OR: Or,
APPLY: Apply,
APPLY_RAW: lambda a, b: Apply(a, b, raw=True),
NOT: Drop,
KARGS: KApply,
RAISE: lambda a, b: KApply(a, raise_error(b)),
REPEAT: RepeatWrapper,
FIRST: First,
MAP: Map,
REDUCE: None,
})


OPERATORS = 'operators'
'''
The name used to retrieve operators definitions.
'''

SPACE_OPT = '/'
'''Name for / operator.'''
SPACE_REQ = '//'
'''Name for // operator.'''
ADD = '+'
'''Name for + operator.'''
AND = '&'
'''Name for & operator.'''
OR = '|'
'''Name for | operator.'''
APPLY = '>'
'''Name for > operator.'''
APPLY_RAW = '>='
'''Name for >= operator.'''
NOT = '~'
'''Name for ~ operator.'''
KARGS = '**'
'''Name for ** operator.'''
RAISE = '^'
'''Name for ^ operator.'''
REPEAT = '[]'
'''Name for [] operator.'''
FIRST = '%'
'''Name for % operator.'''
MAP = '>>'
'''Name for >> operator.'''
REDUCE = '<reduce>'
'''Name for accumulator of data during repetition.'''


class Override(Scope):
'''
Allow an operator to be redefined within a with context. Uses the
OPERATORS namespace.
'''

def __init__(self, space_opt=None, space_req=None, repeat=None,
add=None, and_=None, or_=None, not_=None,
apply_=None, apply_raw=None, kargs=None,
raise_=None, first=None, map_=None, reduce=None):
super(Override, self).__init__(OPERATORS, OperatorNamespace,
{SPACE_OPT: space_opt, SPACE_REQ: space_req,
REPEAT: repeat, ADD: add, AND: and_, OR: or_,
NOT: not_, APPLY: apply_, APPLY_RAW: apply_raw,
KARGS: kargs, RAISE: raise_, FIRST: first, MAP: map_,
REDUCE: reduce})


class _BaseSeparator(Override):
'''
Support class for `Separator` and similar classes.

Uses the OPERATORS namespace.
'''

def __init__(self, separator):
'''
If the separator is a string it is coerced to `Regexp()`; if None
then any previous defined separator is effectively removed.
'''
# Handle circular dependencies
from lepl.matchers.core import Regexp
from lepl.matchers.combine import And
from lepl.matchers.support import coerce_
if separator is None:
and_ = And
repeat = RepeatWrapper
else:
separator = coerce_(separator, Regexp)
(and_, repeat) = self._replacements(separator)
super(_BaseSeparator, self).__init__(and_=and_, repeat=repeat)

def _replacements(self, _separator):
'''
Sub-classes should return (And, Repeat)
'''
raise Exception('Unimplemented')

def _repeat(self, separator):
'''
A simple Repeat with separator.
'''
from lepl.matchers.combine import And
def repeat(m, st=0, sp=None, d=0, s=None, a=False, r=None):
'''
Wrap `Repeat` to adapt the separator.
'''
if s is None:
s = separator
elif not a:
s = And(separator, s, separator)
return RepeatWrapper(m, st, sp, d, s, a, r)
return repeat


class Separator(_BaseSeparator):
'''
Redefine ``[]`` and ``&`` to include the given matcher as a separator
(so it will be used between list items and between matchers separated by the &
operator)

Uses the OPERATORS namespace.
'''

def _replacements(self, separator):
'''
Require the separator on each `And`.
'''
# Handle circular dependencies
from lepl.matchers.combine import And
return (lambda a, b: And(a, separator, b),
self._repeat(separator))


class DroppedSpace(Separator):
'''
Skip spaces (by default, zero or more Space()). Any argument is dropped.
'''

def __init__(self, space=None):
from lepl.matchers.derived import Space, Drop
if space is None:
space = Space()[:]
space = Drop(space)
super(DroppedSpace, self).__init__(space)


class SmartSeparator1(_BaseSeparator):
'''
Similar to `Separator`, but tried to be clever about whether the
separator is needed. It replaces `&` with a matcher that only uses
the separator if the second sub-matcher consumes some input.

Uses the OPERATORS namespace.

