/usr/lib/python3/dist-packages/relational/parser.py is in python3-relational 2.5-1.
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 | # Relational
# Copyright (C) 2008-2016 Salvo "LtWorf" Tomaselli
#
# Relational is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
#
# author Salvo "LtWorf" Tomaselli <tiposchi@tiscali.it>
#
#
#
# This module implements a parser for relational algebra, and can be used
# to convert expressions into python expressions and to get the parse-tree
# of the expression.
#
# Language definition here:
# http://ltworf.github.io/relational/grammar.html
from relational import rtypes
RELATION = 0
UNARY = 1
BINARY = 2
PRODUCT = '*'
DIFFERENCE = '-'
UNION = '∪'
INTERSECTION = '∩'
DIVISION = '÷'
JOIN = '⋈'
JOIN_LEFT = '⧑'
JOIN_RIGHT = '⧒'
JOIN_FULL = '⧓'
PROJECTION = 'π'
SELECTION = 'σ'
RENAME = 'ρ'
ARROW = '➡'
b_operators = (PRODUCT, DIFFERENCE, UNION, INTERSECTION, DIVISION,
JOIN, JOIN_LEFT, JOIN_RIGHT, JOIN_FULL) # List of binary operators
u_operators = (PROJECTION, SELECTION, RENAME) # List of unary operators
# Associates operator with python method
op_functions = {
PRODUCT: 'product', DIFFERENCE: 'difference', UNION: 'union', INTERSECTION: 'intersection', DIVISION: 'division', JOIN: 'join',
JOIN_LEFT: 'outer_left', JOIN_RIGHT: 'outer_right', JOIN_FULL: 'outer', PROJECTION: 'projection', SELECTION: 'selection', RENAME: 'rename'}
class TokenizerException (Exception):
pass
class ParserException (Exception):
pass
class CallableString(str):
'''
This is a string. However it is also callable.
For example:
CallableString('1+1')()
returns 2
It is used to contain Python expressions and print
or execute them.
'''
def __call__(self, context=None):
'''
context is a dictionary where to
each name is associated the relative relation
'''
return eval(self, context)
class Node (object):
'''This class is a node of a relational expression. Leaves are relations
and internal nodes are operations.
The 'kind' property indicates whether the node is a binary operator, unary
operator or relation.
Since relations are leaves, a relation node will have no attribute for
children.
If the node is a binary operator, it will have left and right properties.
If the node is a unary operator, it will have a child, pointing to the
child node and a property containing the string with the props of the
operation.
This class is used to convert an expression into python code.'''
kind = None
__hash__ = None
def __init__(self, expression=None):
'''Generates the tree from the tokenized expression
If no expression is specified then it will create an empty node'''
if expression == None or len(expression) == 0:
return
# If the list contains only a list, it will consider the lower level list.
# This will allow things like ((((((a))))) to work
while len(expression) == 1 and isinstance(expression[0], list):
expression = expression[0]
# The list contains only 1 string. Means it is the name of a relation
if len(expression) == 1:
self.kind = RELATION
self.name = expression[0]
if not rtypes.is_valid_relation_name(self.name):
raise ParserException(
u"'%s' is not a valid relation name" % self.name)
return
# Expression from right to left, searching for binary operators
# this means that binary operators have lesser priority than
# unary operators.
# It finds the operator with lesser priority, uses it as root of this
# (sub)tree using everything on its left as left parameter (so building
# a left subtree with the part of the list located on left) and doing
# the same on right.
# Since it searches for strings, and expressions into parenthesis are
# within sub-lists, they won't be found here, ensuring that they will
# have highest priority.
for i in range(len(expression) - 1, -1, -1):
if expression[i] in b_operators: # Binary operator
self.kind = BINARY
self.name = expression[i]
if len(expression[:i]) == 0:
raise ParserException(
u"Expected left operand for '%s'" % self.name)
if len(expression[i + 1:]) == 0:
raise ParserException(
u"Expected right operand for '%s'" % self.name)
self.left = node(expression[:i])
self.right = node(expression[i + 1:])
return
'''Searches for unary operators, parsing from right to left'''
for i in range(len(expression) - 1, -1, -1):
if expression[i] in u_operators: # Unary operator
self.kind = UNARY
self.name = expression[i]
if len(expression) <= i + 2:
raise ParserException(
u"Expected more tokens in '%s'" % self.name)
self.prop = expression[1 + i].strip()
self.child = node(expression[2 + i])
return
raise ParserException("Expected operator in '%s'" % expression)
def toCode(self):
'''This method converts the AST into a python code object'''
code = self._toPython()
return compile(code, '<relational_expression>', 'eval')
def toPython(self):
'''This method converts the AST into a python code string, which
will require the relation module to be executed.
The return value is a CallableString, which means that it can be
directly called.'''
return CallableString(self._toPython())
def _toPython(self):
'''
Same as toPython but returns a regular string
'''
if self.name in b_operators:
return '%s.%s(%s)' % (self.left.toPython(), op_functions[self.name], self.right.toPython())
elif self.name in u_operators:
prop = self.prop
# Converting parameters
if self.name == PROJECTION:
prop = '\"%s\"' % prop.replace(' ', '').replace(',', '\",\"')
elif self.name == RENAME:
prop = '{\"%s\"}' % prop.replace(
',', '\",\"').replace(ARROW, '\":\"').replace(' ', '')
else: # Selection
prop = repr(prop)
return '%s.%s(%s)' % (self.child.toPython(), op_functions[self.name], prop)
return self.name
def printtree(self, level=0):
'''returns a representation of the tree using indentation'''
r = ''
for i in range(level):
r += ' '
r += self.name
if self.name in b_operators:
r += self.left.printtree(level + 1)
r += self.right.printtree(level + 1)
elif self.name in u_operators:
r += '\t%s\n' % self.prop
r += self.child.printtree(level + 1)
return '\n' + r
def get_left_leaf(self):
'''This function returns the leftmost leaf in the tree.'''
if self.kind == RELATION:
return self
elif self.kind == UNARY:
return self.child.get_left_leaf()
elif self.kind == BINARY:
return self.left.get_left_leaf()
def result_format(self, rels):
'''This function returns a list containing the fields that the resulting relation will have.
