def __init__(self, teryt_file, jst_file, par_file):
"""Initiates TTPDecoder by creating all single decoders.
Arguments:
teryt_file -- name of file with TERYT codes
jst_file -- name of file with jst codes
par_file -- name of file with paragraphs
"""
self.teryt_decoder = TerytDecoder(teryt_file)
self.jst_decoder = JSTDecoder(jst_file)
self.par_decoder = ParDecoder(par_file)
self.header_transform_dict = {
u'Kod województwa wg GUS': u'Województwo',
u'Kod powiatu wg GUS': u'Powiat',
u'Kod gminy wg GUS': u'Gmina',
u'Typ gminy': u'Typ jednostki',
u'Finansowanie paragrafu - 4 cyfra paragrafu': u'Finansowanie'
}
class TTPDecoder:
"""Decodes teryt, jst name and paragraph 4."""
def __init__(self, teryt_file, jst_file, par_file):
"""Initiates TTPDecoder by creating all single decoders.
Arguments:
teryt_file -- name of file with TERYT codes
jst_file -- name of file with jst codes
par_file -- name of file with paragraphs
"""
self.teryt_decoder = TerytDecoder(teryt_file)
self.jst_decoder = JSTDecoder(jst_file)
self.par_decoder = ParDecoder(par_file)
self.header_transform_dict = {
u'Kod województwa wg GUS': u'Województwo',
u'Kod powiatu wg GUS': u'Powiat',
u'Kod gminy wg GUS': u'Gmina',
u'Typ gminy': u'Typ jednostki',
u'Finansowanie paragrafu - 4 cyfra paragrafu': u'Finansowanie'
}
def decode_file(self, source_filename, result_filename):
"""Decodes given file.
Arguments:
source_filename -- name of file to decode
result_filename -- name of file to save decoded data
"""
csv_file = CsvFile(source_filename, delim=';', quote='"')
csv_data = CsvData(csv_file)
new_header = self.decode_header(csv_data.get_header())
new_rows = []
row = csv_data.get_next_row(row_type='list')
i = 0
while row:
i += 1
changed_row = row[:]
is_jst = row[4] in ['z', 'Z']
changed_row[1] = self.teryt_decoder.get_name(row[1])
if changed_row[1] is None:
print i
if is_jst:
changed_row[2] = self.teryt_decoder.get_name(row[1] + row[2])
if changed_row[2] is None:
print i
changed_row[3] = self.jst_decoder.get_name(row[6][1:]) # decoder has xyz, file has 0xyz
if changed_row[3] is None:
print i
changed_row[4] = u'Związek JST'
else:
type = self.teryt_decoder.get_type(row[1])
if row[2] != '00':
changed_row[2] = self.teryt_decoder.get_name(row[1] + row[2])
if changed_row[2] is None:
print i
type = self.teryt_decoder.get_type(row[1] + row[2])
else:
changed_row[2] = ''
if row[3] != '00':
changed_row[3] = self.teryt_decoder.get_name(row[1] + row[2] + row[3])
if changed_row[3] is None:
print i
type = self.teryt_decoder.get_type(row[1] + row[2] + row[3])
else:
changed_row[3] = ''
changed_row[4] = type
self.clean_row(changed_row)
new_rows.append(changed_row)
row = csv_data.get_next_row(row_type='list')
csv_file.close()
new_data = Data([new_header] + new_rows, result_filename)
new_data.save()
def decode_header(self, header):
"""Decodes fields in header, returns changed header.
Arguments:
header -- header of file
"""
changed_header = []
for field in header:
try:
changed_header.append(self.header_transform_dict[field])
except KeyError:
changed_header.append(field)
self.clean_row(changed_header)
return changed_header
def clean_row(self, row):
"""Removes unnecessary fields from row."""
del row[6]
del row[5]
return row
