cups = line[i:j].strip()
all_errors = {}
while c_line:
m = tuple(self.slices(c_line, length_c))
m = map(lambda s: s.strip(), m)
consums = build_dict(self.headers_cons, m)
consums['name'] = cups
result, errors = self.measures_adapter.load(consums)
if errors:
logger.error(errors)
all_errors.update(errors)
measures.append(result)
start += step
c_line = line[start:start + step].strip()
return measures, all_errors
def parse_line(self, line):
line = unicode(line.decode(self.encoding))
all_errors = {}
ps, ps_errors = self.parse_ps(line)
measures, measures_errors = self.parse_measures(line)
parsed = {'ps': ps,
'measures': measures, 'orig': line}
if ps_errors:
all_errors.update(ps_errors)
if measures_errors:
all_errors.update(measures_errors)
return parsed, all_errors
register(Iberdrola)
self.fields = self.fields_ps
def parse_line(self, line):
slinia = tuple(unicode(line.decode(self.encoding)).split(self.delimiter))
slinia = map(lambda s: s.strip(), slinia)
parsed = {'ps': {}, 'measures': {}, 'orig': line}
data = build_dict(self.headers_ps, slinia)
result, errors = self.adapter.load(data)
if errors:
logger.error(errors)
parsed['ps'] = result
return parsed, errors
register(Endesa)
class EndesaCons(Parser):
delimiter = ';'
pattern = '(SEVILLANA|FECSA|ERZ|UNELCO|GESA).INF2.SEG0[1-5].(zip|ZIP)$'
encoding = "iso-8859-15"
def __init__(self, strict=False):
self.schema = EndesaMeasuresSchema(strict=strict)
self.adapter = EndesaMeasuresAdapter(strict=strict)
self.measures_adapter = self.adapter
self.fields = []
self.headers = []
for f in sorted(self.schema.fields,
# passar previament la linia pel csv reader
# per que agafi be els camps tot i les comes dins del camp direccio
# per fer-ho cal passar-la a StringIO
l = StringIO.StringIO(line)
reader = csv.DictReader(l, fieldnames=self.headers_ps, delimiter=',')
linia = reader.next() # nomes n'hi ha una
parsed = {'ps': {}, 'orig': line}
result, errors = self.adapter.load(linia)
if errors:
logger.error(errors)
parsed['ps'] = result
return parsed, errors
register(Cnmc)
class CnmcCons(Parser):
# En el cas de les mesures, usem Schema per mantenir el format i
# perque no hi trobarem mes comes que les delimiters
pattern = '[0-9]{4}-[0-9]{2}-[0-9]{2}_electricidad_consumos.csv'
encoding = "UTF-8"
delimiter = ','
def __init__(self, strict=False):
self.schema = CnmcMeasuresSchema(strict=strict)
self.adapter = CnmcMeasuresAdapter(strict=strict)
self.measures_adapter = self.adapter
self.fields = []
self.headers = []
def parse_line(self, line):
line = unicode(line.decode(self.encoding))
slinia = tuple(self.slices(line, self.slices_ps))
slinia = map(lambda s: s.strip(), slinia)
pslist = slinia[0:len(self.fields_ps)]
# Llista dels valors del tros que agafem dins dels sips
data = build_dict(self.headers_ps, pslist)
result, errors = self.ps_adapter.load(data)
if errors:
logger.error(errors)
parsed = {'ps': result,
'measures': [], 'orig': line}
return parsed, errors
register(Hidrocantabrico)
class HidrocantabricoMeasures(Parser):
pattern = 'HIDROCANTABRICO_CO.*\.(zip|TXT)$'
encoding = "iso-8859-15"
def __init__(self, strict=False):
self.schema = HidrocantabricoMeasuresSchema(strict=strict)
self.adapter = HidrocantabricoMeasuresAdapter(strict=strict)
self.measures_adapter = self.adapter
self.fields = []
self.headers = []
self.measures_slices = []
for f in sorted(self.schema.fields,
key=lambda f: self.schema.fields[f].metadata['position']):