See also `SmartSeparator2`, which is less general, but more efficient.
'''

def _replacements(self, separator):
'''
Require the separator on each `And`.
'''
# Handle circular dependencies
from lepl.matchers.combine import And, Or
from lepl.matchers.core import Consumer
def and_(a, b):
'''
Add space only in the case when both consume something.
'''
return Or(And(Consumer(a), separator, Consumer(b)),
And(Consumer(a), Consumer(b, False)),
And(Consumer(a, False), Consumer(b)),
And(Consumer(a, False), Consumer(b, False)))
return (and_, self._repeat(separator))


GREEDY = 'g'
'''Flag (splice increment) for inefficient, guaranteed greedy matching.'''
NON_GREEDY = 'n'
'''Flag (splice increment) for inefficient, guaranteed non-greedy matching.'''
DEPTH_FIRST = 'd'
'''Flag (splice increment) for efficient, quasi-greedy, matching (default).'''
BREADTH_FIRST = 'b'
'''Flag (splice increment) for efficient, quasi-non-greedy, matching.'''


class OperatorMixin(NamespaceMixin):
'''
Define the operators used to combine elements in a grammar specification.
'''

def __init__(self, name, namespace):
super(OperatorMixin, self).__init__(name, namespace)

def __add__(self, other):
'''
**self + other** - Join strings, merge lists.

Combine adjacent matchers in sequence, merging the result with "+"
(so strings are joined, lists merged).

:Parameters:

other
Another matcher or a string that will be converted to a literal
match.
'''
self.__check(ADD, other, True)
return self._lookup(ADD)(self, other)

def __radd__(self, other):
'''
**other + self** - Join strings, merge lists.

Combine adjacent matchers in sequence, merging the result with "+"
(so strings are joined, lists merged).

:Parameters:

other
Another matcher or a string that will be converted to a literal
match.
'''
self.__check(ADD, other, True)
return self._lookup(ADD)(other, self)

def __and__(self, other):
'''
**self & other** - Append results.

Combine adjacent matchers in sequence. This is equivalent to
`And()`.

:Parameters:

other
Another matcher or a string that will be converted to a literal
match.
'''
self.__check(AND, other, True)
return self._lookup(AND)(self, other)

def __rand__(self, other):
'''
**other & self** - Append results.

Combine adjacent matchers in sequence. This is equivalent to
`And()`.

:Parameters:

other
Another matcher or a string that will be converted to a literal
match.
'''
self.__check(AND, other, True)
return self._lookup(AND)(other, self)

def __div__(self, other):
'''
For 2.6
'''
return self.__truediv__(other)

def __rdiv__(self, other):
'''
For 2.6
'''
return self.__rtruediv__(other)

def __truediv__(self, other):
'''
**self / other** - Append results, with optional separating space.

Combine adjacent matchers in sequence, with an optional space between
them. The space is included in the results.

:Parameters:

other
Another matcher or a string that will be converted to a literal
match.
'''
self.__check(SPACE_OPT, other, True)
return self._lookup(SPACE_OPT)(self, other)

def __rtruediv__(self, other):
'''
**other / self** - Append results, with optional separating space.

Combine adjacent matchers in sequence, with an optional space between
them. The space is included in the results.

:Parameters:

other
Another matcher or a string that will be converted to a literal
match.
'''
self.__check(SPACE_OPT, other, True)
return self._lookup(SPACE_OPT)(other, self)

def __floordiv__(self, other):
'''
**self // other** - Append results, with required separating space.

Combine adjacent matchers in sequence, with a space between them.
The space is included in the results.

:Parameters:

other
Another matcher or a string that will be converted to a literal
match.
'''
self.__check(SPACE_REQ, other, True)
return self._lookup(SPACE_REQ)(self, other)

def __rfloordiv__(self, other):
'''
**other // self** - Append results, with required separating space.

Combine adjacent matchers in sequence, with a space between them.
The space is included in the results.

:Parameters:

other
Another matcher or a string that will be converted to a literal
match.
'''
self.__check(SPACE_REQ, other, True)
return self._lookup(SPACE_REQ)(other, self)

def __or__(self, other):
'''
**self | other** - Try alternative matchers.

