AdvancedSearchTextDetector.py 3.18 KB
Newer Older
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
##############################################################################
#
# Copyright (c) 2008-2009 Nexedi SA and Contributors. All Rights Reserved.
#                    Vincent Pelletier <vincent@nexedi.com>
#
# WARNING: This program as such is intended to be used by professional
# programmers who take the whole responsability of assessing all potential
# consequences resulting from its eventual inadequacies and bugs
# End users who are looking for a ready-to-use solution with commercial
# garantees and support are strongly adviced to contract a Free Software
# Service Company
#
# This program 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 2
# 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, write to the Free Software
# Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA  02111-1307, USA.
#
##############################################################################

from lexer import lexer, update_docstrings

# TODO: remove the special OPERATOR case: it does not work when there are both a valid and an invalid operator

class AdvancedSearchTextDetector(lexer):

  def t_OPERATOR(self, t):
    r'(>=?|<=?|!?=)[ ]*'
    return t

  def t_LEFT_PARENTHESE(self, t):
40 41 42 43
    t.type = 'WORD'
    return t

  def t_RIGHT_PARENTHESE(self, t):
44 45 46 47 48 49 50 51 52
    t.type = 'WORD'
    return t

  def t_STRING(self, t):
    self.found = True
    t.type = 'WORD'
    return t

  def t_COLUMN(self, t):
53
    self.found = self.isColumn(t.value[:-1])
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
    t.type = 'WORD'
    return t

  def t_OR(self, t):
    self.found = True
    t.type = 'WORD'
    return t

  def t_AND(self, t):
    self.found = True
    t.type = 'WORD'
    return t

  def t_NOT(self, t):
    self.found = True
    t.type = 'WORD'
    return t

  def p_search_text(self, p):
    '''search_text : value
                   | value search_text'''
    if len(p) == 2:
      p[0] = p[1]
    else:
      p[0] = p[1] or p[2]

  def p_value(self, p):
    '''value : WORD
             | OPERATOR WORD'''
    p[0] = len(p) == 3 and ' ' not in p[1]

  tokens = (
    'WORD',
    'OPERATOR')

  def real_token(self):
    return lexer.token(self)

  def token(self):
    return self.token_list.pop(0)

95 96
  def __call__(self, input, is_column):
    self.isColumn = is_column
97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114
    try:
      self.found = False
      check_grammar = False
      self.token_list = token_list = []
      append = token_list.append
      self.input(input)
      while not self.found:
        token = self.real_token()
        append(token)
        if token is None:
          break
        if token.type == 'OPERATOR':
          check_grammar = True
      if not self.found and check_grammar:
        self.found = self.parse()
      return self.found
    finally:
      self.isColumn = None
115 116 117

update_docstrings(AdvancedSearchTextDetector)