forked from andialbrecht/sqlparse
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathsql.py
More file actions
586 lines (453 loc) · 17.5 KB
/
sql.py
File metadata and controls
586 lines (453 loc) · 17.5 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
# -*- coding: utf-8 -*-
"""This module contains classes representing syntactical elements of SQL."""
import re
from sqlparse import tokens as T
class Token(object):
"""Base class for all other classes in this module.
It represents a single token and has two instance attributes:
``value`` is the unchange value of the token and ``ttype`` is
the type of the token.
"""
__slots__ = ('value', 'ttype', 'parent', 'normalized', 'is_keyword')
def __init__(self, ttype, value):
self.value = value
self.normalized = value.upper() if ttype in T.Keyword else value
self.ttype = ttype
self.is_keyword = ttype in T.Keyword
self.parent = None
def __str__(self):
return unicode(self).encode('utf-8')
def __repr__(self):
short = self._get_repr_value().encode('utf-8')
return '<%s \'%s\' at 0x%07x>' % (self._get_repr_name(),
short, id(self))
def __unicode__(self):
"""Returns a unicode representation of this object."""
return self.value or ''
def to_unicode(self):
"""Returns a unicode representation of this object.
@deprecated: please use __unicode__()
"""
return unicode(self)
def _get_repr_name(self):
return str(self.ttype).split('.')[-1]
def _get_repr_value(self):
raw = unicode(self)
if len(raw) > 7:
raw = raw[:6] + u'...'
return re.sub('\s+', ' ', raw)
def flatten(self):
"""Resolve subgroups."""
yield self
def match(self, ttype, values, regex=False):
"""Checks whether the token matches the given arguments.
*ttype* is a token type. If this token doesn't match the given token
type.
*values* is a list of possible values for this token. The values
are OR'ed together so if only one of the values matches ``True``
is returned. Except for keyword tokens the comparison is
case-sensitive. For convenience it's ok to pass in a single string.
If *regex* is ``True`` (default is ``False``) the given values are
treated as regular expressions.
"""
type_matched = self.ttype is ttype
if not type_matched or values is None:
return type_matched
if regex:
if isinstance(values, basestring):
values = set([values])
if self.ttype is T.Keyword:
values = set(re.compile(v, re.IGNORECASE) for v in values)
else:
values = set(re.compile(v) for v in values)
for pattern in values:
if pattern.search(self.value):
return True
return False
if isinstance(values, basestring):
if self.is_keyword:
return values.upper() == self.normalized
return values == self.value
if self.is_keyword:
for v in values:
if v.upper() == self.normalized:
return True
return False
return self.value in values
def is_group(self):
"""Returns ``True`` if this object has children."""
return False
def is_whitespace(self):
"""Return ``True`` if this token is a whitespace token."""
return self.ttype and self.ttype in T.Whitespace
def within(self, group_cls):
"""Returns ``True`` if this token is within *group_cls*.
Use this method for example to check if an identifier is within
a function: ``t.within(sql.Function)``.
"""
parent = self.parent
while parent:
if isinstance(parent, group_cls):
return True
parent = parent.parent
return False
def is_child_of(self, other):
"""Returns ``True`` if this token is a direct child of *other*."""
return self.parent == other
def has_ancestor(self, other):
"""Returns ``True`` if *other* is in this tokens ancestry."""
parent = self.parent
while parent:
if parent == other:
return True
parent = parent.parent
return False
class TokenList(Token):
"""A group of tokens.
It has an additional instance attribute ``tokens`` which holds a
list of child-tokens.
"""
__slots__ = ('value', 'ttype', 'tokens')
def __init__(self, tokens=None):
if tokens is None:
tokens = []
self.tokens = tokens
Token.__init__(self, None, unicode(self))
def __unicode__(self):
return ''.join(unicode(x) for x in self.flatten())
def _get_repr_name(self):
return self.__class__.__name__
def _pprint_tree(self, max_depth=None, depth=0):
"""Pretty-print the object tree."""
indent = ' ' * (depth * 2)
for idx, token in enumerate(self.tokens):
if token.is_group():
pre = ' +-'
else:
pre = ' | '
print '%s%s%d %s \'%s\'' % (indent, pre, idx,
token._get_repr_name(),
token._get_repr_value())
if (token.is_group() and (max_depth is None or depth < max_depth)):
token._pprint_tree(max_depth, depth + 1)
def _remove_quotes(self, val):
"""Helper that removes surrounding quotes from strings."""
if not val:
return val
if val[0] in ('"', '\'') and val[-1] == val[0]:
val = val[1:-1]
return val
def flatten(self):
"""Generator yielding ungrouped tokens.
This method is recursively called for all child tokens.
