def _parse_headers(self):
header_arr = utf8_clean(self.header_row).split(delimiter)
summary_line = utf8_clean(self.form_row).split(delimiter)
# These are always consistent
try:
self.headers['form'] = clean_entry(summary_line[0])
self.headers['fec_id'] = clean_entry(summary_line[1])
self.headers['report_num'] = None
except IndexError:
return False
# amendment number - not sure what version it starts in.
if len(summary_line) > 6:
self.headers['report_num'] = clean_entry(summary_line[6])[:3]
# Version number is always the third item
self.version = clean_entry(header_arr[2])
headers_list = new_headers
if float(self.version) <= 5:
headers_list = old_headers
header_hash = {}
for i in range(0, len(headers_list)):
# It's acceptable for header rows to leave off delimiters, so enter missing trailing args as blanks
this_arg = ""
try:
this_arg = clean_entry(header_arr[i])
except IndexError:
pass
self.headers[headers_list[i]] = this_arg
# figure out if this is an amendment, and if so, what's being amended.
form_last_char = self.headers['form'][-1].upper()
if form_last_char == 'A':
self.is_amendment = True
#print "Found amendment %s : %s " % (self.filing_number, self.headers['report_id'])
amendment_match = re.search('^FEC\s*-\s*(\d+)', self.headers['report_id'])
if amendment_match:
original = amendment_match.group(1)
#print "Amends filing: %s" % original
self.headers['filing_amended'] = original
else:
raise Exception("Can't find original filing in amended report %s" % (self.filing_number))
else:
self.is_amendment = False
self.headers['is_amendment'] = self.is_amendment
return True
def get_body_row(self):
"""get the next body row"""
next_line = ''
while True:
next_line = self.fh.readline()
if next_line:
if next_line.isspace():
continue
else:
return utf8_clean(next_line).split(delimiter)
else:
return None
def get_first_row(self):
return(utf8_clean(self.form_row).split(delimiter))