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
|
# -*- coding: utf-8 -*-
import itertools
import re
import types
from sqlparse import tokens as T
from sqlparse.sql import *
def _group_left_right(tlist, ttype, value, cls,
check_right=lambda t: True,
include_semicolon=False):
# [_group_left_right(sgroup, ttype, value, cls, check_right,
# include_semicolon) for sgroup in tlist.get_sublists()
# if not isinstance(sgroup, cls)]
idx = 0
token = tlist.token_next_match(idx, ttype, value)
while token:
right = tlist.token_next(tlist.token_index(token))
left = tlist.token_prev(tlist.token_index(token))
if (right is None or not check_right(right)
or left is None):
token = tlist.token_next_match(tlist.token_index(token)+1,
ttype, value)
else:
if include_semicolon:
right = tlist.token_next_match(tlist.token_index(right),
T.Punctuation, ';')
tokens = tlist.tokens_between(left, right)[1:]
if not isinstance(left, cls):
new = cls([left])
new_idx = tlist.token_index(left)
tlist.tokens.remove(left)
tlist.tokens.insert(new_idx, new)
left = new
left.tokens.extend(tokens)
for t in tokens:
tlist.tokens.remove(t)
token = tlist.token_next_match(tlist.token_index(left)+1,
ttype, value)
def _group_matching(tlist, start_ttype, start_value, end_ttype, end_value,
cls, include_semicolon=False, recurse=False):
def _find_matching(i, tl, stt, sva, ett, eva):
depth = 1
for t in tl.tokens[i:]:
if t.match(stt, sva):
depth += 1
elif t.match(ett, eva):
depth -= 1
if depth == 1:
return t
return None
[_group_matching(sgroup, start_ttype, start_value, end_ttype, end_value,
cls, include_semicolon) for sgroup in tlist.get_sublists()
if recurse]
if isinstance(tlist, cls):
idx = 1
else:
idx = 0
token = tlist.token_next_match(idx, start_ttype, start_value)
while token:
tidx = tlist.token_index(token)
end = _find_matching(tidx, tlist, start_ttype, start_value,
end_ttype, end_value)
if end is None:
idx = tidx+1
else:
if include_semicolon:
next_ = tlist.token_next(tlist.token_index(end))
if next_ and next_.match(T.Punctuation, ';'):
end = next_
group = tlist.group_tokens(cls, tlist.tokens_between(token, end))
_group_matching(group, start_ttype, start_value,
end_ttype, end_value, cls, include_semicolon)
idx = tlist.token_index(group)+1
token = tlist.token_next_match(idx, start_ttype, start_value)
def group_if(tlist):
_group_matching(tlist, T.Keyword, 'IF', T.Keyword, 'END IF', If, True)
def group_for(tlist):
_group_matching(tlist, T.Keyword, 'FOR', T.Keyword, 'END LOOP', For, True)
def group_as(tlist):
_group_left_right(tlist, T.Keyword, 'AS', Identifier)
def group_assignment(tlist):
_group_left_right(tlist, T.Assignment, ':=', Assignment,
include_semicolon=True)
def group_comparsion(tlist):
_group_left_right(tlist, T.Operator, None, Comparsion)
def group_case(tlist):
_group_matching(tlist, T.Keyword, 'CASE', T.Keyword, 'END', Case, True)
def group_identifier(tlist):
def _consume_cycle(tl, i):
x = itertools.cycle((lambda y: y.match(T.Punctuation, '.'),
lambda y: y.ttype in (T.String.Symbol, T.Name)))
for t in tl.tokens[i:]:
if x.next()(t):
yield t
else:
raise StopIteration
# bottom up approach: group subgroups first
[group_identifier(sgroup) for sgroup in tlist.get_sublists()
if not isinstance(sgroup, Identifier)]
