/usr/lib/python3/dist-packages/sqlparse/engine/grouping.py is in python3-sqlparse 0.2.4-0.1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 | # -*- coding: utf-8 -*-
#
# Copyright (C) 2016 Andi Albrecht, albrecht.andi@gmail.com
#
# This module is part of python-sqlparse and is released under
# the BSD License: https://opensource.org/licenses/BSD-3-Clause
from sqlparse import sql
from sqlparse import tokens as T
from sqlparse.utils import recurse, imt
T_NUMERICAL = (T.Number, T.Number.Integer, T.Number.Float)
T_STRING = (T.String, T.String.Single, T.String.Symbol)
T_NAME = (T.Name, T.Name.Placeholder)
def _group_matching(tlist, cls):
"""Groups Tokens that have beginning and end."""
opens = []
tidx_offset = 0
for idx, token in enumerate(list(tlist)):
tidx = idx - tidx_offset
if token.is_whitespace:
# ~50% of tokens will be whitespace. Will checking early
# for them avoid 3 comparisons, but then add 1 more comparison
# for the other ~50% of tokens...
continue
if token.is_group and not isinstance(token, cls):
# Check inside previously grouped (ie. parenthesis) if group
# of differnt type is inside (ie, case). though ideally should
# should check for all open/close tokens at once to avoid recursion
_group_matching(token, cls)
continue
if token.match(*cls.M_OPEN):
opens.append(tidx)
elif token.match(*cls.M_CLOSE):
try:
open_idx = opens.pop()
except IndexError:
# this indicates invalid sql and unbalanced tokens.
# instead of break, continue in case other "valid" groups exist
continue
close_idx = tidx
tlist.group_tokens(cls, open_idx, close_idx)
tidx_offset += close_idx - open_idx
def group_brackets(tlist):
_group_matching(tlist, sql.SquareBrackets)
def group_parenthesis(tlist):
_group_matching(tlist, sql.Parenthesis)
def group_case(tlist):
_group_matching(tlist, sql.Case)
def group_if(tlist):
_group_matching(tlist, sql.If)
def group_for(tlist):
_group_matching(tlist, sql.For)
def group_begin(tlist):
_group_matching(tlist, sql.Begin)
def group_typecasts(tlist):
def match(token):
return token.match(T.Punctuation, '::')
def valid(token):
return token is not None
def post(tlist, pidx, tidx, nidx):
return pidx, nidx
valid_prev = valid_next = valid
_group(tlist, sql.Identifier, match, valid_prev, valid_next, post)
def group_period(tlist):
def match(token):
return token.match(T.Punctuation, '.')
def valid_prev(token):
sqlcls = sql.SquareBrackets, sql.Identifier
ttypes = T.Name, T.String.Symbol
return imt(token, i=sqlcls, t=ttypes)
def valid_next(token):
# issue261, allow invalid next token
return True
def post(tlist, pidx, tidx, nidx):
# next_ validation is being performed here. issue261
sqlcls = sql.SquareBrackets, sql.Function
ttypes = T.Name, T.String.Symbol, T.Wildcard
next_ = tlist[nidx] if nidx is not None else None
valid_next = imt(next_, i=sqlcls, t=ttypes)
return (pidx, nidx) if valid_next else (pidx, tidx)
_group(tlist, sql.Identifier, match, valid_prev, valid_next, post)
def group_as(tlist):
def match(token):
return token.is_keyword and token.normalized == 'AS'
def valid_prev(token):
return token.normalized == 'NULL' or not token.is_keyword
def valid_next(token):
ttypes = T.DML, T.DDL
return not imt(token, t=ttypes) and token is not None
def post(tlist, pidx, tidx, nidx):
return pidx, nidx
_group(tlist, sql.Identifier, match, valid_prev, valid_next, post)
