sirutacsv.py

   1 #!/uss/bin/python
   2
   3 import csv
   4
   5 class SirutaDictReader(csv.DictReader):
   6         """
   7         A CSV dict reader which maps the CSV field names to proper OSM tag names
   8         """
   9
  10         def _mapCSVNamesToOSMNames(self, csvnames):
  11
  12                 namemap = { 'X':u'lon', \
  13                                 'Y':u'lat', \
  14                                 'NAME':u'name', \
  15                                 'SIRUTA':u'siruta:code', \
  16                                 'OLD_POSTAL':u'old_postal_code', \
  17                                 'RANG':u'siruta:rank', \
  18                                 'TIP':u'siruta:type', \
  19                                 'SIRUTA_SUP':u'siruta:code_sup', \
  20                                 'NAME_SUP':u'siruta:name_sup', \
  21                                 'COUNTY':u'siruta:county', \
  22                                 'COUNTY_ID':u'siruta:county_id', \
  23                                 'COUNTY_MN':u'siruta:county_code', \
  24                                 'POP2002':u'population2002', \
  25                                 'REGION':u'region', \
  26                                 'REGION_ID':u'siruta:region_id', \
  27                                 'ENVIRO_TYP':u'siruta:enviro_type', \
  28                                 'SORT_CODE':u'siruta:sortcode' }
  29
  30                 osmnames = []
  31                 for name in csvnames:
  32                         # although this will fail if unknown rows appear, that
  33                         # is the intended behaviour since we don't want to silently
  34                         # add or ignore fields unintentionaly
  35                         osmnames.append(namemap[name])
  36
  37                 return osmnames
  38
  39         def next(self):
  40                 if self.fieldnames is None:
  41                         row = self.reader.next()
  42                         row = self._mapCSVNamesToOSMNames(row)
  43                         self.fieldnames = row
  44
  45                 d = csv.DictReader.next(self)
  46
  47                 for cell in d:
  48                         try:
  49                                 d[cell] = unicode(d[cell], 'utf-8')
  50                         except TypeError:
  51                                 pass
  52                 return d
  53
  54