"""
for token in self.tokens:
if isinstance(token, TokenList):
for item in token.flatten():
yield item
else:
yield token
# def __iter__(self):
# return self
#
# def next(self):
# for token in self.tokens:
# yield token
def is_group(self):
return True
def get_sublists(self):
# return [x for x in self.tokens if isinstance(x, TokenList)]
for x in self.tokens:
if isinstance(x, TokenList):
yield x
@property
def _groupable_tokens(self):
return self.tokens
def token_first(self, ignore_whitespace=True):
"""Returns the first child token.
If *ignore_whitespace* is ``True`` (the default), whitespace
tokens are ignored.
"""
for token in self.tokens:
if ignore_whitespace and token.is_whitespace():
continue
return token
def token_next_by_instance(self, idx, clss):
"""Returns the next token matching a class.
*idx* is where to start searching in the list of child tokens.
*clss* is a list of classes the token should be an instance of.
If no matching token can be found ``None`` is returned.
"""
if isinstance(clss, (list, tuple)):
clss = (clss,)
if isinstance(clss, tuple):
clss = tuple(clss)
for token in self.tokens[idx:]:
if isinstance(token, clss):
return token
def token_next_by_type(self, idx, ttypes):
"""Returns next matching token by it's token type."""
if not isinstance(ttypes, (list, tuple)):
ttypes = [ttypes]
for token in self.tokens[idx:]:
if token.ttype in ttypes:
return token
def token_next_match(self, idx, ttype, value, regex=False):
"""Returns next token where it's ``match`` method returns ``True``."""
if not isinstance(idx, int):
idx = self.token_index(idx)
for n in xrange(idx, len(self.tokens)):
token = self.tokens[n]
if token.match(ttype, value, regex):
return token
def token_not_matching(self, idx, funcs):
for token in self.tokens[idx:]:
passed = False
for func in funcs:
if func(token):
passed = True
break
if not passed:
return token
def token_matching(self, idx, funcs):
for token in self.tokens[idx:]:
for func in funcs:
if func(token):
return token
def token_prev(self, idx, skip_ws=True):
"""Returns the previous token relative to *idx*.
If *skip_ws* is ``True`` (the default) whitespace tokens are ignored.
``None`` is returned if there's no previous token.
"""
if idx is None:
return None
if not isinstance(idx, int):
idx = self.token_index(idx)
while idx:
idx -= 1
if self.tokens[idx].is_whitespace() and skip_ws:
continue
return self.tokens[idx]
def token_next(self, idx, skip_ws=True):
"""Returns the next token relative to *idx*.
If *skip_ws* is ``True`` (the default) whitespace tokens are ignored.
``None`` is returned if there's no next token.
"""
if idx is None:
return None
if not isinstance(idx, int):
idx = self.token_index(idx)
while idx < len(self.tokens) - 1:
idx += 1
if self.tokens[idx].is_whitespace() and skip_ws:
continue
return self.tokens[idx]
def token_index(self, token):
"""Return list index of token."""
return self.tokens.index(token)
def tokens_between(self, start, end, exclude_end=False):
"""Return all tokens between (and including) start and end.
If *exclude_end* is ``True`` (default is ``False``) the end token
is included too.
"""
# FIXME(andi): rename exclude_end to inlcude_end
if exclude_end:
offset = 0
else:
offset = 1
end_idx = self.token_index(end) + offset
start_idx = self.token_index(start)
return self.tokens[start_idx:end_idx]
def group_tokens(self, grp_cls, tokens, ignore_ws=False):
"""Replace tokens by an instance of *grp_cls*."""
idx = self.token_index(tokens[0])
if ignore_ws:
while tokens and tokens[-1].is_whitespace():
tokens = tokens[:-1]
for t in tokens:
self.tokens.remove(t)
grp = grp_cls(tokens)
for token in tokens:
token.parent = grp
grp.parent = self
self.tokens.insert(idx, grp)
return grp
def insert_before(self, where, token):
"""Inserts *token* before *where*."""
self.tokens.insert(self.token_index(where), token)
def insert_after(self, where, token):
"""Inserts *token* after *where*."""
next_token = self.token_next(where)
if next_token is None:
self.tokens.append(token)
else:
self.tokens.insert(self.token_index(next_token), token)
def has_alias(self):
"""Returns ``True`` if an alias is present."""
return self.get_alias() is not None
def get_alias(self):
"""Returns the alias for this identifier or ``None``."""
kw = self.token_next_match(0, T.Keyword, 'AS')
if kw is not None:
alias = self.token_next(self.token_index(kw))
if alias is None:
return None
else:
next_ = self.token_next_by_instance(0, Identifier)
if next_ is None:
next_ = self.token_next_by_type(0, T.String.Symbol)
if next_ is None:
return None
alias = next_
if isinstance(alias, Identifier):
return alias.get_name()
return self._remove_quotes(unicode(alias))
def get_name(self):
"""Returns the name of this identifier.
This is either it's alias or it's real name. The returned valued can
be considered as the name under which the object corresponding to
this identifier is known within the current statement.