It requires a dictionary where keys are the names of the relations and the values are
the relation objects.'''
if rels == None:
return
if self.kind == RELATION:
return list(rels[self.name].header)
elif self.kind == BINARY and self.name in (DIFFERENCE, UNION, INTERSECTION):
return self.left.result_format(rels)
elif self.kind == BINARY and self.name == DIVISION:
return list(set(self.left.result_format(rels)) - set(self.right.result_format(rels)))
elif self.name == PROJECTION:
l = []
for i in self.prop.split(','):
l.append(i.strip())
return l
elif self.name == PRODUCT:
return self.left.result_format(rels) + self.right.result_format(rels)
elif self.name == SELECTION:
return self.child.result_format(rels)
elif self.name == RENAME:
_vars = {}
for i in self.prop.split(','):
q = i.split(ARROW)
_vars[q[0].strip()] = q[1].strip()
_fields = self.child.result_format(rels)
for i in range(len(_fields)):
if _fields[i] in _vars:
_fields[i] = _vars[_fields[i]]
return _fields
elif self.name in (JOIN, JOIN_LEFT, JOIN_RIGHT, JOIN_FULL):
return list(set(self.left.result_format(rels)).union(set(self.right.result_format(rels))))
def __eq__(self, other):
if not (isinstance(other, node) and self.name == other.name and self.kind == other.kind):
return False
if self.kind == UNARY:
if other.prop != self.prop:
return False
return self.child == other.child
if self.kind == BINARY:
return self.left == other.left and self.right == other.right
return True
def __str__(self):
if (self.kind == RELATION):
return self.name
elif (self.kind == UNARY):
return self.name + " " + self.prop + " (" + self.child.__str__() + ")"
elif (self.kind == BINARY):
le = self.left.__str__()
if self.right.kind != BINARY:
re = self.right.__str__()
else:
re = "(" + self.right.__str__() + ")"
return (le + self.name + re)
def _find_matching_parenthesis(expression, start=0, openpar=u'(', closepar=u')'):
'''This function returns the position of the matching
close parenthesis to the 1st open parenthesis found
starting from start (0 by default)'''
par_count = 0 # Count of parenthesis
string = False
escape = False
for i in range(start, len(expression)):
if expression[i] == '\'' and not escape:
string = not string
if expression[i] == '\\' and not escape:
escape = True
else:
escape = False
if string:
continue
if expression[i] == openpar:
par_count += 1
elif expression[i] == closepar:
par_count -= 1
if par_count == 0:
return i # Closing parenthesis of the parameter
def _find_token(haystack, needle):
'''
Like the string function find, but
ignores tokens that are within a string
literal.
'''
r = -1
string = False
escape = False
for i in range(len(haystack)):
if haystack[i] == '\'' and not escape:
string = not string
if haystack[i] == '\\' and not escape:
escape = True
else:
escape = False
if string:
continue
if haystack[i:].startswith(needle):
return i
return r
def tokenize(expression):
'''This function converts a relational expression into a list where
every token of the expression is an item of a list. Expressions into
parenthesis will be converted into sublists.'''
items = [] # List for the tokens
expression = expression.strip() # Removes initial and ending spaces
while len(expression) > 0:
if expression.startswith('('): # Parenthesis state
end = _find_matching_parenthesis(expression)
if end == None:
raise TokenizerException(
"Missing matching ')' in '%s'" % expression)
# Appends the tokenization of the content of the parenthesis
items.append(tokenize(expression[1:end]))
# Removes the entire parentesis and content from the expression
expression = expression[end + 1:].strip()
elif expression.startswith((SELECTION, RENAME, PROJECTION)): # Unary operators
items.append(expression[0:1])
# Adding operator in the top of the list
expression = expression[
1:].strip() # Removing operator from the expression
if expression.startswith('('): # Expression with parenthesis, so adding what's between open and close without tokenization
par = expression.find(
'(', _find_matching_parenthesis(expression))
else: # Expression without parenthesis, so adding what's between start and parenthesis as whole
par = _find_token(expression, '(')
items.append(expression[:par].strip())
# Inserting parameter of the operator
expression = expression[
par:].strip() # Removing parameter from the expression
else: # Relation (hopefully)
expression += ' ' # To avoid the special case of the ending
# Initial part is a relation, stop when the name of the relation is
# over
for r in range(1, len(expression)):
if rtypes.RELATION_NAME_REGEXP.match(expression[:r + 1]) is None:
break
items.append(expression[:r])
expression = expression[r:].strip()
return items
def tree(expression):
'''This function parses a relational algebra expression into a AST and returns
the root node using the Node class.'''
return node(tokenize(expression))
def parse(expr):
'''This function parses a relational algebra expression, and returns a
CallableString (a string that can be called) whith the corresponding
Python expression.
'''
return tree(expr).toPython()
if __name__ == "__main__":
while True:
e = input("Expression: ")
print (parse(e))
# Backwards compatibility
node = Node
|