tests/test_busstopmash_regexes.py

   1 # vi: set fileencoding=latin1 softtabstop=4 shiftwidth=4 tabstop=8 expandtab:
   2 #
   3 # The above line tells Python to use Latin-1, which seems to be right for the
   4 # accented characters coming back from the travel planner.
   5
   6 import unittest
   7 import BusStopMashup
   8
   9 class TestStopRegex(unittest.TestCase):
  10     def testAccentedEInName(self):
  11         text = r"""<span><strong><b>613-560-1000 plus <a href='iframe.asp?route=busstop&INFO_PHONE=3035' target='iframe'>3035</a></b></strong><small>  (RA970)</small><br>HERON STOP / ARRÊT 4A <br><a href='iframe.asp?route=4&dir=10' target='iframe'>4</a> <a href='iframe.asp?route=87&dir=11' target='iframe'>87</a> <a href='iframe.asp?route=107&dir=11' target='iframe'>107</a> <a href='iframe.asp?route=111&dir=10' target='iframe'>111</a> <a href='iframe.asp?route=118&dir=10' target='iframe'>118</a> <a href='iframe.asp?route=140&dir=11' target='iframe'>140</a> <a href='iframe.asp?route=656&dir=11' target='iframe'>656</a> </span>"""
  12         match = BusStopMashup._stop_rx.search(text)
  13         self.assertNotEquals(match, None)
  14         self.assertEquals(match.group("stopnum"), "3035")
  15         self.assertEquals(match.group("code"), "RA970")
  16
  17     def testLongStopCode(self):
  18         text = r"""<span><strong><b>613-560-1000 plus <a href='iframe.asp?route=busstop&INFO_PHONE=3035' target='iframe'>3035</a></b></strong><small>  (SCO018)</small><br>HERON SCOTIABANK 2A<br></span>"""
  19         match = BusStopMashup._stop_rx.search(text)
  20         self.assertNotEquals(match, None)
  21         self.assertEquals(match.group("code"), "SCO018")
  22
  23 if __name__ == '__main__':
  24     unittest.main()