This introduces backtracking. Matches are tried from left to right
and successful results returned (one on each "recall"). This is
equivalent to `Or()`.

:Parameters:

other
Another matcher or a string that will be converted to a literal
match.
'''
self.__check(OR, other, True)
return self._lookup(OR)(self, other)

def __ror__(self, other):
'''
**other | self** - Try alternative matchers.

This introduces backtracking. Matches are tried from left to right
and successful results returned (one on each "recall"). This is
equivalent to `Or()`.

:Parameters:

other
Another matcher or a string that will be converted to a literal
match.
'''
self.__check(OR, other, True)
return self._lookup(OR)(other, self)

def __mod__(self, other):
'''
**self % other** - Take first match (committed choice).

Matches are tried from left to right and the first successful result
is returned. This is equivalent to `First()`.

:Parameters:

other
Another matcher or a string that will be converted to a literal
match.
'''
self.__check(FIRST, other, True)
return self._lookup(FIRST)(self, other)

def __rmod__(self, other):
'''
**other % self** - Take first match (committed choice).

Matches are tried from left to right and the first successful result
is returned. This is equivalent to `First()`.

:Parameters:

other
Another matcher or a string that will be converted to a literal
match.
'''
self.__check(FIRST, other, True)
return self._lookup(FIRST)(other, self)

def __invert__(self):
'''
**~self** - Discard the result.

This generates a matcher that behaves as the original, but returns
an empty list. This is equivalent to `Drop()`.

Note that `Lookahead()` overrides this method to have
different semantics (negative lookahead).
'''
return self._lookup(NOT)(self)

def __getitem__(self, indices):
'''
**self[start:stop:algorithm, separator, ...]** - Repetition and lists.

This is a complex statement that modifies the current matcher so
that it matches several times. A separator may be specified
(eg for comma-separated lists) and the results may be combined with
"+" (so repeated matching of characters would give a word).

start:stop:algorithm
This controls the number of matches made and the order in which
different numbers of matches are returned.

[start]
Repeat exactly *start* times

[start:stop]
Repeat *start* to *stop* times (starting with as many matches
as possible, and then decreasing as necessary).

[start:stop:algorithm]
Direction selects the algorithm for searching.

'b' (BREADTH_FIRST)
A breadth first search is used, which tends to give shorter
matches before longer ones. This tries all possible matches for
the sub-matcher first (before repeating calls to consume more
of the stream). If the sub-matcher does not backtrack then this
guarantees that the number of matches returned will not decrease
(ie will monotonically increase) on backtracking.

'd' (DEPTH_FIRST)
A depth first search is used, which tends to give longer
matches before shorter ones. This tries to repeats matches
with the sub-matcher, consuming as much of the stream as
possible, before backtracking to find alternative matchers.
If the sub-matcher does not backtrack then this guarantees
that the number of matches returned will not increase (ie will
monotonically decrease) on backtracking.

'g' (GREEDY)
An exhaustive search is used, which finds all results (by
breadth first search) and orders them by length before returning
them ordered from longest to shortest. This guarantees that
the number of matches returned will not increase (ie will
monotonically decrease) on backtracking, but can consume a lot
of resources.

'n' (NON_GREEDY)
As for 'g' (GREEDY), but results are ordered shortest to
longest. This guarantees that the number of matches returned
will not decrease (ie will monotonically increase) on
backtracking, but can consume a lot of resources,

Values may be omitted; the defaults are: *start* = 0, *stop* =
infinity, *algorithm* = 'd' (DEPTH_FIRST).

separator
If given, this must appear between repeated values. Matched
separators are returned as part of the result (unless, of course,
they are implemented with a matcher that returns nothing). If
*separator* is a string it is converted to a literal match.

...
If ... (an ellipsis) is given then the results are joined together
with "+".

Examples
--------

Any()[0:3,...] will match 3 or less characters, joining them
together so that the result is a single string.