"""
alias = self.get_alias()
if alias is not None:
return alias
return self.get_real_name()
def get_real_name(self):
"""Returns the real name (object name) of this identifier."""
# a.b
dot = self.token_next_match(0, T.Punctuation, '.')
if dot is None:
next_ = self.token_next_by_type(0, T.Name)
if next_ is not None:
return self._remove_quotes(next_.value)
return None
next_ = self.token_next_by_type(self.token_index(dot),
(T.Name, T.Wildcard, T.String.Symbol))
if next_ is None: # invalid identifier, e.g. "a."
return None
return self._remove_quotes(next_.value)
class Statement(TokenList):
"""Represents a SQL statement."""
__slots__ = ('value', 'ttype', 'tokens')
def get_type(self):
"""Returns the type of a statement.
The returned value is a string holding an upper-cased reprint of
the first DML or DDL keyword. If the first token in this group
isn't a DML or DDL keyword "UNKNOWN" is returned.
"""
first_token = self.token_first()
if first_token is None:
# An "empty" statement that either has not tokens at all
# or only whitespace tokens.
return 'UNKNOWN'
elif first_token.ttype in (T.Keyword.DML, T.Keyword.DDL):
return first_token.normalized
return 'UNKNOWN'
class Identifier(TokenList):
"""Represents an identifier.
Identifiers may have aliases or typecasts.
"""
__slots__ = ('value', 'ttype', 'tokens')
def get_parent_name(self):
"""Return name of the parent object if any.
A parent object is identified by the first occuring dot.
"""
dot = self.token_next_match(0, T.Punctuation, '.')
if dot is None:
return None
prev_ = self.token_prev(self.token_index(dot))
if prev_ is None: # something must be verry wrong here..
return None
return self._remove_quotes(prev_.value)
def is_wildcard(self):
"""Return ``True`` if this identifier contains a wildcard."""
token = self.token_next_by_type(0, T.Wildcard)
return token is not None
def get_typecast(self):
"""Returns the typecast or ``None`` of this object as a string."""
marker = self.token_next_match(0, T.Punctuation, '::')
if marker is None:
return None
next_ = self.token_next(self.token_index(marker), False)
if next_ is None:
return None
return unicode(next_)
class IdentifierList(TokenList):
"""A list of :class:`~sqlparse.sql.Identifier`\'s."""
__slots__ = ('value', 'ttype', 'tokens')
def get_identifiers(self):
"""Returns the identifiers.
Whitespaces and punctuations are not included in this generator.
"""
for x in self.tokens:
if not x.is_whitespace() and not x.match(T.Punctuation, ','):
yield x
class Parenthesis(TokenList):
"""Tokens between parenthesis."""
__slots__ = ('value', 'ttype', 'tokens')
@property
def _groupable_tokens(self):
return self.tokens[1:-1]
class Assignment(TokenList):
"""An assignment like 'var := val;'"""
__slots__ = ('value', 'ttype', 'tokens')
class If(TokenList):
"""An 'if' clause with possible 'else if' or 'else' parts."""
__slots__ = ('value', 'ttype', 'tokens')
class For(TokenList):
"""A 'FOR' loop."""
__slots__ = ('value', 'ttype', 'tokens')
class Comparison(TokenList):
"""A comparison used for example in WHERE clauses."""
__slots__ = ('value', 'ttype', 'tokens')
class Comment(TokenList):
"""A comment."""
__slots__ = ('value', 'ttype', 'tokens')
class Where(TokenList):
"""A WHERE clause."""
__slots__ = ('value', 'ttype', 'tokens')
class Case(TokenList):
"""A CASE statement with one or more WHEN and possibly an ELSE part."""
__slots__ = ('value', 'ttype', 'tokens')
def get_cases(self):
"""Returns a list of 2-tuples (condition, value).
If an ELSE exists condition is None.
"""
CONDITION = 1
VALUE = 2
ret = []
mode = CONDITION
for token in self.tokens:
# Set mode from the current statement
if token.match(T.Keyword, 'CASE'):
continue
elif token.match(T.Keyword, 'WHEN'):
ret.append(([], []))
mode = CONDITION
elif token.match(T.Keyword, 'THEN'):
mode = VALUE
elif token.match(T.Keyword, 'ELSE'):
ret.append((None, []))
mode = VALUE
elif token.match(T.Keyword, 'END'):
mode = None
# First condition without preceding WHEN
if mode and not ret:
ret.append(([], []))
# Append token depending of the current mode
if mode == CONDITION:
ret[-1][0].append(token)
elif mode == VALUE:
ret[-1][1].append(token)
# Return cases list
return ret
class Function(TokenList):
"""A function or procedure call."""
__slots__ = ('value', 'ttype', 'tokens')
def get_parameters(self):
"""Return a list of parameters."""
parenthesis = self.tokens[-1]
for t in parenthesis.tokens:
if isinstance(t, IdentifierList):
return t.get_identifiers()
return []