def unzip(csv_in, fields, csv_out_spec, csv_out_unspec, zip_field='id'):
input_csv = iter(csv_in)
header_row = input_csv.next()
header = Header(header_row)
if zip_field in header:
raise DuplicateFieldError(zip_field)
extract_spec = list_extractor(header.extractors(fields))
extract_unspec = list_extractor(
header.extractor(field)
for field in header_row
if field not in fields)
def extract_to(output, extract, row_id, row):
output.writerow([str(row_id)] + extract(row))
def unzip_row(row_id, row):
extract_to(csv_out_spec, extract_spec, row_id, row)
extract_to(csv_out_unspec, extract_unspec, row_id, row)
unzip_row(zip_field, header_row)
for zip_id, row in enumerate(input_csv):
unzip_row(zip_id, row)
def extract(self, reader, writer):
ireader = iter(reader)
input_header = Header(ireader.next())
extract_entity = tuple_extractor(
input_header.extractors(self.fields_map.input_fields))
def entity_ref(row):
return self.mapper.map(extract_entity(row))
transform = list_extractor(
input_header.extractors(input_header) + [entity_ref])
output_header = (list(input_header) +
list(self.ref_field_map.input_fields))
writer.writerow(output_header)
writer.writerows(transform(row) for row in ireader)
def extract(self, reader, writer):
ireader = iter(reader)
input_header = Header(ireader.next())
extract_entity = tuple_extractor(
input_header.extractors(self.fields_map.input_fields))
def entity_ref(row):
return self.mapper.map(extract_entity(row))
transform = list_extractor(
input_header.extractors(input_header) + [entity_ref])
output_header = (
list(input_header) + list(self.ref_field_map.input_fields))
writer.writerow(output_header)
writer.writerows(transform(row) for row in ireader)
def __init__(self, ref_field, fields, reader, appender):
self.appender = appender
self.max_ref = 0
self.values_to_ref = dict()
fields = list(fields)
reader = iter(reader)
header = Header(reader.next())
self._check_parameters(ref_field, fields, header)
param_header = Header([ref_field] + fields)
self.to_entity_file_order = list_extractor(
param_header.extractors(header))
def permutated_reader():
transform = list_extractor([header.extractor(ref_field)] +
header.extractors(fields))
for row in reader:
yield transform(row)
self._read_existing_mappings(permutated_reader())
def __init__(self, ref_field, fields, reader, appender):
self.appender = appender
self.max_ref = 0
self.values_to_ref = dict()
fields = list(fields)
reader = iter(reader)
header = Header(reader.next())
self._check_parameters(ref_field, fields, header)
param_header = Header([ref_field] + fields)
self.to_entity_file_order = list_extractor(
param_header.extractors(header))
def permutated_reader():
transform = list_extractor(
[header.extractor(ref_field)] + header.extractors(fields))
for row in reader:
yield transform(row)
self._read_existing_mappings(permutated_reader())
def unzip(csv_in, fields, csv_out_spec, csv_out_unspec, zip_field='id'):
input_csv = iter(csv_in)
header_row = input_csv.next()
header = Header(header_row)
if zip_field in header:
raise DuplicateFieldError(zip_field)
extract_spec = list_extractor(header.extractors(fields))
extract_unspec = list_extractor(
header.extractor(field) for field in header_row if field not in fields)
def extract_to(output, extract, row_id, row):
output.writerow([str(row_id)] + extract(row))
def unzip_row(row_id, row):
extract_to(csv_out_spec, extract_spec, row_id, row)
extract_to(csv_out_unspec, extract_unspec, row_id, row)
unzip_row(zip_field, header_row)
for zip_id, row in enumerate(input_csv):
unzip_row(zip_id, row)