Word()[:,','] will match a comma-separated list of words.

value[:] or value[0:] or value[0::'d'] is a "greedy" match that,
if value does not backtrack, is equivalent to the "*" in a regular
expression.
value[::'n'] is the "non-greedy" equivalent (preferring as short a
match as possible) and value[::'g'] is greedy even when value does
provide alternative matches on backtracking.
'''
start = 0
stop = None
step = DEPTH_FIRST
separator = None
add = False
have_index = False
if not isinstance(indices, tuple):
indices = [indices]
for index in indices:
if isinstance(index, int):
if have_index:
raise TypeError(
fmt('Multiple slices not supported: {0!r}', index))
start = index
stop = index
step = DEPTH_FIRST
have_index = True
elif isinstance(index, slice):
if have_index:
raise TypeError(
fmt('Multiple slices not supported: {0!r}', index))
start = index.start if index.start != None else 0
stop = index.stop if not open_stop(index) else None
step = index.step if index.step != None else DEPTH_FIRST
have_index = True
elif index == Ellipsis:
add = True
elif separator is None:
separator = index
else:
raise TypeError(index)
# important for rewriting
if stop == 1:
add = False
return self._lookup(REPEAT)(self, start, stop, step, separator, add,
self._lookup(REDUCE))

def __gt__(self, function):
'''
**self > function** - Process or label the results.

Create a named pair or apply a function to the results. This is
equivalent to `Apply()`.

:Parameters:

function
This can be a string or a function.

If a string is given each result is replaced by a
(name, value) pair, where name is the string and value is the
result.

If a function is given it is called with the results as an
argument. The return value is used *within a list* as the new
result. This is equivalent to `Apply()` with raw=False.
'''
self.__check(APPLY, function, False)
return self._lookup(APPLY)(self, function)

def __ge__(self, function):
'''
**self >= function** - Process or label the results.

Apply a function to the results.
This is equivalent to `Apply(raw=True)`.

:Parameters:

function
This is called with the results as an argument. The return value
is used as the new result. This is equivalent to `Apply()` with
raw=True.
'''
self.__check(APPLY_RAW, function, False)
return self._lookup(APPLY_RAW)(self, function)

def __rshift__(self, function):
'''
**self >> function** - Process or label the results (map).

Create a named pair or apply a function to each result in turn.
This is equivalent to `Map()`. It is similar to
*self >= function*, except that the function is applied to each
result in turn.

:Parameters:

function
This can be a string or a function.

If a string is given each result is replaced by a
(name, value) pair, where name is the string and value is the
result.

If a function is given it is called with each result in turn.
The return values are used as the new result.
'''
self.__check(MAP, function, False)
return self._lookup(MAP)(self, function)

def __pow__(self, function):
'''
**self \** function** - Process the results (\**kargs).

Apply a function to keyword arguments
This is equivalent to `KApply()`.

:Parameters:

function
A function that is called with the keyword arguments described below.
The return value is used as the new result.

Keyword arguments:

stream_in
The stream passed to the matcher.

stream_out
The stream returned from the matcher.

results
A list of the results returned.
'''
self.__check(KARGS, function, False)
return self._lookup(KARGS)(self, function)

def __xor__(self, message):
'''
**self ^ message**

Raise a SytaxError.

:Parameters:

message
The message for the SyntaxError.
'''
return self._lookup(RAISE)(self, message)

def __check(self, name, other, is_match):
'''
Provide some diagnostics if the syntax is completely mixed up.
'''
if not isinstance(other, basestring): # can go either way
if is_match != isinstance(other, Matcher):
if is_match:
msg = 'The operator {0} for {1} was applied to something ' \
'that is not a matcher ({2}).'
else:
msg = 'The operator {0} for {1} was applied to a matcher ' \
'({2}).'
msg += ' Check syntax and parentheses.'
raise SyntaxError(fmt(msg, name, self, other))

Change log

839e1b36de53 by andrew on Mar 1, 2011   Diff
large data volumes!
Go to: 
Project members, sign in to write a code review

Older revisions

42ad0c331b0a by andrew on Feb 25, 2011   Diff
very basic (indent only) offside
lexing now works
73aef46134e1 by andrew on Jan 28, 2011   Diff
further limit / repeat work
d8f3eb2d1b3f by and...@small.europa2189 on May 18, 2010   Diff
explicit encode unicode chars in
regexps to avoid starange bug
All revisions of this file

File info

Size: 25599 bytes, 736 lines
Powered by Google Project Hosting