def group_assignment(tlist):
def match(token):
return token.match(T.Assignment, ':=')
def valid(token):
return token is not None and token.ttype not in (T.Keyword)
def post(tlist, pidx, tidx, nidx):
m_semicolon = T.Punctuation, ';'
snidx, _ = tlist.token_next_by(m=m_semicolon, idx=nidx)
nidx = snidx or nidx
return pidx, nidx
valid_prev = valid_next = valid
_group(tlist, sql.Assignment, match, valid_prev, valid_next, post)
def group_comparison(tlist):
sqlcls = (sql.Parenthesis, sql.Function, sql.Identifier,
sql.Operation)
ttypes = T_NUMERICAL + T_STRING + T_NAME
def match(token):
return token.ttype == T.Operator.Comparison
def valid(token):
if imt(token, t=ttypes, i=sqlcls):
return True
elif token and token.is_keyword and token.normalized == 'NULL':
return True
else:
return False
def post(tlist, pidx, tidx, nidx):
return pidx, nidx
valid_prev = valid_next = valid
_group(tlist, sql.Comparison, match,
valid_prev, valid_next, post, extend=False)
@recurse(sql.Identifier)
def group_identifier(tlist):
ttypes = (T.String.Symbol, T.Name)
tidx, token = tlist.token_next_by(t=ttypes)
while token:
tlist.group_tokens(sql.Identifier, tidx, tidx)
tidx, token = tlist.token_next_by(t=ttypes, idx=tidx)
def group_arrays(tlist):
sqlcls = sql.SquareBrackets, sql.Identifier, sql.Function
ttypes = T.Name, T.String.Symbol
def match(token):
return isinstance(token, sql.SquareBrackets)
def valid_prev(token):
return imt(token, i=sqlcls, t=ttypes)
def valid_next(token):
return True
def post(tlist, pidx, tidx, nidx):
return pidx, tidx
_group(tlist, sql.Identifier, match,
valid_prev, valid_next, post, extend=True, recurse=False)
def group_operator(tlist):
ttypes = T_NUMERICAL + T_STRING + T_NAME
sqlcls = (sql.SquareBrackets, sql.Parenthesis, sql.Function,
sql.Identifier, sql.Operation)
def match(token):
return imt(token, t=(T.Operator, T.Wildcard))
def valid(token):
return imt(token, i=sqlcls, t=ttypes)
def post(tlist, pidx, tidx, nidx):
tlist[tidx].ttype = T.Operator
return pidx, nidx
valid_prev = valid_next = valid
_group(tlist, sql.Operation, match,
valid_prev, valid_next, post, extend=False)
def group_identifier_list(tlist):
m_role = T.Keyword, ('null', 'role')
sqlcls = (sql.Function, sql.Case, sql.Identifier, sql.Comparison,
sql.IdentifierList, sql.Operation)
ttypes = (T_NUMERICAL + T_STRING + T_NAME +
(T.Keyword, T.Comment, T.Wildcard))
def match(token):
return token.match(T.Punctuation, ',')
def valid(token):
return imt(token, i=sqlcls, m=m_role, t=ttypes)
def post(tlist, pidx, tidx, nidx):
return pidx, nidx
valid_prev = valid_next = valid
_group(tlist, sql.IdentifierList, match,
valid_prev, valid_next, post, extend=True)
@recurse(sql.Comment)
def group_comments(tlist):
tidx, token = tlist.token_next_by(t=T.Comment)
while token:
eidx, end = tlist.token_not_matching(
lambda tk: imt(tk, t=T.Comment) or tk.is_whitespace, idx=tidx)
if end is not None:
eidx, end = tlist.token_prev(eidx, skip_ws=False)
tlist.group_tokens(sql.Comment, tidx, eidx)
tidx, token = tlist.token_next_by(t=T.Comment, idx=tidx)
@recurse(sql.Where)
def group_where(tlist):
tidx, token = tlist.token_next_by(m=sql.Where.M_OPEN)
while token:
eidx, end = tlist.token_next_by(m=sql.Where.M_CLOSE, idx=tidx)
if end is None:
end = tlist._groupable_tokens[-1]
else:
end = tlist.tokens[eidx - 1]