# real processing
idx = 0
token = tlist.token_next_by_type(idx, (T.String.Symbol, T.Name))
while token:
identifier_tokens = [token]+list(
_consume_cycle(tlist,
tlist.token_index(token)+1))
group = tlist.group_tokens(Identifier, identifier_tokens)
idx = tlist.token_index(group)+1
token = tlist.token_next_by_type(idx, (T.String.Symbol, T.Name))
def group_identifier_list(tlist):
[group_identifier_list(sgroup) for sgroup in tlist.get_sublists()
if not isinstance(sgroup, IdentifierList)]
idx = 0
token = tlist.token_next_by_instance(idx, Identifier)
while token:
tidx = tlist.token_index(token)
end = tlist.token_not_matching(tidx+1,
[lambda t: isinstance(t, Identifier),
lambda t: t.is_whitespace(),
lambda t: t.match(T.Punctuation,
',')
])
if end is None:
idx = tidx + 1
else:
grp_tokens = tlist.tokens_between(token, end, exclude_end=True)
while grp_tokens and (grp_tokens[-1].is_whitespace()
or grp_tokens[-1].match(T.Punctuation, ',')):
grp_tokens.pop()
if len(grp_tokens) <= 1:
idx = tidx + 1
else:
group = tlist.group_tokens(IdentifierList, grp_tokens)
idx = tlist.token_index(group)
token = tlist.token_next_by_instance(idx, Identifier)
def group_parenthesis(tlist):
_group_matching(tlist, T.Punctuation, '(', T.Punctuation, ')', Parenthesis)
def group_comments(tlist):
[group_comments(sgroup) for sgroup in tlist.get_sublists()
if not isinstance(sgroup, Comment)]
idx = 0
token = tlist.token_next_by_type(idx, T.Comment)
while token:
tidx = tlist.token_index(token)
end = tlist.token_not_matching(tidx+1,
[lambda t: t.ttype in T.Comment,
lambda t: t.is_whitespace()])
if end is None:
idx = tidx + 1
else:
eidx = tlist.token_index(end)
grp_tokens = tlist.tokens_between(token,
tlist.token_prev(eidx, False))
group = tlist.group_tokens(Comment, grp_tokens)
idx = tlist.token_index(group)
token = tlist.token_next_by_type(idx, T.Comment)
def group_where(tlist):
[group_where(sgroup) for sgroup in tlist.get_sublists()
if not isinstance(sgroup, Where)]
idx = 0
token = tlist.token_next_match(idx, T.Keyword, 'WHERE')
stopwords = ('ORDER', 'GROUP', 'LIMIT', 'UNION')
while token:
tidx = tlist.token_index(token)
end = tlist.token_next_match(tidx+1, T.Keyword, stopwords)
if end is None:
end = tlist.tokens[-1]
else:
end = tlist.tokens[tlist.token_index(end)-1]
group = tlist.group_tokens(Where, tlist.tokens_between(token, end))
idx = tlist.token_index(group)
token = tlist.token_next_match(idx, T.Keyword, 'WHERE')
def group_aliased(tlist):
[group_aliased(sgroup) for sgroup in tlist.get_sublists()
if not isinstance(sgroup, Identifier)]
idx = 0
token = tlist.token_next_by_instance(idx, Identifier)
while token:
next_ = tlist.token_next(tlist.token_index(token))
if next_ is not None and isinstance(next_, Identifier):
grp = tlist.tokens_between(token, next_)[1:]
token.tokens.extend(grp)
for t in grp:
tlist.tokens.remove(t)
idx = tlist.token_index(token)+1
token = tlist.token_next_by_instance(idx, Identifier)
def group_typecasts(tlist):
_group_left_right(tlist, T.Punctuation, '::', Identifier)
def group(tlist):
for func in [group_parenthesis,
group_comments,
group_where,
group_case,
group_identifier,
group_typecasts,
group_as,
group_aliased,
group_assignment,
group_comparsion,
group_identifier_list,
group_if,
group_for,]:
func(tlist)
|