# TODO: convert this to eidx instead of end token.
# i think above values are len(tlist) and eidx-1
eidx = tlist.token_index(end)
tlist.group_tokens(sql.Where, tidx, eidx)
tidx, token = tlist.token_next_by(m=sql.Where.M_OPEN, idx=tidx)
@recurse()
def group_aliased(tlist):
I_ALIAS = (sql.Parenthesis, sql.Function, sql.Case, sql.Identifier,
sql.Operation, sql.Comparison)
tidx, token = tlist.token_next_by(i=I_ALIAS, t=T.Number)
while token:
nidx, next_ = tlist.token_next(tidx)
if isinstance(next_, sql.Identifier):
tlist.group_tokens(sql.Identifier, tidx, nidx, extend=True)
tidx, token = tlist.token_next_by(i=I_ALIAS, t=T.Number, idx=tidx)
@recurse(sql.Function)
def group_functions(tlist):
has_create = False
has_table = False
for tmp_token in tlist.tokens:
if tmp_token.value == 'CREATE':
has_create = True
if tmp_token.value == 'TABLE':
has_table = True
if has_create and has_table:
return
tidx, token = tlist.token_next_by(t=T.Name)
while token:
nidx, next_ = tlist.token_next(tidx)
if isinstance(next_, sql.Parenthesis):
tlist.group_tokens(sql.Function, tidx, nidx)
tidx, token = tlist.token_next_by(t=T.Name, idx=tidx)
def group_order(tlist):
"""Group together Identifier and Asc/Desc token"""
tidx, token = tlist.token_next_by(t=T.Keyword.Order)
while token:
pidx, prev_ = tlist.token_prev(tidx)
if imt(prev_, i=sql.Identifier, t=T.Number):
tlist.group_tokens(sql.Identifier, pidx, tidx)
tidx = pidx
tidx, token = tlist.token_next_by(t=T.Keyword.Order, idx=tidx)
@recurse()
def align_comments(tlist):
tidx, token = tlist.token_next_by(i=sql.Comment)
while token:
pidx, prev_ = tlist.token_prev(tidx)
if isinstance(prev_, sql.TokenList):
tlist.group_tokens(sql.TokenList, pidx, tidx, extend=True)
tidx = pidx
tidx, token = tlist.token_next_by(i=sql.Comment, idx=tidx)
def group(stmt):
for func in [
group_comments,
# _group_matching
group_brackets,
group_parenthesis,
group_case,
group_if,
group_for,
group_begin,
group_functions,
group_where,
group_period,
group_arrays,
group_identifier,
group_order,
group_typecasts,
group_operator,
group_comparison,
group_as,
group_aliased,
group_assignment,
align_comments,
group_identifier_list,
]:
func(stmt)
return stmt
def _group(tlist, cls, match,
valid_prev=lambda t: True,
valid_next=lambda t: True,
post=None,
extend=True,
recurse=True
):
"""Groups together tokens that are joined by a middle token. ie. x < y"""
tidx_offset = 0
pidx, prev_ = None, None
for idx, token in enumerate(list(tlist)):
tidx = idx - tidx_offset
if token.is_whitespace:
continue
if recurse and token.is_group and not isinstance(token, cls):
_group(token, cls, match, valid_prev, valid_next, post, extend)
if match(token):
nidx, next_ = tlist.token_next(tidx)
if prev_ and valid_prev(prev_) and valid_next(next_):
from_idx, to_idx = post(tlist, pidx, tidx, nidx)
grp = tlist.group_tokens(cls, from_idx, to_idx, extend=extend)
tidx_offset += to_idx - from_idx
pidx, prev_ = from_idx, grp
continue
pidx, prev_ = tidx, token
|